{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T16:53:12Z","timestamp":1782492792195,"version":"3.54.5"},"reference-count":44,"publisher":"BMJ","issue":"3","license":[{"start":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T00:00:00Z","timestamp":1773360000000},"content-version":"unspecified","delay-in-days":12,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004726","name":"British Columbia Ministry of Health","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004726","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2026,2,18]]},"published-print":{"date-parts":[[2026,3]]},"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To estimate the prevalence of potential overtreatment of type 2 diabetes mellitus (T2DM) among older adults and to develop and compare predictive models to identify patient and physician characteristics associated with overtreatment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design<\/jats:title>\n                    <jats:p>Population-based retrospective cohort study with predictive modelling.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Setting<\/jats:title>\n                    <jats:p>A province-wide, publicly funded healthcare system in British Columbia, Canada, using linked administrative health claims data from 2016 to 2023.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Participants<\/jats:title>\n                    <jats:p>Residents of long-term care facilities over age 65, and community-dwelling individuals over age 75, with a diagnosis of T2DM and a glycated haemoglobin (A1C) laboratory value \u22647.0%. Participants were required to have \u2265365 days of continuous provincial health insurance coverage prior to their index A1C test. Patients receiving palliative care and those with missing physician information were excluded.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Primary and secondary outcome measures<\/jats:title>\n                    <jats:p>Potential overtreatment of T2DM, defined a priori as overlapping prescriptions for \u22652 glucose-lowering medications or \u22651 insulin or sulfonylurea dispensing within 90 days after the index A1C test.<\/jats:p>\n                    <jats:p>Model performance outcomes included discrimination (area under the curve (AUC), sensitivity, specificity, positive predictive value and negative predictive value). Performance metrics were calculated with 95% CIs using a 25% temporally distinct test dataset (2021\u20132023). No changes were made to outcome definitions after protocol development.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among 133\u2009773\u2009patients with an A1C\u22647.0%, 38\u2009074 (28.5%) were classified as overtreated. These patients had a mean age of 79.6 years, were 47% female, and had a median A1C of 6.4%. The gradient boost model was the best performing model overall, using a combination of expert-selected variables and data-driven variables, achieving an AUC of 0.87, sensitivity of 0.81 and negative predictive value of 0.89. The top predictors of overtreatment included use of blood glucose test strips, A1C test volume, polypharmacy, specialist involvement and measures of diabetes severity.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Overtreatment of T2DM was prevalent among older adults in our cohort. Machine learning algorithms that integrate clinical expertise with data-driven variable selection performed the best in predicting T2DM overtreatment. We identified several patient and physician characteristics as key contributors that may inform future clinical practice and quality improvement initiatives, although external validation is required before clinical implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjopen-2025-106707","type":"journal-article","created":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T12:55:15Z","timestamp":1773406515000},"page":"e106707","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["Estimating prevalence and predictors of glucose-lowering overtreatment among older adults with type 2 diabetes in long-term care and community settings: a machine learning\u2013based cohort study"],"prefix":"10.1136","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7438-5172","authenticated-orcid":false,"given":"Greg","family":"Carney","sequence":"first","affiliation":[{"name":"The University