To see the other types of publications on this topic, follow the link: Mortality and Length of stay Prediction.
Journal articles on the topic 'Mortality and Length of stay Prediction'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Mortality and Length of stay Prediction.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Awad, Aya, Mohamed Bader–El–Den, and James McNicholas. "Patient length of stay and mortality prediction: A survey." Health Services Management Research 30, no. 2 (March 22, 2017): 105–20. http://dx.doi.org/10.1177/0951484817696212.
Full textAbstract:
Over the past few years, there has been increased interest in data mining and machine learning methods to improve hospital performance, in particular hospitals want to improve their intensive care unit statistics by reducing the number of patients dying inside the intensive care unit. Research has focused on prediction of measurable outcomes, including risk of complications, mortality and length of hospital stay. The length of stay is an important metric both for healthcare providers and patients, influenced by numerous factors. In particular, the length of stay in critical care is of great significance, both to patient experience and the cost of care, and is influenced by factors specific to the highly complex environment of the intensive care unit. The length of stay is often used as a surrogate for other outcomes, where those outcomes cannot be measured; for example as a surrogate for hospital or intensive care unit mortality. The length of stay is also a parameter, which has been used to identify the severity of illnesses and healthcare resource utilisation. This paper examines a range of length of stay and mortality prediction applications in acute medicine and the critical care unit. It also focuses on the methods of analysing length of stay and mortality prediction. Moreover, the paper provides a classification and evaluation for the analytical methods of the length of stay and mortality prediction associated with a grouping of relevant research papers published in the years 1984 to 2016 related to the domain of survival analysis. In addition, the paper highlights some of the gaps and challenges of the domain.
2
Alghatani, Khalid, Nariman Ammar, Abdelmounaam Rezgui, and Arash Shaban-Nejad. "Predicting Intensive Care Unit Length of Stay and Mortality Using Patient Vital Signs: Machine Learning Model Development and Validation." JMIR Medical Informatics 9, no. 5 (May 5, 2021): e21347. http://dx.doi.org/10.2196/21347.
Full textAbstract:
Background Patient monitoring is vital in all stages of care. In particular, intensive care unit (ICU) patient monitoring has the potential to reduce complications and morbidity, and to increase the quality of care by enabling hospitals to deliver higher-quality, cost-effective patient care, and improve the quality of medical services in the ICU. Objective We here report the development and validation of ICU length of stay and mortality prediction models. The models will be used in an intelligent ICU patient monitoring module of an Intelligent Remote Patient Monitoring (IRPM) framework that monitors the health status of patients, and generates timely alerts, maneuver guidance, or reports when adverse medical conditions are predicted. Methods We utilized the publicly available Medical Information Mart for Intensive Care (MIMIC) database to extract ICU stay data for adult patients to build two prediction models: one for mortality prediction and another for ICU length of stay. For the mortality model, we applied six commonly used machine learning (ML) binary classification algorithms for predicting the discharge status (survived or not). For the length of stay model, we applied the same six ML algorithms for binary classification using the median patient population ICU stay of 2.64 days. For the regression-based classification, we used two ML algorithms for predicting the number of days. We built two variations of each prediction model: one using 12 baseline demographic and vital sign features, and the other based on our proposed quantiles approach, in which we use 21 extra features engineered from the baseline vital sign features, including their modified means, standard deviations, and quantile percentages. Results We could perform predictive modeling with minimal features while maintaining reasonable performance using the quantiles approach. The best accuracy achieved in the mortality model was approximately 89% using the random forest algorithm. The highest accuracy achieved in the length of stay model, based on the population median ICU stay (2.64 days), was approximately 65% using the random forest algorithm. Conclusions The novelty in our approach is that we built models to predict ICU length of stay and mortality with reasonable accuracy based on a combination of ML and the quantiles approach that utilizes only vital signs available from the patient’s profile without the need to use any external features. This approach is based on feature engineering of the vital signs by including their modified means, standard deviations, and quantile percentages of the original features, which provided a richer dataset to achieve better predictive power in our models.
3
Burdick, Hoyt, Eduardo Pino, Denise Gabel-Comeau, Andrea McCoy, Carol Gu, Jonathan Roberts, Sidney Le, et al. "Effect of a sepsis prediction algorithm on patient mortality, length of stay and readmission: a prospective multicentre clinical outcomes evaluation of real-world patient data from US hospitals." BMJ Health & Care Informatics 27, no. 1 (April 2020): e100109. http://dx.doi.org/10.1136/bmjhci-2019-100109.
Full textAbstract:
BackgroundSevere sepsis and septic shock are among the leading causes of death in the USA. While early prediction of severe sepsis can reduce adverse patient outcomes, sepsis remains one of the most expensive conditions to diagnose and treat.ObjectiveThe purpose of this study was to evaluate the effect of a machine learning algorithm for severe sepsis prediction on in-hospital mortality, hospital length of stay and 30-day readmission.DesignProspective clinical outcomes evaluation.SettingEvaluation was performed on a multiyear, multicentre clinical data set of real-world data containing 75 147 patient encounters from nine hospitals across the continental USA, ranging from community hospitals to large academic medical centres.ParticipantsAnalyses were performed for 17 758 adult patients who met two or more systemic inflammatory response syndrome criteria at any point during their stay (‘sepsis-related’ patients).InterventionsMachine learning algorithm for severe sepsis prediction.Outcome measuresIn-hospital mortality, length of stay and 30-day readmission rates.ResultsHospitals saw an average 39.5% reduction of in-hospital mortality, a 32.3% reduction in hospital length of stay and a 22.7% reduction in 30-day readmission rate for sepsis-related patient stays when using the machine learning algorithm in clinical outcomes analysis.ConclusionsReductions of in-hospital mortality, hospital length of stay and 30-day readmissions were observed in real-world clinical use of the machine learning-based algorithm. The predictive algorithm may be successfully used to improve sepsis-related outcomes in live clinical settings.Trial registration numberNCT03960203
4
Cai, Xiongcai, Oscar Perez-Concha, Enrico Coiera, Fernando Martin-Sanchez, Richard Day, David Roffe, and Blanca Gallego. "Real-time prediction of mortality, readmission, and length of stay using electronic health record data." Journal of the American Medical Informatics Association 23, no. 3 (September 15, 2015): 553–61. http://dx.doi.org/10.1093/jamia/ocv110.
Full textAbstract:
Objective To develop a predictive model for real-time predictions of length of stay, mortality, and readmission for hospitalized patients using electronic health records (EHRs). Materials and Methods A Bayesian Network model was built to estimate the probability of a hospitalized patient being “at home,” in the hospital, or dead for each of the next 7 days. The network utilizes patient-specific administrative and laboratory data and is updated each time a new pathology test result becomes available. Electronic health records from 32 634 patients admitted to a Sydney metropolitan hospital via the emergency department from July 2008 through December 2011 were used. The model was tested on 2011 data and trained on the data of earlier years. Results The model achieved an average daily accuracy of 80% and area under the receiving operating characteristic curve (AUROC) of 0.82. The model’s predictive ability was highest within 24 hours from prediction (AUROC = 0.83) and decreased slightly with time. Death was the most predictable outcome with a daily average accuracy of 93% and AUROC of 0.84. Discussion We developed the first non–disease-specific model that simultaneously predicts remaining days of hospitalization, death, and readmission as part of the same outcome. By providing a future daily probability for each outcome class, we enable the visualization of future patient trajectories. Among these, it is possible to identify trajectories indicating expected discharge, expected continuing hospitalization, expected death, and possible readmission. Conclusions Bayesian Networks can model EHRs to provide real-time forecasts for patient outcomes, which provide richer information than traditional independent point predictions of length of stay, death, or readmission, and can thus better support decision making.
5
Wang, Chen-Yu, Chen Liu, Hsien-Hui Yang, Pei-Ying Tseng, and Jong-Yi Wang. "The Association between Medical Utilization and Chronic Obstructive Pulmonary Disease Severity: A Comparison of the 2007 and 2011 Guideline Staging Systems." Healthcare 10, no. 4 (April 13, 2022): 721. http://dx.doi.org/10.3390/healthcare10040721.
Full textAbstract:
(1) Background: This study aimed to investigate the associations between the Global Initiative for Chronic Obstructive Lung Disease (GOLD) staging systems, medical costs, and mortality among patients with chronic obstructive lung disease (COPD). Predictions of the effectiveness of the two versions of the staging systems were also compared. (2) Purpose: this study investigated the associations between the Global Initiative for Chronic Obstructive Lung Disease (GOLD) staging systems, medical costs, and mortality among patients with COPD. Predicting effectiveness between the two versions of the staging systems was also compared. (3) Procedure: This study used a secondary clinical database of a medical center in central Taiwan to examine records between 2011 and 2017. A total of 613 patients with COPD were identified. The independent variables comprised the COPD GOLD Guideline staging of the 2007 and 2011 versions, demographic characteristics, health status, and physician seniority. The dependent variables included total medical cost, average length of hospital stay, and mortality. The statistical methods included binomial logistic regression and the general linear model (GLM). (4) Discussion: The total medical cost during the observation period for patients with COPD averaged TWD 292,455.6. The average length of hospital stay was 9.7 days. The mortality rate was 9.6%, compared with that of patients in Grade 1 of the 2007 version; patients in Grade 4 of the 2007 version had significantly higher odds of death (OR = 4.07, p = 0.02). The accuracy of mortality prediction for both the 2007 and 2011 versions of the staging was equal, at 90.4%. The adjusted GLM analysis revealed that patients in Group D of the 2011 version had a significantly longer length of hospital stay than those in Group A of the 2011 version (p = 0.04). No difference between the 2007 and 2011 versions was found regarding the total medical cost. Complications were significantly associated with the total medical cost and average length of hospital stay. (5) Conclusions: The COPD staging 2011 version was associated with an average length of hospital stay, whereas the COPD staging 2007 version was related to mortality risk. Therefore, the 2011 version can estimate the length of hospital stay. However, in predicting prognosis and mortality, the 2007 version is recommended.
6
Ghorbani, Mohammad, Haleh Ghaem, Abbas Rezaianzadeh, Zahra Shayan, Farid Zand, and Reza Nikandish. "A study on the efficacy of APACHE-IV for predicting mortality and length of stay in an intensive care unit in Iran." F1000Research 6 (November 20, 2017): 2032. http://dx.doi.org/10.12688/f1000research.12290.1.
Full textAbstract:
Background:Clinical assessment of disease severity is an important part of medical practice for prediction of mortality and morbidity in Intensive Care Unit (ICU). A disease severity scoring system can be used as guidance for clinicians for objective assessment of disease outcomes and estimation of the chance of recovery. This study aimed to evaluate the hypothesis that the mortality and length of stay in emergency ICUs predicted by APACHE-IV is different to the real rates of mortality and length of stay observed in our emergency ICU in Iran.Methods:This was a retrospective cohort study conducted on the data of 839 consecutive patients admitted to the emergency ICU of Nemazi Hospital, Shiraz, Iran, during 2012-2015. The relevant variables were used to calculate APACHE-IV. Length of stay and death or discharge, Glasgow coma score, and acute physiology score were also evaluated. Moreover, the accuracy of APACHE-IV for mortality was assessed using area under the Receiver Operator Characteristic (ROC) curve.Results:Of the studied patients, 157 died and 682 were discharged (non-survivors and survivors, respectively). The length of stay in the ICU was 10.98±14.60, 10.22 ± 14.21 and 14.30±15.80 days for all patients, survivors, and non-survivors, respectively. The results showed that APACHE-IV model underestimated length of stay in our emergency ICU (p<0.001). In addition, the overall observed mortality was 17.8%, while the predicted mortality by APACHE-IV model was 21%. Therefore, there was an overestimation of predicted mortality by APACHE-IV model, with an absolute difference of 3.2% (p=0.036).Conclusion:The findings showed that APACHE-IV was a poor predictor of length of stay and mortality rate in emergency ICU. Therefore, specific models based on big sample sizes of Iranian patients are required to improve accuracy of predictions.
