Literatura académica sobre el tema "ML prognostic model"
Crea una cita precisa en los estilos APA, MLA, Chicago, Harvard y otros
Consulte las listas temáticas de artículos, libros, tesis, actas de conferencias y otras fuentes académicas sobre el tema "ML prognostic model".
Junto a cada fuente en la lista de referencias hay un botón "Agregar a la bibliografía". Pulsa este botón, y generaremos automáticamente la referencia bibliográfica para la obra elegida en el estilo de cita que necesites: APA, MLA, Harvard, Vancouver, Chicago, etc.
También puede descargar el texto completo de la publicación académica en formato pdf y leer en línea su resumen siempre que esté disponible en los metadatos.
Artículos de revistas sobre el tema "ML prognostic model"
1
Uneno, Yu, Tadayuki Kou, Masashi Kanai, Michio Yamamoto, Peng Xue, Yukiko Mori, Yasushi Kudo et al. "Prognostic model for survival in patients with advanced pancreatic cancer receiving palliative chemotherapy." Journal of Clinical Oncology 33, n.º 3_suppl (20 de enero de 2015): 248. http://dx.doi.org/10.1200/jco.2015.33.3_suppl.248.
Texto completoResumen
248 Background: The prognosis of patients with advanced pancreatic cancer (APC) is extremely poor. Several clinical and laboratory factors have been known to be associated with prognosis of APC patients. However, there are few clinically available prognostic models predicting survival in APC patients receiving palliative chemotherapy. Methods: To construct a prognostic model to predict survival in APC patients receiving palliative chemotherapy, we analyzed the clinical data from 306 consecutive patients with pathologically confirmed APC who received palliative chemotherapy. We selected six independent prognostic factors which remained independent prognostic factors after multivariate analysis. Thereafter, we rounded the regression coefficient (β) for each independent prognostic factor derived from the Cox regression equation (HR = eβ) and developed a prognostic index (PI). Results: Developed prognostic index (PI) was as follows: PI = 2 (if performance status score 2–3) + 1 (if metastatic disease) + 1 (if initially unresectable disease) + 1 (if carcinoembryonic antigen level ≥5.0 ng/ml) + 1 (if carbohydrate antigen 19-9 level ≥1000 U/ml) + 2 (if neutrophil–lymphocyte ratio ≥5). The patients were classified into three prognostic groups: favorable (PI 0–1, n = 73), intermediate (PI 2–3, n = 145), and poor prognosis (PI 4–8, n = 88). The median overall survival for each prognostic group was 16.5, 12.3 and 6.2 months, respectively, and the 1-year survival rates were 67.3%, 51.3%, and 19.1%, respectively (P < 0.01). The c index of the model was 0.658. This model was well calibrated to predict 1-year survival, in which overestimation (2.4% and 0.2% in the favorable and poor prognosis groups, respectively) and underestimation (3.6% in the intermediate prognosis group) were observed. Conclusions: This prognostic model based on readily available clinical factors would help clinicians in estimating the overall survival in APC patients receiving palliative chemotherapy.
2
Shen, Ziyuan, Shuo Zhang, Yaxue Jiao, Yuye Shi, Hao Zhang, Fei Wang, Ling Wang et al. "LASSO Model Better Predicted the Prognosis of DLBCL than Random Forest Model: A Retrospective Multicenter Analysis of HHLWG". Journal of Oncology 2022 (16 de septiembre de 2022): 1–10. http://dx.doi.org/10.1155/2022/1618272.
Texto completoResumen
Background. Diffuse large B-cell lymphoma (DLBCL) is a heterogeneous non-Hodgkin’s lymphoma with great clinical challenge. Machine learning (ML) has attracted substantial attention in diagnosis, prognosis, and treatment of diseases. This study is aimed at exploring the prognostic factors of DLBCL by ML. Methods. In total, 1211 DLBCL patients were retrieved from Huaihai Lymphoma Working Group (HHLWG). The least absolute shrinkage and selection operator (LASSO) and random forest algorithm were used to identify prognostic factors for the overall survival (OS) rate of DLBCL among twenty-five variables. Receiver operating characteristic (ROC) curve and decision curve analysis (DCA) were utilized to compare the predictive performance and clinical effectiveness of the two models, respectively. Results. The median follow-up time was 43.4 months, and the 5-year OS was 58.5%. The LASSO model achieved an Area under the curve (AUC) of 75.8% for the prognosis of DLBCL, which was higher than that of the random forest model (AUC: 71.6%). DCA analysis also revealed that the LASSO model could augment net benefits and exhibited a wider range of threshold probabilities by risk stratification than the random forest model. In addition, multivariable analysis demonstrated that age, white blood cell count, hemoglobin, central nervous system involvement, gender, and Ann Arbor stage were independent prognostic factors for DLBCL. The LASSO model showed better discrimination of outcomes compared with the IPI and NCCN-IPI models and identified three groups of patients: low risk, high-intermediate risk, and high risk. Conclusions. The prognostic model of DLBCL based on the LASSO regression was more accurate than the random forest, IPI, and NCCN-IPI models.
3
Qin, Yuchao, Ahmed Alaa, Andres Floto y Mihaela van der Schaar. "External validity of machine learning-based prognostic scores for cystic fibrosis: A retrospective study using the UK and Canadian registries". PLOS Digital Health 2, n.º 1 (12 de enero de 2023): e0000179. http://dx.doi.org/10.1371/journal.pdig.0000179.
