{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T08:16:23Z","timestamp":1765872983008,"version":"3.48.0"},"reference-count":34,"publisher":"BMJ","issue":"7","license":[{"start":{"date-parts":[[2021,7,29]],"date-time":"2021-07-29T00:00:00Z","timestamp":1627516800000},"content-version":"unspecified","delay-in-days":28,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000272","name":"National Institute for Health Research","doi-asserted-by":"crossref","award":["Imperial Biomedical Research Centre"],"award-info":[{"award-number":["Imperial Biomedical Research Centre"]}],"id":[{"id":"10.13039\/501100000272","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000272","name":"National Institute for Health Research","doi-asserted-by":"crossref","award":["Imperial NIHR Patient Safety Translational Research"],"award-info":[{"award-number":["Imperial NIHR Patient Safety Translational Research"]}],"id":[{"id":"10.13039\/501100000272","id-type":"DOI","asserted-by":"crossref"}]},{"name":"FCT\/PARSUK","award":["Bilateral Research Fund 2020"],"award-info":[{"award-number":["Bilateral Research Fund 2020"]}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2021,7,5]]},"published-print":{"date-parts":[[2021,7]]},"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Type 2 diabetes mellitus (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 sociodemographic determinants, self-management ability or access to healthcare. Additionally, most tools are based in clinical trials, with limited external generalisability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Sample and design<\/jats:title>\n                    <jats:p>Retrospective cohort study of patients with diagnosis of T2DM on 1 January 2015, with a 5-year follow-up. Anonymised electronic healthcare records from the Whole System Integrated Care (WSIC) database will be used.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Preliminary outcomes<\/jats:title>\n                    <jats:p>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\u2019 ability to self-manage disease, clinical and metabolic parameters and healthcare service usage. Prognostic models will be defined using multidependence Bayesian networks. 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 curve in the derivation cohort with those calculated from a leave-one-out and a 10 times twofold cross-validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Ethics and dissemination<\/jats:title>\n                    <jats:p>The study has received approvals from the Information Governance Committee at the WSIC. Results will be made available to people with T2DM, their caregivers, the funders, diabetes care societies and other researchers.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjopen-2020-046716","type":"journal-article","created":{"date-parts":[[2021,7,30]],"date-time":"2021-07-30T10:39:25Z","timestamp":1627641565000},"page":"e046716","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":9,"title":["Using electronic health records to develop and validate a machine-learning tool to predict type 2 diabetes outcomes: a study protocol"],"prefix":"10.1136","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7107-7211","authenticated-orcid":false,"given":"Ana Luisa","family":"Neves","sequence":"first","affiliation":[{"name":"NIHR Imperial Patient Safety Translational Research Centre, Imperial College London, London, UK"},{"name":"Center for Health Technology and Services Research, Faculty of Medicine, University of Porto, Porto, Portugal"}]},{"given":"Pedro","family":"Pereira Rodrigues","sequence":"additional","affiliation":[{"name":"Center for Health Technology and Services Research, Faculty of Medicine, University of Porto, Porto, Portugal"}]},{"given":"Abdulrahim","family":"Mulla","sequence":"additional","affiliation":[{"name":"Imperial College Healthcare NHS Trust, London, UK"}]},{"given":"Ben","family":"Glampson","sequence":"additional","affiliation":[{"name":"Imperial College Healthcare NHS Trust, London, UK"}]},{"given":"Tony","family":"Willis","sequence":"additional","affiliation":[{"name":"North West London Diabetes Transformation Programme, North West London Health and Care Partnership, London, UK"}]},{"given":"Ara","family":"Darzi","sequence":"additional","affiliation":[{"name":"NIHR Imperial Patient Safety Translational Research Centre, Imperial College London, London, UK"}]},{"given":"Erik","family":"Mayer","sequence":"additional","affiliation":[{"name":"NIHR Imperial Patient Safety Translational Research Centre, Imperial College London, London, UK"}]}],"member":"239","published-online":{"date-parts":[[2021,7,30]]},"reference":[{"key":"2025121600133130000_11.7.e046716.1","doi-asserted-by":"publisher","DOI":"10.2337\/diacare.27.5.1047"},{"key":"2025121600133130000_11.7.e046716.2","doi-asserted-by":"publisher","DOI":"10.2337\/diab.23.2.105"},{"key":"2025121600133130000_11.7.e046716.3","doi-asserted-by":"publisher","DOI":"10.1007\/BF00274216"},{"key":"2025121600133130000_11.7.e046716.4","doi-asserted-by":"publisher","DOI":"10.1111\/j.1464-5491.2012.03698.x"},{"key":"2025121600133130000_11.7.e046716.5","doi-asserted-by":"publisher","DOI":"10.1186\/s12913-016-1365-y"},{"key":"2025121600133130000_11.7.e046716.6","doi-asserted-by":"publisher","DOI":"10.1016\/j.amepre.2014.07.009"},{"key":"2025121600133130000_11.7.e046716.7","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2013.393"},{"key":"2025121600133130000_11.7.e046716.8","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2011.1562"},{"key":"2025121600133130000_11.7.e046716.9","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.m958"},{"key":"2025121600133130000_11.7.e046716.10","doi-asserted-by":"crossref","first-page":"296","DOI":"10.4239\/wjd.v5.i3.296","article-title":"Social determinants of type 2 diabetes and health in the United States","volume":"5","author":"Clark","year":"2014","journal-title":"World J