7
Choi, Jeff, Edward B. Vendrow, Michael Moor, and David A. Spain. "Development and Validation of a Model to Quantify Injury Severity in Real Time." JAMA Network Open 6, no. 10 (October 9, 2023): e2336196. http://dx.doi.org/10.1001/jamanetworkopen.2023.36196.
Full textAbstract:
ImportanceQuantifying injury severity is integral to trauma care benchmarking, decision-making, and research, yet the most prevalent metric to quantify injury severity—Injury Severity Score (ISS)— is impractical to use in real time.ObjectiveTo develop and validate a practical model that uses a limited number of injury patterns to quantify injury severity in real time through 3 intuitive outcomes.Design, Setting, and ParticipantsIn this cohort study for prediction model development and validation, training, development, and internal validation cohorts comprised 223 545, 74 514, and 74 514 admission encounters, respectively, of adults (age ≥18 years) with a primary diagnosis of traumatic injury hospitalized more than 2 days (2017-2018 National Inpatient Sample). The external validation cohort comprised 3855 adults admitted to a level I trauma center who met criteria for the 2 highest of the institution’s 3 trauma activation levels.Main Outcomes and MeasuresThree outcomes were hospital length of stay, probability of discharge disposition to a facility, and probability of inpatient mortality. The prediction performance metric for length of stay was mean absolute error. Prediction performance metrics for discharge disposition and inpatient mortality were average precision, precision, recall, specificity, F1 score, and area under the receiver operating characteristic curve (AUROC). Calibration was evaluated using calibration plots. Shapley addictive explanations analysis and bee swarm plots facilitated model explainability analysis.ResultsThe Length of Stay, Disposition, Mortality (LDM) Injury Index (the model) comprised a multitask deep learning model trained, developed, and internally validated on a data set of 372 573 traumatic injury encounters (mean [SD] age = 68.7 [19.3] years, 56.6% female). The model used 176 potential injuries to output 3 interpretable outcomes: the predicted hospital length of stay, probability of discharge to a facility, and probability of inpatient mortality. For the external validation set, the ISS predicted length of stay with mean absolute error was 4.16 (95% CI, 4.13-4.20) days. Compared with the ISS, the model had comparable external validation set discrimination performance (facility discharge AUROC: 0.67 [95% CI, 0.67-0.68] vs 0.65 [95% CI, 0.65-0.66]; recall: 0.59 [95% CI, 0.58-0.61] vs 0.59 [95% CI, 0.58-0.60]; specificity: 0.66 [95% CI, 0.66-0.66] vs 0.62 [95%CI, 0.60-0.63]; mortality AUROC: 0.83 [95% CI, 0.81-0.84] vs 0.82 [95% CI, 0.82-0.82]; recall: 0.74 [95% CI, 0.72-0.77] vs 0.75 [95% CI, 0.75-0.76]; specificity: 0.81 [95% CI, 0.81-0.81] vs 0.76 [95% CI, 0.75-0.77]). The model had excellent calibration for predicting facility discharge disposition, but overestimated inpatient mortality. Explainability analysis found the inputs influencing model predictions matched intuition.Conclusions and RelevanceIn this cohort study using a limited number of injury patterns, the model quantified injury severity using 3 intuitive outcomes. Further study is required to evaluate the model at scale.
8
Barsasella, Diana, Karamo Bah, Pratik Mishra, Mohy Uddin, Eshita Dhar, Dewi Lena Suryani, Dedi Setiadi, et al. "A Machine Learning Model to Predict Length of Stay and Mortality among Diabetes and Hypertension Inpatients." Medicina 58, no. 11 (October 31, 2022): 1568. http://dx.doi.org/10.3390/medicina58111568.
Full textAbstract:
Background and Objectives: Taiwan is among the nations with the highest rates of Type 2 Diabetes Mellitus (T2DM) and Hypertension (HTN). As more cases are reported each year, there is a rise in hospital admissions for people seeking medical attention. This creates a burden on hospitals and affects the overall management and administration of the hospitals. Hence, this study aimed to develop a machine learning (ML) model to predict the Length of Stay (LoS) and mortality among T2DM and HTN inpatients. Materials and Methods: Using Taiwan’s National Health Insurance Research Database (NHIRD), this cohort study consisted of 58,618 patients, where 25,868 had T2DM, 32,750 had HTN, and 6419 had both T2DM and HTN. We analyzed the data with different machine learning models for the prediction of LoS and mortality. The evaluation was done by plotting descriptive statistical graphs, feature importance, precision-recall curve, accuracy plots, and AUC. The training and testing data were set at a ratio of 8:2 before applying ML algorithms. Results: XGBoost showed the best performance in predicting LoS (R2 0.633; RMSE 0.386; MAE 0.123), and RF resulted in a slightly lower performance (R2 0.591; RMSE 0.401; MAE 0.027). Logistic Regression (LoR) performed the best in predicting mortality (CV Score 0.9779; Test Score 0.9728; Precision 0.9432; Recall 0.9786; AUC 0.97 and AUPR 0.93), closely followed by Ridge Classifier (CV Score 0.9736; Test Score 0.9692; Precision 0.9312; Recall 0.9463; AUC 0.94 and AUPR 0.89). Conclusions: We developed a robust prediction model for LoS and mortality of T2DM and HTN inpatients. Linear Regression showed the best performance for LoS, and Logistic Regression performed the best in predicting mortality. The results showed that ML algorithms can not only help healthcare professionals in data-driven decision-making but can also facilitate early intervention and resource planning.
9
Sessler, Daniel I., Jeffrey C. Sigl, Paul J. Manberg, Scott D. Kelley, Armin Schubert, and Nassib G. Chamoun. "Broadly Applicable Risk Stratification System for Predicting Duration of Hospitalization and Mortality." Anesthesiology 113, no. 5 (November 1, 2010): 1026–37. http://dx.doi.org/10.1097/aln.0b013e3181f79a8d.
Full textAbstract:
Background Hospitals are increasingly required to publicly report outcomes, yet performance is best interpreted in the context of population and procedural risk. We sought to develop a risk-adjustment method using administrative claims data to assess both national-level and hospital-specific performance. Methods A total of 35,179,507 patient stay records from 2001-2006 Medicare Provider Analysis and Review (MEDPAR) files were randomly divided into development and validation sets. Risk stratification indices (RSIs) for length of stay and mortality endpoints were derived from aggregate risk associated with individual diagnostic and procedure codes. Performance of RSIs were tested prospectively on the validation database, as well as a single institution registry of 103,324 adult surgical patients, and compared with the Charlson comorbidity index, which was designed to predict 1-yr mortality. The primary outcome was the C statistic indicating the discriminatory power of alternative risk-adjustment methods for prediction of outcome measures. Results A single risk-stratification model predicted 30-day and 1-yr postdischarge mortality; separate risk-stratification models predicted length of stay and in-hospital mortality. The RSIs performed well on the national dataset (C statistics for median length of stay and 30-day mortality were 0.86 and 0.84). They performed significantly better than the Charlson comorbidity index on the Cleveland Clinic registry for all outcomes. The C statistics for the RSIs and Charlson comorbidity index were 0.89 versus 0.60 for median length of stay, 0.98 versus 0.65 for in-hospital mortality, 0.85 versus 0.76 for 30-day mortality, and 0.83 versus 0.77 for 1-yr mortality. Addition of demographic information only slightly improved performance of the RSI. Conclusion RSI is a broadly applicable and robust system for assessing hospital length of stay and mortality for groups of surgical patients based solely on administrative data.
10
Widyastuti, Yunita, Akhmad Yun Jufan, Untung Widodo, Calcarina Fitriani Retno Wisudarti, Sudadi ., Rizki Ahmad Fauzi, and Firman Ardiansyah. "A tertiary care center-based study of a novel ‘ICU Mortality and Prolonged Stay Risk Scoring System’." Anaesthesia, Pain & Intensive Care 28, no. 1 (February 4, 2024): 100–107. http://dx.doi.org/10.35975/apic.v28i1.2382.
Full textAbstract:
Background & objective: Intensive care has been associated with high cost and resource-intensive medical care. Therefore, a risk prediction model is required to plan time allocation, human resources, and the required equipment. Various risk predictions for ICU mortality and ‘Prolonged Length of Stay’ (PLOS) scores are already available. Still, the established model, such as the APACHE IV score or SAPS II, sometimes became impractical since they required many laboratory parameters. A model based on co-morbidities and demographic factors may be more useful in limited resources setting. Hence, we developed a simple ICU mortality and PLOS risk prediction model based on co-morbidities and demographic data.
Methodology: This retrospective cohort study was performed to develop a risk scoring for mortality and PLOS, using data from Dr. Sardjito Hospital Yogyakarta database between January 01-December 31, 2019. Logistic regression and bootstrap methods were used to create a risk score for estimating the risk. The discrimination performance of the model was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC). The Hosmer-Lemeshow test was employed to assess the model’s calibration.
Results: A total of 415 patients were included in this study. The risk factors for mortality were perioperative support medication, kidney failure, neurologic disorder, respiratory failure, and intraoperative blood transfusion. The mortality score of 6 was associated with a 100% probability of mortality. Medical cases, GCS < 8, vasoactive/inotropic medication, sepsis, respiratory failure, and kidney failure were the risk factors for PLOS. PLOS score of 3 was associated with a 100% probability of PLOS. The discrimination for either mortality or PLOS was considered excellent with the AUC (± 95% CI) for mortality 0.896 (0.853-0.94), while for PLOS 0.878 (0.80-0.90). The calibration test found that both models had good calibration with P values of 0.53 and 0.55 for mortality and PLOS, respectively.
Conclusion: The ‘Mortality and Prolonged Length of Stay Prediction Score’ based on co-morbidities and demographic data upon admission to ICU had good accuracy and can be applied as a potential new scoring system in healthcare institutions.
Abbreviations: APACHE- Acute Physiologic Assessment and Chronic Health Evaluation; AUC; Area Under the Curve GCS- Glasgow Coma Scale; ICU- Intensive Care Unit; PLOS- ‘Prolonged Length of Stay’; PRC- Packed Red Cells; SAPS- Simplified Acute Physiology Score
Keywords: Risk Scoring; Mortality; Prolonged Length of Stay; ICU
Citation: Widyastuti Y, Jufan AY, Widodo U, Wisudarti CFR, Sudadi, Fauzi RA, Ardiansyah F. A tertiary care center-based study of a novel ‘ICU Mortality and Prolonged Stay Risk Scoring System’. Anaesth. pain intensive care 2024;28(1):100−107; DOI: 10.35975/apic.v28i1.2382
Received: October 02, 2023; Reviewed: November 27, 2023; Accepted: December 17, 2023
11
Anagnostopoulos, Constantine E., Ioannis K. Toumpoulis, and Joseph J. DeRose. "Prediction of length of stay postoperative complications and long term mortality by EuroSCORE." International Journal of Cardiology 105, no. 1 (October 2005): 119–20. http://dx.doi.org/10.1016/j.ijcard.2005.04.016.