Texto completoResumen
Precise and timely referral for lung transplantation is critical for the survival of cystic fibrosis patients with terminal illness. While machine learning (ML) models have been shown to achieve significant improvement in prognostic accuracy over current referral guidelines, the external validity of these models and their resulting referral policies has not been fully investigated. Here, we studied the external validity of machine learning-based prognostic models using annual follow-up data from the UK and Canadian Cystic Fibrosis Registries. Using a state-of-the-art automated ML framework, we derived a model for predicting poor clinical outcomes in patients enrolled in the UK registry, and conducted external validation of the derived model using the Canadian Cystic Fibrosis Registry. In particular, we studied the effect of (1) natural variations in patient characteristics across populations and (2) differences in clinical practice on the external validity of ML-based prognostic scores. Overall, decrease in prognostic accuracy on the external validation set (AUCROC: 0.88, 95% CI 0.88-0.88) was observed compared to the internal validation accuracy (AUCROC: 0.91, 95% CI 0.90-0.92). Based on our ML model, analysis on feature contributions and risk strata revealed that, while external validation of ML models exhibited high precision on average, both factors (1) and (2) can undermine the external validity of ML models in patient subgroups with moderate risk for poor outcomes. A significant boost in prognostic power (F1 score) from 0.33 (95% CI 0.31-0.35) to 0.45 (95% CI 0.45-0.45) was observed in external validation when variations in these subgroups were accounted in our model. Our study highlighted the significance of external validation of ML models for cystic fibrosis prognostication. The uncovered insights on key risk factors and patient subgroups can be used to guide the cross-population adaptation of ML-based models and inspire new research on applying transfer learning methods for fine-tuning ML models to cope with regional variations in clinical care.
4
Filipow, Nicole, Eleanor Main, Neil J. Sebire, John Booth, Andrew M. Taylor, Gwyneth Davies y Sanja Stanojevic. "Implementation of prognostic machine learning algorithms in paediatric chronic respiratory conditions: a scoping review". BMJ Open Respiratory Research 9, n.º 1 (marzo de 2022): e001165. http://dx.doi.org/10.1136/bmjresp-2021-001165.
Texto completoResumen
Machine learning (ML) holds great potential for predicting clinical outcomes in heterogeneous chronic respiratory diseases (CRD) affecting children, where timely individualised treatments offer opportunities for health optimisation. This paper identifies rate-limiting steps in ML prediction model development that impair clinical translation and discusses regulatory, clinical and ethical considerations for ML implementation. A scoping review of ML prediction models in paediatric CRDs was undertaken using the PRISMA extension scoping review guidelines. From 1209 results, 25 articles published between 2013 and 2021 were evaluated for features of a good clinical prediction model using the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) guidelines.Most of the studies were in asthma (80%), with few in cystic fibrosis (12%), bronchiolitis (4%) and childhood wheeze (4%). There were inconsistencies in model reporting and studies were limited by a lack of validation, and absence of equations or code for replication. Clinician involvement during ML model development is essential and diversity, equity and inclusion should be assessed at each step of the ML pipeline to ensure algorithms do not promote or amplify health disparities among marginalised groups. As ML prediction studies become more frequent, it is important that models are rigorously developed using published guidelines and take account of regulatory frameworks which depend on model complexity, patient safety, accountability and liability.
5
Ferroni, Patrizia, Fabio Zanzotto, Silvia Riondino, Noemi Scarpato, Fiorella Guadagni y Mario Roselli. "Breast Cancer Prognosis Using a Machine Learning Approach". Cancers 11, n.º 3 (7 de marzo de 2019): 328. http://dx.doi.org/10.3390/cancers11030328.
Texto completoResumen
Machine learning (ML) has been recently introduced to develop prognostic classification models that can be used to predict outcomes in individual cancer patients. Here, we report the significance of an ML-based decision support system (DSS), combined with random optimization (RO), to extract prognostic information from routinely collected demographic, clinical and biochemical data of breast cancer (BC) patients. A DSS model was developed in a training set (n = 318), whose performance analysis in the testing set (n = 136) resulted in a C-index for progression-free survival of 0.84, with an accuracy of 86%. Furthermore, the model was capable of stratifying the testing set into two groups of patients with low- or high-risk of progression with a hazard ratio (HR) of 10.9 (p < 0.0001). Validation in multicenter prospective studies and appropriate management of privacy issues in relation to digital electronic health records (EHR) data are presently needed. Nonetheless, we may conclude that the implementation of ML algorithms and RO models into EHR data might help to achieve prognostic information, and has the potential to revolutionize the practice of personalized medicine.
6
Muscas, Giovanni, Tommaso Matteuzzi, Eleonora Becattini, Simone Orlandini, Francesca Battista, Antonio Laiso, Sergio Nappini et al. "Development of machine learning models to prognosticate chronic shunt-dependent hydrocephalus after aneurysmal subarachnoid hemorrhage". Acta Neurochirurgica 162, n.º 12 (8 de julio de 2020): 3093–105. http://dx.doi.org/10.1007/s00701-020-04484-6.
Texto completoResumen
Abstract Background Shunt-dependent hydrocephalus significantly complicates subarachnoid hemorrhage (SAH), and reliable prognosis methods have been sought in recent years to reduce morbidity and costs associated with delayed treatment or neglected onset. Machine learning (ML) defines modern data analysis techniques allowing accurate subject-based risk stratifications. We aimed at developing and testing different ML models to predict shunt-dependent hydrocephalus after aneurysmal SAH. Methods We consulted electronic records of patients with aneurysmal SAH treated at our institution between January 2013 and March 2019. We selected variables for the models according to the results of the previous works on this topic. We trained and tested four ML algorithms on three datasets: one containing binary variables, one considering variables associated with shunt-dependency after an explorative analysis, and one including all variables. For each model, we calculated AUROC, specificity, sensitivity, accuracy, PPV, and also, on the validation set, the NPV and the Matthews correlation coefficient (ϕ). Results Three hundred eighty-six patients were included. Fifty patients (12.9%) developed shunt-dependency after a mean follow-up of 19.7 (± 12.6) months. Complete information was retrieved for 32 variables, used to train the models. The best models were selected based on the performances on the validation set and were achieved with a distributed random forest model considering 21 variables, with a ϕ = 0.59, AUC = 0.88; sensitivity and specificity of 0.73 (C.I.: 0.39–0.94) and 0.92 (C.I.: 0.84–0.97), respectively; PPV = 0.59 (0.38–0.77); and NPV = 0.96 (0.90–0.98). Accuracy was 0.90 (0.82–0.95). Conclusions Machine learning prognostic models allow accurate predictions with a large number of variables and a more subject-oriented prognosis. We identified a single best distributed random forest model, with an excellent prognostic capacity (ϕ = 0.58), which could be especially helpful in identifying low-risk patients for shunt-dependency.
