Dissertations / Theses: 'Medical Prediction'

1

Shadabi, Fariba, and N/A. "Medical Outcome Prediction: A Hybrid Artificial Neural Networks Approach." University of Canberra. Information Sciences & Engineering, 2007. http://erl.canberra.edu.au./public/adt-AUC20070816.130444.

Full text

Abstract:

This thesis advances the understanding of the application of artificial neural networks ensemble to clinical data by addressing the following fundamental question: What is the potentiality of an ensemble of neural networks models as a filter and classifier in a complex clinical situation? A novel neural networks ensemble classification model called Rules and Information Driven by Consistency in Artificial Neural Networks Ensemble (RIDCANNE) is developed for the purpose of prediction of medical outcomes or events, such as kidney transplants. The proposed classification model is based on combination of initial data preparations, preliminary classification by ensembles of Neural Networks, and generation of new training data based on criteria of highly accuracy and model agreement. Furthermore, it can also generate decision tree classification models to provide classification of data and the prediction results. The case studies described in this thesis are from a kidney transplant database and two well-known collections of benchmark data known as the Pima Indian Diabetes and Wisconsin Cancer datasets. An implication of this study is that further attention needs to be given to both data collection and preparation stages. This study revealed that even neural network ensemble models that are known for their strong generalization ability might not be able to provide a high level of accuracy for complex, noisy and incomplete clinical data. However, by using a selective subset of data points, it is possible to improve the overall accuracy. In summary, the research conducted for this thesis advances the current clinical data preparation and classification techniques in which the task is to extract patterns that contain higher information content from a sea of noisy and incomplete clinical data, and build accurate and transparent classifiers. The RIDC-ANNE approach improves an analyst�s ability to better understand the data. Furthermore, it shows great promise for use in clinical decision making systems. It can provide us with a valuable data mining tool with great research and commercial potential.

APA, Harvard, Vancouver, ISO, and other styles

2

Shadabi, Fariba. "Medical outcome prediction : a hybrid artificial neural networks approach /." Canberra, 2007. http://erl.canberra.edu.au/public/adt-AUC20070816.130444/index.html.

Full text

Abstract:

Thesis (PhD) -- University of Canberra, 2007.
Thesis submitted in fulfilment of the requirements of the Degree of Doctor of Philosophy in Information Sciences and Engineering, University of Canberra, January 2007. Bibliography: leaves 110-127.

APA, Harvard, Vancouver, ISO, and other styles

3

Kyei-Blankson, Lydia S. "Predictive Validity, Differential Validity, and Differential Prediction of the Subtests of the Medical College Admission Test." Ohio University / OhioLINK, 2005. http://www.ohiolink.edu/etd/view.cgi?ohiou1125524238.

Full text

APA, Harvard, Vancouver, ISO, and other styles

4

Sultan, Ahmad Hasane. "Prediction of medical technologists' scores on the MT (ASCP) certification examinations." Diss., This resource online, 1992. http://scholar.lib.vt.edu/theses/available/etd-07282008-134142/.

Full text

APA, Harvard, Vancouver, ISO, and other styles

5

Meng, Mingyuan. "Deep Learning for Medical Image Registration and Radiomics-based Survival Prediction." Thesis, The University of Sydney, 2021. https://hdl.handle.net/2123/25391.

Full text

Abstract:

With the importance of medical images for disease diagnosis and prognosis becoming widely recognized, medical image analysis has drawn much attention among researchers and clinicians. The goal of medical image analysis is to identify diagnostic and prognostic information from medical images and to establish diagnosis/prognosis models for assisting in clinical decision making and personalized treatments. Deep learning-based methods have achieved great success in computer vision research. This success is mainly attributed to its outstanding ability to learn high-level pattern representations from big data, and has motivated many investigators for applying deep learning-based algorithms in medical image analysis. The objectives of this thesis are to explore and develop deep learning methods for two medical image analysis tasks: medical image registration and radiomics. Firstly, we focused on medical image registration, a fundamental step of various medical image analysis tasks. We identified that a key challenge for accurate image registration is the variations in image appearance. Hence, we proposed an Appearance Adjustment Network (AAN) where we leverage anatomy edges, through an anatomy-constrained loss function, to generate an anatomy-preserving appearance transformation. We designed the AAN so that it can be readily embedded into a wide range of deep learning-based registration frameworks, to reduce the appearance differences between input image pairs and thereby improve registration accuracy. In this study, we experimented with Brain MRI data and observed improvements in registration accuracy. The results show that our AAN enhanced the baseline registration methods by roughly 2% in Dice score, while adding a fractional computational load. Secondly, we explored radiomics-based survival prediction of patients with advanced Nasopharyngeal Carcinoma (NPC). Radiomics refers to the extraction and analysis of high-dimensional quantitative features from non-invasive images. In this study, we incorporated deep learning into radiomics and developed an end-to-end multi-modality deep-learning model using pretreatment PET/CT images to predict 5-year progression-free survival. Furthermore, the deep-learning model was extensively compared with a large number of conventional radiomics methods for prognostic performance. The results show that the proposed deep-learning model outperformed conventional radiomics methods by roughly 5% in AUC. Our experimental results demonstrated that our models on two tasks outperform the existing methods, suggesting that deep learning is an effective tool for enhancing medical image analysis.

APA, Harvard, Vancouver, ISO, and other styles

6

Söderlund, Anne. "Physiotherapy Management, Coping and Outcome Prediction in Whiplash Associated Disorders (WAD)." Doctoral thesis, Uppsala University, Department of Public Health and Caring Sciences, 2001. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-601.

Full text

Abstract:

The aims of the present thesis were to evaluate the management of acute WAD and to develop, describe and evaluate a cognitive behavioural approach for the physiotherapy management of long-term WAD as well as to study the predictors and mediating factors for long-term disability and pain after a whiplash injury.

Two approaches for acute and chronic WAD were evaluated in experimental studies. Fifty-nine patients with acute whiplash injury (study I) and 33 patients with chronic WAD (study V), were randomised into experimental and control groups. In addition, three chronic WAD patients participated in an experimental single case study (study IV). Home exercise programmes for patients with acute WAD were used in study I. In study IV a physiotherapy management with integrated components of cognitive-behavioural origin was tried for chronic WAD patients. In study V physiotherapy treatment in primary care units and a physiotherapy management with integrated components of cognitive-behavioural origin was tried for chronic WAD patients. Study I showed that a home exercise programme including training of neck and shoulder range of motion (ROM), relaxation and general advice, appears to be a sufficient treatment for most acute WAD patients. Further, the results of study IV and V suggest that cognitive behavioural components m be useful in physiotherapy treatment for patients with chronic WAD, but its contribution is not yet fully understood.

Study III showed that the significance of coping as an explanatory factor for disability increased during the one-year period after a whiplash injury. In study V it was concluded that self-efficacy is related to patients' use of different coping styles. A model to study coping as a mediator between self-efficacy and disability was therefore introduced. In a path-analytic framework, data from subjects in study I were re-analysed to illustrate a theoretical standpoint that emphasises the process of coping. With regard to disability, the proportion of explained variance increased from 39% at three weeks after the accident, to 79% at one-year follow-up. These results also show that coping has a crucial and mediating role between self-efficacy and disability. Positive long- term outcomes in WAD-patients would therefore be improved by, shortly after an accident, boosting self- efficacy and teaching patients to use active, adaptive coping strategies to manage their problems.

APA, Harvard, Vancouver, ISO, and other styles

7

Halvarsson, Klara. "Dieting and eating attitudes in girls : Development and prediction." Doctoral thesis, Uppsala University, Department of Public Health and Caring Sciences, 2000. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-538.

Full text

Abstract:

The aims of the present thesis were to study: 1. reported eating attitudes, dieting behavior and body image over a 1-year period among preadolescent girls (age 7-8); 2. differences in eating attitudes and coping between groups of teenage girls differing in dieting frequency, and to assess changes with increasing age (age 13-17); and 3. to what extent eating attitudes, self-esteem and coping predict disturbed eating attitudes. A final aim was to explore differences in the reported wish to be thinner, dieting, and eating attitudes between two age-matched cohorts of girls in 1995 and 1999 (7-15 years).

The project is designed as a longitudinal prospective study, spanning seven years. 1300 girls in the ages (1995) 7, 9, 11, 13 and 15 years have been assessed annually for three consecutive years (1995-1997) (Main Cohort). An additional group matched for age with the original group was recruited in 1999 (Societal Cohort). The results suggest that dieting and the wish to be thinner starts as early as at 7 years of age, and that repeated dieting attempts correlate with disturbed eating attitudes. A marked increase of the wish to be thinner was evident in the 10- to 14-year age range, and significant increases in dieting attempts occurred mainly between ages 9 and 13. There were no differences between 1995 (Main Cohort) and 1999 (Societal Cohort) (except among 7 and 11-year-olds) with regard to dieting, the wish to be thinner and disturbed eating attitudes. Eating patterns and attitudes were shown to be the strongest predictors of disturbed eating attitudes three years later. Assessment of dieting, the wish to be thinner and eating attitudes is suggested BS a component in school health care.

