Using electronic health records to develop and validate a machine learning tool to predict type 2 diabetes outcomes: a study protocol
File(s)
Published version
Author(s)
Type
Journal Article
Abstract
Introduction: Type 2 diabetes (T2DM) is a major cause of blindness, kidney failure, myocardial infarction, stroke and lower limb amputation. We are still unable, however, to accurately predict or identify which patients are at a higher risk of deterioration. Most risk stratification tools do not account for novel factors such as socio-demographic determinants, self-management ability, or access to healthcare. Additionally, most tools are based in clinical trials, with limited external generalisability.
Objective: The aim of this work is to design and validate a machine learning-based tool to identify patients with T2DM at high risk of clinical deterioration, based on a comprehensive set of patient level characteristics retrieved from a population health linked dataset.
Sample and design: Retrospective cohort study of patients with diagnosis of T2DM on Jan 1st, 2015, with a 5-year follow-up. Anonymised electronic health care records from the Whole System Integrated Care (WSIC) database will be used.
Preliminary outcomes: Outcome variables of clinical deterioration will include retinopathy, chronic renal disease, myocardial infarction, stroke, peripheral arterial disease, or death. Predictor variables will include sociodemographic and geographic data, patients’ ability to self-manage disease, clinical and metabolic parameters and healthcare service usage. Prognostic models will be defined using multi-dependence Bayesian networks (BN). The derivation cohort, comprising 80% of the patients, will be used to define the prognostic models. Model parameters will be internally validated by comparing the area under the receiver operating characteristic (ROC) curve (AUC) in the derivation cohort with those calculated from a leave-one-out and a 10 times 2-fold cross-validation.
Ethics and dissemination: The study has received approvals from the Information Governance Committee at the Whole Systems Integrated Care. Results will be made available to people with type 2 diabetes, their caregivers, the funders, diabetes care societies and other researchers.
Objective: The aim of this work is to design and validate a machine learning-based tool to identify patients with T2DM at high risk of clinical deterioration, based on a comprehensive set of patient level characteristics retrieved from a population health linked dataset.
Sample and design: Retrospective cohort study of patients with diagnosis of T2DM on Jan 1st, 2015, with a 5-year follow-up. Anonymised electronic health care records from the Whole System Integrated Care (WSIC) database will be used.
Preliminary outcomes: Outcome variables of clinical deterioration will include retinopathy, chronic renal disease, myocardial infarction, stroke, peripheral arterial disease, or death. Predictor variables will include sociodemographic and geographic data, patients’ ability to self-manage disease, clinical and metabolic parameters and healthcare service usage. Prognostic models will be defined using multi-dependence Bayesian networks (BN). The derivation cohort, comprising 80% of the patients, will be used to define the prognostic models. Model parameters will be internally validated by comparing the area under the receiver operating characteristic (ROC) curve (AUC) in the derivation cohort with those calculated from a leave-one-out and a 10 times 2-fold cross-validation.
Ethics and dissemination: The study has received approvals from the Information Governance Committee at the Whole Systems Integrated Care. Results will be made available to people with type 2 diabetes, their caregivers, the funders, diabetes care societies and other researchers.
Date Issued
2021-07-30
Date Acceptance
2021-07-06
Citation
BMJ Open, 2021, 11 (7), pp.1-5
ISSN
2044-6055
Publisher
BMJ Journals
Start Page
1
End Page
5
Journal / Book Title
BMJ Open
Volume
11
Issue
7
Copyright Statement
© Author(s) (or their employer(s)) 2021. Re-use permitted under CC BY. Published by BMJ. https://creativecommons.org/licenses/by/4.0/
This is an open access article distributed in accordance with the Creative Commons Attribution 4.0 Unported (CC BY 4.0) license, which permits others to copy, redistribute, remix, transform and build upon this work for any purpose, provided the original work is properly cited, a link to the licence is given, and indication of whether changes were made. See: https://creativecommons.org/licenses/by/4.0/.
This is an open access article distributed in accordance with the Creative Commons Attribution 4.0 Unported (CC BY 4.0) license, which permits others to copy, redistribute, remix, transform and build upon this work for any purpose, provided the original work is properly cited, a link to the licence is given, and indication of whether changes were made. See: https://creativecommons.org/licenses/by/4.0/.
License URL
Sponsor
Imperial College Healthcare NHS Trust- BRC Funding
National Institute for Health Research
Imperial College Healthcare NHS Trust
Imperial College Healthcare NHS Trust- BRC Funding
Imperial College Healthcare NHS Trust- BRC Funding
NHS North West London CCG
Identifier
https://bmjopen.bmj.com/content/11/7/e046716
Grant Number
RDB04
n/a
FR775
RDF01
RDF01
XXKSARAVANAKUMAR
Subjects
diabetes & endocrinology
health & safety
health informatics
Bayes Theorem
Diabetes Mellitus, Type 2
Electronic Health Records
Humans
Machine Learning
Retrospective Studies
Humans
Diabetes Mellitus, Type 2
Bayes Theorem
Retrospective Studies
Electronic Health Records
Machine Learning
1103 Clinical Sciences
1117 Public Health and Health Services
1199 Other Medical and Health Sciences
Publication Status
Published
Date Publish Online
2021-07-30