7
Park, Hyung Soon, Ji Soo Park, Yun Ho Roh, Jieun Moon, Dong Sup Yoon y Hei-Cheul Jeung. "Prognostic factors and scoring model for survival in advanced biliary tract cancer." Journal of Clinical Oncology 35, n.º 4_suppl (1 de febrero de 2017): 264. http://dx.doi.org/10.1200/jco.2017.35.4_suppl.264.
Texto completoResumen
264 Background: Metastatic biliary tract cancer (BTC) has dismal prognosis. We herein presented multivariate analysis using routinely evaluated clinico-laboratory parameters at the time of initial diagnosis, to implement a scoring model that can effectively identify risk groups, and we finally validated the model using independent dataset. Methods: From September 2006 to February 2015, 482 patients with metastatic BTC were analyzed. Patients were randomly assigned (7:3) into investigational (n = 340) and validation dataset (n = 142). Continuous variables were dichotomized according to the normal range or the best cutoff values statistically determined by Contal and O’Quigley method. Multivariate analysis using Cox’s proportional hazard model was done to find independent prognostic factors, and scoring model were derived by summing the rounded χ2 scores for the factors emerged in the multivariate analysis. Results: Performance status (ECOG 3-4), hypoalbuminemia ( < 3.4 mg/dL), carcinoembryonic antigen (≥9 ng/mL), neutrophil-lymphocyte ratio (≥3.0), and carbohydrate antigen 19-9 (≥120 U/mL) were identified as independent factors for poor survival in investigational dataset. When assigning patients into three risk groups based on these factors, survival was 14.0, 7.3, and 2.3 months for the low, intermediate, and high-risk groups, respectively (P < 0.001). Harrell’s C-index and integrated AUC for scoring model were 0.682 and 0.653, respectively. In validation dataset, prognosis was also well-divided according to the risk groups (median OS, 16.7, 7.5 and 1.9 months, respectively, P < 0.001). Chemotherapy gave a survival benefit in low and intermediate-risk group (11.4 vs. 4.8 months; P< 0.001), but not in high-risk group (median OS, 4.3 vs. 1.1 months; P = 0.105). Conclusions: We propose a set of prognostic criteria for metastatic BTC, which can help accurate patient risk stratification and aid in treatment selection.
8
Hulsbergen, Alexander, Yu Tung Lo, Vasileios Kavouridis, John Phillips, Timothy Smith, Joost Verhoeff, Kun-Hsing Yu, Marike Broekman y Omar Arnaout. "SURG-02. SURVIVAL PREDICTION AFTER NEUROSURGICAL RESECTION OF BRAIN METASTASES: A MACHINE LEARNING APPROACH". Neuro-Oncology 22, Supplement_2 (noviembre de 2020): ii203. http://dx.doi.org/10.1093/neuonc/noaa215.849.
Texto completoResumen
Abstract INTRODUCTION Survival prediction in brain metastases (BMs) remains challenging. Current prognostic models have been created and validated almost completely with data from patients receiving radiotherapy only, leaving uncertainty about surgical patients. Therefore, the aim of this study was to build and validate a model predicting 6-month survival after BM resection using different machine learning (ML) algorithms. METHODS An institutional database of 1062 patients who underwent resection for BM was split into a 80:20 training and testing set. Seven different ML algorithms were trained and assessed for performance. Moreover, an ensemble model was created incorporating random forest, adaptive boosting, gradient boosting, and logistic regression algorithms. Five-fold cross validation was used for hyperparameter tuning. Model performance was assessed using area under the receiver-operating curve (AUC) and calibration and was compared against the diagnosis-specific graded prognostic assessment (ds-GPA); the most established prognostic model in BMs. RESULTS The ensemble model showed superior performance with an AUC of 0.81 in the hold-out test set, a calibration slope of 1.14, and a calibration intercept of -0.08, outperforming the ds-GPA (AUC 0.68). Patients were stratified into high-, medium- and low-risk groups for death at 6 months; these strata strongly predicted both 6-months and longitudinal overall survival (p < 0.001). CONCLUSIONS We developed and internally validated an ensemble ML model that accurately predicts 6-month survival after neurosurgical resection for BM, outperforms the most established model in the literature, and allows for meaningful risk stratification. Future efforts should focus on external validation of our model.
9
Xiao, Changhu, Yuan Guo, Kaixuan Zhao, Sha Liu, Nongyue He, Yi He, Shuhong Guo y Zhu Chen. "Prognostic Value of Machine Learning in Patients with Acute Myocardial Infarction". Journal of Cardiovascular Development and Disease 9, n.º 2 (11 de febrero de 2022): 56. http://dx.doi.org/10.3390/jcdd9020056.
Texto completoResumen
(1) Background: Patients with acute myocardial infarction (AMI) still experience many major adverse cardiovascular events (MACEs), including myocardial infarction, heart failure, kidney failure, coronary events, cerebrovascular events, and death. This retrospective study aims to assess the prognostic value of machine learning (ML) for the prediction of MACEs. (2) Methods: Five-hundred patients diagnosed with AMI and who had undergone successful percutaneous coronary intervention were included in the study. Logistic regression (LR) analysis was used to assess the relevance of MACEs and 24 selected clinical variables. Six ML models were developed with five-fold cross-validation in the training dataset and their ability to predict MACEs was compared to LR with the testing dataset. (3) Results: The MACE rate was calculated as 30.6% after a mean follow-up of 1.42 years. Killip classification (Killip IV vs. I class, odds ratio 4.386, 95% confidence interval 1.943–9.904), drug compliance (irregular vs. regular compliance, 3.06, 1.721–5.438), age (per year, 1.025, 1.006–1.044), and creatinine (1 µmol/L, 1.007, 1.002–1.012) and cholesterol levels (1 mmol/L, 0.708, 0.556–0.903) were independent predictors of MACEs. In the training dataset, the best performing model was the random forest (RDF) model with an area under the curve of (0.749, 0.644–0.853) and accuracy of (0.734, 0.647–0.820). In the testing dataset, the RDF showed the most significant survival difference (log-rank p = 0.017) in distinguishing patients with and without MACEs. (4) Conclusions: The RDF model has been identified as superior to other models for MACE prediction in this study. ML methods can be promising for improving optimal predictor selection and clinical outcomes in patients with AMI.