of British Columbia, Vancouver, British Columbia, Canada"},{"name":"Department of Anesthesiology, Pharmacology and Therapeutics, The University of British Columbia, Vancouver, British Columbia, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sean","family":"Burnett","sequence":"additional","affiliation":[{"name":"The University of British Columbia, Vancouver, British Columbia, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anshula","family":"Ambasta","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, Pharmacology and Therapeutics, The University of British Columbia, Vancouver, British Columbia, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wade","family":"Thompson","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, Pharmacology and Therapeutics, The University of British Columbia, Vancouver, British Columbia, Canada"},{"name":"Research Unit of General Practice, University of Southern Denmark, Odense, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linda","family":"Lapp","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, Pharmacology and Therapeutics, The University of British Columbia, Vancouver, British Columbia, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Colin","family":"Dormuth","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, Pharmacology and Therapeutics, The University of British Columbia, Vancouver, British Columbia, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,3,13]]},"reference":[{"key":"2026062609362908000_16.3.e106707.1","unstructured":"Hallman S , LeVasseu S , Berard-Chagnon J , et al . A portrait of Canada\u2019s growing population aged 85 and older from the 2021 census. Statistics Canada. Available: https:\/\/www12.statcan.gc.ca\/census-recensement\/2021\/as-sa\/98-200-X\/2021004\/98-200-X2021004-eng.cfm [Accessed 11 Oct 2022]."},{"key":"2026062609362908000_16.3.e106707.2","doi-asserted-by":"publisher","DOI":"10.2337\/dc12-1801"},{"key":"2026062609362908000_16.3.e106707.3","doi-asserted-by":"crossref","DOI":"10.1136\/bmj.l5887","article-title":"Benefits and harms of intensive glycemic control in patients with type 2 diabetes","volume":"PMID","author":"Rodriguez-Gutierrez","year":"2019","journal-title":"BMJ"},{"key":"2026062609362908000_16.3.e106707.4","doi-asserted-by":"publisher","DOI":"10.14336\/AD.2014.0330"},{"key":"2026062609362908000_16.3.e106707.5","doi-asserted-by":"publisher","DOI":"10.2337\/dc13-0610"},{"key":"2026062609362908000_16.3.e106707.6","first-page":"1116","article-title":"National trends in US hospital admissions for hyperglycemia and hypoglycemia among Medicare beneficiaries","volume":"174","author":"Lipska","year":"1999","journal-title":"Med"},{"key":"2026062609362908000_16.3.e106707.7","doi-asserted-by":"crossref","first-page":"969","DOI":"10.1001\/jamainternmed.2016.2275","article-title":"Intensive Treatment and Severe Hypoglycemia Among Adults With Type 2 Diabetes","volume":"176","author":"McCoy","year":"2016","journal-title":"JAMA Intern Med"},{"key":"2026062609362908000_16.3.e106707.8","doi-asserted-by":"publisher","DOI":"10.2337\/dc20-0876"},{"key":"2026062609362908000_16.3.e106707.9","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.0299"},{"key":"2026062609362908000_16.3.e106707.10","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1001\/jamainternmed.2014.7345","article-title":"Potential overtreatment of diabetes mellitus in older adults with tight glycemic control","volume":"175","author":"Lipska","year":"2015","journal-title":"JAMA Intern Med"},{"key":"2026062609362908000_16.3.e106707.11","first-page":"832","article-title":"Deprescribing antihyperglycemic agents in older persons: Evidence-based clinical practice guideline","volume":"63","author":"Farrell","year":"2017","journal-title":"Can Fam Physician"},{"key":"2026062609362908000_16.3.e106707.12","doi-asserted-by":"crossref","first-page":"892","DOI":"10.1111\/dom.12683","article-title":"Treatment intensification for patients with type 2 diabetes and poor glycaemic control","volume":"18","author":"Fu","year":"2016","journal-title":"Diabetes Obes Metab"},{"key":"2026062609362908000_16.3.e106707.13","doi-asserted-by":"crossref","first-page":"1775","DOI":"10.2147\/PPA.S208947","article-title":"De-Intensification Of Blood Glucose Lowering Medication In People Identified As Being Over-Treated: A Mixed Methods