APA, Harvard, Vancouver, ISO, and other styles

8

So, Hon-cheong, and 蘇漢昌. "Genetic architecture and risk prediction of complex diseases." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 2010. http://hub.hku.hk/bib/B4452805X.

Full text

APA, Harvard, Vancouver, ISO, and other styles

9

Braithwaite, Emma Annette. "Neural networks for medical condition prediction : an investigation of neonatal respiratory disorder." Thesis, University of Edinburgh, 1998. http://hdl.handle.net/1842/12658.

Full text

Abstract:

This thesis investigates how various signal processing techniques can be applied to diagnose problems in the medical domain. In particular it concentrates on breathing problems often experienced by premature babies who undergo artificial respiration. Medical Decision Support is an area of increasing research interest. The neonatal intensive care unit (NICU) is a prime example. This thesis describes the investigation of techniques to be used as the core of a decision support device in Edinburgh's NICU. At present physiological signals are taken from the patient and archived, little diagnostic use is made of these signals and no investigation has taken place into their diagnostic relevance. Within the scope of the work an investigation has taken place into the application area and some of its current problems have been identified. From these a physiological problem, respiratory disorder, was identified with characteristics which made it worthy of detailed study: it was extremely common, moreover expert knowledge and data about it already existed. With the current techniques the development of respiratory disorder is often missed or diagnosed too late. Signal processing techniques were evaluated with a view to applying them to predict the onset, or classify the development of, respiratory disorder, and a multi-layer perceptron network was chosen to perform as a classifier in the decision support tool. A number of tests were run which included an investigation of the efficiency of the chosen feature extraction techniques and the diagnostic relevance (with respect to the condition under investigation) of the signals being used to assist in diagnosis. Results show that at present the signals of greatest diagnostic relevance are not always used: a decision support device can be developed using a multi-layer perceptron classifier in combination with other signal processing techniques. The thesis also identifies other techniques where there is potential for improving the decision support tool's predictive and classification ability.

APA, Harvard, Vancouver, ISO, and other styles

10

Arens, Fanelo James. "The Altman corporation failure prediction model : applied among South African medical schemes." Master's thesis, University of Cape Town, 2014. http://hdl.handle.net/11427/13084.

Full text

Abstract:

Includes bibliographical references.
This study has a number of interrelated objectives that seek to understand and contextualize the Altman bankruptcy prediction model in the setting of the South African medical schemes over a ten year period (2002 to 2011). The main objective of this study is to validate the Altman Z₂ model amongst the medical schemes in South Africa; in terms of accurately classifying Z₂-scores of ≤ 1.23 and ≥ 2.9 into the a priori groups of failed and non-failed schemes. The average classification rates in the period 2002 to 2011 are as follows: 82% accuracy rate and 17.9% error rate. A linear trend line inserted in the graph shows the accuracy improving from 72% to 91% between the period 2003/2004 to 2011/2012. This outcome is consistent with the conclusion in previous studies (Aziz and Humayon, 2006: 27) that showed the accuracy rates in most failure prediction studies to be as follows: 84%, 88%, and 85% for statistical models, AEIS models and theoretical models respectively. Although this study validated the Altman model, further studies are required to test the rest of the study objectives under conditions where some of the assumptions are revised.

APA, Harvard, Vancouver, ISO, and other styles

11

Cao, Feng. "Classification, detection and prediction of adverse and anomalous events in medical robots." Case Western Reserve University School of Graduate Studies / OhioLINK, 2012. http://rave.ohiolink.edu/etdc/view?acc_num=case1339166738.

Full text

APA, Harvard, Vancouver, ISO, and other styles

12

Postovskaya, Anna. "Rule-based machine learning for prediction of Macaca mulatta SIV-vaccination outcome using transcriptome profiles." Thesis, Uppsala universitet, Institutionen för farmaceutisk biovetenskap, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-440182.

Full text

Abstract:

One of the reasons, why the development of an effective HIV vaccine remains challenging, is the lack of understanding of potential vaccination-induced protection mechanisms. In the present study, Rhesus Macaques (Macaca mulatta) gene expression profiles obtained during vaccination with promising candidate vaccines against Simian Immunodeficiency Virus (SIV) were processed with a rule-based supervised machine learning approach to analyze the effects of vaccine combination treatment. The findings from constructed rule-based classifiers suggest that the immune response against SIV builds up throughout the immunization procedure. The upregulation of three genes (NHEJ1, GBP7, LAMB1), known to contribute to immune system development and functioning, cellular signalling, and DNA reparation, during or after vaccination boost appears to play an important role in the development of protection against SIV. What is more, the data suggest that the mechanisms of protection development might be dependent on the vaccine type providing a plausible explanation for the difference in effect between vaccines. Further studies are necessary to confirm or disprove our preliminary understanding of the vaccination-induced protection mechanisms against SIV and to use this information for rational vaccine design.

APA, Harvard, Vancouver, ISO, and other styles

13

Price, Megan Rae. "Differential Prediction of Medical School Selection Factors for Rural and Non-Rural Populations." Thesis, Virginia Tech, 2008. http://hdl.handle.net/10919/42384.

Full text

Abstract:

Differential predictive validity in assessing academic performance in institutions of higher education has been assessed for a number of years. Historically, this body of research focused on gender and ethnicity. This study extends that research to geographic region (e.g., rural and non-rural populations). Specifically, this study predicted relationships between preadmission variables of incoming grade point average (GPA) and medical college admissions test (MCAT) and output variables of medical school GPA and comprehensive osteopathic medical licensing exam (COMLEX). Results indicate incoming GPA and MCAT are good variables to use to predict academic performance in medical school and score on the licensing board exam. Further, rural populations presented similar scores on preadmission variables and, thus, are not at a disadvantage in the admission process. A second goal of this study was to explore differential prediction of medical school GPA and COMLEX Level 1 score for the MCAT for rural and non-rural populations. Results provide some evidence of differential prediction of COMLEX score for the physical and biological sciences MCAT sub-tests such that rural populationsâ performance on the COMLEX Level 1 exam was underpredicted. Hence, when rural and non-rural populations present the same physical sciences and biological sciences MCAT sub-test score, the rural sub-group is predicted to obtain a lower COMLEX score and non-rural sub-group is predicted to obtain a higher COMLEX score. Further, when the two sub-groups present different MCAT scores for the physical and biological sciences sub-test, they are likely to obtain similar scores on the COMLEX. Implications and recommendations for future research are discussed.
Master of Science

APA, Harvard, Vancouver, ISO, and other styles

14

Emilsson, Linnea, and Yevgen Tarasov. "Minimizing the Number of Electrodes for Epileptic Seizures Prediction." Thesis, KTH, Skolan för teknik och hälsa (STH), 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-213001.

Full text

Abstract:

Epilepsy is a neurological disorder affecting 1-2 % of the population in the world. People diagnosed with epilepsy are put at high risk of getting injured due to the unpredictable seizures caused by the disorder. Electroencephalography (EEG) in combination with machine learning can be used for prediction of an epileptic seizure. Therefore, a portable prediction device is of great interest with high emphasis for it to be user-friendly. One way to achieve this is by minimizing the number of electrodes placed on the scalp. This study examines the number of electrodes that provide sufficient information for prediction of a seizure. The highest prediction accuracy of 91 %, 97 % sensitivity and 85 % specificity was achieved with as few as 16 electrodes. Due to the limitation of the intracranial EEG recordings further testing must be performed on scalp EEG recordings to provide valid results.

APA, Harvard, Vancouver, ISO, and other styles

15

Mayaud, Louis. "Prediction of mortality in septic patients with hypotension." Thesis, University of Oxford, 2014. http://ora.ox.ac.uk/objects/uuid:55a57418-de16-4932-8a42-af56bd380056.

Full text

Abstract:

Sepsis remains the second largest killer in the Intensive Care Unit (ICU), giving rise to a significant economic burden ($17b per annum in the US, 0.3% of the gross domestic product). The aim of the work described in this thesis is to improve the estimation of severity in this population, with a view to improving the allocation of resources. A cohort of 2,143 adult patients with sepsis and hypotension was identified from the MIMIC-II database (v2.26). The implementation of state-of-the-art models confirms the superiority of the APACHE-IV model (AUC=73.3%) for mortality prediction using ICU admission data. Using the same subset of features, state-of-the art machine learning techniques (Support Vector Machines and Random Forests) give equivalent results. More recent mortality prediction models are also implemented and offer an improvement in discriminatory power (AUC=76.16%). A shift from expert-driven selection of variables to objective feature selection techniques using all available covariates leads to a major gain in performance (AUC=80.4%). A framework allowing simultaneous feature selection and parameter pruning is developed, using a genetic algorithm, and this offers similar performance. The model derived from the first 24 hours in the ICU is then compared with a “dynamic” model derived over the same time period, and this leads to a significant improvement in performance (AUC=82.7%). The study is then repeated using data surrounding the hypotensive episode in an attempt to capture the physiological response to hypotension and the effects of treatment. A significant increase in performance (AUC=85.3%) is obtained with the static model incorporating data both before and after the hypotensive episode. The equivalent dynamic model does not demonstrate a statistically significant improvement (AUC=85.6%). Testing on other ICU populations with sepsis is needed to validate the findings of this thesis, but the results presented in it highlight the role that data mining will increasingly play in clinical knowledge generation.