Full text
12
Taylor, Morgan A., Randy D. Kearns, Jeffrey E. Carter, Mark H. Ebell, and Curt A. Harris. "45 Application of Machine Learning Models to Thermal Burn Patient Outcome Predictions in the Aftermath of a Nuclear Event." Journal of Burn Care & Research 42, Supplement_1 (April 1, 2021): S33—S34. http://dx.doi.org/10.1093/jbcr/irab032.049.
Full textAbstract:
Abstract Introduction A nuclear disaster would generate an unprecedented volume of thermal burn patients from the explosion and subsequent mass fires (Figure 1). Prediction models characterizing outcomes for these patients may better equip healthcare providers and other responders to manage large scale nuclear events. Logistic regression models have traditionally been employed to develop prediction scores for mortality of all burn patients. However, other healthcare disciplines have increasingly transitioned to machine learning (ML) models, which are automatically generated and continually improved, potentially increasing predictive accuracy. Preliminary research suggests ML models can predict burn patient mortality more accurately than commonly used prediction scores. The purpose of this study is to examine the efficacy of various ML methods in assessing thermal burn patient mortality and length of stay in burn centers. Methods This retrospective study identified patients with fire/flame burn etiologies in the National Burn Repository between the years 2009 – 2018. Patients were randomly partitioned into a 67%/33% split for training and validation. A random forest model (RF) and an artificial neural network (ANN) were then constructed for each outcome, mortality and length of stay. These models were then compared to logistic regression models and previously developed prediction tools with similar outcomes using a combination of classification and regression metrics. Results During the study period, 82,404 burn patients with a thermal etiology were identified in the analysis. The ANN models will likely tend to overfit the data, which can be resolved by ending the model training early or adding additional regularization parameters. Further exploration of the advantages and limitations of these models is forthcoming as metric analyses become available. Conclusions In this proof-of-concept study, we anticipate that at least one ML model will predict the targeted outcomes of thermal burn patient mortality and length of stay as judged by the fidelity with which it matches the logistic regression analysis. These advancements can then help disaster preparedness programs consider resource limitations during catastrophic incidents resulting in burn injuries.
13
Safura Riaz, Abdul Waheed Mir, Suhail Sidiq, Showkat Ahmed Gurcoo, Mohammad Akbar Shah, Falak Ara, Akif Mutahar Shah, and Altaf Hussain Mir. "Perioperative serum lactate as a predictor of post-operative length of hospital stay and in-hospital mortality in patients undergoing major emergency abdominal surgeries." Asian Journal of Medical Sciences 15, no. 5 (May 1, 2024): 16–21. http://dx.doi.org/10.3126/ajms.v15i5.62619.
Full textAbstract:
Background: Major surgeries can develop metabolic acidosis during the perioperative period. Any clinical condition leading to decreased tissue oxygenation causes lactate levels to rise proportionally. Aims and Objectives: This study was aimed at evaluating perioperative serum lactate as a predictor of length of hospital stay and in-hospital mortality in patients undergoing emergency major abdominal surgeries. Materials and Methods: Adult patients posted for emergency abdominal surgical procedures were enrolled for 2 years. Patients were observed intraoperatively and lactate levels were measured. In post-operative period lactate levels were recorded for 24 h. Relationship of lactate with hospital length of stay and in-hospital mortality was analyzed. Results: Total of 93 patients were enrolled for 2 years. Mean age was 50.4 years. Mean baseline lactate was 2.95 mmol/L. Total in-hospital mortality was 16.1%. Thirteen patients had perioperative serum lactate level of ≤ 2 mmol/l, with a mean hospital length of stay of 8.6 days and no mortality. Fifty-one patients having perioperative serum lactate between 2 and 4 mmol/L, with a mean hospital length of stay of 11.2 days and mortality of 13.3%. Twenty-nine patients had serum lactate of >4 mmol/L, with a mean hospital length of stay of 17.3 days and mortality of 86.7%. Elevated serum lactate was associated with a longer length of hospital stay, with lactate at 12 h having the highest predictive value (area under curve 0.987). Similarly, lactate at 12 h had the highest accuracy at predicting mortality as per receiver operating characteristic (AUC 0.895). Conclusion: Serum lactate was associated with increased in-hospital mortality and longer length of hospital stay in emergency abdominal surgeries.
14
Rongpi, Ranjib, Imad Ahmed Choudhury, Hemendra Chandra Nath, Atul Chandra Baro, and Anadi Swami Tassa. "PROSPECTIVE EVALUATION OF PANC 3 SCORE IN PREDICTING SEVERITY OF ACUTE PANCREATITIS." International Journal of Advanced Research 10, no. 03 (March 31, 2022): 1181–86. http://dx.doi.org/10.21474/ijar01/14506.
Full textAbstract:
Background: About 15-20% of cases of acute pancreatitis progress to a severe form, leading to high mortality rates. Thus early prediction of severity is utmost important so as to provide better management and decrease mortality. Objective: To explore the efficiency of PANC 3 SCORE in predicting the severity in patients with acute pancreatitis on admission and its relation to clinical outcome. Methods: Patients with Acute pancreatitis were assessed to sex, age, body mass index (BMI), etiology of pancreatitis, Hematocrit and presence or absence of pleural effusion at the time of admission intensive care need, length of hospital stay, length of stay in intensive care unit and mortality. The PANC 3 score was determined on admission and compared to acute pancreatitis grade of the Revised Atlanta classification. Results: Out of 46 patients diagnosed with acute pancreatitis, 46 patients met the inclusion criteria. The PANC 3 score was positive in 4 cases (8.69%), pancreatitis progressed to a severe form in 7 cases (15.2%) and 3 patients (6.5%) died. Patients with a positive score and severe pancreatitis required intensive care more often, and stayed for a longer period in intensive care units. The PANC 3 score showed sensitivity of 42.85%, specificity of 97.45%, accuracy of 90.17%, positive predictive value of 75% and negative predictive value of 89.13% in prediction of severe acute pancreatitis. Conclusion: The PANC 3 score has high specificity, high accuracy and high predictive value in prediction of severe acute pancreatitis. It has only 3 parameters which can be easily done in any healthcare system. It does not need much expertise to analyze PANC3 at the time of admission which adds the advantage of this score over other scoring systems.
15
Rongpi, Ranjib, Imad Ahmed Choudhury, Hemendra Chandra Nath, Atul Chandra Baro, and Anadi Swami Tassa. "PROSPECTIVE EVALUATION OF PANC 3 SCORE IN PREDICTING SEVERITY OF ACUTE PANCREATITIS." International Journal of Advanced Research 10, no. 03 (March 31, 2022): 1181–86. http://dx.doi.org/10.21474/ijar01/14506.
Full textAbstract:
Background: About 15-20% of cases of acute pancreatitis progress to a severe form, leading to high mortality rates. Thus early prediction of severity is utmost important so as to provide better management and decrease mortality. Objective: To explore the efficiency of PANC 3 SCORE in predicting the severity in patients with acute pancreatitis on admission and its relation to clinical outcome. Methods: Patients with Acute pancreatitis were assessed to sex, age, body mass index (BMI), etiology of pancreatitis, Hematocrit and presence or absence of pleural effusion at the time of admission intensive care need, length of hospital stay, length of stay in intensive care unit and mortality. The PANC 3 score was determined on admission and compared to acute pancreatitis grade of the Revised Atlanta classification. Results: Out of 46 patients diagnosed with acute pancreatitis, 46 patients met the inclusion criteria. The PANC 3 score was positive in 4 cases (8.69%), pancreatitis progressed to a severe form in 7 cases (15.2%) and 3 patients (6.5%) died. Patients with a positive score and severe pancreatitis required intensive care more often, and stayed for a longer period in intensive care units. The PANC 3 score showed sensitivity of 42.85%, specificity of 97.45%, accuracy of 90.17%, positive predictive value of 75% and negative predictive value of 89.13% in prediction of severe acute pancreatitis. Conclusion: The PANC 3 score has high specificity, high accuracy and high predictive value in prediction of severe acute pancreatitis. It has only 3 parameters which can be easily done in any healthcare system. It does not need much expertise to analyze PANC3 at the time of admission which adds the advantage of this score over other scoring systems.
16
Kalarickal, Anil, Saumy Johnson, and Anitha Shenoy. "Comparison of Acute Physiology and Chronic Health Evaluation (APACHE) IV and Simplified Acute Physiology Score (SAPS) II in a Tertiary Care Hospital ICU in India." Indian Journal of Respiratory Care 01, no. 02 (December 1, 2022): 156–60. http://dx.doi.org/10.5005/ijrc-1-1-156.
Full textAbstract:
Background: APACHE IV and SAPS II are ICU scoring systems used to predict mortality in critically ill patients in the ICU. Aim: To compare mortality prediction using APACHE IV and SAPS II in an Indian ICU. Methods: This prospective study included 225 patients. SAPS II and APACHE IV scoring and predicted mortality were obtained for each patient using online calculators and correlated with actual mortality and length of stay. Results: 183/225 of these admissions were due to medical causes. The mean±SD SAPS II score was 37.97 (±15.85) and APACHE IV score was 64.15 (±20.04). The median SAPS II predicted mortality rate was 19.6% and by APACHE IV was 17.4%. Actual mortality was 25.33%. Area under the curve (AUC) for SAPS II was 0.723 and APACHE IV was 0.701. AUC for SAPS II and APACHE IV for medical admissions were 0.712 and 0.681 respectively and for surgical admissions was 0.803 and 0.811 respectively. The best cut off value of SAPS II was 37 and APACHE IV was 70.5 for surgical patients. The mean predicted mortalities for patients with SAPS II score <37 and .37 were 4.95±3.87% and 37.15±16.5% respectively and APACHE IV score <70.5 and .70.5 were 16.82±11.48% and 40.6±15.72% respectively. There was no correlation between predicted and actual length of stay. Conclusions: Both APACHE IV and SAPS II ICU scoring systems are inaccurate in predicting overall mortality in our ICU. APACHE IV is not reliable in predicting length of stay of all patients in our ICU.
17
ÇORAPLI, Mahmut, and Gökhan ÇORAPLI. "Prognosis prediction of the mean tracheal air column area in COVID-19 patients." Anatolian Current Medical Journal 5, no. 1 (January 20, 2023): 24–28. http://dx.doi.org/10.38053/acmj.1206657.
Full textAbstract:
Aim: SARS-CoV-2 infection frequently affects the lungs, it can also cause severe inflammation in the lower respiratory tract, leading to tracheal damage. We aimed to investigate the relationship between the mean tracheal air column and COVID-19.Material and Method: Chest computed tomography scans of COVID-19 patients treated in an intensive care unit between June 1st, 2020 and October 1st 2022 were retrospectively evaluated. The air column area of the trachea was measured and the effect of the values obtained on mortality and length of stay in the intensive care unit for patients COVID-19 was examined.Results: We found that an increase in the mean tracheal air column increased mortality by 1.218 times. We also determined that an increase in the mean area of the tracheal air column increased the length of stay in the intensive care unit. Furthermore, we showed that advanced age and an increase in the length of stay in the intensive care unit were factors that increased mortality.Conclusion: Tracheomegaly is a poor prognostic factor in COVID-19 disease and is easily diagnosed with CT.
