Accepted for/Published in: JMIR Research Protocols
Date Submitted: Dec 15, 2021
Open Peer Review Period: Dec 15, 2021 - Feb 9, 2022
Date Accepted: Mar 7, 2022
(closed for review but you can still tweet)
Life.course digital T.wins – I.ntelligent M.onitoring for E.arly and continuous intervention and prevention (LifeTIME): Proposal for a proof-of-concept study
ABSTRACT
Background:
Multimorbidity, which is associated with significant negative outcomes for individuals and healthcare systems, is increasing in the UK. However, there is a lack of knowledge about the risk factors (including health, behaviour, and environment) for multimorbidity over time. An interdisciplinary approach is essential, as data science, artificial intelligence, and concepts from engineering (digital twins), have the potential to enable personalised simulation of life-course risk for the development of multimorbidity by identifying key risk factors throughout the life course. Predicting the risk of developing clusters of health conditions before they occur would add clinical value by enabling targeted early preventive interventions, advancing personalised care to improve outcomes, and reducing the burden on the UK’s healthcare systems.
Objective:
This study aims to identify key risk factors that predict multimorbidity throughout the lifetime through the development of an intelligent agent using digital twins so that early interventions can be delivered to improve health outcomes. The objectives of this study are to identify key predictors of lifetime risk of multimorbidity, create a series of simulated computational digital twins that predict levels of risk for specific clusters of factors, and test the feasibility of the system.
Methods:
This study will use machine learning to identify key risk factors throughout life that predict the risk of later multimorbidity to develop digital twins. The first stage of the development will be the training of a base predictive model. Data from the National Child Development Study (NCDS), the North West London Integrated Care Record (NWL ICR), the Clinical Practice Research Datalink (CPRD), and Cerner's Real World Data will be split into subsets for training and validation, which will be done following the k-fold cross-validation procedure and assessed with the PROBAST risk of bias tool. Two additional datasets - from the early-LIfe data cross-LInkage in Research (eLIXIR) study and the Children and Young People’s Health Partnership (CYPHP) randomised controlled trial - will be used in addition to the model to develop a series of digital twin personas that simulate clusters of factors that predict different levels of risk of developing multimorbidity.
Results:
The expected results are a validated model, a series of digital twin personas, and an assessment of proof-of-concept.
Conclusions:
Digital twins could provide an individualised early warning system that predicts the risk of future health conditions and recommends the intervention that is most likely to be effective at minimising that risk. These insights could have a significant positive impact on an individual’s quality of life and healthy life expectancy and reduce population-level health burdens.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.