Abstract Background Integrated Care Systems in the NHS are implementing population health management approaches to target population segments for primary or secondary prevention. Population segments tend to be identified in one of two ways. The first uses a priori categories, such as patients with learning disabilities or children and young people, often chosen on the basis of costs to the health and care system. The second uses risk prediction tools which identify individuals at risk of untoward events – usually unplanned hospital admissions -- and then stratifies groups based on the level of risk. Both of these approaches result in heterogeneous population segments with limited information on either risk or the group characteristics. Machine learning (ML) techniques using electronic health care records have the potential to address these limitations and provide actionable insights for population health management.Practical applications: Unsupervised ML techniques such as k-means and hierarchical clustering identify groups with common patterns of characteristics which can then be related to outcomes. Using clustering methods, Pikoula Quint Nissen et al (2019) identified 5 subtypes of COPD patients with distinct characteristics for whom targeted interventions might improve outcomes. Classification and regression trees (CART) and random forest are supervised ML methods which predict risks of specified outcomes for groups with shared characteristics, providing human interpretable decision rules to inform policy making. Using CART, we will identify segments at increased risk of unplanned admissions for community acquired pneumonia using a cohort of 4.7 million patients for whom targeted interventions could be implemented. External funding details JG is part-funded by Health Education England / National Institute of Health Research (ICA CL-2016-02-024). MP is supported by a British Lung Foundation award (JRFG18–1). SD is supported by an Alan Turing Fellowship. The BigData@Heart Consortium is funded by the Innovative Medicines Initiative-2 Joint Undertaking under grant agreement No. 116074. This Joint Undertaking receives support from the European Union's Horizon 2020 research and innovation programme and EFPIA; it is chaired, by DE Grobbee and SD Anker, partnering with 20 academic and industry partners and ESC. This work was partly supported by Health Data Research UK, which receives its funding from HDR UK Ltd (LOND1) funded by the UK Medical Research Council, Engineering and Physical Sciences Research Council, Economic and Social Research Council, Department of Health and Social Care (England), Chief Scientist Office of the Scottish Government Health and Social Care Directorates, Health and Social Care Research and Development Division (Welsh Government), Public Health Agency (Northern Ireland), British Heart Foundation (BHF) and the Wellcome Trust. This work was partly supported by National Institute for Health Research (RP-PG-0407-10314), Wellcome Trust (086091/Z/08/Z). This work was partly supported by the Farr Institute of Health Informatics Research at UCL Partners, from the Medical Research Council, Arthritis Research UK, British Heart Foundation, Cancer Research UK, Chief Scientist Office, Economic and Social Research Council, Engineering and Physical Sciences Research Council, National Institute for Health Research, National Institute for Social Care and Health Research, and Wellcome Trust (MR/K006584/1). This work represents independent research part funded by the National Institute for Health Research (NIHR) Biomedical Research Centre at University College London Hospitals.
Abstract Background Integrated Care Systems in the NHS are implementing population health management approaches to target population segments for primary or secondary prevention. Population segments tend to be identified in one of two ways. The first uses a priori categories, such as patients with learning disabilities or children and young people, often chosen on the basis of costs to the health and care system. The second uses risk prediction tools which identify individuals at risk of untoward events – usually unplanned hospital admissions -- and then stratifies groups based on the level of risk. Both of these approaches result in heterogeneous population segments with limited information on either risk or the group characteristics. Machine learning (ML) techniques using electronic health care records have the potential to address these limitations and provide actionable insights for population health management.Practical applications: Unsupervised ML techniques such as k-means and hierarchical clustering identify groups with common patterns of characteristics which can then be related to outcomes. Using clustering methods, Pikoula Quint Nissen et al (2019) identified 5 subtypes of COPD patients with distinct characteristics for whom targeted interventions might improve outcomes. Classification and regression trees (CART) and random forest are supervised ML methods which predict risks of specified outcomes for groups with shared characteristics, providing human interpretable decision rules to inform policy making. Using CART, we will identify segments at increased risk of unplanned admissions for community acquired pneumonia using a cohort of 4.7 million patients for whom targeted interventions could be implemented. External funding details JG is part-funded by Health Education England / National Institute of Health Research (ICA CL-2016-02-024). MP is supported by a British Lung Foundation award (JRFG18–1). SD is supported by an Alan Turing Fellowship. The BigData@Heart Consortium is funded by the Innovative Medicines Initiative-2 Joint Undertaking under grant agreement No. 116074. This Joint Undertaking receives support from the European Union's Horizon 2020 research and innovation programme and EFPIA; it is chaired, by DE Grobbee and SD Anker, partnering with 20 academic and industry partners and ESC. This work was partly supported by Health Data Research UK, which receives its funding from HDR UK Ltd (LOND1) funded by the UK Medical Research Council, Engineering and Physical Sciences Research Council, Economic and Social Research Council, Department of Health and Social Care (England), Chief Scientist Office of the Scottish Government Health and Social Care Directorates, Health and Social Care Research and Development Division (Welsh Government), Public Health Agency (Northern Ireland), British Heart Foundation (BHF) and the Wellcome Trust. This work was partly supported by National Institute for Health Research (RP-PG-0407-10314), Wellcome Trust (086091/Z/08/Z). This work was partly supported by the Farr Institute of Health Informatics Research at UCL Partners, from the Medical Research Council, Arthritis Research UK, British Heart Foundation, Cancer Research UK, Chief Scientist Office, Economic and Social Research Council, Engineering and Physical Sciences Research Council, National Institute for Health Research, National Institute for Social Care and Health Research, and Wellcome Trust (MR/K006584/1). This work represents independent research part funded by the National Institute for Health Research (NIHR) Biomedical Research Centre at University College London Hospitals.
By clicking “Accept Terms & all Cookies” or by continuing to browse, you agree to the storing of third-party cookies on your device to enhance your user experience and agree to the user terms and conditions of this learning management system (LMS). USER TERMS AND CONDITIONS | PRIVACY POLICY
Cookie Settings
Accept Terms & all Cookies
Anonymous User Privacy Preferences
Strictly Necessary Cookies (Always Active)
MULTILEARNING platforms and tools hereinafter referred as “MLG SOFTWARE” are provided to you as pure educational platforms/services requiring cookies to operate. In the case of the MLG SOFTWARE, cookies are essential for the Platform to function properly for the provision of education. If these cookies are disabled, a large subset of the functionality provided by the Platform will either be unavailable or cease to work as expected. The MLG SOFTWARE do not capture non-essential activities such as menu items and listings you click on or pages viewed.
Performance Cookies
Performance cookies are used to analyse how visitors use a website in order to provide a better user experience.