18
Huang, Yii-Ting, Ying-Hsien Huang, Ching-Hua Hsieh, Chao-Jui Li, and I.-Min Chiu. "Comparison of Injury Severity Score, Glasgow Coma Scale, and Revised Trauma Score in Predicting the Mortality and Prolonged ICU Stay of Traumatic Young Children: A Cross-Sectional Retrospective Study." Emergency Medicine International 2019 (December 1, 2019): 1–7. http://dx.doi.org/10.1155/2019/5453624.
Full textAbstract:
Introduction. The purpose of this study was to examine the capacity of commonly used trauma scoring systems such as the Glasgow Coma Scale (GCS), Injury Severity Score (ISS), and Revised Trauma Score (RTS) to predict outcomes in young children with traumatic injuries. Methods. This retrospective study was conducted for the period from 2009 to 2016 in Kaohsiung Chang Gung Memorial Medical Hospital, a level I trauma center. We included all children under the age of 6 years admitted to the hospital via the emergency department with any traumatic injury and compared the trauma scores of GCS, ISS, and RTS on patients’ outcome. The primary outcomes were mortality and prolonged Intensive Care Unit (ICU) stay, with the latter defined as an ICU stay longer than 14 days. The secondary outcome was the hospital length of stay (HLOS). Receiver operating characteristic (ROC) analysis was also adopted with the value of the area under the ROC curve (AUC) for comparing trauma score prediction with patient mortality. Cutoff values from each trauma score for mortality prediction were also measured by determining the point along the ROC curve where Youden’s index was maximum. Results. We included a total of 938 patients in this study, with a mean age of 3.1 ± 1.82 years. The mortality rate was 0.9%, and 93 (9.9%) patients had a prolonged ICU stay. An elevated ISS (34 ± 19.9 vs. 5 ± 5.1, p=0.004), lower GCS (8 ± 5.0 vs. 15 ± 1.3, p=0.006), and lower RTS (5.58 ± 1.498 vs. 7.64 ± 0.640, p=0.006) were all associated with mortality. All three scores were considered to be independent risk factors of mortality and prolonged ICU stay and had a linear correlation with increased HLOS. With regard to predicting mortality, ISS has the highest AUC value (ISS: 0.975; GCS: 0.864; and RTS: 0.899). The prediction cutoff values of ISS, GCS, and RTS on mortality were 15, 11, and 7, respectively. Conclusion. Regarding traumatic injuries in young children, worse ISS, GCS, and RTS were all associated with increased mortality, prolonged ICU stay, and longer hospital LOS. Of these scoring systems, ISS was the best at predicting mortality.
19
Kaya, Hakki, Recep Kurt, Osman Beton, Ali Zorlu, Hasan Yucel, Hakan Gunes, Didem Oguz, and Mehmet Birhan Yilmaz. "Cancer Antigen 125 is Associated with Length of Stay in Patients with Acute Heart Failure." Texas Heart Institute Journal 44, no. 1 (February 1, 2017): 22–28. http://dx.doi.org/10.14503/thij-15-5626.
Full textAbstract:
Length of stay is the primary driver of heart-failure hospitalization costs. Because cancer antigen 125 has been associated with poor morbidity and mortality rates in heart failure, we investigated the relationship between admission cancer antigen 125 levels and lengths of stay in heart-failure patients. A total of 267 consecutive patients (184 men, 83 women) with acute decompensated heart failure were evaluated prospectively. The median length of stay was 4 days, and the patients were classified into 2 groups: those with lengths of stay ≤4 days and those with lengths of stay >4 days. Patients with longer lengths of stay had a significantly higher cancer antigen 125 level of 114 U/mL (range, 9–298 U/mL) than did those with a shorter length of stay (19 U/mL; range; 3–68) (P <0.001). The optimal cutoff level of cancer antigen 125 in the prediction of length of stay was >48 U/mL, with a specificity of 95.8% and a sensitivity of 96% (area under the curve, 0.979; 95% confidence interval [CI], 0.953–0.992). In the multivariate logistic regression model, cancer antigen 125 >48 U/mL on admission (odds ratio=4.562; 95% CI, 1.826–11.398; P=0.001), sodium level (P<0.001), creatinine level (P=0.009), and atrial fibrillation (P=0.015) were also associated with a longer length of stay after adjustment for variables found to be statistically significant in univariate analysis and correlated with cancer antigen 125 level. In addition, it appears that in a cohort of patients with acute decompensated heart failure, cancer antigen 125 is independently associated with prolonged length of stay.
20
Zahmatkeshan, Mozhgan, Zahra Serati, Shole Freydooni, Ali Reza Safarpour, Atefeh Esmailnejad, and Saeede Haghbin. "Prediction of Early Liver Failure in Pediatric Patients Admitted to Intensive Care Unit." Middle East Journal of Digestive Diseases 11, no. 3 (June 14, 2019): 141–46. http://dx.doi.org/10.15171/mejdd.2019.140.
Full textAbstract:
BACKGROUND Hepatic dysfunction has been associated with poor prognosis in critically ill patients. We aimed to investigate the incidence of early liver dysfunction and its association with probable predictive variables in a group of Iranian patients. METHODS The study was conducted on 149 pediatric patients referred to the pediatric intensive care unit (PICU), Shiraz University of Medical Sciences, Shiraz, Iran between April and October 2016. Serum levels of liver aminotransferase, alkaline phosphatase, total bilirubin, direct bilirubin, and international normalized ratio (INR) were recorded in 24, 48, and 96 hours after admission. RESULTS On the first day of admission, direct bilirubin was the least (9.1%) and abnormal alkaline phosphatase level was the most (66.9%) common abnormalities. Abnormal levels of all tests except alkaline phosphatase were predictive of increased rate of mortality. In univariable logistic regression, abnormal aminotransferases (ALT and AST), INR, total bilirubin, and direct bilirubin had significant relationship with patients’ mortality after 24, 48, and 96 hours. In multivariable logistic regression only ALT and INR in the first 24 hours had significant relationship with mortality in final model. Although univariate logistic regression revealed a significant relationship between AST and ALT levels with PICU length of stay, no significant relationship was observed between these variables and PICU length of stay (except AST in the first 24 hours) in multivariable analysis. CONCLUSION Increase in liver enzymes may predict mortality and increased PICU length of stay in critically ill children.
21
Onah, Chimdimma Noelyn, Richard Allmendinger, Julia Handl, and Ken W. Dunn. "Surviving Burn Injury: Drivers of Length of Hospital Stay." International Journal of Environmental Research and Public Health 18, no. 2 (January 18, 2021): 761. http://dx.doi.org/10.3390/ijerph18020761.
Full textAbstract:
With a reduction in the mortality rate of burn patients, length of stay (LOS) has been increasingly adopted as an outcome measure. Some studies have attempted to identify factors that explain a burn patient’s LOS. However, few have investigated the association between LOS and a patient’s mental and socioeconomic status. There is anecdotal evidence for links between these factors; uncovering these will aid in better addressing the specific physical and emotional needs of burn patients and facilitate the planning of scarce hospital resources. Here, we employ machine learning (clustering) and statistical models (regression) to investigate whether segmentation by socioeconomic/mental status can improve the performance and interpretability of an upstream predictive model, relative to a unitary model. Although we found no significant difference in the unitary model’s performance and the segment-specific models, the interpretation of the segment-specific models reveals a reduced impact of burn severity in LOS prediction with increasing adverse socioeconomic and mental status. Furthermore, the socioeconomic segments’ models highlight an increased influence of living circumstances and source of injury on LOS. These findings suggest that in addition to ensuring that patients’ physical needs are met, management of their mental status is crucial for delivering an effective care plan.
22
Takekawa, Daiki, Hideki Endo, Eiji Hashiba, and Kazuyoshi Hirota. "Predict models for prolonged ICU stay using APACHE II, APACHE III and SAPS II scores: A Japanese multicenter retrospective cohort study." PLOS ONE 17, no. 6 (June 16, 2022): e0269737. http://dx.doi.org/10.1371/journal.pone.0269737.
Full textAbstract:
Prolonged ICU stays are associated with high costs and increased mortality. Thus, early prediction of such stays would help clinicians to plan initial interventions, which could lead to efficient utilization of ICU resources. The aim of this study was to develop models for predicting prolonged stays in Japanese ICUs using APACHE II, APACHE III and SAPS II scores. In this multicenter retrospective cohort study, we analyzed the cases of 85,558 patients registered in the Japanese Intensive care Patient Database between 2015 and 2019. Prolonged ICU stay was defined as an ICU stay of >14 days. Multivariable logistic regression analyses were performed to develop three predictive models for prolonged ICU stay using APACHE II, APACHE III and SAPS II scores, respectively. After exclusions, 79,620 patients were analyzed, 2,364 of whom (2.97%) experienced prolonged ICU stays. Multivariable logistic regression analyses showed that severity scores, BMI, MET/RRT, postresuscitation, readmission, length of stay before ICU admission, and diagnosis at ICU admission were significantly associated with higher risk of prolonged ICU stay in all models. The present study developed predictive models for prolonged ICU stay using severity scores. These models may be helpful for efficient utilization of ICU resources.
23
Clark, David E., and Louise M. Ryan. "Concurrent Prediction of Hospital Mortality and Length of Stay from Risk Factors on Admission." Health Services Research 37, no. 3 (June 2002): 631–45. http://dx.doi.org/10.1111/1475-6773.00041.
Full text
24
Bottino, Francesca, Emanuela Tagliente, Luca Pasquini, Alberto Di Napoli, Martina Lucignani, Lorenzo Figà-Talamanca, and Antonio Napolitano. "COVID Mortality Prediction with Machine Learning Methods: A Systematic Review and Critical Appraisal." Journal of Personalized Medicine 11, no. 9 (September 7, 2021): 893. http://dx.doi.org/10.3390/jpm11090893.
Full textAbstract:
More than a year has passed since the report of the first case of coronavirus disease 2019 (COVID), and increasing deaths continue to occur. Minimizing the time required for resource allocation and clinical decision making, such as triage, choice of ventilation modes and admission to the intensive care unit is important. Machine learning techniques are acquiring an increasingly sought-after role in predicting the outcome of COVID patients. Particularly, the use of baseline machine learning techniques is rapidly developing in COVID mortality prediction, since a mortality prediction model could rapidly and effectively help clinical decision-making for COVID patients at imminent risk of death. Recent studies reviewed predictive models for SARS-CoV-2 diagnosis, severity, length of hospital stay, intensive care unit admission or mechanical ventilation modes outcomes; however, systematic reviews focused on prediction of COVID mortality outcome with machine learning methods are lacking in the literature. The present review looked into the studies that implemented machine learning, including deep learning, methods in COVID mortality prediction thus trying to present the existing published literature and to provide possible explanations of the best results that the studies obtained. The study also discussed challenging aspects of current studies, providing suggestions for future developments.
25
KOCATÜRK, İdris, and Sedat GÜLTEN. "Immature granulocyte and other markers in prediction of the short-term and long-term prognosis of patients with acute ischemic stroke." Neurology Asia 28, no. 4 (December 2023): 825–33. http://dx.doi.org/10.54029/2023dcd.
