Predictive Risk Modelling of Hospital Emergency Readmission, and Temporal Comorbidity Index Modelling Using Machine Learning Methods

Mesgarpour, M. 2017. Predictive Risk Modelling of Hospital Emergency Readmission, and Temporal Comorbidity Index Modelling Using Machine Learning Methods. PhD thesis University of Westminster Computer Science https://doi.org/10.34737/q3031

TitlePredictive Risk Modelling of Hospital Emergency Readmission, and Temporal Comorbidity Index Modelling Using Machine Learning Methods
TypePhD thesis
AuthorsMesgarpour, M.
Abstract

This thesis considers applications of machine learning techniques in hospital emergency readmission and comorbidity risk problems, using healthcare administrative data. The aim is to introduce generic and robust solution approaches that can be applied to different healthcare settings. Existing solution methods and techniques of predictive risk modelling of hospital emergency readmission and comorbidity risk modelling are
reviewed. Several modelling approaches, including Logistic Regression, Bayes Point Machine, Random Forest and Deep Neural Network are considered.

Firstly, a framework is proposed for pre-processing hospital administrative data, including data preparation, feature generation and feature selection. Then, the Ensemble Risk Modelling of Hospital Readmission (ERMER) is presented, which is a generative ensemble risk model of hospital readmission model. After that, the Temporal-Comorbidity Adjusted Risk of Emergency Readmission (T-CARER) is presented for identifying very sick comorbid patients. A Random Forest and a Deep Neural Network are used to model risks of temporal comorbidity, operations and complications of
patients using the T-CARER.

The computational results and benchmarking are presented using real data from Hospital Episode Statistics (HES) with several samples across a ten-year period. The models select features from a large pool of generated features, add temporal dimensions into the models and provide highly accurate and precise models of problems with complex structures. The performances of all the models have been evaluated across different timeframes, sub-populations and samples, as well as previous models.

Year2017
File
PublisherUniversity of Westminster
Digital Object Identifier (DOI)https://doi.org/10.34737/q3031

Related outputs

Emergency Readmission for Integrated Care (ERIC) Model: Using an Automated Feature Generation & a Multi-Task Learner
Chaussalet, T.J., Mesgarpour, M., Worrall, P. and Chahed, S. 2017. Emergency Readmission for Integrated Care (ERIC) Model: Using an Automated Feature Generation & a Multi-Task Learner. Operational Research Applied to Health Services 2017. Bath, UK 24 - 28 Jul 2017

Risk Modelling Framework for Emergency Hospital Readmission, Using Hospital Episode Statistics Inpatient Data
Mesgarpour, M., Chaussalet, T.J. and Chahed, S. 2016. Risk Modelling Framework for Emergency Hospital Readmission, Using Hospital Episode Statistics Inpatient Data. IEEE 29th International Symposium on Computer-Based Medical Systems. Dublin and Belfast 20 - 23 Jun 2016 IEEE . https://doi.org/10.1109/CBMS.2016.21

Predictive Risk Modelling for Integrated Care: a Structured Review
Mesgarpour, M., Chaussalet, T.J., Worrall, P. and Chahed, S. 2016. Predictive Risk Modelling for Integrated Care: a Structured Review. IEEE 29th International Symposium on Computer-Based Medical Systems. Dublin and Belfast 20 - 23 Jun 2016 IEEE . https://doi.org/10.1109/CBMS.2016.34

A review of dynamic Bayesian network techniques with applications in healthcare risk modelling
Mesgarpour, M., Chaussalet, T.J. and Chahed, S. 2014. A review of dynamic Bayesian network techniques with applications in healthcare risk modelling. 4th Student Conference on Operational Research (SCOR14). Nottingham, UK May 2–4, 2014 Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik. https://doi.org/10.4230/OASIcs.SCOR.2014.89

Permalink - https://westminsterresearch.westminster.ac.uk/item/q3031/predictive-risk-modelling-of-hospital-emergency-readmission-and-temporal-comorbidity-index-modelling-using-machine-learning-methods


Share this

Usage statistics

280 total views
1149 total downloads
These values cover views and downloads from WestminsterResearch and are for the period from September 2nd 2018, when this repository was created.