APA, Harvard, Vancouver, ISO, and other styles

16

Louise, Christa Claire. "A Bootstrapped Regression Model of Psychological Predictors of Success in Naturopathic Medical School." PDXScholar, 1994. https://pdxscholar.library.pdx.edu/open_access_etds/4846.

Full text

Abstract:

In response to a need for more primary care physicians and patients' growing attraction to alternative health care, greater numbers of individuals are applying to naturopathic colleges. With increasing numbers of applicants, better methods of predicting potential effectiveness as an N.D. are needed. This study examined factors (both academic and psychosocial) that best predict success in naturopathic school. Demographic, academic, and psychosocial survey data were collected from thirty-three students who had just completed their second year of naturopathic medical school. This information was correlated with scores on the NPLEX Basic Science exams which were taken the following summer. Because of the small sample size, a bootstrap resampling technique was used to produce estimates for a hierarchical regression. Demographic variables (sex, age, whether or not English was the first language) and undergraduate major, explained almost 10% of the variance in Basic Science Exams (BSE) scores; however, none of these variables were significant predictors in the first step of the regression. As predicted, the addition of undergraduate grade point average (GPA) significantly increased the amount of variance accounted for (to 39.9%) in BSE scores. Also as predicted, adding the psychosocial variables to the model increased the amount of variance accounted for to 52%. This addition also made sex a significant predictor, but external locus of control was the only psychosocial variable which was significant in any of the models. The best model contained the psychosocial variables of both internal and external locus of control but not commitment and accounted for 51 % of the variance in BSE scores. Sex, undergraduate GPA, and external locus of control were significant predictors. Results are consistent with previous research using data on students from allopathic medical schools. However, complex relationships exist among the psychosocial variables and between the psychosocial variables and gender. The suppression effect of the psychosocial variables with gender, multicolinearity between the commitment and locus of control variables, and suppression due to common method variance between the internal and external locus of control variables are discussed. Limitations of bootstrap methodology are considered.

APA, Harvard, Vancouver, ISO, and other styles

17

Johnson, Alistair E. W. "Mortality prediction and acuity assessment in critical care." Thesis, University of Oxford, 2014. https://ora.ox.ac.uk/objects/uuid:2486465e-8fda-47a9-b82e-c0a93f4f1fc4.

Full text

Abstract:

Accurate mortality prediction in intensive care units (ICUs) allows for the risk adjustment of study populations, aids in patient care and provides a method for benchmarking overall hospital and ICU performance. ICU risk-adjustment models are primarily comprised of an integer severity of illness score which increases with increasing patient risk of mortality. First published in the 1980s, the improvements to these scores primarily consisted of increasing the dimensionality of the model, and hence also increasing their complexity. This thesis aims to improve upon these models. First, the field is surveyed and the major models for risk-adjusting critically ill patient cohorts are identified including the acute physiology score (APS) and the simplified acute physiology score (SAPS). A key component of model performance is data preprocessing. The effect of preprocessing ICU data is quantified on a dataset of 8,000 ICU patients, and it is shown that after preprocessing to remove extreme values a logistic regression (LR) model performed competitively (AUROC of 0.8633) with the more complex machine learning model; a support vector machine (SVM) which had an AUROC of 0.8653. For validation, model development was repeated in a larger database containing over 80,000 patients admitted to 89 ICUs in the United States. Results were similar (AUROC of 0.8895 for the LR vs 0.8917 for the SVM) but showed the performance gain when using automated outlier rejection is less pronounced in well quality controlled datasets (0.8883 for LR without rejection). It is hypothesised from this that simpler models can perform competitively with more complicated models, while having a greatly reduced burden of data collection. A severity score is developed on the large multi-center database using a Genetic Algorithm and Particle Swarm Optimisation. The severity score, named the Oxford Acute Severity of Illness Score (OASIS), is shown to outperform the APS III (AUROC 0.837 vs 0.822) and perform competitively with APACHE IV when used as a covariate in a regression model (AUROC 0.868 vs 0.881). The severity score requires only 10 variables (58% as many as APS III), reducing the burden of quality control and data collection. These variables are routinely collected in critical care by continuous monitors and do not include comorbidities, diagnosis or laboratory measurements. The severity score is then externally evaluated in an American hospital and shown to discriminate well (AUROC 0.790 vs. 0.782 for the APS III) with excellent calibration. Finally, the severity score was evaluated in an English hospital and compared to other severity scores. OASIS again had excellent calibration and discrimination (AUROC 0.776 vs 0.750 for APS III) whilst requiring a much smaller number of variables. OASIS has many applications, including both simplifying data collection for studies and improving the risk assessment therein.

APA, Harvard, Vancouver, ISO, and other styles

18

You, Shu-Chyng. "Validating the therapy prediction model through a breakdown analysis on ICU patient medical records." Thesis, Massachusetts Institute of Technology, 2006. http://hdl.handle.net/1721.1/42122.

Full text

Abstract:

Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2006.
Includes bibliographical references (p. 81-83).
With the rapid advancement of computational data analysis tools, medical informatics has emerged as a discipline that explores the use of medical information in clinical practice. It searches for ways to effectively integrate as much information as is available to physicians when they make clinical decisions and represent the information in the most intelligent way possible. As part of an overall effort to develop a program that assists physicians in making clinical decisions on patients with heart disease, we developed a model for predicting therapy effects in heart disease using signal flow analysis that describes constraint relations among physiological parameters. In order to accurately describe and predict the therapy effects on a patient in heart failure, the model needs to be tested and analyzed with real-life patient data including any cardiovascular parameters measurable in the patient. This thesis will present methods for extracting hemodynamic relations and drug effects from patients in the intensive care unit. In this thesis, we propose to test our hypothesis that significant relationships between hemodynamic parameters can be derived from certain classifications of patients and sectioning of hospital stays, and explore the effects of drugs on patients with different sets of diseases.
by Chu-Chyng You.
M.Eng.

APA, Harvard, Vancouver, ISO, and other styles

19

Chen, Yang. "DEVELOPMENT OF COMPUTATIONAL APPROACHES FOR MEDICAL IMAGE RETRIEVAL, DISEASE GENE PREDICTION, AND DRUG DISCOVERY." Case Western Reserve University School of Graduate Studies / OhioLINK, 2015. http://rave.ohiolink.edu/etdc/view?acc_num=case1435601642.

Full text

APA, Harvard, Vancouver, ISO, and other styles

20

Yan, Jia. "Using Genetic Information in Risk Prediction for Alcohol Dependence." VCU Scholars Compass, 2012. http://scholarscompass.vcu.edu/etd/2878.

Full text

Abstract:

Family-based and genome-wide association studies (GWAS) of alcohol dependence (AD) have reported numerous associated variants. The clinical validity of these variants for predicting AD compared to family history has not yet been reported. These studies aim to explore the aggregate impact of multiple genetic variants with small effect sizes on risk prediction in order to provide a clinical interpretation of genetic contributions to AD. Data simulations showed that given AD’s prevalence and heritability, a risk prediction model incorporating all genetic contributions would have an area under the receiver operating characteristic curve (AUC) approaching 0.80, which is often a target AUC for screening. Adding additional environmental factors could increase the AUC to 0.95. Using the Collaborative Study on the Genetics of Alcoholism (COGA) and the Study of Addiction: Genes and Environment (SAGE) GWAS samples, we used several different sources to capture genetic information associated with AD in discovery samples, and then tested genetic sum scores created based on this information for predictive accuracy in validation samples. Scores were assessed separately for single nucleotide polymorphisms (SNPs) associated in candidate gene studies and in GWAS analyses. Candidate gene sum scores did not exhibit significant predictive accuracy, but SNPs meeting less stringent p-value thresholds in GWAS analyses did, ranging from mean estimates of 0.549 for SNPs meeting p<0.01 to 0.565 for SNPs meeting p<0.50. Variants associated with subtypes of AD showed that there is similarly modest and significant predictive ability for an externalizing subtype. Scores created based on all individual SNP effects in aggregate across the entire genome accounted for 0.46%-0.57% of the variance in AD symptom count, and have AUCs of 0.527 to 0.549. Additional covariates and environmental factors that are correlated with AD increased the AUC to 0.865. Family history was a better classifier of case-control status than genetic sum scores, with an AUC of 0.686 in COGA and 0.614 in SAGE. This project suggests that SNPs from candidate gene studies and genome-wide association studies currently have limited clinical validity, but there is potential for enhanced predictive ability with better detection of genetic factors contributing to AD.

APA, Harvard, Vancouver, ISO, and other styles

21

Hutchings, Lynn. "Early identification and prediction of multiple organ failure following major trauma." Thesis, University of Oxford, 2014. http://ora.ox.ac.uk/objects/uuid:bece7667-770b-4cdf-87d8-407dca80a4ee.