Full textAbstract:
Background & Objectives: To evaluate immature granulocytes, a new inflammatory biomarker, and other markers in short- and long-term prognosis in patients with acute ischemic stroke (AIS). Methods: Laboratory information system data from a tertiary hospital in Turkiye were used in this retrospective study. Of the 327 patients with the diagnosis of AIS, 275 recovered, and 52 died. It was determined that 31 of these 275 patients, who were followed up retrospectively, died within 12 months after discharge. Routinely measured immature granulocyte (IG), other hemogram parameters in the Sysmex XN 1000 (XN-1000-Hematology-Analyzer-Sysmex Corporation, Japan), and demographic data were statistically compared in both groups. We tried to estimate the short- and long-term mortality from the blood samples of these patients at their first admission to the hospital. Results: Of the patients included in the study, 150 (45.9%) were female, and 177 (54.1%) were male. National Institutes Of Health Stroke Scale (NIHSS) (AUC=960), length of stay (AUC=791), red blood cell distribution width – standard deviation (RDW-CV) (AUC=728), and IG (AUC=712) were the most effective parameters in predicting short-term mortality, while age (AUC=764) in predicting long-term mortality was the most effective parameters. Conclusion: IG, together with NIHSS and length of stay, shows moderate and high predictive properties in prognosticating short-term mortality but is ineffective in prognosticating long-term mortality. Age was found to be the most predictive marker for long-term mortality.
26
Balan, Gheorghe Gh, Oana Timofte, Georgiana-Emmanuela Gilca-Blanariu, Catalin Sfarti, Smaranda Diaconescu, Nicoleta Gimiga, Simona Petronela Antighin, et al. "Predicting Hospitalization, Organ Dysfunction, and Mortality in Post-Endoscopic Retrograde Cholangiopancreatography Acute Pancreatitis: Are SIRS and qSOFA Reliable Tools?" Applied Sciences 13, no. 11 (May 30, 2023): 6650. http://dx.doi.org/10.3390/app13116650.
Full textAbstract:
Background: Post-endoscopic retrograde cholangiopancreatography (ERCP) pancreatitis (PEP) has shown constant incidence throughout time, despite advances in endoscopic technology, devices, or personal skills of the operating endoscopists, with prevention and prediction of severity in PEP being constant concerns. Several prospective studies have investigated the role of systemic inflammatory response syndrome (SIRS) criteria or the quick Sequential Organ Failure Assessment (qSOFA) score in the PEP severity assessment. However, there are no clearly defined tools for the prediction of PEP severity. Methods: A total of 403 patients were prospectively monitored 60 days after ERCP for the detection of PEP development. Consequently, we evaluated the lengths of stay, incidence of organic dysfunction, and mortality rates of these patients. The predictive power of the univariate model was evaluated by using the receiver operating characteristic curve and analyzing the area under the curve (AUC). Results: Incidence of PEP was similar to that reported in the majority of trials. The 60-day survival rate of PEP patients reached 82.8%. A qSOFA score ≥ 1 is a very good predictor for organ dysfunction (AUC 0.993, p < 0.0001). SIRS can also be considered a significant predictor for organic dysfunctions in PEP patients (AUC 0.926, p < 0.0001). However, only qSOFA was found to significantly predict mortality in PEP patients (AUC 0.885, p = 0.003), with SIRS criteria showing a much lower predictive power. Neither SIRS nor qSOFA showed any predictive value for the length of stay of PEP patients. Conclusion: Our study offers novel information about severity prediction in PEP patients. Both SIRS criteria and qSOFA showed good predictive value for organic dysfunction, mortality, and hospitalization.
27
Jaskolowska, Joanna, Elzbieta Balcerzyk-Barzdo, Agnieszka Jozwik, Tomasz Gaszynski, and Pawel Ratajczyk. "Selected Predictors of COVID-19 Mortality in the Hospitalised Patient Population in a Single-Centre Study in Poland." Healthcare 11, no. 5 (March 1, 2023): 719. http://dx.doi.org/10.3390/healthcare11050719.
Full textAbstract:
Background: The correct analysis of COVID-19 predictors could substantially improve the clinical decision-making process and enable emergency department patients at higher mortality risk to be identified. Methods: We retrospectively explored the relationship between some demographic and clinical factors, such as age and sex, as well as the levels of ten selected factors, namely, CRP, D-dimer, ferritin, LDH, RDW-CV, RDW-SD, procalcitonin, blood oxygen saturation, lymphocytes, and leukocytes, and COVID-19 mortality risk in 150 adult patients diagnosed with COVID-19 at Provincial Specialist Hospital in Zgierz, Poland (this hospital was transformed, in March 2020, into a hospital admitting COVID-19 cases only). All blood samples for testing were collected in the emergency room before admission. The length of stay in the intensive care unit and length of hospitalisation were also analysed. Results: The only factor that was not significantly related to mortality was the length of stay in the intensive care unit. The odds of dying were significantly lower in males, patients with a longer hospital stay, patients with higher lymphocyte levels, and patients with higher blood oxygen saturation, while the chances of dying were significantly higher in older patients; patients with higher RDW-CV and RDW-SD levels; and patients with higher levels of leukocytes, CRP, ferritin, procalcitonin, LDH, and D-dimers. Conclusions: Six potential predictors of mortality were included in the final model: age, RDW-CV, procalcitonin, and D-dimers level; blood oxygen saturation; and length of hospitalisation. The results obtained from this study suggest that a final predictive model with high accuracy in mortality prediction (over 90%) was successfully built. The suggested model could be used for therapy prioritization.
28
Singer, Kathleen, Jalen Harvey, and Elizabeth Dale. "516 Mortality from Inhalation Injury in Oxygen Dependent Patients Exceeds Prediction from Prognostic Models." Journal of Burn Care & Research 41, Supplement_1 (March 2020): S95—S96. http://dx.doi.org/10.1093/jbcr/iraa024.148.
Full textAbstract:
Abstract Introduction The Boston Criteria and the Abbreviated Burn Severity Index (ABSI) are two widely accepted models for predicting mortality in burn patients. We aimed to elucidate whether these models are able to accurately predict risk of mortality in patients who sustain burns while smoking on home oxygen given their overall clinical fragility. Methods We conducted a retrospective chart review of 48 patients admitted to our burn center from November 2013 to September 2017 who sustained a burn while smoking on home oxygen. Yearlong mortality was the primary outcome of the investigation; secondary outcomes included discharge to facility, length of stay, and need for tracheostomy. We then calculated the expected mortality rate for each patient based on Boston Criteria and ABSI, respectively, and compared the mortality rate observed in our cohort. Results Patients in our cohort suffered a 54% mortality rate within a year of injury, compared to a 23.5% mortality predicted by Boston Criteria, which was found to be statistically significant by chi-square analysis (p < 0.05). ABSI predicted mortality was 19.7%. While the absolute value of difference in mortality was greater, this was not found to be significant on chi-square analysis due to the small sample size. Our secondary outcomes revealed 42% discharge to facility, average length of stay of 6.2 days, and 6.25% required tracheostomy. Patients in our cohort suffered a 54% mortality rate within a year of injury, compared to a 23.5% mortality predicted by Boston Criteria, which was found to be statistically significant by chi-square analysis (p < 0.05). ABSI predicted mortality was 19.7%. While the absolute value of difference in mortality was greater, this was not found to be significant on chi-square analysis due to the small sample size. Our secondary outcomes revealed 42% discharge to facility, average length of stay of 6.2 days, and 6.25% required tracheostomy. Conclusions Patients whose burns are attributable to smoking on home oxygen may have an increased risk of mortality than prognostication models, such as the Boston Criteria and ABSI, may suggest. This bears significant clinical impact, particularly regarding family and provider decision-making in pursuing aggressive management. Applicability of Research to Practice This data indicates that these injuries are direr than expected, which may have significant impact on family and provider decision-making.
29
Prabhakar, P. Niranjan, R. Anand, K. Rajkumar, and V. Sri Andaal. "The Impact of Serum Albumin on the Mortality Prediction in COVID Patients at a Private Hospital in Madurai." Journal of Association of Pulmonologist of Tamil Nadu 7, no. 1 (2024): 2–4. http://dx.doi.org/10.4103/japt.japt_38_23.
Full textAbstract:
Abstract Background: The objective of the study was to identify the serum albumin levels and their correlation with the length of hospital stay and mortality in coronavirus disease 2019 (COVID-19) patients. To achieve this, we studied the correlation between serum albumin levels to the length of hospital stay and mortality outcomes. Materials and Methods: It is a retrospective observational study in which information about COVID-19 patients admitted to a private hospital in Madurai was collected between March 2021 and August 2021. The time from admission to discharge of patients and mortality outcomes was taken into account. Results: A total of 176 COVID-19 patients were included, of which 150 patients (85%) recovered and 26 patients (15%) died during the hospital admission. The median length of hospital stays of COVID-19 patients who were hospitalized and discharged alive was found to be 8.5 ± 4.6 days by the Kaplan–Meier curve. The mean albumin levels in alive patients were found to be 3.5 ± 0.37 g/dl compared to expired COVID-19 patients with low albumin levels of 3.3 ± 043 g/dl. Hence, we conclude that serum albumin levels had an impact on the outcome and hospital stay. Conclusion: Serum albumin levels at admission might reflect the severity of infection and thus can serve as a predictive factor for COVID-19 outcomes.
30
Huang, Kexin, Tamryn F. Gray, Santiago Romero-Brufau, James A. Tulsky, and Charlotta Lindvall. "Using nursing notes to improve clinical outcome prediction in intensive care patients: A retrospective cohort study." Journal of the American Medical Informatics Association 28, no. 8 (April 21, 2021): 1660–66. http://dx.doi.org/10.1093/jamia/ocab051.
Full textAbstract:
Abstract Objective Electronic health record documentation by intensive care unit (ICU) clinicians may predict patient outcomes. However, it is unclear whether physician and nursing notes differ in their ability to predict short-term ICU prognosis. We aimed to investigate and compare the ability of physician and nursing notes, written in the first 48 hours of admission, to predict ICU length of stay and mortality using 3 analytical methods. Materials and Methods This was a retrospective cohort study with split sampling for model training and testing. We included patients ≥18 years of age admitted to the ICU at Beth Israel Deaconess Medical Center in Boston, Massachusetts, from 2008 to 2012. Physician or nursing notes generated within the first 48 hours of admission were used with standard machine learning methods to predict outcomes. Results For the primary outcome of composite score of ICU length of stay ≥7 days or in-hospital mortality, the gradient boosting model had better performance than the logistic regression and random forest models. Nursing and physician notes achieved area under the curves (AUCs) of 0.826 and 0.796, respectively, with even better predictive power when combined (AUC, 0.839). Discussion Models using only nursing notes more accurately predicted short-term prognosis than did models using only physician notes, but in combination, the models achieved the greatest accuracy in prediction. Conclusions Our findings demonstrate that statistical models derived from text analysis in the first 48 hours of ICU admission can predict patient outcomes. Physicians’ and nurses’ notes are both uniquely important in mortality prediction and combining these notes can produce a better predictive model.
31
BEDUSCHI, Murilo Gamba, André Luiz Parizi MELLO, Bruno VON-MÜHLEN, and Orli FRANZON. "THE PANC 3 SCORE PREDICTING SEVERITY OF ACUTE PANCREATITIS." ABCD. Arquivos Brasileiros de Cirurgia Digestiva (São Paulo) 29, no. 1 (March 2016): 5–8. http://dx.doi.org/10.1590/0102-6720201600010002.