Study","volume":"13","author":"Hart","year":"2019","journal-title":"Patient Prefer Adherence"},{"key":"2026062609362908000_16.3.e106707.14","doi-asserted-by":"crossref","first-page":"344","DOI":"10.2337\/ds21-0068","article-title":"Using an Electronic Health Record and Deficit Accumulation to Pragmatically Identify Candidates for Optimal Prescribing in Patients With Type 2 Diabetes","volume":"35","author":"Callahan","year":"2022","journal-title":"Diabetes Spectr"},{"key":"2026062609362908000_16.3.e106707.15","doi-asserted-by":"crossref","DOI":"10.1136\/bmjdrc-2022-002995","article-title":"Treatment pattern trends of medications for type 2 diabetes in British Columbia, Canada","volume":"10","author":"Carney","year":"2022","journal-title":"BMJ Open Diabetes Res Care"},{"key":"2026062609362908000_16.3.e106707.16","doi-asserted-by":"crossref","DOI":"10.3390\/biomedicines10092267","article-title":"Predicting Outcome in Patients with Brain Injury: Differences between Machine Learning versus Conventional Statistics","volume":"10","author":"Cerasa","year":"2022","journal-title":"Biomedicines"},{"key":"2026062609362908000_16.3.e106707.17","doi-asserted-by":"crossref","DOI":"10.3390\/biomedicines10092188","article-title":"An Artificial Intelligence Approach to Guiding the Management of Heart Failure Patients Using Predictive Models: A Systematic Review","volume":"10","author":"B\u0142aziak","year":"2022","journal-title":"Biomedicines"},{"key":"2026062609362908000_16.3.e106707.18","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.18391"},{"key":"2026062609362908000_16.3.e106707.19","doi-asserted-by":"crossref","unstructured":"Memarzadeh K. A . The rise of artificial intelligence in healthcare applications. Artificial Intelligence in Healthcare 2020;25\u201360. doi:10.1016\/B978-0-12-818438-7.00002-2","DOI":"10.1016\/B978-0-12-818438-7.00002-2"},{"key":"2026062609362908000_16.3.e106707.20","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(19)30149-4"},{"key":"2026062609362908000_16.3.e106707.21","doi-asserted-by":"publisher","DOI":"10.1007\/s10067-020-05196-z"},{"key":"2026062609362908000_16.3.e106707.22","first-page":"295","article-title":"The Use of Artificial Intelligence in Pharmacovigilance: A Systematic Review of the Literature","volume":"36","author":"Salas","year":"2022","journal-title":"Pharmaceut Med"},{"key":"2026062609362908000_16.3.e106707.23","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/j.zefq.2016.07.010","article-title":"Das RECORD-Statement zum Berichten von Beobachtungsstudien, die routinem\u00e4\u00dfig gesammelte Gesundheitsdaten verwenden","volume":"115\u2013116","author":"Benchimol","year":"2016","journal-title":"Zeitschrift F\u00fcr Evidenz, Fortbildung Und Qualit\u00e4t Im Gesundheitswesen"},{"key":"2026062609362908000_16.3.e106707.24","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"PMCID","author":"Dhiman","year":"2024","journal-title":"BMJ"},{"key":"2026062609362908000_16.3.e106707.25","doi-asserted-by":"publisher","DOI":"10.1093\/ejcts\/ezy180"},{"key":"2026062609362908000_16.3.e106707.26","doi-asserted-by":"crossref","DOI":"10.3390\/biomedicines11020581","article-title":"Enhanced Preprocessing Approach Using Ensemble Machine Learning Algorithms for Detecting Liver Disease","volume":"11","author":"Md","year":"2023","journal-title":"Biomedicines"},{"key":"2026062609362908000_16.3.e106707.27","doi-asserted-by":"crossref","DOI":"10.3389\/fphar.2020.01028","article-title":"Artificial Intelligence in Pharmacoepidemiology: A Systematic Review. Part 1-Overview of Knowledge Discovery Techniques in Artificial Intelligence","volume":"11","author":"Sessa","year":"2020","journal-title":"Front Pharmacol"},{"key":"2026062609362908000_16.3.e106707.28","doi-asserted-by":"crossref","DOI":"10.3389\/fphar.2020.568659","article-title":"Artificial Intelligence in Pharmacoepidemiology: A Systematic Review. Part 2-Comparison of the Performance of Artificial Intelligence and Traditional Pharmacoepidemiological Techniques","volume":"11","author":"Sessa","year":"2020","journal-title":"Front Pharmacol"},{"key":"2026062609362908000_16.3.e106707.29","doi-asserted-by":"publisher","DOI":"10.1177\/1932296814554260"},{"key":"2026062609362908000_16.3.e106707.30","doi-asserted-by":"publisher","DOI":"10.1002\/sim.6526"},{"key":"2026062609362908000_16.3.e106707.31","doi-asserted-by":"crossref","unstructured":"Kuhn M . Caret: classification and regression training (version 7.0-1) [r package]. Comprehensive R Archive Network; 2008. Available: https:\/\/cran.r-project.org\/web\/packages\/caret\/index.html","DOI":"10.32614\/CRAN.package.caret"},{"key":"2026062609362908000_16.3.e106707.32","unstructured":"Breiman L , Cutler A , Liaw A , et al . RandomForest: breiman and cutler\u2019s random forests for classification and regression (version 4.7-1.2) [r package]. Comprehensive R Archive Network; 2024. Available: https:\/\/cran.r-project.org\/web\/packages\/randomForest\/refman\/randomForest.html"},{"key":"2026062609362908000_16.3.e106707.33","unstructured":"Meyer D , Dimitriadou E , Hornik K , et al . E1071:misc functions of the department of statistics, probability theory group (formerly: e1071), TU Wien (version 1.7-16) [r package]. Comprehensive R Archive Network (CRAN); 2024. Available: https:\/\/cran.r-project.org\/web\/packages\/e1071\/refman\/e1071.html"},{"key":"2026062609362908000_16.3.e106707.34","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0084217","article-title":"100% Classification Accuracy Considered Harmful: The Normalized Information Transfer Factor Explains the Accuracy Paradox","volume":"9","author":"Valverde-Albacete","year":"2014","journal-title":"PLoS ONE"},{"key":"2026062609362908000_16.3.e106707.35","first-page":"230","article-title":"Topic Group \u2018Evaluating diagnostic tests and prediction models\u2019 of the STRATOS initiative. Calibration: the Achilles heel of predictive analytics","volume":"PMCID","author":"Calster","year":"2019","journal-title":"BMC Med"},{"key":"2026062609362908000_16.3.e106707.36","first-page":"29138153","article-title":"Deprescribing antihyperglycemic agents in older persons: Evidence-based clinical practice guideline","volume":"63","author":"Black C,","year":"2017","journal-title":"Can Fam Physician"},{"key":"2026062609362908000_16.3.e106707.37","doi-asserted-by":"publisher","DOI":"10.4102\/phcfm.v16i1.4476"},{"key":"2026062609362908000_16.3.e106707.38","doi-asserted-by":"publisher","DOI":"10.7326\/0003-4819-151-12-200912150-00005"},{"key":"2026062609362908000_16.3.e106707.39","doi-asserted-by":"crossref","DOI":"10.1136\/bmj.h6138","article-title":"HbA1c overtesting and overtreatment among US adults with controlled type 2 diabetes, 2001-13: observational population based study","volume":"351","author":"McCoy","year":"2015","journal-title":"BMJ"},{"key":"2026062609362908000_16.3.e106707.40","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0078962","article-title":"The landscape of inappropriate laboratory testing: a 15-year meta-analysis","volume":"8","author":"Zhi","year":"2013","journal-title":"PLoS One"},{"key":"2026062609362908000_16.3.e106707.41","doi-asserted-by":"publisher","DOI":"10.1016\/j.jamda.2021.04.013"},{"key":"2026062609362908000_16.3.e106707.42","doi-asserted-by":"crossref","first-page":"2657","DOI":"10.1111\/jgs.18377","article-title":"Rates of overtreatment and deprescribing of antihyperglycemics among long-term care residents in British Columbia","volume":"71","author":"Pan","year":"2023","journal-title":"J Am Geriatr Soc"},{"key":"2026062609362908000_16.3.e106707.43","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1016\/j.jamda.2023.11.025","article-title":"Barriers and Enablers for Deprescribing Glucose-Lowering Treatment in Older Adults: A Systematic Review","volume":"25","author":"Mellot","year":"2024","journal-title":"J Am Med Dir Assoc"},{"key":"2026062609362908000_16.3.e106707.44","doi-asserted-by":"crossref","DOI":"10.3390\/jcm11175134","article-title":"Potential Risk of Overtreatment in Patients with Type 2 Diabetes Aged 75 Years or Older: Data from a Population Database in Catalonia, Spain","volume":"11","author":"Mata-Cases","year":"2022","journal-title":"J Clin Med"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2025-106707","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T16:41:21Z","timestamp":1782492081000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2025-106707"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":44,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3,13]]},"published-print":{"date-parts":[[2026,3]]}},"alternative-id":["10.1136\/bmjopen-2025-106707"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2025-106707","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}