10
Dou, Guanhua, Dongkai Shan, Kai Wang, Xi Wang, Zinuan Liu, Wei Zhang, Dandan Li et al. "Integrating Coronary Plaque Information from CCTA by ML Predicts MACE in Patients with Suspected CAD". Journal of Personalized Medicine 12, n.º 4 (7 de abril de 2022): 596. http://dx.doi.org/10.3390/jpm12040596.
Texto completoResumen
Conventional prognostic risk analysis in patients undergoing noninvasive imaging is based upon a limited selection of clinical and imaging findings, whereas machine learning (ML) algorithms include a greater number and complexity of variables. Therefore, this paper aimed to explore the predictive value of integrating coronary plaque information from coronary computed tomographic angiography (CCTA) with ML to predict major adverse cardiovascular events (MACEs) in patients with suspected coronary artery disease (CAD). Patients who underwent CCTA due to suspected coronary artery disease with a 30-month follow-up for MACEs were included. We collected demographic characteristics, cardiovascular risk factors, and information on coronary plaques by analyzing CCTA information (plaque length, plaque composition and coronary artery stenosis of 18 coronary artery segments, coronary dominance, myocardial bridge (MB), and patients with vulnerable plaque) and follow-up information (cardiac death, nonfatal myocardial infarction and unstable angina requiring hospitalization). An ML algorithm was used for survival analysis (CoxBoost). This analysis showed that chest symptoms, the stenosis severity of the proximal anterior descending branch, and the stenosis severity of the middle right coronary artery were among the top three variables in the ML model. After the 22nd month of follow-up, in the testing dataset, ML showed the largest C-index and AUC compared with Cox regression, SIS, SIS score + clinical factors, and clinical factors. The DCA of all the models showed that the net benefit of the ML model was the highest when the treatment threshold probability was between 1% and 9%. Integrating coronary plaque information from CCTA based on ML technology provides a feasible and superior method to assess prognosis in patients with suspected coronary artery disease over an approximately three-year period.
Tesis sobre el tema "ML prognostic model"
1
Navicelli, Andrea, Mario Tucci y Filippo De Carlo. "Analisi ed applicazione di modelli diagnostici e prognostici per guasti e prestazioni di componenti di impianti industriali nell’era I4.0". Doctoral thesis, 2021. http://hdl.handle.net/2158/1234822.
Texto completoResumen
Il ruolo fondamentale che la manutenzione gioca nei costi di esercizio e nella produttività degli impianti industriali ha portato le aziende e i ricercatori a spostare il loro interesse su questo tema. L'ultima frontiera dell'innovazione in campo manutentivo, resa possibile anche dall'avvento della quarta rivoluzione industriale che promuove la sensorizzazione e l’interconnessione di tutti i macchinari di impianto, è la manutenzione predittiva. Essa mira ad ottenere una previsione accurata della vita utile dei componenti degli impianti industriali al fine di ottimizzare la schedulazione degli interventi sul campo.
Lo studio parte da una accurata revisione della letteratura scientifica di settore riguardante le tecniche diagnostiche e prognostiche applicate a componenti di impianti industriali, necessaria alla comprensione dei diversi modelli sviluppati in funzione della tipologia di componente e modo di guasto in analisi. Successivamente ho spostato l’attenzione sul concetto di manutenzione 4.0 al fine di mappare tutte le caratteristiche associate al paradigma dell'Industria 4.0 e le loro possibili applicazioni alla manutenzione.
Lo studio condotto ha portato poi alla progettazione, sviluppo e validazione delle metodologie necessarie all’applicazione in real-time di modelli diagnostici e prognostici avanzati, sia statistici che machine learning, necessari all’implementazione sul campo di un sistema di manutenzione predittiva.
Grazie all’applicazione delle metodologie proposte ad un caso studio è stato possibile non solo validare i modelli proposti ma anche definire l’architettura informatica necessaria alla loro corretta implementazione sul sistema distribuito di controllo (Distributed Control System - DCS) di impianto in funzione della tipologia del componente e del guasto in analisi.
I modelli testati e validati hanno mostrato elevate prestazioni diagnostiche soprattutto per quanto riguarda i modelli ML che sfruttano le Support Vector Machine (SVM).
In definitiva, questo lavoro di tesi mostra nel dettaglio tutti i passaggi necessari allo sviluppo di un sistema di manutenzione predittiva efficace in impianto: partendo dall’analisi dei modi di guasto e dalla sensorizzazione dei componenti, passando poi allo sviluppo dei modelli diagnostici e prognostici real-time fino alla costruzione dell’interfaccia di visualizzazione dei risultati delle analisi svolte, analizzando anche l’architettura informatica necessaria al suo corretto funzionamento.
The fundamental role that maintenance plays in the operating costs and productivity of industrial plants has led companies and researchers to shift their interest in this issue. The last frontier of innovation in the maintenance field, made possible also by the advent of the fourth industrial revolution which promotes the sensorisation and interconnection of all plant machinery, is predictive maintenance. It aims to obtain an accurate forecast of the useful life of the industrial plants’ components in order to optimise the scheduling of interventions in the field.
The study starts from an accurate review of the scientific literature concerning the diagnostic and prognostic techniques applied to industrial plant components, necessary to understand the different models developed according to the type of component and failure mode under analysis. Subsequently I shifted the focus to the maintenance 4.0 concept in order to map all the characteristics associated with the Industry 4.0 paradigm and their possible applications to maintenance operations.