Full textAbstract:
Background: About 20% of cases of acute pancreatitis progress to a severe form, leading to high mortality rates. Several studies suggested methods to identify patients that will progress more severely. However, most studies present problems when used on daily practice. Objective: To assess the efficacy of the PANC 3 score to predict acute pancreatitis severity and its relation to clinical outcome. Methods: Acute pancreatitis patients were assessed as to sex, age, body mass index (BMI), etiology of pancreatitis, intensive care need, length of stay, length of stay in intensive care unit and mortality. The PANC 3 score was determined within the first 24 hours after diagnosis and compared to acute pancreatitis grade of the Revised Atlanta classification. Results: Out of 64 patients diagnosed with acute pancreatitis, 58 met the inclusion criteria. The PANC 3 score was positive in five cases (8.6%), pancreatitis progressed to a severe form in 10 cases (17.2%) and five patients (8.6%) died. Patients with a positive score and severe pancreatitis required intensive care more often, and stayed for a longer period in intensive care units. The PANC 3 score showed sensitivity of 50%, specificity of 100%, accuracy of 91.4%, positive predictive value of 100% and negative predictive value of 90.6% in prediction of severe acute pancreatitis. Conclusion: The PANC 3 score is useful to assess acute pancreatitis because it is easy and quick to use, has high specificity, high accuracy and high predictive value in prediction of severe acute pancreatitis.
32
Ariaka, Herbert, Joel Kiryabwire, Ssenyonjo Hussein, Alfred Ogwal, Emmanuel Nkonge, and Felix Oyania. "A Comparison of the Predictive Value of the Glasgow Coma Scale and the Kampala Trauma Score for Mortality and Length of Hospital Stay in Head Injury Patients at a Tertiary Hospital in Uganda: A Diagnostic Prospective Study." Surgery Research and Practice 2020 (October 13, 2020): 1–9. http://dx.doi.org/10.1155/2020/1362741.
Full textAbstract:
Introduction. The prevalence rates of head injury have been shown to be as high as 25% among trauma patients with severe head injury contributing to about 31% of all trauma deaths. Triage utilizes numerical cutoff points along the scores continuum to predict the greatest number of people who would have a poor outcome, “severe” patients, when scoring below the threshold and a good outcome “non severe” patients, when scoring above the cutoff or numerical threshold. This study aimed to compare the predictive value of the Glasgow Coma Scale and the Kampala Trauma Score for mortality and length of hospital stay at a tertiary hospital in Uganda. Methods. A diagnostic prospective study was conducted from January 12, 2018 to March 16, 2018. We recruited patients with head injury admitted to the accidents and emergency department who met the inclusion criteria for the study. Data on patient’s demographic characteristics, mechanisms of injury, category of road use, and classification of injury according to the GCS and KTS at initial contact and at 24 hours were collected. The receiver operating characteristics (ROC) analysis and logistic regression analysis were used for comparison. Results. The GCS predicted mortality and length of hospital stay with the GCS at admission with AUC of 0.9048 and 0.7972, respectively (KTS at admission time, AUC 0.8178 and 0.7243). The GCS predicted mortality and length of hospital stay with the GCS at 24 hours with AUC of 0.9567 and 0.8203, respectively (KTS at 24 hours, AUC 0.8531 and 0.7276). At admission, the GCS at a cutoff of 11 had a sensitivity of 83.23% and specificity of 82.61% while the KTS had 88.02% and 73.91%, respectively, at a cutoff of 13 for predicting mortality. At admission, the GCS at a cutoff of 13 had sensitivity of 70.48% and specificity of 66.67% while the KTS had 68.07% and 62.50%, respectively, at a cutoff of 14 for predicting length of hospital stay. Conclusion. Comparatively, the GCS performed better than the KTS in predicting mortality and length of hospital stay. The GCS was also more accurate at labelling the head injury patients who died as severely injured as opposed to the KTS that categorized most of them as moderately injured. In general, the two scores were sensitive at detection of mortality and length of hospital stay among the study population.
33
Alemneh, Girma Neshir, Hirut Bekele Ashagrie, and Lemlem K. Tegegne. "Feature Selection Methods for ICU Mortality Prediction Model." Journal of Computational Science and Data Analytics 01, no. 1 (September 30, 2024): 14–38. http://dx.doi.org/10.69660/jcsda.01012402.
Full textAbstract:
The goal of this research is to offer insightful information that can improve Ethiopia's intensive care unit (ICU) services. There is an increased risk of patients' death in Intensive Care Units (ICUs). This is because of several variables, including preexisting medical issues, lack of resources, and delayed decisions. Healthcare professionals can better prioritize their patients in need of intensive care, distribute resources more efficiently, and enhance patient outcomes by using predictive models to estimate ICU mortality. ICU data is collected from five Ethiopian public hospitals to develop a machine learning method for predicting ICU mortality. The data includes demographic features, vital signs, lab results, and discharge status of 10,798 ICU dataset records. We employed a range of feature selection techniques, such as filters, wrappers, and embedding methods, to identify the most crucial features for mortality prediction. We also compared the performance of two machine learning algorithms, Random Forest and Decision Tree. These models are trained using ICU data with features encompassing age, length of stay, temperature, neutrophil, Diagnosis (DX) condition, PH, and Lymphocite. These features are selected using Recursive Feature Elimination (RFE). Using a number of different evaluation methods, including accuracy (99.7%), precision (99.4%), recall (98.8%), F1 score (99.1%), and area under the curve (AUC) (99.3%), Random Forest performed better than Decision Tree. Based on our findings, we made recommendations for healthcare practitioners and policy makers. We also suggest key future research directions for researchers in the area.
34
Zisiopoulou, Maria, Alexander Berkowitsch, Leonard Redlich, Thomas Walther, Stephan Fichtlscherer, and David M. Leistner. "Personalised preinterventional risk stratification of mortality, length of stay and hospitalisation costs in transcatheter aortic valve implantation using a machine learning algorithm: a pilot trial." Open Heart 11, no. 1 (February 2024): e002540. http://dx.doi.org/10.1136/openhrt-2023-002540.
Full textAbstract:
IntroductionRisk stratification based on Euroscore II (ESII) is used in some centres to assist decisions to perform transcatheter aortic valve implant (TAVI) procedures. ESII is a generic, non-TAVI-specific metric, and its performance fades for mortality at follow-up longer than 30 days. We investigated if a TAVI-specific predictive model could achieve improved predictive preinterventional accuracy of 1-year mortality compared with ESII.Patients and methodsIn this prospective pilot study, 284 participants with severe symptomatic aortic valve stenosis who underwent TAVI were enrolled. Standard clinical metrics (American Society of Anesthesiology (ASA), New York Heart Association and ESII) and patient-reported outcome measures (EuroQol-5 Dimension-Visual Analogue Scale, Kansas City Cardiomyopathy Questionnaire and Clinical Frailty Scale (CFS)) were assessed 1 day before TAVI. Using these data, we tested predictive models (logistic regression and decision tree algorithm (DTA)) with 1-year mortality as the dependent variable.ResultsLogistic regression yielded the best prediction, with ASA and CFS as the strongest predictors of 1-year mortality. Our logistic regression model score showed significantly better prediction accuracy than ESII (area under the curve=0.659 vs 0.800; p=0.002). By translating our results to a DTA, cut-off score values regarding 1-year mortality risk emerged for low, intermediate and high risk. Treatment costs and length of stay (LoS) significantly increased in high-risk patients.Conclusions and significanceA novel TAVI-specific model predicts 1-year mortality, LoS and costs after TAVI using simple, established, transparent and inexpensive metrics before implantation. Based on this preliminary evidence, TAVI team members and patients can make informed decisions based on a few key metrics. Validation of this score in larger patient cohorts is needed.
35
Kim, Jee-Yun, Jeong Yee, Tae-Im Park, So-Youn Shin, Man-Ho Ha, and Hye-Sun Gwak. "Risk Scoring System of Mortality and Prediction Model of Hospital Stay for Critically Ill Patients Receiving Parenteral Nutrition." Healthcare 9, no. 7 (July 6, 2021): 853. http://dx.doi.org/10.3390/healthcare9070853.
Full textAbstract:
Predicting the clinical progression of intensive care unit (ICU) patients is crucial for survival and prognosis. Therefore, this retrospective study aimed to develop the risk scoring system of mortality and the prediction model of ICU length of stay (LOS) among patients admitted to the ICU. Data from ICU patients aged at least 18 years who received parenteral nutrition support for ≥50% of the daily calorie requirement from February 2014 to January 2018 were collected. In-hospital mortality and log-transformed LOS were analyzed by logistic regression and linear regression, respectively. For calculating risk scores, each coefficient was obtained based on regression model. Of 445 patients, 97 patients died in the ICU; the observed mortality rate was 21.8%. Using logistic regression analysis, APACHE II score (15–29: 1 point, 30 or higher: 2 points), qSOFA score ≥ 2 (2 points), serum albumin level < 3.4 g/dL (1 point), and infectious or respiratory disease (1 point) were incorporated into risk scoring system for mortality; patients with 0, 1, 2–4, and 5–6 points had approximately 10%, 20%, 40%, and 65% risk of death. For LOS, linear regression analysis showed the following prediction equation: log(LOS) = 0.01 × (APACHE II) + 0.04 × (total bilirubin) − 0.09 × (admission diagnosis of gastrointestinal disease or injury, poisoning, or other external cause) + 0.970. Our study provides the mortality risk score and LOS prediction equation. It could help clinicians to identify those at risk and optimize ICU management.
36
Vong, Tyrus, Lisa R. Yanek, Lin Wang, Huimin Yu, Christopher Fan, Elinor Zhou, Sun Jung Oh, et al. "Malnutrition Increases Hospital Length of Stay and Mortality among Adult Inpatients with COVID-19." Nutrients 14, no. 6 (March 21, 2022): 1310. http://dx.doi.org/10.3390/nu14061310.
Full textAbstract:
Background: Malnutrition has been linked to adverse health economic outcomes. There is a paucity of data on malnutrition in patients admitted with COVID-19. Methods: This is a retrospective cohort study consisting of 4311 COVID-19 adult (18 years and older) inpatients at 5 Johns Hopkins-affiliated hospitals between 1 March and 3 December 2020. Malnourishment was identified using the malnutrition universal screening tool (MUST), then confirmed by registered dietitians. Statistics were conducted with SAS v9.4 (Cary, NC, USA) software to examine the effect of malnutrition on mortality and hospital length of stay among COVID-19 inpatient encounters, while accounting for possible covariates in regression analysis predicting mortality or the log-transformed length of stay. Results: COVID-19 patients who were older, male, or had lower BMIs had a higher likelihood of mortality. Patients with malnutrition were 76% more likely to have mortality (p < 0.001) and to have a 105% longer hospital length of stay (p < 0.001). Overall, 12.9% (555/4311) of adult COVID-19 patients were diagnosed with malnutrition and were associated with an 87.9% increase in hospital length of stay (p < 0.001). Conclusions: In a cohort of COVID-19 adult inpatients, malnutrition was associated with a higher likelihood of mortality and increased hospital length of stay.
37
Jones, Dominic, Allan Cameron, David J. Lowe, Suzanne M. Mason, Colin A. O'Keeffe, and Eilidh Logan. "Multicentre, prospective observational study of the correlation between the Glasgow Admission Prediction Score and adverse outcomes." BMJ Open 9, no. 8 (August 2019): e026599. http://dx.doi.org/10.1136/bmjopen-2018-026599.
