{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T15:21:03Z","timestamp":1779376863041,"version":"3.53.1"},"reference-count":59,"publisher":"BMJ","issue":"8","license":[{"start":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T00:00:00Z","timestamp":1692662400000},"content-version":"unspecified","delay-in-days":21,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2023,7,26]]},"published-print":{"date-parts":[[2023,8]]},"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To construct a machine-learning (ML) model for health systems with organised falls prevention programmes to identify older adults at risk for fall-related admissions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design<\/jats:title>\n                    <jats:p>This prognostic study used population-level administrative health data to develop an ML prediction model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Setting<\/jats:title>\n                    <jats:p>This study took place in Alberta, Canada during 2018\u20132019.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Participants<\/jats:title>\n                    <jats:p>Albertans aged 65 and older with at least one prior admission. Those with palliative conditions or emigrated out of Alberta were excluded.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Exposure<\/jats:title>\n                    <jats:p>Unit of analysis was the individual person.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Main outcomes\/measures<\/jats:title>\n                    <jats:p>We identified fall-related admissions. A CatBoost model was developed on 2018 data to predict risk of fall-related emergency department visits or hospitalisations. Temporal validation was done using 2019 data to evaluate model performance. We reported discrimination, calibration and other relevant metrics measured at the end of 2019 on both ranked predictions and predicted probability thresholds. A cost-savings simulation was performed using 2019 data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Final number of study participants was 224\u2009445. The validation set had 203\u2009584 participants with 19\u2009389 fall-related events (9.5% pretest probability) and an ML model c-statistic of 0.70. The highest ranked predictions had post-test probabilities ranging from 40% to 50%. Net benefit analysis presented mixed results with some net benefit using the ML model in the 6%\u201330%\u2009range. The top 50 percentile of predicted risks represented nearly $C60\u2009million in health system costs related to falls. Intervening on the top 25 or 50 percentiles of predicted risk could realise substantial (up to $C16\u2009million) savings.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>ML prediction models based on population-level administrative data can assist health systems with fall prevention programmes identify older adults at risk of fall-related admissions and reduce costs. ML predictions based on ranked predictions or probability thresholds could guide subsequent interventions to mitigate fall risks. Increased access to diverse forms of data could improve ML performance and further reduce costs.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjopen-2022-071321","type":"journal-article","created":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T12:30:45Z","timestamp":1692707445000},"page":"e071321","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":8,"title":["Predicting falls-related admissions in older adults in Alberta, Canada: a machine-learning falls prevention tool developed using population administrative health data"],"prefix":"10.1136","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7907-1183","authenticated-orcid":false,"given":"Vishal","family":"Sharma","sequence":"first","affiliation":[{"name":"School of Public Health, University of Alberta, Edmonton, Alberta, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vinaykumar","family":"Kulkarni","sequence":"additional","affiliation":[{"name":"University of Alberta, Edmonton, Alberta, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tanya","family":"Joon","sequence":"additional","affiliation":[{"name":"OKAKI, Calgary, Alberta, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2197-0463","authenticated-orcid":false,"given":"Dean T","family":"Eurich","sequence":"additional","affiliation":[{"name":"School of Public Health, University of Alberta, Edmonton, Alberta, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9880-2129","authenticated-orcid":false,"given":"Scot H","family":"Simpson","sequence":"additional","affiliation":[{"name":"Faculty of Pharmacy and Pharmaceutical Sciences, University of Alberta, Edmonton, Alberta, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Don","family":"Voaklander","sequence":"additional","affiliation":[{"name":"School of Public Health, University of Alberta, Edmonton, Alberta, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bruce","family":"Wright","sequence":"additional","affiliation":[{"name":"Island Medical Program, University of Victoria, Victoria, British Columbia, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Salim","family":"Samanani","sequence":"additional","affiliation":[{"name":"OKAKI, Calgary, Alberta, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2023,8,22]]},"reference":[{"key":"2025121411481206000_13.8.e071321.1","first-page":"771","article-title":"Falls in the elderly","volume":"57","author":"Al-Aama","year":"2011","journal-title":"Spectrum Prevention"},{"key":"2025121411481206000_13.8.e071321.2","unstructured":"British Columbia Ministry of Health . Bcguidelines.ca: falls: prevention, risk assessment and management for community dwelling older adults. Guidelines & Protocols Advisory Committee 2021."},{"key":"2025121411481206000_13.8.e071321.3","first-page":"419","article-title":"Epidemiology, clinical significance, costs and fall prevention in elderly people","volume":"10","author":"Czerwi\u0144ski","year":"2008","journal-title":"Ortop Traumatol Rehabil"},{"key":"2025121411481206000_13.8.e071321.4","doi-asserted-by":"crossref","first-page":"e189","DOI":"10.17269\/cjph.106.4776","article-title":"Engaging community organizations in falls prevention for older adults: moving from research to action","volume":"106","author":"Markle-Reid","year":"2015","journal-title":"Can J Public Health"},{"key":"2025121411481206000_13.8.e071321.5","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2019.16489"},{"key":"2025121411481206000_13.8.e071321.6","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2020-037860","article-title":"Predicting population health with machine learning: a Scoping review","volume":"10","author":"Morgenstern","year":"2020","journal-title":"BMJ Open"},{"key":"2025121411481206000_13.8.e071321.7","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2019.0348","article-title":"Assessment of machine learning vs standard prediction rules for predicting hospital Readmissions","volume":"2","author":"Morgan","year":"2019","journal-title":"JAMA Netw Open"},{"key":"2025121411481206000_13.8.e071321.8","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijmedinf.2020.104105","article-title":"Identification of elders at higher risk for fall with statewide electronic health records and a machine learning algorithm","volume":"137","author":"Ye","year":"2020","journal-title":"Int J Med Inform"},{"key":"2025121411481206000_13.8.e071321.9","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.12126"},{"key":"2025121411481206000_13.8.e071321.10","doi-asserted-by":"publisher","DOI":"10.1001\/jama.1994.03510330081039"},{"key":"2025121411481206000_13.8.e071321.11","doi-asserted-by":"crossref","DOI":"10.2196\/jmir.5870","article-title":"Guidelines for developing and reporting machine learning predictive models in BIOMEDICAL research: A Multidisciplinary view","volume":"18","author":"Luo","year":"2016","journal-title":"J Med Internet Res"},{"key":"2025121411481206000_13.8.e071321.12","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2015.37"},{"key":"2025121411481206000_13.8.e071321.13","doi-asserted-by":"crossref","DOI":"10.1136\/bmj.i6","article-title":"Net benefit approaches to the evaluation of prediction models, molecular markers, and diagnostic tests","volume":"352","author":"Vickers","year":"2016","journal-title":"BMJ"},{"key":"2025121411481206000_13.8.e071321.14","unstructured":"World Health Organization . International language for drug utilization research, ATC\/DDD. 2020. Available: https:\/\/www.whocc.no"},{"key":"2025121411481206000_13.8.e071321.15","unstructured":"Alberta College of Pharmacy . Alberta, Canada 2019. n.d. Available: https:\/\/abpharmacy.ca"},{"key":"2025121411481206000_13.8.e071321.16","unstructured":"World health Organization . Classification of diseases (ICD) 2019. n.d. Available: https:\/\/www.who.int\/classifications\/icd\/icdonlineversions\/en"},{"key":"2025121411481206000_13.8.e071321.17","unstructured":"Canadian Institute for health information. 2019. Available: https:\/\/www.cihi.ca\/en"},{"key":"2025121411481206000_13.8.e071321.18","doi-asserted-by":"publisher","DOI":"10.1007\/s40520-014-0308-x."},{"key":"2025121411481206000_13.8.e071321.19","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1007\/s00198-021-06080-5","article-title":"Hip fracture predicts subsequent hip fracture: a retrospective observational study to support a call to early hip fracture prevention efforts in post-fracture patients","volume":"33","author":"Schemitsch","year":"2022","journal-title":"Osteoporos Int"},{"key":"2025121411481206000_13.8.e071321.20","unstructured":"Brownlee J . A gentle introduction to imbalanced classification. 2020. Available: https:\/\/machinelearningmastery.com\/what-is-imbalanced-classification"},{"key":"2025121411481206000_13.8.e071321.21","doi-asserted-by":"publisher","DOI":"10.1093\/oxfordjournals.pan.a004868"},{"key":"2025121411481206000_13.8.e071321.22","unstructured":"Government of Canada . Forward Sortation area\u2014definition 2015. n.d. Available: https:\/\/www.ic.gc.ca\/eic\/site\/bsf-osb.nsf\/eng\/br03396.html"},{"key":"2025121411481206000_13.8.e071321.23","doi-asserted-by":"publisher","DOI":"10.1097\/01.mlr.0000182534.19832.83"},{"key":"2025121411481206000_13.8.e071321.24","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1017\/S0714980817000393","article-title":"Rules to identify persons with frailty in administrative health databases","volume":"36","author":"Urquhart","year":"2017","journal-title":"Can J Aging"},{"key":"2025121411481206000_13.8.e071321.25","doi-asserted-by":"crossref","unstructured":"Chen T , Guestrin C , eds. Xgboost: A Scalable tree boosting system. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining; 2016 doi:10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"key":"2025121411481206000_13.8.e071321.26","unstructured":"GitHub . Catboost 2022. n.d. Available: https:\/\/catboost.ai"},{"key":"2025121411481206000_13.8.e071321.27","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2010.04.018"},{"key":"2025121411481206000_13.8.e071321.28","unstructured":"Ali M . Pycaret: an open source, low-code machine learning library in python version 2.3 April 2020. n.d. Available: https:\/\/pycaret.org\/about"},{"key":"2025121411481206000_13.8.e071321.29","doi-asserted-by":"crossref","first-page":"1311","DOI":"10.1002\/pds.5501","article-title":"Artificial intelligence in Pharmacovigilance: do we need Explainability","volume":"31","author":"Hauben","year":"2022","journal-title":"Pharmacoepidemiol Drug Saf"},{"key":"2025121411481206000_13.8.e071321.30","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2006.01.014"},{"key":"2025121411481206000_13.8.e071321.31","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehw302"},{"key":"2025121411481206000_13.8.e071321.32","doi-asserted-by":"publisher","DOI":"10.1037\/1082-989X.7.2.147"},{"key":"2025121411481206000_13.8.e071321.33","doi-asserted-by":"crossref","DOI":"10.2196\/11605","article-title":"A new insight into missing data in intensive care unit patient profiles: observational study","volume":"7","author":"Sharafoddini","year":"2019","journal-title":"JMIR Med Inform"},{"key":"2025121411481206000_13.8.e071321.34","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2020.03.028"},{"key":"2025121411481206000_13.8.e071321.35","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2017.03.009"},{"key":"2025121411481206000_13.8.e071321.36","unstructured":"van M , Groenwold RHH , Moons KGM . n.d. A cautionary note on the use of the missing indicator method for handling missing data in prediction research. J Clin Epidemiol"},{"key":"2025121411481206000_13.8.e071321.37","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1001\/jamacardio.2016.3956","article-title":"Prediction of 30-day all-cause Readmissions in patients hospitalized for heart failure: comparison of machine learning and other statistical approaches","volume":"2","author":"Frizzell","year":"2017","journal-title":"JAMA Cardiol"},{"key":"2025121411481206000_13.8.e071321.38","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1002\/ehf2.13073","article-title":"Machine learning vs. conventional statistical models for predicting heart failure readmission and mortality","volume":"8","author":"Shin","year":"2021","journal-title":"ESC Heart Fail"},{"key":"2025121411481206000_13.8.e071321.39","doi-asserted-by":"crossref","DOI":"10.2196\/14756","article-title":"Readmission risk Trajectories for patients with heart failure using a dynamic prediction approach: retrospective study","volume":"7","author":"Jiang","year":"2019","journal-title":"JMIR Med Inform"},{"key":"2025121411481206000_13.8.e071321.40","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehu207"},{"key":"2025121411481206000_13.8.e071321.41","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2019-034568","article-title":"Reporting quality of studies using machine learning models for medical diagnosis: a systematic review","volume":"10","author":"Yusuf","year":"2020","journal-title":"BMJ Open"},{"key":"2025121411481206000_13.8.e071321.42","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0118432","article-title":"The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced Datasets","volume":"10","author":"Saito","year":"2015","journal-title":"PLOS ONE"},{"key":"2025121411481206000_13.8.e071321.43","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2021.11315","article-title":"Development and validation of a machine learning model using administrative health data to predict onset of type 2 diabetes","volume":"4","author":"Ravaut","year":"2021","journal-title":"JAMA Netw Open"},{"key":"2025121411481206000_13.8.e071321.44","doi-asserted-by":"publisher","DOI":"10.1001\/jama.1994.03510290071040"},{"key":"2025121411481206000_13.8.e071321.45","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2018.17163"},{"key":"2025121411481206000_13.8.e071321.46","unstructured":"Molnar C . Interpretable machine learning. In: A guide for making black box models explainable. 2019."},{"key":"2025121411481206000_13.8.e071321.47","unstructured":"Lundberg SM , Lee S-I . A unified approach to interpreting model predictions. In: Advances in neural information processing systems. 2017."},{"key":"2025121411481206000_13.8.e071321.48","article-title":"Physicians in health care management: 3. case mix groups and resource intensity weights: an overview for physicians","volume":"150","author":"Pink","year":"1994","journal-title":"CMAJ: Canadian Medical Association Journal"},{"key":"2025121411481206000_13.8.e071321.49","article-title":"Physicians in health care management: 4. case mix groups and resource intensity weights: physicians and hospital funding","volume":"150","author":"Pink","year":"1994","journal-title":"CMAJ: Canadian Medical Association Journal"},{"key":"2025121411481206000_13.8.e071321.50","unstructured":"Canadian Institute for Health Information . Your Health System. Ottawa, ON: CIHI, 2022. Available: https:\/\/yourhealthsystem.cihi.ca\/hsp\/indepth?lang=en#\/indicator\/015\/2\/C20018"},{"key":"2025121411481206000_13.8.e071321.51","unstructured":"Canadian Institute for Health Information . Patient cost estimator: methodology notes and glossary. Ottawa, ON: CIHI, Available: https:\/\/www.cihi.ca\/sites\/default\/files\/document\/patient-cost-estimator-methodology-notes-2021-en.pdf"},{"key":"2025121411481206000_13.8.e071321.52","first-page":"1","article-title":"Canadian case mixed groups (CMG+) costing proxy for acute myocardial infarction","volume":"2","author":"Chu","year":"2016","journal-title":"Journal of Health & Medical Economics"},{"key":"2025121411481206000_13.8.e071321.53","doi-asserted-by":"crossref","DOI":"10.1016\/j.jval.2014.08.1394","article-title":"Comparing actual patient level hospital costs to the Canadian Cmg+ costing estimates for acute myocardial infarction","volume":"17","author":"Chu","year":"2014","journal-title":"Value Health"},{"key":"2025121411481206000_13.8.e071321.54","unstructured":"Glussich A . Estimating costs of hospital stays. 2016 CADTH Symposium; Ottawa, ON, Canada: Canadian Institute for Health Information, 2016"},{"key":"2025121411481206000_13.8.e071321.55","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2019.103256","article-title":"Readmission prediction using deep learning on electronic health records","volume":"97","author":"Ashfaq","year":"2019","journal-title":"J Biomed Inform"},{"key":"2025121411481206000_13.8.e071321.56","doi-asserted-by":"publisher","DOI":"10.7326\/L15-5093"},{"key":"2025121411481206000_13.8.e071321.57","unstructured":"Buitinck L , Louppe G , Blondel M , et al . API design for machine learning software: experiences from the Scikit-learn project. arXiv 2013:13090238."},{"key":"2025121411481206000_13.8.e071321.58","unstructured":"The Pandas Development Team . Pandas-Dev\/Pandas: Pandas: Zenodo. 2020. 10.5281\/zenodo.3509134"},{"key":"2025121411481206000_13.8.e071321.59","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCOUTCOMES.112.967356"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2022-071321","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T19:48:24Z","timestamp":1765741704000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2022-071321"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":59,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2023,8,22]]},"published-print":{"date-parts":[[2023,8]]}},"alternative-id":["10.1136\/bmjopen-2022-071321"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2022-071321","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8]]}}}