The study then led to the design, development and validation of the methodologies necessary for the real-time application of advanced diagnostic and prognostic models, both statistical and machine learning, necessary for the field implementation of a predictive maintenance system.
Thanks to the application of the proposed methodologies to a case study, it was possible not only to validate the proposed models but also to define the IT architecture necessary for their correct implementation on the plant's Distributed Control System (DCS) according to the type of component and the fault under analysis.
The tested and validated models showed high diagnostic performance, especially regarding the Support Vector Machine (SVM) Machine Learning models.
Ultimately, this thesis shows in detail all the steps necessary for the development of an effective predictive maintenance system in the plant: starting from the analysis of failure modes and component sensorisation, then moving on to the development of real-time diagnostic and prognostic models up to the build-up of the interface for visualising the results of the analyses carried out, also analysing the IT architecture necessary for its correct operation.
Capítulos de libros sobre el tema "ML prognostic model"
1
Aria, Massimo, Corrado Cuccurullo y Agostino Gnasso. "Supporting decision-makers in healthcare domain. A comparative study of two interpretative proposals for Random Forests". En Proceedings e report, 179–84. Florence: Firenze University Press, 2021. http://dx.doi.org/10.36253/978-88-5518-461-8.34.
Texto completoResumen
The growing success of Machine Learning (ML) is making significant improvements to predictive models, facilitating their integration in various application fields, especially the healthcare context. However, it still has limitations and drawbacks, such as the lack of interpretability which does not allow users to understand how certain decisions are made. This drawback is identified with the term "Black-Box", as well as models that do not allow to interpret the internal work of certain ML techniques, thus discouraging their use. In a highly regulated and risk-averse context such as healthcare, although "trust" is not synonymous with decision and adoption, trusting an ML model is essential for its adoption. Many clinicians and health researchers feel uncomfortable with black box ML models, even if they achieve high degrees of diagnostic or prognostic accuracy. Therefore more and more research is being conducted on the functioning of these models. Our study focuses on the Random Forest (RF) model. It is one of the most performing and used methodologies in the context of ML approaches, in all fields of research from hard sciences to humanities. In the health context and in the evaluation of health policies, their use is limited by the impossibility of obtaining an interpretation of the causal links between predictors and response. This explains why we need to develop new techniques, tools, and approaches for reconstructing the causal relationships and interactions between predictors and response used in a RF model. Our research aims to perform a machine learning experiment on several medical datasets through a comparison between two methodologies, which are inTrees and NodeHarvest. They are the main approaches in the rules extraction framework. The contribution of our study is to identify, among the approaches to rule extraction, the best proposal for suggesting the appropriate choice to decision-makers in the health domain.
2
Kolossváry, Márton. "Artificial intelligence in cardiac CT". En EACVI Handbook of Cardiovascular CT, editado por Oliver Gaemperli, Pal Maurovich-Horvat, Koen Nieman, Gianluca Pontone y Francesca Pugliese, 349—C3.16.S7. Oxford University PressOxford, 2022. http://dx.doi.org/10.1093/med/9780192884459.003.0037.
Texto completoResumen
Abstract The amount of imaging data yielded from cardiac CT images is very large. However, the human ability to interpret, quantify, and integrate these data sets is limited. Artificial intelligence (AI) is a general term that describes computational processes that mimic or exceed human intelligence. The main part of these processes is machine learning (ML), which takes inputs and, using novel analytical and statistical techniques, maps them to given outputs. For cardiac CT, AI techniques have been used at different levels, from image postprocessing to diagnosis and prognosis. Validated indications for AI in cardiac CT include image reconstruction and segmentation, plaque characterization (e.g. the identification of high-risk coronary plaques), myocardial tissue characterization, and prosthetic heart valve evaluation. Moreover, ML models combining imaging data with clinical variables have demonstrated to be accurate in the prediction of cardiovascular outcomes.
3
Chaudhry, Abdul Aziz, Rafia Mumtaz, Usman Ahmad Siddiqui, Syed Hassan Muzammil y Muhammad Ali Tahir. "Automated Multi-Sensor Board for IoT and ML-Enabled Livestock Monitoring". En Empowering Sustainable Industrial 4.0 Systems With Machine Intelligence, 60–85. IGI Global, 2022. http://dx.doi.org/10.4018/978-1-7998-9201-4.ch003.
Texto completoResumen
Livestock monitoring is one of the most common problems in the current time, and to sustain the lifecycle and support the nature of domesticated animals, the standard checking of animal wellbeing is fundamental. Moreover, many diseases are spread from animals to human beings; hence, an early prognosis in regard to cow wellbeing and illness is essential. This chapter proposed an internet of things (IoT)-based framework for domesticated animal wellbeing checking. The proposed framework comprises of a specially crafted multi-sensor board to record a few physiological boundaries including skin temperature, pulse, and rumination with regards to encompassing temperature, stickiness, and a camera for picture examination to recognize diverse standards of health. The data is collected using LoRa gateway technology, where gathered data is examined and utilized for performing ML models to identify diseased and healthy creatures and foresee cow wellbeing for giving early and convenient clinical consideration. The results obtained are used for careful insights regarding animal health and wellbeing.
4
Chhillar, Rajender Singh. "Disease Prediction using Deep Learning Algorithms in Healthcare Sector". En Machine Learning Algorithms for Intelligent Data Analytics. Technoarete Research And Development Association, 2022. http://dx.doi.org/10.36647/mlaida/2022.12.b1.ch008.
Texto completoResumen
Deep Learning (DL) is a major focus of discussion in the healthcare sector. The healthcare sector in the United States generates around one trillion Gigabytes of clinical data annually. With limited resources, manually analyzing these massive amounts of data is a tremendously time-consuming. Finding useful patterns and acquiring knowledge from high-dimensional, poorly annotated, heterogeneous and complex clinical data continues to be a significant challenge in the health care sector. Latest advancements in DL have been shown as an efficacious approach to building end-to-end learning models for disease prognosis and diagnosis. In the past, discovering information from data has been accomplished through the use of conventional Machine Learning (ML) techniques. These techniques first require optimal features to be extracted from clinical data before building a disease predictive model on top of them. Problems with these techniques are that they do not scale properly with the increase in data due to a lack of domain knowledge. Firstly, this chapter explores popular DL algorithms for various types of clinical data. These algorithms can potentially prevent infectious disease, reducing operating costs, and efforts. Finally, the challenges while designing and implementing a holistic DL model have been discussed for disease prediction.