Diabetes"},{"key":"2025121600133130000_11.7.e046716.11","doi-asserted-by":"publisher","DOI":"10.1177\/0145721709335004"},{"key":"2025121600133130000_11.7.e046716.12","doi-asserted-by":"publisher","DOI":"10.1097\/JAC.0b013e3181ba6e77"},{"key":"2025121600133130000_11.7.e046716.13","doi-asserted-by":"publisher","DOI":"10.1186\/1741-7015-9-103"},{"key":"2025121600133130000_11.7.e046716.14","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMsa0900592"},{"key":"2025121600133130000_11.7.e046716.15","doi-asserted-by":"crossref","DOI":"10.21037\/jmai-20-4","article-title":"Impact of machine learning and feature selection on type 2 diabetes risk prediction","volume":"3","author":"Riihimaa","year":"2020","journal-title":"J Med Artif Intell"},{"key":"2025121600133130000_11.7.e046716.16","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1016\/j.jval.2019.01.006","article-title":"Bayesian networks for risk prediction using real-world data: a tool for precision medicine","volume":"22","author":"Arora","year":"2019","journal-title":"Value Health"},{"key":"2025121600133130000_11.7.e046716.17","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-019-09857-1"},{"key":"2025121600133130000_11.7.e046716.18","unstructured":"Pearl J . Probabilistic reasoning in intelligent systems. In: Networks of plausible inference. San Francisco, CA, USA: Morgan Kaufmann Publishers Inc, 1988."},{"key":"2025121600133130000_11.7.e046716.19","first-page":"150","article-title":"Networking analysis on superior vena cava arrhythmogenicity in atrial fibrillation","volume":"22","author":"Ebana","year":"2019","journal-title":"Int J Cardiol Heart Vasc"},{"key":"2025121600133130000_11.7.e046716.20","doi-asserted-by":"crossref","first-page":"274","DOI":"10.3844\/jcssp.2015.274.282","article-title":"Diagnosis of cardiovascular diseases with Bayesian classifiers","volume":"11","author":"Elsayad","year":"2015","journal-title":"J Comp Sci"},{"key":"2025121600133130000_11.7.e046716.21","first-page":"1539","article-title":"An efficient coronary heart disease prediction by semi parametric extended dynamic Bayesian network with optimized cut points","volume":"13","author":"Gomathi","year":"2018","journal-title":"ARPN J Eng Appl Sci"},{"key":"2025121600133130000_11.7.e046716.22","first-page":"21","article-title":"Diabetes prediction: a deep learning approach","volume":"2","author":"Ayon","year":"2019","journal-title":"Int J Inform Engr Electr Business"},{"key":"2025121600133130000_11.7.e046716.23","doi-asserted-by":"crossref","DOI":"10.3390\/machines7040074","article-title":"Comparative machine-learning approach: a follow-up study on type 2 diabetes predictions by cross-validation methods","volume":"7","author":"Battineni","year":"2019","journal-title":"Machines"},{"key":"2025121600133130000_11.7.e046716.24","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2007.06.004"},{"key":"2025121600133130000_11.7.e046716.25","unstructured":"North West London Collaboration of Clinical Commissioning Groups . Whole systems integrated care (WSIC) dashboards and information sharing [online], 2020. Available: https:\/\/www.healthiernorthwestlondon.nhs.uk\/news-resources\/information-sharing [Accessed 15 Sep 2020]."},{"key":"2025121600133130000_11.7.e046716.26","unstructured":"Ministry of Housing, Communities and Local Government . The English indices of deprivation 2019 (IoD 2019) [online], 2020. Available: https:\/\/assets.publishing.service.gov.uk\/government\/uploads\/system\/uploads\/attachment_data\/file\/835115\/IoD2019_Statistical_Release.pdf [Accessed 15 Sep 2020]."},{"key":"2025121600133130000_11.7.e046716.27","unstructured":"Office for National Statistics . ONS postcode directory [online], 2020. Available: http:\/\/geoportal.statistics.gov.uk\/datasets\/ons-postcode-directory-may-2020 [Accessed 15 Sep 2020]."},{"key":"2025121600133130000_11.7.e046716.28","doi-asserted-by":"publisher","DOI":"10.1111\/j.1475-6773.2004.00269.x"},{"key":"2025121600133130000_11.7.e046716.29","doi-asserted-by":"crossref","DOI":"10.1186\/s12963-016-0115-z","article-title":"A quantitative evidence base for population health: applying utilization-based cluster analysis to segment a patient population","volume":"14","author":"Vuik","year":"2016","journal-title":"Popul Health Metr"},{"key":"2025121600133130000_11.7.e046716.30","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2015-008149"},{"key":"2025121600133130000_11.7.e046716.31","unstructured":"Health Survey for England . 2012 adult trend tables 2012 [online], 2020. Available: http:\/\/www.hscic.gov.uk\/pubs\/hse10trends [Accessed 15 Sep 2020]."},{"key":"2025121600133130000_11.7.e046716.32","doi-asserted-by":"crossref","unstructured":"Kj\u00e6rulff UB , Madsen A , Networks B . Influence diagrams: a guide to construction and analysis. 2nd edn. New York, NY: Springer-Verlag, 2013.","DOI":"10.1007\/978-1-4614-5104-4"},{"key":"2025121600133130000_11.7.e046716.33","unstructured":"Koller D , Friedman N , Bach F . Probabilistic graphical models: principles and techniques - adaptive computation and machine learning. Cambridge, MA: The MIT Press, 2009."},{"key":"2025121600133130000_11.7.e046716.34","doi-asserted-by":"publisher","DOI":"10.3399\/bjgp17X693077"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2020-046716","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T08:13:45Z","timestamp":1765872825000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2020-046716"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7]]},"references-count":34,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2021,7,30]]},"published-print":{"date-parts":[[2021,7]]}},"alternative-id":["10.1136\/bmjopen-2020-046716"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2020-046716","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"type":"print","value":"2044-6055"},{"type":"electronic","value":"2044-6055"}],"subject":[],"published":{"date-parts":[[2021,7]]}}}