Full textAbstract:
ObjectivesTo assess whether the Glasgow Admission Prediction Score (GAPS) is correlated with hospital length of stay, 6-month hospital readmission and 6-month all-cause mortality. This study represents a 6-month follow-up of patients who were included in an external validation of the GAPS’ ability to predict admission at the point of triage.SettingSampling was conducted between February and May 2016 at two separate emergency departments (EDs) in Sheffield and Glasgow.ParticipantsData were collected prospectively at triage for consecutive adult patients who presented to the ED within sampling times. Any patients who avoided formal triage were excluded from the study. In total, 1420 patients were recruited.Primary outcomesGAPS was calculated following triage and did not influence patient management. Length of hospital stay, hospital readmission and mortality against GAPS were modelled using survival analysis at 6 months.ResultsOf the 1420 patients recruited, 39.6% of these patients were initially admitted to hospital. At 6 months, 30.6% of patients had been readmitted and 5.6% of patients had died. For those admitted at first presentation, the chance of being discharged fell by 4.3% (95% CI 3.2% to 5.3%) per GAPS point increase. Cox regression indicated a 9.2% (95% CI 7.3% to 11.1%) increase in the chance of 6-month hospital readmission per point increase in GAPS. An association between GAPS and 6-month mortality was demonstrated, with a hazard increase of 9.0% (95% CI 6.9% to 11.2%) for every point increase in GAPS.ConclusionA higher GAPS is associated with increased hospital length of stay, 6-month hospital readmission and 6-month all-cause mortality. While GAPS’s primary application may be to predict admission and support clinical decision making, GAPS may provide valuable insight into inpatient resource allocation and bed planning.
38
Attia, A. F. "Predictive models for mortality and length of hospital stay in an Egyptian burns centre." Eastern Mediterranean Health Journal 6, no. 5-6 (December 15, 2000): 1055–61. http://dx.doi.org/10.26719/2000.6.5-6.1055.
Full textAbstract:
Our aim was to obtain a statistical profile of survivors and deaths among burn victims and to develop predictive models for mortality and length of hospital stay. All patients admitted to the Burns Unit of Alexandria Main University Hospital over a 1-year period were included. Of 533 cases, mean length of hospital stay was 15.5 +/- 21.6 days and the mortality rate was 33%. Total surface area burnt, inhalation burns, age, sex, depth and degree of burn wounds were the significant independent predictors of mortality in multiple logistic regression analysis. The significant independent predictors of the length of hospital stay were clothing ignition, total surface area burnt, sex, degree and depth of burn and inhalation burns.
39
Pouwels, Sjaak, Dharmanand Ramnarain, Emily Aupers, Laura Rutjes-Weurding, and Jos van Oers. "Obesity May Not Be Associated with 28-Day Mortality, Duration of Invasive Mechanical Ventilation and Length of Intensive Care Unit and Hospital Stay in Critically Ill Patients with Severe Acute Respiratory Syndrome Coronavirus-2: A Retrospective Cohort Study." Medicina 57, no. 7 (June 29, 2021): 674. http://dx.doi.org/10.3390/medicina57070674.
Full textAbstract:
Background and Objectives: The aim of this study was to investigate the association between obesity and 28-day mortality, duration of invasive mechanical ventilation and length of stay at the Intensive Care Unit (ICU) and hospital in patients admitted to the ICU for SARS-CoV-2 pneumonia. Materials and Methods: This was a retrospective observational cohort study in patients admitted to the ICU for SARS-CoV-2 pneumonia, in a single Dutch center. The association between obesity (body mass index > 30 kg/m2) and 28-day mortality, duration of invasive mechanical ventilation and length of ICU and hospital stay was investigated. Results: In 121 critically ill patients, pneumonia due to SARS-CoV-2 was confirmed by RT-PCR. Forty-eight patients had obesity (33.5%). The 28-day all-cause mortality was 28.1%. Patients with obesity had no significant difference in 28-day survival in Kaplan–Meier curves (log rank p 0.545) compared with patients without obesity. Obesity made no significant contribution in a multivariate Cox regression model for prediction of 28-day mortality (p = 0.124), but age and the Sequential Organ Failure Assessment (SOFA) score were significant independent factors (p < 0.001 and 0.002, respectively). No statistically significant correlation was observed between obesity and duration of invasive mechanical ventilation and length of ICU and hospital stay. Conclusion: One-third of the patients admitted to the ICU for SARS-CoV-2 pneumonia had obesity. The present study showed no relationship between obesity and 28-day mortality, duration of invasive mechanical ventilation, ICU and hospital length of stay. Further studies are needed to substantiate these findings.
40
Maldonado Belmonte, Enrique, Salvador Oton-Tortosa, Jose-Maria Gutierrez-Martinez, and Ana Castillo-Martinez. "An Intelligent Model and Methodology for Predicting Length of Stay and Survival in a Critical Care Hospital Unit." Informatics 11, no. 2 (May 17, 2024): 34. http://dx.doi.org/10.3390/informatics11020034.
Full textAbstract:
This paper describes the design and methodology for the development and validation of an intelligent model in the healthcare domain. The generated model relies on artificial intelligence techniques, aiming to predict the length of stay and survival rate of patients admitted to a critical care hospitalization unit with better results than predictive systems using scoring. The proposed methodology is based on the following stages: preliminary data analysis, analysis of the architecture and systems integration model, the big data model approach, information structure and process development, and the application of machine learning techniques. This investigation substantiates that automated machine learning models significantly surpass traditional prediction techniques for patient outcomes within critical care settings. Specifically, the machine learning-based model attained an F1 score of 0.351 for mortality forecast and 0.615 for length of stay, in contrast to the traditional scoring model’s F1 scores of 0.112 for mortality and 0.412 for length of stay. These results strongly support the advantages of integrating advanced computational techniques in critical healthcare environments. It is also shown that the use of integration architectures allows for improving the quality of the information by providing a data repository large enough to generate intelligent models. From a clinical point of view, obtaining more accurate results in the estimation of the ICU stay and survival offers the possibility of expanding the uses of the model to the identification and prioritization of patients who are candidates for admission to the ICU, as well as the management of patients with specific conditions.
41
Chiavone, Paulo Antonio, and Samir Rasslan. "Influence of time elapsed from end of emergency surgery until admission to intensive care unit, on Acute Physiology and Chronic Health Evaluation II (APACHE II) prediction and patient mortality rate." Sao Paulo Medical Journal 123, no. 4 (2005): 167–74. http://dx.doi.org/10.1590/s1516-31802005000400003.
Full textAbstract:
CONTEXT AND OBJECTIVE: Patients are often admitted to intensive care units with delay in relation to when this service was indicated. The objective was to verify whether this delay influences hospital mortality, length of stay in the unit and hospital, and APACHE II prediction. DESIGN AND SETTING: Prospective and accuracy study, in intensive care unit of Santa Casa de São Paulo, a tertiary university hospital. METHODS: We evaluated all 94 patients admitted following emergency surgery, from August 2002 to July 2003. The variables studied were APACHE II, death risk, length of stay in the unit and hospital, and hospital mortality rate. The patients were divided into two groups according to the time elapsed between end of surgery and admission to the unit: up to 12 hours and over 12 hours. RESULTS: The groups were similar regarding gender, age, diagnosis, APACHE II score and hospital stay. The death risk factors were age, APACHE II and elapsed time (p < 0.02). The mortality rate for the over 12-hour group was higher (54% versus 26.1%; p = 0.018). For the over 12-hour group, observed mortality was higher than expected mortality (p = 0.015). For the up to 12-hour group, observed and expected mortality were similar (p = 0.288). CONCLUSION: APACHE II foresaw the mortality rate among patients that arrived faster to the intensive care unit, while the mortality rate was higher among those patients whose admission to the intensive care unit took longer.
42
Mahbub, Maria, Sudarshan Srinivasan, Ioana Danciu, Alina Peluso, Edmon Begoli, Suzanne Tamang, and Gregory D. Peterson. "Unstructured clinical notes within the 24 hours since admission predict short, mid & long-term mortality in adult ICU patients." PLOS ONE 17, no. 1 (January 6, 2022): e0262182. http://dx.doi.org/10.1371/journal.pone.0262182.
Full textAbstract:
Mortality prediction for intensive care unit (ICU) patients is crucial for improving outcomes and efficient utilization of resources. Accessibility of electronic health records (EHR) has enabled data-driven predictive modeling using machine learning. However, very few studies rely solely on unstructured clinical notes from the EHR for mortality prediction. In this work, we propose a framework to predict short, mid, and long-term mortality in adult ICU patients using unstructured clinical notes from the MIMIC III database, natural language processing (NLP), and machine learning (ML) models. Depending on the statistical description of the patients’ length of stay, we define the short-term as 48-hour and 4-day period, the mid-term as 7-day and 10-day period, and the long-term as 15-day and 30-day period after admission. We found that by only using clinical notes within the 24 hours of admission, our framework can achieve a high area under the receiver operating characteristics (AU-ROC) score for short, mid and long-term mortality prediction tasks. The test AU-ROC scores are 0.87, 0.83, 0.83, 0.82, 0.82, and 0.82 for 48-hour, 4-day, 7-day, 10-day, 15-day, and 30-day period mortality prediction, respectively. We also provide a comparative study among three types of feature extraction techniques from NLP: frequency-based technique, fixed embedding-based technique, and dynamic embedding-based technique. Lastly, we provide an interpretation of the NLP-based predictive models using feature-importance scores.
43
Salo, Jonathan C., Patrick Leland Meadors, Sally J. Trufan, Nicole Lee Gower, Michael David Watson, Lauren A. Jeck, Joshua S. Hill, and Declan Walsh. "Patient-reported distress and symptoms predict post-esophagectomy outcomes." Journal of Clinical Oncology 37, no. 15_suppl (May 20, 2019): e15567-e15567. http://dx.doi.org/10.1200/jco.2019.37.15_suppl.e15567.
Full textAbstract:
e15567 Background: Esophagectomy is accompanied by significant morbidity, mortality and altered quality of life. Understanding the factors responsible for adverse post-operative outcomes is essential for risk stratification in the selection of patients for surgery. Patient-reported measures are important not only as treatment outcome metrics, but also in predicting tolerance to therapy. Postoperative length of stay is a convenient measurement of patient tolerance of surgery. Our study aim was to determine whether preoperative patient-reported measures could add additional predictive power to clinical variables in predicting postoperative length of stay. Methods: A tablet-based symptom screening tool measured Distress, Anxiety (GAD-2), and cancer-related symptoms preoperatively. A generalized linear model predicting postoperative length of stay was constructed using age, gender, insurance status, income, T stage, and sarcopenia (hand-grip strength < 25kg). Patient-reported variables were then evaluated for their ability to predict length of stay in addition to these clinical factors. Factors found not significant (p > 0.05) are indicated N.S. Results: Esophagectomy (n = 58): Median age 62 (IQR 54-70) and 46 men (79%). Adenocarcinoma in 52 (90%). Neoadjuvant chemoradiation administered in 37 (64%). Major complications occurred in 13 (22%). Median postoperative length of stay was 8 days (IQR 6-10). Distress, Pain, Nausea/Vomiting, Trouble Swallowing, and Insurance or Financial Concerns independently predicted postoperative longer length of stay on multivariable analysis, while accounting for preoperative clinical factors. Conclusions: Preoperative cancer patient symptom reporting adds additional information to traditional clinical factors in predicting length of stay post-esophagectomy. Patient-reported measures may identify patients who benefit from interventions for preoperative optimization.[Table: see text]
44
Takada, Julio Yoshio, Rogério Bicudo Ramos, Solange Desiree Avakian, Soane Mota dos Santos, José Antonio Franchini Ramires, and Antonio de Pádua Mansur. "BNP and Admission Glucose as In-Hospital Mortality Predictors in Non-ST Elevation Myocardial Infarction." Scientific World Journal 2012 (2012): 1–7. http://dx.doi.org/10.1100/2012/397915.
Full textAbstract:
Objectives. Admission hyperglycemia and B-type natriuretic peptide (BNP) are associated with mortality in acute coronary syndromes, but no study compares their prediction in-hospital death.Methods. Patients with non-ST-elevation myocardial infarction (NSTEMI), in-hospital mortality and two-year mortality or readmission were compared for area under the curve (AUC), sensitivity (SEN), specificity (SPE), positive predictive value (PPV), negative predictive value (NPV), and accuracy (ACC) of glycemia and BNP.Results. Respectively, AUC, SEN, SPE, PPV, NPV, and ACC for prediction of in-hospital mortality were 0.815, 71.4%, 84.3%, 26.3%, 97.4%, and 83.3% for glycemia = 200 mg/dL and 0.748, 71.4%, 68.5%, 15.2%, 96.8% and 68.7% for BNP = 300 pg/mL. AUC of glycemia was similar to BNP (P=0.411). In multivariate analysis we found glycemia ≥200mg/dL related to in-hospital death (P=0.004). No difference was found in two-year mortality or readmission in BNP or hyperglycemic subgroups.Conclusion. Hyperglycemia was an independent risk factor for in-hospital mortality in NSTEMI and had a good ROC curve level. Hyperglycemia and BNP, although poor in-hospital predictors of unfavorable events, were independent risk factors for death or length of stay >10 days. No relation was found between hyperglycemia or BNP and long-term events.
45
Patel, A., M. Johnson, and R. R. Aparasu. "Predicting in-hospital mortality and hospital length of stay in diabetic patients." Value in Health 16, no. 3 (May 2013): A17. http://dx.doi.org/10.1016/j.jval.2013.03.103.
Full text
46
Zisiopoulou, Maria, Alexander Berkowitsch, Philipp Seppelt, Andreas M. Zeiher, and Mariuca Vasa-Nicotera. "A Novel Method to Predict Mortality and Length of Stay after Transfemoral Transcatheter Aortic Valve Implantation." Medicina 57, no. 12 (December 6, 2021): 1332. http://dx.doi.org/10.3390/medicina57121332.
Full textAbstract:
Background and Objectives: We tested if a novel combination of predictors could improve the accuracy of outcome prediction after transfemoral transcatheter aortic valve implantation (TAVI). Materials and Methods: This prospective study recruited 169 participants (49% female; median age 81 years). The primary endpoint was midterm mortality; secondary endpoints were acute Valve Academic Research Consortium (VARC)-3 complication rate and post-TAVI in-hospital length of stay (LoS). EuroSCORE II (ESII), comorbidities (e.g., coronary artery disease), eGFR (estimated glomerular filtration rate; based on cystatin C), hemoglobin, creatinine, N-Terminal pro-Brain Natriuretic Peptide (NTproBNP) levels and patient-reported outcome measures (PROMs, namely EuroQol-5-Dimension-5-Levels, EQ5D5L; Kansas City Cardiomyopathy Questionnaire, KCCQ; clinical frailty scale, CFS) at baseline were tested as predictors. Regression (uni- and multi-variate Cox; linear; binary logistic) and receiver operating characteristic (ROC)-curve analysis were applied. Results: Within a median follow-up of 439 (318–585) days, 12 participants died (7.1%). Independent predictors of mortality using multivariate Cox regression were baseline eGFR (p = 0.001) and KCCQ (p = 0.037). Based on these predictors, a Linear Prediction Score (LPS1) was calculated. The LPS1-area under the curve (AUC)-value (0.761) was significantly higher than the ESII-AUC value (0.597; p = 0.035). Independent predictors for LoS > 6 days (the median LoS) were eGFR (p = 0.028), NTproBNP (p = 0.034), and EQ5D5L values (p = 0.002); a respective calculated LPS2 provided an AUC value of 0.677 (p < 0.001). Eighty participants (47.3%) experienced complications. Male sex predicted complications only in the univariate analysis. Conclusions: The combination of KCCQ and eGFR can better predict midterm mortality than ES II alone. Combining eGFR, NTproBNP, and EQ5D5L can reliably predict LoS after TAVI. This novel method improves personalized TAVI risk stratification and hence may help reduce post-TAVI risk.
47
Cao, Yang, Maximilian Peter Forssten, Babak Sarani, Scott Montgomery, and Shahin Mohseni. "Development and Validation of an XGBoost-Algorithm-Powered Survival Model for Predicting In-Hospital Mortality Based on 545,388 Isolated Severe Traumatic Brain Injury Patients from the TQIP Database." Journal of Personalized Medicine 13, no. 9 (September 19, 2023): 1401. http://dx.doi.org/10.3390/jpm13091401.
Full textAbstract:
Background: Traumatic brain injury (TBI) represents a significant global health issue; the traditional tools such as the Glasgow Coma Scale (GCS) and Abbreviated Injury Scale (AIS) which have been used for injury severity grading, struggle to capture outcomes after TBI. Aim and methods: This paper aims to implement extreme gradient boosting (XGBoost), a powerful machine learning algorithm that combines the predictions of multiple weak models to create a strong predictive model with high accuracy and efficiency, in order to develop and validate a predictive model for in-hospital mortality in patients with isolated severe traumatic brain injury and to identify the most influential predictors. In total, 545,388 patients from the 2013–2021 American College of Surgeons Trauma Quality Improvement Program (TQIP) database were included in the current study, with 80% of the patients used for model training and 20% of the patients for the final model test. The primary outcome of the study was in-hospital mortality. Predictors were patients’ demographics, admission status, as well as comorbidities, and clinical characteristics. Penalized Cox regression models were used to investigate the associations between the survival outcomes and the predictors and select the best predictors. An extreme gradient boosting (XGBoost)-powered Cox regression model was then used to predict the survival outcome. The performance of the models was evaluated using the Harrell’s concordance index (C-index). The time-dependent area under the receiver operating characteristic curve (AUC) was used to evaluate the dynamic cumulative performance of the models. The importance of the predictors in the final prediction model was evaluated using the Shapley additive explanations (SHAP) value. Results: On average, the final XGBoost-powered Cox regression model performed at an acceptable level for patients with a length of stay up to 250 days (mean time-dependent AUC = 0.713) in the test dataset. However, for patients with a length of stay between 20 and 213 days, the performance of the model was relatively poor (time-dependent AUC < 0.7). When limited to patients with a length of stay ≤20 days, which accounts for 95.4% of all the patients, the model achieved an excellent performance (mean time-dependent AUC = 0.813). When further limited to patients with a length of stay ≤5 days, which accounts for two-thirds of all the patients, the model achieved an outstanding performance (mean time-dependent AUC = 0.917). Conclusion: The XGBoost-powered Cox regression model can achieve an outstanding predictive ability for in-hospital mortality during the first 5 days, primarily based on the severity of the injury, the GCS on admission, and the patient’s age. These variables continue to demonstrate an excellent predictive ability up to 20 days after admission, a period of care that accounts for over 95% of severe TBI patients. Past 20 days of care, other factors appear to be the primary drivers of in-hospital mortality, indicating a potential window of opportunity for improving outcomes.
48
ElBarragah, Kesmat Abdelhamid, Mohamed Tawfiq Elrewiny, Ezzat Ali Ahmed, and Ahmed Abdelfattah Sabry. "Assessment of risk stratification scoring systems in upper gastrointestinal bleeding patients in the emergency department." Research and Opinion in Anesthesia & Intensive Care 10, no. 3 (July 2023): 242–49. http://dx.doi.org/10.4103/roaic.roaic_73_19.
Full textAbstract:
Background Acute upper gastrointestinal bleeding (UGIB) is a common medical emergency presented to the emergency department that requires early assessment and management. Many risk stratification scores have been developed to predict the clinical outcomes in patients with UGIB. The commonly used risk scores the Rockall scoring systems (PRS and FRS), Glasgow–Blatchford score (GBS) and AIMS65 score. Aim The aim of the present study was to assess and compare the ability of the wildly used risk scores the RS, GBS, and AIMS65 to predict the clinical outcomes in UGIB patients Patients and methods One hundred patients (age >18 years) with acute UGIB in the emergency department of Alexandria Main University Hospital were prospectively studied. All the study scores were calculated and compared using the area under the receiver operating characteristic curve (AUC) method to evaluate the performance of each score to predict the mortality, blood transfusion, endoscopic intervention, ICU admission, rebleeding, and length of hospital stay. Results Among the one hundred patients included in the study, 65% were males with a median of age 58 years. 56% had esophageal varices and 63% with liver disease. All the used scores were statistically significant in predicting all clinical outcomes. GBS had the best AUC among the AIMS65, PRS, and FRS scores in predicting mortality with (AUC= 0.80 vs. 0.76, 0.69), blood transfusion need with (AUC= 0.92 vs. 0.88, 0.87), ICU admission with (AUC= 0.86 vs. 0.83, 0.81), rebleeding with (AUC= 0.81 vs. 0.77, 0.69), and length of hospital stay with (AUC= 0.81 vs. 0.75. 0.79). Conclusion All the study scores (GBS, AIMS65, PRS, and FRS) were able to predict the clinical outcomes in the UGIB patients. GBS was the best performing risk score among the four scores for predicting all the clinical outcomes (mortality, blood transfusion, rebleeding, ICU admission, and length of hospital stay) except the prediction of endoscopic intervention in our study population.
49
Honna, Lulu, Silvia Triratna, Triwani Triwani, and Theodorus Theodorus. "Use of pediatric logistic organ dysfunction in determining prognostic among pediatric intensive care unIt patIents." Paediatrica Indonesiana 50, no. 6 (October 26, 2016): 347. http://dx.doi.org/10.14238/pi50.6.2010.347-50.
Full textAbstract:
Background Pediatric intensive care unit is the place for caring the children \\lith higher risk of mortality, usually with multiple organ dysfunction syndrome (MODS) that can increase difficulty in detennining prognostic. Th erefore, an objective severity of illness and organ dysfunction score is needed. Pediatric logistic organ dysfunction (PELOD) score can be considered as a representative for probability of death and predicting the prognostic.Objective To determine the prognostic of patients in PICU Mohammad Hoesin hospital (RSMH), Palembang, using PELOD score.Methods An observational study was conducted from April-September 2009 among PICU patients. PELOD score was assessed in the first 24 hour. S tatistical analysis was performed using Z-Mann Whitney test, Hosmer-Lemeshow goodness-of-fit, ROC curve and survival analysis Kaplan Meier (KM).Results There were 45 (55%) boys and 36 (44%) girls with mean age 51 (SD 6 ,4 7) months. Children with MODS were 75%. Death was 37 (45%) and survival was 44 (54%) with mean length of stay was 181,92 (SE 30,23) hours. PELOD score was from 0 to 51. The best PELOD score related to death in coordinate point was 20,5 with ROC 0,862. Length of stay in grup \\lith PELOD score < 20.5 was 371.22 (SE 82.13) hours and > 20.5 was 93 (SE 17.48) hours (log rank P=0.000). S urvival function KM showed that the higher PELOD score, the shorter length of stay in PICU.Henceforth, the higher probability prediction of mortality.Conclusion PELOD score can be used as a prognostic predictor of mortality among PICU patients in Mohammad Hoesin Hospital (RSMH), Palemhang.
50
Paterson, R., DC MacLeod, D. Thetford, A. Beattie, C. Graham, S. Lam, and D. Bell. "Prediction of in-hospital mortality and length of stay using an early warning scoring system: clinical audit." Clinical Medicine 6, no. 3 (May 1, 2006): 281–84. http://dx.doi.org/10.7861/clinmedicine.6-3-281.
Full text