Full text

Abstract:

Introduction: Trauma is the main cause of death in working-age adults in the UK. Multiple organ failure (MOF) is associated with a high proportion of late trauma deaths, and MOF survivors have poor long-term outcomes. Early prediction of patients at risk of MOF would assist treatment decisions and allow targeted interventions. Methods: A cohort of major trauma patients requiring intensive care unit (ICU) treatment at the John Radcliffe Hospital was identified. Data were obtained from the two national databases of the Trauma Audit Research Network and the Intensive Care National Audit and Research Centre, and from a local ICU database with hourly data recording. Literature review and questionnaire analysis of trauma clinicians identified candidate predictors of MOF, grouped into patient, injury, physiological, laboratory and management variables. MOF scoring systems were reviewed to determine the most appropriate for use in trauma patients. Prediction models of post-trauma MOF were developed using logistic regression at a range of times from 0 to 48 hours after injury. Models were internally validated using bootstrapping. Results: 517 adult trauma patients were identified from 2003-2011. Overall mortality was 14.9%, with 491 patients surviving more than 48 hours, and therefore being at risk of MOF development. For these 491 patients, MOF incidence depended on the definition, and ranged from 23% (Denver score) to 58% (SOFA score). MOF was associated with mortality, time to ICU admission, and length of ICU and hospital stay. MOF could be predicted with an accuracy of up to 81.3% at 2 hours post-injury, and 84.2% at 12 hours post-injury using small numbers of clinical variables. Age, head injury, abdominal injury, maximum heart rate and the need for vasopressors were strong predictors of all definitions of MOF. Conclusions: Post-trauma MOF can be predicted early after injury using combinations of clinical variables. Further validation of the identified variables on external populations would allow development of a clinical score to assist clinicians in trauma management.

APA, Harvard, Vancouver, ISO, and other styles

22

Falodi, Abiodun. "Prediction of the biomechanical perfomance of a novel total disc replacement." Thesis, University of Nottingham, 2010. http://etheses.nottingham.ac.uk/1266/.

Full text

Abstract:

The pain experience as a result of disc degeneration disease (DDD) can be debilitating. When drug administration and physiotherapy treatment fail, surgical methods are used. These involve removal of the affected intervertebral disc IVD, followed by either decompression and fusion of the adjacent vertebral bodies or replacement of the removed IVD with an implant. Fusion is seen to be the gold standard for surgical treatment of DDD, but questions have been raised about its effectiveness in the long term due to its association with the adjacent levels disc degeneration. Disc replacement has been developed as an alternative to overcome this problem. The aim of the implant, in contrast to fusion, is the preservation of motion at the treated level. This has been said to maintain the adjacent level biomechanics and hence, prevent rapid degeneration. A novel graduated modulus polymeric total disc replacement device, Compliant Artificial Disc (CAdisc) developed by Ranier Technology Limited was studied in this project. Its design is such as to provide load-bearing capability and motion preservation at the implanted site. Through a unique manufacturing process, Precision Polyurethane Manufacturing PPM, the lower modulus nucleus material of this device is encapsulated by the higher modulus annulus with presence of graduated modulus in between. This project, aims to analyse the CAdisc mechanical properties and evaluate its biomechanical performance. Scanning Acoustic Microscope SAM and nano-indentation was used to analyse the CAdisc internal modulus distribution. The results show different modulus regions (the annulus, the graduated and the nucleus regions) in the CAdisc device and demonstrate the potential of the PPM process to produce consistent graduated region. It was also found that the SAM results were comparable to the nano-indentation with a significant correlation between the results. The technology in the development of the CAdisc-L (lumbar disc replacement) has been used to develop its cervical counterpart, CAdisc-C which is in its initial stage of design. Using a validated highly meshed 3D FEM of the cervical spine (C4-C7), developed from CT data, the biomechanical performance of cervical version of the CAdisc (CAdisc-C) was evaluated. The result shows the implant preserved motion at the treated level and gives a performance that preserved the biomechanics of the adjacent level compared to fusion. The study also shows that misplacement of the implant from its optimal position will not significantly affect its performance.

APA, Harvard, Vancouver, ISO, and other styles

23

Wiseman, Scott. "Bayesian learning in graphical models." Thesis, University of Kent, 1999. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.311261.

Full text

APA, Harvard, Vancouver, ISO, and other styles

24

Johansson, Birgitta. "Intensified primary health care for cancer patients : Utilisation of medical services." Doctoral thesis, Uppsala University, Department of Public Health and Caring Sciences, 2000. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-512.

Full text

Abstract:

The aim of the present thesis is to evaluate the effects of an Intensified Primary Health Care (IPHC) intervention on GPs' and home care nurses' possibilities to monitor and support cancer patients, and on cancer patients utilisation of medical services. A further aim is to identify determinants of cancer patients' utilisation of such services. A total of 485 patients newly diagnosed with breast, colorectal, gastric or prostate cancer were randomised to the intervention or to a control group. The follow-up period was 24 months for all patients.

Patients randomised to the IPHC were referred to the home care nurse. The home care nurse and the GP received copies of the medical record each time the patient was discharged from hospital after a period of in-patient care, or had visited a specialist out-patient clinic. In addition to this, recurrent education and supervision in cancer care were arranged.

The IPHC resulted in a marked increase of home care nurse follow-up contacts. The majority of control patients (74%) reported no such contacts, while 89% of IPHC patients reported this. High age (=80 yr) was the strongest predictor within the IPHC group for reporting a continuing home care nurse contact. Furthermore, the IPHC increased GPs' knowledge about patients' disease and treatments, and appeared to facilitate their possibilities to support the patients. The IPHC reduced the utilisation of specialist care among elderly cancer patients. The number of days of hospitalisation for older patients (=70 yr) randomised to the IPHC were 393 less than for older control patients during the 3 first months after inclusion. Regression analyses defined diagnosis, extensive treatment, comorbidity, low functional status, pain and socio-economic factors as predictors of a high utilisation of medical services.

APA, Harvard, Vancouver, ISO, and other styles

25

Alleman, Brandon Wesley. "Preterm birth: prediction, prevention, care." Diss., University of Iowa, 2014. https://ir.uiowa.edu/etd/4563.

Full text

Abstract:

Preterm birth (PTB) is defined as birth before 37 weeks gestational age. PTB is a common outcome and one that may be increasing in prevalence with serious individual and public health implications both immediately and long term. While PTB is a pregnancy specific outcome it is more appropriately viewed as the culmination of risk factors present both before pregnancy and possibly in past generations. This thesis attempts to review the implications, risk factors and current prevention strategies directed at PTB while placing it in an intergenerational and life cycle context. Three novel investigations are presented and their consequences are discussed. These investigations cover the lifespan and relate to identifying PTB and treating its immediate health outcomes. The first examines mitochondrial genetics and it's relation to PTB. There is a strong a priori hypothesis that mitochondrial genetics, being maternally inherited, may contribute to an individual's risk for PTB. However, in two genome wide association studies, no evidence is found for any mitochondrial polymorphisms being related to PTB. The second investigation reports an attempt to identify women at risk for PTB within a given pregnancy. Using routinely collected maternal information and serum screening data a potentially useful screening method is derived. While the algorithm does not have ideal performance characteristics it compares favorably to other population wide screening techniques and could be improved through future validation and data collection. The third and final investigation attempts to address quality of care for infants born preterm. In a network of neonatal intensive care units, wide variations in mortality outcomes are observed. Intensity of medical intervention appears to be an important predictor of mortality for the lowest gestational age infants. However, this intensity of intervention does not fully explain the observed differences in mortality outcomes. Finally, these study are discussed in context with one another and a new framework for considering PTB is presented that may help to guide future investigation into predicting, preventing and caring for those at risk for or experiencing a PTB.

APA, Harvard, Vancouver, ISO, and other styles

26

Brunty, Tom J. "The prediction of return-to-work in a chronic pain population : psychological, demographic and medical variables /." The Ohio State University, 1992. http://rave.ohiolink.edu/etdc/view?acc_num=osu1487775034178146.

Full text

APA, Harvard, Vancouver, ISO, and other styles

27

Bou, Rjeily Carine. "Data mining and learning for markers extraction to improve the medical monitoring platforms." Thesis, Bourgogne Franche-Comté, 2019. http://www.theses.fr/2019UBFCA012.