5
Brucato, Antonio y Stefano Maggiolini. "Pericardial effusion". En ESC CardioMed, editado por Yehuda Adler, 1572–75. Oxford University Press, 2018. http://dx.doi.org/10.1093/med/9780198784906.003.0377.
Texto completoResumen
Pericardial effusion is classified according to its onset—acute, subacute, or chronic (>3 months)—distribution (circumferential or loculated), and haemodynamic impact. Concerning the size, we propose a simple semiquantitative echocardiographic assessment: mild (<10 mm), moderate (10–20 mm), and large (>20 mm), evaluated as the largest telediastolic echo-free space in two-dimensional mode. Symptoms vary according to the speed of accumulation; slow accumulation may induce no or minor symptoms. In the presence of chronic, large pericardial effusions, appropriate tests for neoplasms, tuberculosis, and hypothyroidism should be considered. Chest computed tomography scanning is helpful in reaching an aetiological diagnosis (neoplasms, lymphomas, pneumonia, tuberculosis). High values of proteins, albumin, and lactate dehydrogenase are usually considered indicative of an exudate, as in pleural fluid, but this may not be true for pericardial fluid, and cytology has a sensitivity of only 50% for neoplasm. Mycobacterium cultures and a genome search for tuberculosis with the polymerase chain reaction in pericardial fluid are mandatory if pericardiocentesis is performed. If inflammatory signs are present, the clinical management should be that of pericarditis and a trial of non-steroidal anti-inflammatory drugs, colchicine, or low-dose corticosteroids, or a combination of these, may be tried. In about 60% of cases, the effusion is associated with a known disease, and the therapy should be targeted. When pericardiocentesis is performed in large effusions, prolonged pericardial drainage of up to 30 mL/24 h has been suggested to prevent recurrences, although evidence to support this is scarce. Prognosis is related to the aetiology, and idiopathic effusions may have a good prognosis especially if the effusion is mild to moderate.
6
Brucato, Antonio y Stefano Maggiolini. "Pericardial effusion". En ESC CardioMed, editado por Yehuda Adler, 1572–75. Oxford University Press, 2018. http://dx.doi.org/10.1093/med/9780198784906.003.0377_update_001.
Texto completoResumen
Pericardial effusion is classified according to its onset—acute, subacute, or chronic (>3 months)—distribution (circumferential or loculated), and haemodynamic impact. Concerning the size, we propose a simple semiquantitative echocardiographic assessment: mild (<10 mm), moderate (10–20 mm), and large (>20 mm), evaluated as the largest telediastolic echo-free space in two-dimensional mode. Symptoms vary according to the speed of accumulation; slow accumulation may induce no or minor symptoms. In the presence of chronic, large pericardial effusions, appropriate tests for neoplasms, tuberculosis, and hypothyroidism should be considered. Chest computed tomography scanning is helpful in reaching an aetiological diagnosis (neoplasms, lymphomas, pneumonia, tuberculosis). High values of proteins, albumin, and lactate dehydrogenase are usually considered indicative of an exudate, as in pleural fluid, but this may not be true for pericardial fluid, and cytology has a sensitivity of only 50% for neoplasm. Mycobacterium cultures and a genome search for tuberculosis with the polymerase chain reaction in pericardial fluid are mandatory if pericardiocentesis is performed. If inflammatory signs are present, the clinical management should be that of pericarditis and a trial of non-steroidal anti-inflammatory drugs, colchicine, or low-dose corticosteroids, or a combination of these, may be tried. In about 60% of cases, the effusion is associated with a known disease, and the therapy should be targeted. When pericardiocentesis is performed in large effusions, prolonged pericardial drainage of up to 30 mL/24 h has been suggested to prevent recurrences, although evidence to support this is scarce. Prognosis is related to the aetiology, and idiopathic effusions may have a good prognosis especially if the effusion is mild to moderate.
Actas de conferencias sobre el tema "ML prognostic model"
1
Almeida Filho, Benedito de Sousa, Michelle Sako Omodei, Eduardo Carvalho Pessoa, Heloisa de Luca Vespoli y Eliana Aguiar Petri Nahas. "NEGATIVE IMPACT OF SERUM VITAMIN D DEFICIENCY ON BREAST CANCER SURVIVAL". En XXIV Congresso Brasileiro de Mastologia. Mastology, 2022. http://dx.doi.org/10.29289/259453942022v32s1058.
Texto completoResumen
Introduction: It is known that breast cancer is the type of cancer that mostly affects women in the world, both in the developing and developed countries, with about 2.3 million new cases in 2020, comprising 25% of all cancers diagnosed in women. Vitamin D concentration has been studied as a risk and prognostic factor in women with breast cancer; its deficiency is common in women with postmenopausal breast cancer, and some evidence suggests that low vitamin D status increases the risk for disease development. The impact of vitamin D at the time of diagnosis on the outcome of patients with breast cancer is less well understood. In view of the increasing number of breast cancer survivors and the high prevalence of vitamin D deficiency among patients with breast cancer, an evaluation of the role of vitamin D in prognosis and survival among patients with breast cancer is essential. Objective: The aim of this study was to evaluate the association between serum vitamin D (VD) levels at diagnosis and overall survival (OS), disease-free survival (DFS), and cancer-specific survival (CSS) in postmenopausal women treated for breast cancer. Methods: This is a single-center prospective cohort. The study included patients newly diagnosed with invasive breast cancer between 2014 and 2016, aged ≥45 years, and in amenorrhea for ≥12 months, and VD assessment at the time of diagnosis, before any cancer treatment. Patients were classified into three groups according to serum levels of 25-hydroxyvitamin-D [25(OH)D]: sufficient (≥30 ng/mL), insufficient (between 20 and 29 ng/mL), and deficient (<20 ng/mL). Clinical and anatomopathological data were collected. The primary outcome was OS and secondary outcomes were DFS and CSS. Kaplan-Meier curve and Cox regression model were used to assess the association between 25(OH)D levels and OS, DFS, and CSS. Differences in survival were evaluated by hazard ratios (HRs). The study was approved by the Ethics Committee (CAAE: 71399117.2.0000.5411). Results: The study included 192 women with a mean age of 61.3±9.6 years at diagnosis, mean 25(OH)D levels of 25.8 ng/mL (ranging from 12.0 to 59.2 ng/mL), and follow-up period between 54 and 78 months. Sufficient VD levels were detected in 65 patients (33.9%), insufficient in 92 (47.9%), and deficient in 35 (18.2%). Patients with 25(OH)D insufficiency and deficiency had a larger proportion of high-grade tumors, locally advanced and with distant metastasis, positive axillary lymph nodes, negative estrogen receptors (ER), and progesterone receptors (PR), and higher Ki67 index (p<0.05 ). The mean OS time was 54.4±20.2 months (range 9–78 months), and 51 patients (26.6%) died during the study period. Patients with VD deficiency and insufficiency at diagnosis had significantly lower OS, DFS, and CSS compared to patients with sufficient values (p <0.0001). After the adjustment for clinical and tumoral prognostic factors, patients with serum 25(OH)D levels considered deficient at the time of diagnosis had a significantly higher risk of global death (HR=4.65, 95%CI 1.65–13.12), higher risk of disease recurrence (HR=6.87, 95%CI 2.35–21.18), and higher risk of death from the disease (HR=5.91, 95%CI 1.98–17.60) than the group with sufficient 25(OH)D levels.
2
Al-Mannai, Rashid Ebrahim, Mohammed Hamad Almerekhi, Mohammed Abdulla Al-Mannai, Mishahira N, Kishor Kumar Sadasivuni, Huseyin Cagatay Yalcin, Hassen M. Ouakad, Issam Bahadur, Somaya Al-Maadeed y Asiya Albusaidi. "Artificial Intelligence in Predicting Heart Failure". En Qatar University Annual Research Forum & Exhibition. Qatar University Press, 2021. http://dx.doi.org/10.29117/quarfe.2021.0130.
Texto completoResumen
Heart Failure is a major chronic disease that is increasing day by day and a great health burden in health care systems world wide. Artificial intelligence (AI) techniques such as machine learning (ML), deep learning (DL), and cognitive computer can play a critical role in the early detection and diagnosis of Heart Failure Detection, as well as outcome prediction and prognosis evaluation. The availability of large datasets from difference sources can be leveraged to build machine learning models that can empower clinicians by providing early warnings and insightful information on the underlying conditions of the patients
3
Kornev, Denis, Roozbeh Sadeghian, Stanley Nwoji, Qinghua He, Amir Gandjbbakhche y Siamak Aram. "Machine Learning-Based Gaming Behavior Prediction Platform". En 13th International Conference on Applied Human Factors and Ergonomics (AHFE 2022). AHFE International, 2022. http://dx.doi.org/10.54941/ahfe1001826.
Texto completoResumen
Brain disorders caused by Gaming Addiction drastically increased due to the rise of Internet users and Internet Gaming auditory. Driven by such a tendency, in 2018, World Health Organization (WHO) and the American Medical Association (AMA) addressed this problem as a “gaming disorder” and added it to official manuals. Scientific society equipped by statistical analysis methods such as t-test, ANOVA, and neuroimaging techniques, such as functional magnetic resonance imaging (fMRI), positron emission tomography (PET), and electroencephalography (EEG), has achieved significant success in brain mapping, examining dynamics and patterns in different conditions and stages. Nevertheless, more powerful, self-learning intelligent algorithms are suitable not only to evaluate the correlation between gaming addiction patterns but also to predict behavior and prognosis brain response depending on the addiction severity. The current paper aims to enrich the knowledge base of the correlation between gaming activity, decision-making, and brain activation, using Machine Learning (ML) algorithms and advanced neuroimaging techniques. The proposed gaming behavior patterns prediction platform was built inside the experiment environment composed of a Functional Near-Infrared Spectrometer (fNIRS) and the computer version of Iowa Gambling Task (IGT). Thirty healthy participants were hired to perform 100 cards selection while equipped with fNIRS. Thus, accelerated by IGT gaming decision-making process was synchronized with changes of oxy-hemoglobin (HbO) levels in the human brain, averaged, and investigated in the left and the right brain hemispheres as well as different psychosomatic conditions, conditionally divided by blocks with 20 card trials in each: absolute unknown and uncertainty in the first block, “pre-hunch” and “hunch” in the second and third blocks, and conceptuality and risky in the fourth and fifth blocks. The features space was constructed around the HbO signal, split by training and tested in two proportions 70/30 and 80/20, and drove patterns prediction ML-based platform consisted of five mechanics, such as Multiple Regression, Classification and Regression Trees (CART), Support Vector Machine (SVM), Artificial Neural Network (ANN), and Random Forest. The algorithm prediction power was validated by the 5- and 10-fold cross-validation method and compared by Root Mean Squared Error (RMSE) and coefficient of determination (R Squared) metrics. Indicators of “the best” fit model, lowest RMSE, and highest R Squared were determined for each block and both brain hemispheres and used to make a conclusion about prediction accuracy: SVM algorithm with RBF kernel, Random Forest, and ANN demonstrated the best accuracy in most cases. Lastly, “best fit” classifiers were applied to the testing dataset and finalized the experiment. Hence, the distribution of gaming score was predicted by five blocks and both brain hemispheres that reflect the decision-making process patterns during gaming. The investigation showed increasing ML algorithm prediction power from IGT block one to five, reflecting an increasing learning effect as a behavioral pattern. Furthermore, performed inside constructed platform simulation could benefit in diagnosing gaming disorders, their patterns, mechanisms, and abnormalities.
4
Viale, Luca, Alessandro Paolo Daga, Luigi Garibaldi, Salvatore Caronia y Ilaria Ronchi. "Books Trimmer Industrial Machine Knives Diagnosis: A Condition-Based Maintenance Strategy Through Vibration Monitoring via Novelty Detection". En ASME 2022 International Mechanical Engineering Congress and Exposition. American Society of Mechanical Engineers, 2022. http://dx.doi.org/10.1115/imece2022-94547.
Texto completoResumen
Abstract In recent years, Artificial Intelligence (AI) is ever more exploited in all the scientific and industrial fields and is allowing significant developments in mechanical engineering too. An emblematic contribution was given in terms of safety and reliability since Machine Learning (ML) techniques permitted the monitoring and the prediction of the state of health of machinery, allowing the adoption of predictive maintenance strategies. In fact, data-driven models — based on acquisitions — attract considerable interest both thanks to its theoretical and application development. The evolution of diagnostic techniques is oriented towards Condition-Based Maintenance (CBM) strategies, thus allowing improvements in terms of safety enhancement, cost reduction and increased performances. This paper proposes the development and implementation of a diagnostic/prognostic tool applied to an automated books trimmer industrial machine, implementing condition monitoring by means of accelerometers which can be integrated into a Supervisory Control And Data Acquisition (SCADA) system. Given its use, the core components of this production line are three knives, subjected to significant impulsive forces. Therefore, the target of the work is to infer the wear of these three knives, as they are critical elements of the machinery and have a high impact on the quality of the final product. The project was carried out in collaboration with Tecnau — an industry-leading company — which made it possible to conduct experimentation and data acquisition on their machinery. An appropriate Design Of Experiments (DOE) and the use of inferential statistical techniques — such as the ANalysis Of VAriance (ANOVA) and the identification of significant effects — applied to the multivariate dataset allowed recognizing the most relevant features for Novelty Detection (ND). Both the Linear Discriminant Analysis (LDA) and the k-Nearest Neighbors (kNN) method permitted to correctly distinguish the patterns representing the health conditions of the machinery, classifying the data in the reduced multidimensional space according to the final product quality. The results obtained in terms of accuracy are very positive and promising. This means that the developed method is able to successfully identify the state of health of the blade in spite of varying functioning parameters (book thickness and size, paper type and characteristics) and operating conditions. The algorithm speed and its integration into the industrial line make a real-time condition-based maintenance strategy possible. This diagnostic method is suitable for applications oriented to the paradigm of Industry 4.0 and the digitalization of the industrial sector, which can be integrated with the Internet of Things (IoT) and cloud systems.
5
Апарцин, Константин y Konstantin Apartsin. "The results of fundamental and translational research carried out In the Department of Biomedical Research and Technology of the SBRAS INC in 2012-2016". En Topical issues of translational medicine: a collection of articles dedicated to the 5th anniversary of the day The creation of a department for biomedical research and technology of the Irkutsk Scientific Center Siberian Branch of RAS. Москва: INFRA-M Academic Publishing LLC., 2017. http://dx.doi.org/10.12737/conferencearticle_58be81eca22ad.
Texto completoResumen
The results of basic and translational research of the Department of Biomedical Research and Technology of Irkutsk Scientific Center of the Siberian Branch of the Russian Academy of Sciences in 2012–2016 The paper presents the results of interdisciplinary research carried out in 2012–2016. The review includes the study of molecular mechanisms of pathogenesis of reparative regeneration, experimental substantiation of methods of diagnosis and prognosis of systemic disturbances of regeneration process, carrying out clinical trials of medicinal products and the formation of observational studies in the field of personalized medicine, the preparation of practical recommendations on the testing of previously developed surgical methods of prevention or correction of postoperative recovery disorders. New data are obtained on the role of the MAP-kinase cascade in the process of regeneration of muscle tissue. It has been established, that with a significant increase of VEGF concentration at the site of the repair of ischemic myocardium, progenitor cells with the CD34+CD45+ phenotype appear, which opens up prospects for the development of biotechnology to restore the damaged myocardium with its own pool of progenitor cells. The new data on the role of growth factors in the post-infarction remodeling are found. It has been revealed, that in local increase of selenium concentration low intensity of mineralization of forming callus in the area of the damage is observed and the formation of bone regeneration slows down. Prospects for the use of nanocomposites of elemental selenium for modulation of reparative response are marked. The dynamics of the level of free circulating mitochondrial DNA (mtDNA) of blood in the early stages of experimental dyslipidemia has been studied. Atherogenic blood factors do not have a significant effect on the release of the mtDNA from dyslipidemia target cells. On the model of acute small-focal myocardial ischemia, we revealed the increase in the mtDNA levels. Prospects of broadcast of diagnostic mtDNA monitoring technology in myocardial ischemia have been marked. The mtDNA monitoring was first tested as a molecular risk pattern in acute coronary syndrome. In survived patients, the concentration of freely circulating mtDNA in blood plasma was 164 times lower. The probability of death of the patient with a high level of mtDNA (over 4000 copies/mL) was 50 % (logit analysis). Methodological level of translational research in the ISC SB RAS has increased due to effective participation in international multi-center clinical trials of drugs, mainly direct anticoagulants: fondaparinux, edoksabana, betriksabana. “Feedback broadcast” of the results of clinical trials of p38-kinase inhibitor, was carried out in the process of changing the model (initially – neuropathic pain) for coronary atherosclerosis. Technologies of pharmacogenetic testing and personalized treatment of diseases in the employees of the Irkutsk Scientific Center were applied. Step T2. Previously developed at the Irkutsk State Medical University and the Irkutsk Scientific Center of Surgery and Traumatologies approaches to surgical prevention and medicinal correction of postoperative hyposplenism were translated into practical health care. Thus, these results obtained in different areas of translational medicine will determine scientific topics of the department in future research cycle.