Full text

Abstract:

Selon l’Organisation mondiale de la santé, environ 31% des décès dans le monde sont causés par des maladies cardiaques chaque année. L’exploration de données est un processus d’extraction intéressant d’informations non triviales, implicites et potentiellement utiles, à partir de grands ensembles de données. L’exploration de données médicales est la science qui consiste à examiner des données médicales (signes vitaux) pour explorer des informations importantes. L’analyse et l’interprétation des données complexes dans un diagnostic thérapeutique approprié avec les bons résultats, est une tâche assez ardue. Néanmoins, le fait qu’il soit possible de combiner ces facteurs jusqu’à un certain point et d’extraire un plan de traitement, de prévention et de rétablissement généralement couronnée de succès, est un signe des avantages à venir. Grâce à cela, il est maintenant possible d’améliorer la qualité de vie des patients, de prévenir une aggravation de la maladie tout en maintenant les coûts médicaux à la baisse. Cela explique la popularité croissante de l’utilisation et de l’application des techniques d’apprentissage automatique pour analyser, prédire et classifier les données médicales. Dans une première contribution, nous avons étudié de nombreux algorithmes de motifs séquentiels qui sont des techniques prometteuses pour l’exploration de données. Nous les avons classés afin de choisir un algorithme approprié pour prédire les classes d’insuffisance cardiaque et sa présence. Après avoir comparé tous les algorithmes et les avoir mis en œuvre sur le même ensemble de données médicales, le CPT +, un algorithme de prédiction de séquence, a été choisi en donnant les résultats les plus précis avec une précision de 90,5% dans la prédiction de l’insuffisance cardiaque et de ses classes. En utilisant cet algorithme, avec des données des patients réels, nous avons pu prédire une insuffisance cardiaque 10 à 12 jours à priori. Après, nous avons basculé nos études vers une stratégie de séries chronologiques et nous avons utilisé des données réelles extraites de patients réels. 5 paramètres ont été extraits de 3 patients au cours de quelques années. L’algorithme RandomTree a donné plus de 85% de prédictions correctes de l’insuffisance cardiaque 7 jours à l’avance
The World Health Organization accords that about 31 % of deaths worldwide are caused by heart diseases every year. Data mining is a process of extracting interesting non-trivial, previously unknownand potentially useful information from huge amount of data. Medical data mining is the science of investigating medical data (i.e. vital signs) to explore significant information. Analyzing and interpreting the huge amount of complicated data into an appropriate therapeutic diagnosis with the right results is quite challenging task. Still, the fact that it is possible to combine these factors up to a certain point and extract a usually successful treatment, prevention and recovery plan is a sign of the good things to come. Thanks to that, it is now possible to improve patients’ quality of life, prevent condition worsening while maintaining medical costs at the decrease. This explains the increasing popularity in the usage and application of machine learning techniques to analyze, predict and classify medical data. As a first contribution, we studied many sequential patterns algorithms that are promising techniques in exploring data and we classified them in order to choose an appropriate one for predicting Heart Failure classes and presence. After comparing all the algorithms and implementing them on the same medical dataset, the CPT+ a sequence prediction algorithm has been chosen as it gave the most accurate results reaching an accuracy of 90.5% in predicting heart failure and its classes. By using the CPT+ algorithm with real patients dataset, we predicted heart failure 10 to 12 days prior. Thereafter, we switched our studies to time series strategy, and worked on real data extracted from real patients. 5 parameters were extracted from 3 patients over the course of a few years. The Random Tree algorithm yielded more the 85% correct predictions of heart failure 7 days prior

APA, Harvard, Vancouver, ISO, and other styles

28

Conic, Julijana Zoran. "Incremental Prognostic Impact of Imaging Characteristic for Comprehensive Risk Stratification in Patients with Advanced Ischemic Cardiomyopathy." Case Western Reserve University School of Graduate Studies / OhioLINK, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=case1591016434442071.

Full text

APA, Harvard, Vancouver, ISO, and other styles

29

Hellström, Terese. "Deep-learning based prediction model for dose distributions in lung cancer patients." Thesis, Stockholms universitet, Fysikum, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-196891.

Full text

Abstract:

Background To combat one of the leading causes of death worldwide, lung cancer treatment techniques and modalities are advancing, and the treatment options are becoming increasingly individualized. Modern cancer treatment includes the option for the patient to be treated with proton therapy, which can in some cases spare healthy tissue from excessive dose better than conventional photon radiotherapy. However, to assess the benefit of proton therapy compared to photon therapy, it is necessary to make both treatment plans to get information about the Tumour Control Probability (TCP) and the Normal Tissue Complication Probability (NTCP). This requires excessive treatment planning time and increases the workload for planners. Aim This project aims to investigate the possibility for automated prediction of the treatment dose distribution using a deep learning network for lung cancer patients treated with photon radiotherapy. This is an initial step towards decreasing the overall planning time and would allow for efficient estimation of the NTCP for each treatment plan and lower the workload of treatment planning technicians. The purpose of the current work was also to understand which features of the input data and training specifics were essential for producing accurate predictions. Methods Three different deep learning networks were developed to assess the difference in performance based on the complexity of the input for the network. The deep learning models were applied for predictions of the dose distribution of lung cancer treatment and used data from 95 patient treatments. The networks were trained with a U-net architecture using input data from the planning Computed Tomography (CT) and volume contours to produce an output of the dose distribution of the same image size. The network performance was evaluated based on the error of the predicted mean dose to Organs At Risk (OAR) as well as the shape of the predicted Dose-Volume Histogram (DVH) and individual dose distributions. Results The optimal input combination was the CT scan and lung, mediastinum envelope and Planning Target Volume (PTV) contours. The model predictions showed a homogenous dose distribution over the PTV with a steep fall-off seen in the DVH. However, the dose distributions had a blurred appearance and the predictions of the doses to the OARs were therefore not as accurate as of the doses to the PTV compared to the manual treatment plans. The performance of the network trained with the Houndsfield Unit input of the CT scan had similar performance as the network trained without it. Conclusions As one of the novel attempts to assess the potential for a deep learning-based prediction model for the dose distribution based on minimal input, this study shows promising results. To develop this kind of model further a larger data set would be needed and the training method could be expanded as a generative adversarial network or as a more developed U-net network.

APA, Harvard, Vancouver, ISO, and other styles

30

Tiltu, Klintborg Anna. "BCR-ABL1A TYROSINE KINASE ASSOCIATED WITH CHRONIC MYELOID LEUKEMIA : Calculation of solvation energiesand electrostatics by APBS and prediction of 2D and 3D structureby homology protein modeling." Thesis, Umeå universitet, Institutionen för integrativ medicinsk biologi (IMB), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-182126.

Full text

APA, Harvard, Vancouver, ISO, and other styles

31

Lange, Katrin Susanne [Verfasser]. "Calving prediction and evaluation of calving ease after medical treatment in Holstein-Friesian heifers / Katrin Susanne Lange." Berlin : Freie Universität Berlin, 2020. http://d-nb.info/1221130056/34.

Full text

APA, Harvard, Vancouver, ISO, and other styles

32

Izad, Shenas Seyed Abdolmotalleb. "Predicting High-cost Patients in General Population Using Data Mining Techniques." Thèse, Université d'Ottawa / University of Ottawa, 2012. http://hdl.handle.net/10393/23461.

Full text

Abstract:

In this research, we apply data mining techniques to a nationally-representative expenditure data from the US to predict very high-cost patients in the top 5 cost percentiles, among the general population. Samples are derived from the Medical Expenditure Panel Survey’s Household Component data for 2006-2008 including 98,175 records. After pre-processing, partitioning and balancing the data, the final MEPS dataset with 31,704 records is modeled by Decision Trees (including C5.0 and CHAID), Neural Networks. Multiple predictive models are built and their performances are analyzed using various measures including correctness accuracy, G-mean, and Area under ROC Curve. We conclude that the CHAID tree returns the best G-mean and AUC measures for top performing predictive models ranging from 76% to 85%, and 0.812 to 0.942 units, respectively. Among a primary set of 66 attributes, the best predictors to estimate the top 5% high-cost population include individual’s overall health perception, history of blood cholesterol check, history of physical/sensory/mental limitations, age, and history of colonic prevention measures. It is worthy to note that we do not consider number of visits to care providers as a predictor since it has a high correlation with the expenditure, and does not offer a new insight to the data (i.e. it is a trivial predictor). We predict high-cost patients without knowing how many times the patient was visited by doctors or hospitalized. Consequently, the results from this study can be used by policy makers, health planners, and insurers to plan and improve delivery of health services.

APA, Harvard, Vancouver, ISO, and other styles

33

McEntyre, Wanda L. J. "Self-efficacy expectations, outcome expectations and the prediction of medication usage, pain level and work readiness /." The Ohio State University, 1985. http://rave.ohiolink.edu/etdc/view?acc_num=osu1487260531958244.

Full text

APA, Harvard, Vancouver, ISO, and other styles

34

Smith, Amie L. "Biopsychosocial Variables Predict Compensation and Medical Costs of Radiofrequency Neurotomy in Utah Workers' Compensation Patients." DigitalCommons@USU, 2014. https://digitalcommons.usu.edu/etd/3854.

Full text

Abstract:

Back pain is one of the most expensive medical conditions to treat. There has been a great deal of research showing that back pain surgery is expensive, but less is known about the costs of less-invasive spine procedures such as radiofrequency neurotomy. Radiofrequency neurotomy is used to treat facet joint pain and typically offers temporary pain relief by coagulating the affected nerve with radiofrequency waves to block pain messages from reaching the brain. This study aimed to document the costs of radiofrequency neurotomy in a group of participants who received the procedure through the Workers’ Compensation Fund of Utah (WCFU). Another goal of the study was to determine if any biopsychosocial variables of participants predicted costs. Biopsychosocial variables include biological (e.g., age), psychological (e.g., depression), and social (e.g., hiring a lawyer) characteristics about participants. Costs and characteristics were collected from participant medical records. Compensation and medical costs were collected; compensation costs were wage payouts as a result of an on-the-job injury, and medical costs were direct medical costs. Both compensation and medical costs were substantial and similar to other more invasive procedures. Furthermore, three biopsychosocial characteristics predicted high costs. A high number of prior back and neck surgery and lawyer involvement predicted high compensation costs. Those same variables plus history of depression predicted high medical costs. This was the first known study to document medical and compensation costs associated with spinal radiofrequency neurotomy. The findings add to the line of research suggesting that a biopsychosocial framework can be used to predict costs in spine care. Discovering participant characteristics that may predict high costs can inform policylevel decisions for insurers, and can be used by medical providers to influence patient care decisions. More research on the presurgical variables may lead to interventions at the patient level that can reduce high cost outcomes which could benefit both patients and payers.

APA, Harvard, Vancouver, ISO, and other styles

35

Clark, James. "A Data Mining Framework for Improving Student Outcomes on Step 1 of the United States Medical Licensing Examination." Diss., NSUWorks, 2019. https://nsuworks.nova.edu/gscis_etd/1070.

Full text

Abstract:

Identifying the factors associated with medical students who fail Step 1 of the United States Medical Licensing Examination (USMLE) has been a focus of investigation for many years. Some researchers believe lower scores on the Medical Colleges Admissions Test (MCAT) are the sole factor used to identify failure. Other researchers believe lower course outcomes during the first two years of medical training are better indicators of failure. Yet, there are medical students who fail Step 1 of the USMLE who enter medical school with high MCAT scores, and conversely medical students with lower academic credentials who are expected to have difficulty passing Step 1 but pass on the first attempt. Researchers have attempted to find the factors associated with Step 1 outcomes; however, there are two problems associated with their methods used. First is the small sample size due to the high national pass rate of Step 1. And second, research using multivariate regression models indicate correlates of Step 1 but does not predict individual student performance. This study used data mining methods to create models which predict medical students at risk of failing Step 1 of the USMLE. Predictor variables include those available to admissions committees at application time, and final grades in courses taken during the preclinical years of medical education. Models were trained, tested, and validated using a stepwise approach, adding predictor variables in the order of courses taken to identify the point during the medical education continuum which best predicts students who will fail Step 1. Oversampling techniques were employed to resolve the problem of small sample sizes. Results of this study suggest at risk medical students can be identified as early as the end of the first term during the first year. The approach used in this study can serve as a framework which if implemented at other U.S. allopathic medical schools can identify students in time for appropriate interventions to impact Step 1 outcomes

APA, Harvard, Vancouver, ISO, and other styles

36

Chaganti, Vasanta Gayatri. "Wireless body area networks : accuracy of channel modelling and prediction." Phd thesis, Canberra, ACT : The Australian National University, 2014. http://hdl.handle.net/1885/150112.

Full text

APA, Harvard, Vancouver, ISO, and other styles

37

Sikkema, Kathleen J. "Psychosocial variables in the prediction of somatic complaints with applications to stress-related disorders." Thesis, Virginia Tech, 1988. http://hdl.handle.net/10919/44688.

Full text

Abstract:

In Study 1, 280 undergraduate students (177 female, 103 male) were administered a battery of questionnaires assessing functional somatic symptoms, psychosocial variables, and behavioral responses to health-related situations. Significant predictors of functional somatic symptoms differed for females and males. The amount of stress experienced, perceived susceptibility to illness, perceived barriers to health care and level of pain tolerance were significant predictors for males. Significant predictors for females included perceived susceptibility to illness, amount of stress experienced, and not responding to health-related situations by seeking medical attention. A discriminant analysis correctly classified 21.25% of these groups.

Master of Science

APA, Harvard, Vancouver, ISO, and other styles

38

Alaskar, Haya Mohmmad. "Dynamic self-organised neural network inspired by the immune algorithm for financial time series prediction and medical data classification." Thesis, Liverpool John Moores University, 2014. http://researchonline.ljmu.ac.uk/4562/.

Full text

Abstract:

Artificial neural networks have been proposed as useful tools in time series analysis in a variety of applications. They are capable of providing good solutions for a variety of problems, including classification and prediction. However, for time series analysis, it must be taken into account that the variables of data are related to the time dimension and are highly correlated. The main aim of this research work is to investigate and develop efficient dynamic neural networks in order to deal with data analysis issues. This research work proposes a novel dynamic self-organised multilayer neural network based on the immune algorithm for financial time series prediction and biomedical signal classification, combining the properties of both recurrent and self-organised neural networks. The first case study that has been addressed in this thesis is prediction of financial time series. The financial time series signal is in the form of historical prices of different companies. The future prediction of price in financial time series enables businesses to make profits by predicting or simply guessing these prices based on some historical data. However, the financial time series signal exhibits a highly random behaviour, which is non-stationary and nonlinear in nature. Therefore, the prediction of this type of time series is very challenging. In this thesis, a number of experiments have been simulated to evaluate the ability of the designed recurrent neural network to forecast the future value of financial time series. The resulting forecast made by the proposed network shows substantial profits on financial historical signals when compared to the self-organised hidden layer inspired by immune algorithm and multilayer perceptron neural networks. These results suggest that the proposed dynamic neural networks has a better ability to capture the chaotic movement in financial signals. The second case that has been addressed in this thesis is for predicting preterm birth and diagnosing preterm labour. One of the most challenging tasks currently facing the healthcare community is the identification of preterm labour, which has important significances for both healthcare and the economy. Premature birth occurs when the baby is born before completion of the 37-week gestation period. Incomplete understanding of the physiology of the uterus and parturition means that premature labour prediction is a difficult task. The early prediction of preterm births could help to improve prevention, through appropriate medical and lifestyle interventions. One promising method is the use of Electrohysterography. This method records the uterine electrical activity during pregnancy. In this thesis, the proposed dynamic neural network has been used for classifying between term and preterm labour using uterine signals. The results indicated that the proposed network generated improved classification accuracy in comparison to the benchmarked neural network architectures.

APA, Harvard, Vancouver, ISO, and other styles

39

Gilbreath, Donna Arlene. "PROJECTING THE RESULTS OF STATE SMOKING BAN INITIATIVES USING CARTOGRAPHIC ANALYSIS." UKnowledge, 2007. http://uknowledge.uky.edu/gradschool_theses/453.

Full text

Abstract:

Because tobacco smoking causes 430,000 U.S. deaths annually, wide-reaching smoking bans are needed. Bans reduce cigarette consumption, encourage cessation, protect nonsmokers from second-hand smoke, and promote an attitude that smoking is undesirable. Therefore, bans may prevent future generations from suffering many smoking-related health problems. The federal government has not implemented widereaching smoking bans so it falls on individual states, counties, or communities to devise appropriate smoking policy. To date, smoking policy has been determined by legislators, who may have conflicts that prevent them from acting in the publics best interest. However, this method of implementing smoking policy may be changing. In 2005, Washington residents voted by ballot initiative to strengthen existing state smoking regulations. In 2006, Arizona, Nevada, and Ohio residents voted by ballot initiatives to implement strict statewide smoking bans. This research presents a way to predict how residents of other states might vote if given the opportunity. Two research hypotheses are tested and accepted: a positive relationship between favorable votes and urbanness, and a preference favoring smoking bans where smoking regulations already exist. Finally, a projection is made that a smoking ban vote in Kentucky would yield favorable results, and a map showing projected county votes is provided.

APA, Harvard, Vancouver, ISO, and other styles

40

Wright, James Scott. "Academic Lineage and Student Performance in Medical School." Thesis, University of North Texas, 1999. https://digital.library.unt.edu/ark:/67531/metadc2206/.

Full text

Abstract:

This research investigated the association between academic lineage and student performance in medical school. The purposes of the study were to: (1) determine whether the Carnegie classifications of medical school applicants' institutions of origin are associated with academic performance in medical school; (2) consider the relationship between the admission selectivity of the schools of origin and the academic performance of medical school students; (3) compare the performance of medical students from institutions under public governing control with students from privately controlled institutions; and (4) establish a model by which the relative academic strengths of applicants from a variety of undergraduate institutions can be understood more clearly based on the previous performance of medical students from schools with similar institutional characteristics. A review of the literature on medical school admissions was completed and used to develop this research. Medical students from the University of Texas Southwestern Medical Center at Dallas who enrolled between the years 1990 and 1994 and graduated or were dismissed between the years 1994 and 1998 were selected as the sample for the study (n=933). The undergraduate institution of origin for each student was coded based on its Carnegie classification, admissions selectivity group, and whether its governing control was public or private. Because the sample was not randomly selected and the data likely would not meet the assumptions of equal means and variance with the population, nonparametric analyses of variance and multiple comparison tests were completed to compare the groups of the independent variables over each dependent variable. The analyses revealed that for the sample of medical students selected for this study there was an association between academic lineage and student performance in medical school. Differences were found among Carnegie classifications on the dependent variables of cumulative medical school grade point average, class rank, failure rate, and score on Step 1 of the United States Medical Licensure Examination. Further, it was found that admission selectivity was also associated with student performance in medical school for each dependent variable except failure rate. Finally, the study results indicated no association between public or private governing control and student performance in medical school.

APA, Harvard, Vancouver, ISO, and other styles

41

Blackbeard, Jill Margaret. "Reticulocyte maturation index: a prediction tool for recovery in post bone marrow and peripheral blood stem cell transplant patients." Thesis, Cape Technikon, 2002. http://hdl.handle.net/20.500.11838/1466.

Full text

Abstract:

Thesis (MTech (Medical Technology))--Cape Technikon, Cape Town, 2002
Erythropoietic response is the first indication of bone marrow recovery following bone marrow or peripheral blood stem cell transplantation. Manual reticulocyte counting has not only proven to be outdated but an extremely crude method of analysis, particularly if accurate and reliable means of assessing erythroid response is required to assess bone marrow recovery. Automated methods allow for the quantification of maturation within each reticulocyte, by measuring the amount of RNA present. The method of choice for our reticulocyte analysis was the Reticulocyte Maturation Index (RMI). The RMI was obtained by dividing the number of immature reticulocytes counted by the total number of reticulocytes counted producing a reportable value of International Units (IU). A normal Reticulocyte Maturation Index is 0.20 to 0.50 IU. The aim of the study was multifold. We wanted to prove that the Reticulocyte Maturation Index (RMI) is indeed the fastest means to assess bone marrow recovery in various types of transplants, including Bone Marrow Transplant (BMT) and Peripheral Blood Stem Cell Transplant (PBSCT). We also wanted to draw comparisons between allogeneic and autologous transplants, as well as further assessing different disease types. This was done by measuring the Reticulocyte Maturation Index (RMI), Absolute Neutrophil Count (ANe) and the Platelet Count (PLT) within the various groups. We further wanted to assess the effect of preconditioning treatment, Mononuclear Counts (MNC) and Colony Forming Unit - Granulocyte and Monocyte Counts (CFU-GM) on the early RMI response. These comparisons resulted in a need to establish a working range to determine patients response therein, and final outcome of the transplants. Finally we wanted to establish whether the "day 14" marrow biopsy is necessary, particularly if the three peripheral blood parameters, RMI, ANC and PLT were used as routine procedure following transplantation. The Reticulocyte Maturation Index (RMI) was measured on the Coulter EPICS ProfIle II flow cytometer; the ANC and PLT were measured on the Technicon H2 Haematology System. All other results such as the Mononuclear Counts (MNC), Colony Forming Unit - Granulocyte and Monocyte counts (CFU-GM), "day 14" and "day 28" bone marrow biopsies were retrieved from laboratory records. Forty nine transplant patients were evaluated for RMI over a period of six months, at the Department of Haematology, Groote Schuur Hospital, Cape Town. Four patients failed to engraft; and were not used in the calculations; but were evaluated as an aspect of the study in the final analysis. Forty five patients were analysed to establish the values used in the study, these patients were divided into eleven groups.

APA, Harvard, Vancouver, ISO, and other styles

42

Arochena, H. E. "Modelling and prediction of parameters affecting attendance to the NHS breast cancer screening programme." Thesis, Coventry University, 2003. http://curve.coventry.ac.uk/open/items/3d5373c6-9442-4479-77a2-c1bc37662cf5/1.

Full text

Abstract:

This thesis focuses on the modelling and prediction of factors affecting attendance to screening invitations of the NHS Breast Screening Programme. The analysis is based on data collected by the Warwickshire, Solihull and Coventry Breast Screening Unit from 1989 up to 2001 with respect to invitation to screening for the prevention of breast cancer in non-symptomatic women. Using a novel approach to the analysis of the data, from the perspective of the screening episode of each woman, rather than the usual analysis from the perspective of the screening round of the units, a statistical analysis is carried out on the whole registered population for the first time. Amendments to the current formulae for coverage calculations, the introduction of a new parameter (invitation rate) and the proposal for a reduction of the invitation period (period of time between two consecutive invitations) follows from the analysis. A preliminary analysis of predictive methodologies, including traditional statistical methods and artificial intelligent methods, gives the foundation to the formulation of two new algorithms; the first, for the prediction of attendance of women to screening invitations, and the second for the prediction of occurrence of screening variation (change of appointment dates) of women to invitations. Both algorithms are based on neural network generated models able to learn from the previous screening behaviour history of the woman, a technique not previously explored for the prediction of attendance. The accuracy of the new proposed algorithm for the prediction of attendance to invitation is tested on a blind study using data not previously seen by the predictive system, and for which results were unknown at the time when the predictions were made. From the obtained results, it is concluded to recommend the implementation by the NHS Breast Screening Unit of the two algorithms proposed for the prediction of the women’s attendance and screening variation to their invitation for screening. With these predictions, women likely not to attend, or change appointment date, can be identified and appropriately targeted with the aim of increasing their attendance in the short term, and in the long term, reducing breast cancer mortality.

APA, Harvard, Vancouver, ISO, and other styles

43

Viti, Mario. "Automated prediction of major adverse cardiovascular events." Electronic Thesis or Diss., université Paris-Saclay, 2022. http://www.theses.fr/2022UPASG084.

Full text

Abstract:

Dans ce projet de recherche financé en contrat CIFRE avec GE Healthcare, on cherche a prédire les épisodes cardio-vasculaire adverses majeurs (ECAM), c’est à dire typiquement les embolies et les anévrismes dans l’aorte et les artères coronaires, qui donnent lieu a une respectivement à une interruption catastrophique du flux sanguin vers le coeur et donc un infarctus, ou à une hémorragie interne. Les deux types d’épisodes sont extrêmement graves. Lorsqu’un patient est hospitalisé pour une alerte reliée à ces épisodes, il va subir un examen scanner X, injecté ou non, plus ou moins invasif. Un objectif majeur de cette recherche est d’utiliser au mieux l’information obtenue sous forme d’images 3D ainsi que l’historique du patient pour éviter de soumettre le patient à des examens inutiles, invasifs ou dangereux, tout en garantissant le meilleur résultat clinique. Les méthodologies proposées reposeront sur des techniques d’analyse et traitement d’image, de vision par ordinateur et d’imagerie médicale qui seront développée en partenariat entre GE Healthcare et le laboratoire Centre de Vision Numérique (CVN) de CentraleSupélec
This research project is expected to be financed by a CIFRE scholarship in collaboration between GE Healthcare and CentraleSupelec. We are seeking to predict Major Adverse Cardiovascular Events (MACE). These are typically embolism and aneurisms in the aorta and the coronary arteries, that give rise respectively to interrupted blood flow to the heart and so a risk of infarctus, or major hemorrhage. Both are life-threatening. When a patient is brought to hospital for an alert (angina, etc), they will undergo an X-ray CAT scan, which can be more or less invasive. A major objective of this research is to utilize as well as possible the available information in the form of 3D images together with patient history and other data, in order to avoid needless, invasive, irradiating or dangerous exams, while simultaneously guaranteeing optimal care and the best possible clinical outcome. The proposed methodologies include image analysis, image processing, computer vision and medical imaging procedures and methods, that will be developed in partnership between GE Healthcare and the CVN lab of CENTRALE SUPELEC

APA, Harvard, Vancouver, ISO, and other styles

44

Bergelin, Victor. "Human Activity Recognition and Behavioral Prediction using Wearable Sensors and Deep Learning." Thesis, Linköpings universitet, Matematiska institutionen, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-138064.

Full text

Abstract:

When moving into a more connected world together with machines, a mutual understanding will be very important. With the increased availability in wear- able sensors, a better understanding of human needs is suggested. The Dart- mouth Research study at the Psychiatric Research Center has examined the viability of detecting and further on predicting human behaviour and complex tasks. The field of smoking detection was challenged by using the Q-sensor by Affectiva as a prototype. Further more, this study implemented a framework for future research on the basis for developing a low cost, connected, device with Thayer Engineering School at Dartmouth College. With 3 days of data from 10 subjects smoking sessions was detected with just under 90% accuracy using the Conditional Random Field algorithm. However, predicting smoking with Electrodermal Momentary Assessment (EMA) remains an unanswered ques- tion. Hopefully a tool has been provided as a platform for better understanding of habits and behaviour.

APA, Harvard, Vancouver, ISO, and other styles

45

DallaPiazza, Kristin Lee. "A Global Approach to Disease Prevention: Predicting High Risk Areas for West Nile Infection in the Us." Thesis, Virginia Tech, 2009. http://hdl.handle.net/10919/33083.

Full text

Abstract:

WN virus has spread for over 60 years creating endemic and epidemic areas throughout Africa, Asia, and Europe, affecting human, bird, and equine populations. Its 1999 appearance in New York shows the ability of the virus to cross barriers and travel great distances, emerging into new territories previously free of infection. Spreading much faster than expected, WN virus has infected thousands of birds, equine, and humans throughout the conterminous United States (US). Case and serological studies performed in the Eastern hemisphere prior to 1999 offer detailed descriptions of endemic and epidemic locations in regards to geography, land cover, land use, population, climate, and weather patterns. Based on the severity of WN activity within each study area, the patterns associated with these environmental factors allow for the identification of values associated with different levels of risk. We can then model the landscape of the disease within the US and identify areas of high risk for infection. State and county public health officials can use this model as a decision-making tool to allocate funding for disease prevention and control. Dynamic factors associated with increased transmission, such as above average temperature and precipitation, can be closely monitored and measures of prevention can be implemented when necessary. In turn, detailed information from higher resolution analyses can be documented to an online GIS (Geographic Information System) that would contribute to a global collaboration on outbreaks and prevention of disease.
Master of Science

APA, Harvard, Vancouver, ISO, and other styles

46

Lines, Lisa M. "Outpatient Emergency Department Utilization: Measurement and Prediction: A Dissertation." eScholarship@UMMS, 2014. https://escholarship.umassmed.edu/gsbs_diss/710.

Full text

Abstract:

Approximately half of all emergency department (ED) visits are primary-care sensitive (PCS) – meaning that they could potentially be avoided with timely, effective primary care. Reducing undesirable types of healthcare utilization (including PCS ED use) requires the ability to define, measure, and predict such use in a population. In this retrospective, observational study, we quantified ED use in 2 privately insured populations and developed ED risk prediction models. One dataset, obtained from a Massachusetts managed-care network (MCN), included data from 2009-11. The second was the MarketScan database, with data from 2007-08. The MCN study included 64,623 individuals enrolled for at least 1 base-year month and 1 prediction-year month in Massachusetts whose primary care provider (PCP) participated in the MCN. The MarketScan study included 15,136,261 individuals enrolled for at least 1 base-year month and 1 prediction-year month in the 50 US states plus DC, Puerto Rico, and the US Virgin Islands. We used medical claims to identify principal diagnosis codes for ED visits, and scored each according to the New York University Emergency Department algorithm. We defined primary-care sensitive (PCS) ED visits as those in 3 subcategories: nonemergent, emergent but primary-care treatable, and emergent but preventable/avoidable. We then: 1) defined and described the distributions of 3 ED outcomes: any ED use; number of ED visits; and a new outcome, based on the NYU algorithm, that we call PCS ED use; 2) built and validated predictive models for these outcomes using administrative claims data; 3) compared the performance of models predicting any ED use, number of ED visits, and PCS ED use; 4) enhanced these models by adding enrollee characteristics from electronic medical records, neighborhood characteristics, and payor/provider characteristics, and explored differences in performance between the original and enhanced models. In the MarketScan sample, 10.6% of enrollees had at least 1 ED visit, with about half of utilization scored as PCS. For the top risk group (those in the 99.5th percentile), the model’s sensitivity was 3.1%, specificity was 99.7%, and positive predictive value (PPV) was 49.7%. The model predicting PCS visits yielded sensitivity of 3.8%, specificity of 99.7%, and PPV of 40.5% for the top risk group. In the MCN sample, 14.6% (±0.1%) had at least 1 ED visit during the prediction period, with an overall rate of 18.8 (±0.2) visits per 100 persons and 7.6 (±0.1) PCS ED visits per 100 persons. Measuring PCS ED use with a threshold-based approach resulted in many fewer visits counted as PCS, discarding information unnecessarily. Out of 45 practices, 5 to 11 (11-24%) had observed values that were statistically significantly different from their expected values. Models predicting ED utilization using age, sex, race, morbidity, and prior use only (claims-based models) had lower R2 (ranging from 2.9% to 3.7%) and poorer predictive ability than the enhanced models that also included payor, PCP type and quality, problem list conditions, and covariates from the EMR, Census tract, and MCN provider data (enhanced model R2 ranged from 4.17% to 5.14%). In adjusted analyses, age, claims-based morbidity score, any ED visit in the base year, asthma, congestive heart failure, depression, tobacco use, and neighborhood poverty were strongly associated with increased risk for all 3 measures (all P<.001).

APA, Harvard, Vancouver, ISO, and other styles

47

Lines, Lisa M. "Outpatient Emergency Department Utilization: Measurement and Prediction: A Dissertation." eScholarship@UMMS, 2004. http://escholarship.umassmed.edu/gsbs_diss/710.

Full text

Abstract:

Approximately half of all emergency department (ED) visits are primary-care sensitive (PCS) – meaning that they could potentially be avoided with timely, effective primary care. Reducing undesirable types of healthcare utilization (including PCS ED use) requires the ability to define, measure, and predict such use in a population. In this retrospective, observational study, we quantified ED use in 2 privately insured populations and developed ED risk prediction models. One dataset, obtained from a Massachusetts managed-care network (MCN), included data from 2009-11. The second was the MarketScan database, with data from 2007-08. The MCN study included 64,623 individuals enrolled for at least 1 base-year month and 1 prediction-year month in Massachusetts whose primary care provider (PCP) participated in the MCN. The MarketScan study included 15,136,261 individuals enrolled for at least 1 base-year month and 1 prediction-year month in the 50 US states plus DC, Puerto Rico, and the US Virgin Islands. We used medical claims to identify principal diagnosis codes for ED visits, and scored each according to the New York University Emergency Department algorithm. We defined primary-care sensitive (PCS) ED visits as those in 3 subcategories: nonemergent, emergent but primary-care treatable, and emergent but preventable/avoidable. We then: 1) defined and described the distributions of 3 ED outcomes: any ED use; number of ED visits; and a new outcome, based on the NYU algorithm, that we call PCS ED use; 2) built and validated predictive models for these outcomes using administrative claims data; 3) compared the performance of models predicting any ED use, number of ED visits, and PCS ED use; 4) enhanced these models by adding enrollee characteristics from electronic medical records, neighborhood characteristics, and payor/provider characteristics, and explored differences in performance between the original and enhanced models. In the MarketScan sample, 10.6% of enrollees had at least 1 ED visit, with about half of utilization scored as PCS. For the top risk group (those in the 99.5th percentile), the model’s sensitivity was 3.1%, specificity was 99.7%, and positive predictive value (PPV) was 49.7%. The model predicting PCS visits yielded sensitivity of 3.8%, specificity of 99.7%, and PPV of 40.5% for the top risk group. In the MCN sample, 14.6% (±0.1%) had at least 1 ED visit during the prediction period, with an overall rate of 18.8 (±0.2) visits per 100 persons and 7.6 (±0.1) PCS ED visits per 100 persons. Measuring PCS ED use with a threshold-based approach resulted in many fewer visits counted as PCS, discarding information unnecessarily. Out of 45 practices, 5 to 11 (11-24%) had observed values that were statistically significantly different from their expected values. Models predicting ED utilization using age, sex, race, morbidity, and prior use only (claims-based models) had lower R2 (ranging from 2.9% to 3.7%) and poorer predictive ability than the enhanced models that also included payor, PCP type and quality, problem list conditions, and covariates from the EMR, Census tract, and MCN provider data (enhanced model R2 ranged from 4.17% to 5.14%). In adjusted analyses, age, claims-based morbidity score, any ED visit in the base year, asthma, congestive heart failure, depression, tobacco use, and neighborhood poverty were strongly associated with increased risk for all 3 measures (all P<.001).

APA, Harvard, Vancouver, ISO, and other styles

48

Kondepudi, Karthik Chalam. "Computational prediction of enhanced solubility of poorly aqueous soluble drugs prepared by hot melt method." Scholarly Commons, 2015. https://scholarlycommons.pacific.edu/uop_etds/267.

Full text

Abstract:

Solubility is the concentration of a solute in a saturated solution at a given temperature and pressure. Solubility of a drug in aqueous media is a pre-requisite to achieve desired concentration of a drug in the systemic circulation. Low aqueous solubility is a major problem encountered with formulation development of recently designed new chemical entities. Solubility of poorly soluble drugs is enhanced by physical and chemical modifications of drug. Shake flask method is the most commonly used experimental method to determine solubility. However, this method has several limitations. A single solubility experiment can go on for several days and even weeks. Besides this, a large amount of drug is required to carry out the experiment. In order to overcome this and make initial screening easier, computational method can be used to predict solubility. In this study, the solubility of 12 small molecules of BCS class II having a wide range of physicochemical properties were studied to enhance their solubility by hot melt method. Three different grades of PEG (1450, 4000, 8000), PVP K17 and Urea as the hydrophilic carriers was employed for the solubility enhancement. The overall objective of this investigation is to develop a model that could estimate enhanced solubility using physicochemical descriptors. Multiple linear regression (MLR), a statistical tool, was used to generate a equation for the solubility by correlating physicochemical properties of the drug like- molecular size, logP, pKa, HBA, HBD, melting point, polar surface area, and number of rotatable bonds. Solubility enhancement is also influenced by the carrier used, we included the physicochemical properties of the carriers like molecular weight and solubility parameter in the development of the model. MLR analysis model, resulted in an equation, where, Log solubility = 5.982-0.010 MW (drug)-0.452 LogP-0.320 HBA-0.095 ?solubility parameter+0.015 MV. A regression analysis yielded a good fit with a regression value (adjusted R2) of 0.74. The model has been validated by leave one out method. This model has the potential to estimate the solubility of a physically modified drug in screening stages of drug development.

APA, Harvard, Vancouver, ISO, and other styles

49

Lloyd, Joshua S. "Commercialization of Software for the Prediction of Structural and Optical Consequences Resulting from Corneal Corrective Treatments." Case Western Reserve University School of Graduate Studies / OhioLINK, 2016. http://rave.ohiolink.edu/etdc/view?acc_num=case1447778132.

Full text

APA, Harvard, Vancouver, ISO, and other styles

50

Mitchell, Barbara E. "Physical health of maltreated children shortly after entry into foster care : assessment and prediction of documented medical problems and caregiver reported health status /." Diss., Connect to a 24 p. preview or request complete full text in PDF format. Access restricted to UC campuses, 2002. http://wwwlib.umi.com/cr/ucsd/fullcit?p3044789.

Full text

APA, Harvard, Vancouver, ISO, and other styles

Dissertations / Theses on the topic 'Medical Prediction'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles