{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T15:24:53Z","timestamp":1787498693079,"version":"build-2736575974"},"reference-count":38,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":28,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,11,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Bias evaluations of machine learning (ML) models often focus on performance in research settings, with limited assessment of downstream bias following clinical deployment. The objective of this study was to evaluate whether CHARTwatch, a real-time ML early warning system for inpatient deterioration, demonstrated algorithmic bias in model performance, or produced disparities in care processes, and outcomes across patient sociodemographic groups.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We evaluated CHARTwatch implementation on the internal medicine service at a large academic hospital. Patient outcomes during the intervention period (November 1, 2020\u2013June 1, 2022) were compared to the control period (November 1, 2016\u2013December 31, 2019) using propensity score overlap weighting. We evaluated differences across key sociodemographic subgroups, including age, sex, homelessness, and neighborhood-level socioeconomic and racialized composition. Outcomes included model performance (sensitivity and specificity), processes of care, and patient outcomes (non-palliative in-hospital death).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among 12\u2009877 patients (9079 control, 3798 intervention), 13.3% were experiencing homelessness and 36.9% lived in the quintile with the highest neighborhood racialized and newcomer populations. Model sensitivity was 70.1% overall, with no significant variation across subgroups. Model specificity varied by age, &amp;lt;60 years: 93% (95% Confidence Interval [CI] 91-95%), 60-80 years: 90% (95%CI 87-92%), and &amp;gt;80 years: 84% (95%CI 79-88%), P\u2009&amp;lt;\u2009.001, but not other subgroups. CHARTwatch implementation was associated with an increase in code status documentation among patients experiencing homelessness, without significant differences in other care processes or outcomes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>CHARTwatch model performance and impact were generally consistent across measured sociodemographic subgroups. ML-based clinical decision support tools, and associated standardization of care, may reduce existing inequities, as was observed for code status orders among patients experiencing homelessness. This evaluation provides a framework for future bias assessments of deployed ML-CDS tools.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jamiaopen\/ooaf158","type":"journal-article","created":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T12:59:00Z","timestamp":1762865940000},"source":"Crossref","is-referenced-by-count":3,"title":["Evaluating sociodemographic bias in a deployed machine-learned patient deterioration model"],"prefix":"10.1093","volume":"8","author":[{"given":"Michael","family":"Colacci","sequence":"first","affiliation":[{"name":"Li Ka Shing Knowledge Institute, St Michael\u2019s Hospital, Unity Health Toronto , Toronto, Ontario, M5B 1X3,","place":["Canada"]},{"name":"Department of Medicine, University of Toronto , Toronto, Ontario, M5S 1A8,","place":["Canada"]},{"name":"Institute of Health Policy, Management and Evaluation, Dalla Lana School of Public Health, University of Toronto , Toronto, Ontario, M5T 3M6,","place":["Canada"]},{"name":"St Michael\u2019s Hospital, Unity Health Toronto , Toronto, Ontario, M5B 1W8,","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chloe","family":"Pou-Prom","sequence":"additional","affiliation":[{"name":"Li Ka Shing Knowledge Institute, St Michael\u2019s Hospital, Unity Health Toronto , Toronto, Ontario, M5B 1X3,","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2458-9011","authenticated-orcid":false,"given":"Arjumand","family":"Siddiqi","sequence":"additional","affiliation":[{"name":"Institute of Health Policy, Management and Evaluation, Dalla Lana School of Public Health, University of Toronto , Toronto, Ontario, M5T 3M6,","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad","family":"Mamdani","sequence":"additional","affiliation":[{"name":"Li Ka Shing Knowledge Institute, St Michael\u2019s Hospital, Unity Health Toronto , Toronto, Ontario, M5B 1X3,","place":["Canada"]},{"name":"Institute of Health Policy, Management and Evaluation, Dalla Lana School of Public Health, University of Toronto , Toronto, Ontario, M5T 3M6,","place":["Canada"]},{"name":"St Michael\u2019s Hospital, Unity Health Toronto , Toronto, Ontario, M5B 1W8,","place":["Canada"]},{"name":"Department of Laboratory Medicine and Pathobiology, University of Toronto , Toronto, Ontario, M5S 3K3,","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6857-931X","authenticated-orcid":false,"given":"Amol A","family":"Verma","sequence":"additional","affiliation":[{"name":"Li Ka Shing Knowledge Institute, St Michael\u2019s Hospital, Unity Health Toronto , Toronto, Ontario, M5B 1X3,","place":["Canada"]},{"name":"Department of Medicine, University of Toronto , Toronto, Ontario, M5S 1A8,","place":["Canada"]},{"name":"Institute of Health Policy, Management and Evaluation, Dalla Lana School of Public Health, University of Toronto , Toronto, Ontario, M5T 3M6,","place":["Canada"]},{"name":"St Michael\u2019s Hospital, Unity Health Toronto , Toronto, Ontario, M5B 1W8,","place":["Canada"]},{"name":"Department of Laboratory Medicine and Pathobiology, University of Toronto , Toronto, Ontario, M5S 3K3,","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,12,1]]},"reference":[{"key":"2025120116480622300_ooaf158-B1","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1126\/science.aax2342","article-title":"Dissecting racial bias in an algorithm used to manage the health of populations","volume":"366","author":"Obermeyer","year":"2019","journal-title":"Science (1979)"},{"key":"2025120116480622300_ooaf158-B2","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1167\/tvst.10.2.13","article-title":"Addressing artificial intelligence bias in retinal diagnostics","volume":"10","author":"Burlina","year":"2021","journal-title":"Transl Vis Sci Technol"},{"key":"2025120116480622300_ooaf158-B3","doi-asserted-by":"publisher","first-page":"S1","DOI":"10.1016\/j.jval.2021.04.007","article-title":"AI2 the impact of including race and ethnicity in risk prediction models on racial bias","volume":"24","author":"Khor","year":"2021","journal-title":"Value in Health"},{"key":"2025120116480622300_ooaf158-B4","doi-asserted-by":"publisher","first-page":"1142","DOI":"10.1093\/jamia\/ocac052","article-title":"Assessing socioeconomic bias in machine learning algorithms in health care: a case study of the HOUSES index","volume":"29","author":"Juhn","year":"2022","journal-title":"J Am Med Inform Assoc"},{"key":"2025120116480622300_ooaf158-B5","doi-asserted-by":"publisher","DOI":"10.15779\/Z38BG31","article-title":"Big data\u2019s disparate impact","author":"Barocas","year":"2016","journal-title":"Calif Law Rev"},{"key":"2025120116480622300_ooaf158-B6","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1001\/jama.2022.23867","article-title":"Prevention of bias and discrimination in clinical practice algorithms","volume":"329","author":"Shachar","year":"2023","journal-title":"JAMA"},{"key":"2025120116480622300_ooaf158-B7","doi-asserted-by":"publisher","first-page":"2255","DOI":"10.1001\/jama.2023.22557","article-title":"Automation bias and assistive AI: risk of harm from AI-driven clinical decision support","volume":"330","author":"Khera","year":"2023","journal-title":"JAMA"},{"key":"2025120116480622300_ooaf158-B8","doi-asserted-by":"publisher","first-page":"2275","DOI":"10.1001\/jama.2023.22295","article-title":"Measuring the impact of AI in the diagnosis of hospitalized patients: a randomized clinical vignette survey study","volume":"330","author":"Jabbour","year":"2023","journal-title":"JAMA"},{"key":"2025120116480622300_ooaf158-B9","doi-asserted-by":"publisher","first-page":"2838","DOI":"10.1038\/s41591-024-03113-4","article-title":"The limits of fair medical imaging AI in real-world generalization","volume":"30","author":"Yang","year":"2024","journal-title":"Nat Med"},{"key":"2025120116480622300_ooaf158-B10","doi-asserted-by":"publisher","first-page":"705","DOI":"10.1097\/01.ccm.0000811944.77042.17","article-title":"1405: assessing clinical use and performance of a machine learning sepsis alert for sex and racial bias","volume":"50","author":"Adams","year":"2022","journal-title":"Crit Care Med"},{"key":"2025120116480622300_ooaf158-B11","doi-asserted-by":"publisher","first-page":"e36388","DOI":"10.2196\/36388","article-title":"Evaluation and mitigation of racial bias in clinical machine learning models: scoping review","volume":"10","author":"Huang","year":"2022","journal-title":"JMIR Med Inform"},{"key":"2025120116480622300_ooaf158-B12","doi-asserted-by":"publisher","first-page":"e078378","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ."},{"key":"2025120116480622300_ooaf158-B13","doi-asserted-by":"publisher","first-page":"2218","DOI":"10.1038\/s41591-022-01772-9","article-title":"Reporting guideline for the early-stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI","volume":"28","author":"Vasey","year":"2022","journal-title":"Nat Med"},{"key":"2025120116480622300_ooaf158-B14","doi-asserted-by":"publisher","first-page":"E1027","DOI":"10.1503\/cmaj.240132","article-title":"Clinical evaluation of a machine learning-based early warning system for patient deterioration","volume":"196","author":"Verma","year":"2024","journal-title":"CMAJ"},{"key":"2025120116480622300_ooaf158-B15","doi-asserted-by":"publisher","first-page":"e0897","DOI":"10.1097\/CCE.0000000000000897","article-title":"Developing and validating a prediction model for death or critical illness in hospitalized adults, an opportunity for human-computer collaboration","volume":"5","author":"Verma","year":"2023","journal-title":"Crit Care Explor"},{"key":"2025120116480622300_ooaf158-B16","doi-asserted-by":"publisher","first-page":"E1351","DOI":"10.1503\/cmaj.202434","article-title":"Implementing machine learning in medicine","volume":"193","author":"Verma","year":"2021","journal-title":"CMAJ"},{"key":"2025120116480622300_ooaf158-B17","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176347963","article-title":"Multivariate adaptive regression splines","volume":"19","author":"Friedman","year":"1991","journal-title":"Ann Stat"},{"key":"2025120116480622300_ooaf158-B18","article-title":"Ontario agency for health protection and promotion (public health Ontario)","author":"Matheson","year":"2016","journal-title":"Ontario Marginalization Index: User Guide."},{"key":"2025120116480622300_ooaf158-B19","doi-asserted-by":"publisher","first-page":"644","DOI":"10.1055\/s-0040-1715896","article-title":"Accuracy of the preferred language field in the electronic health records of two Canadian hospitals","volume":"11","author":"Rajaram","year":"2020","journal-title":"Appl Clin Inform"},{"key":"2025120116480622300_ooaf158-B20","volume-title":"How to Integrate Intersectionality Theory in Quantitative Health Equity Analysis? A Rapid Review and Checklist of Promising Practices","author":"Public Health Agency of Canada","year":"2022"},{"key":"2025120116480622300_ooaf158-B21","doi-asserted-by":"publisher","first-page":"e0247872","DOI":"10.1371\/journal.pone.0247872","article-title":"Cohort profile: St michael\u2019s hospital tuberculosis database (SMH-TB), a retrospective cohort of electronic health record data and variables extracted using natural language processing","volume":"16","author":"Landsman","year":"2021","journal-title":"PLoS One"},{"key":"2025120116480622300_ooaf158-B22","doi-asserted-by":"publisher","first-page":"e030221","DOI":"10.1136\/bmjopen-2019-030221","article-title":"Validation study of health administrative data algorithms to identify individuals experiencing homelessness and estimate population prevalence of homelessness in Ontario, Canada","volume":"9","author":"Richard","year":"2019","journal-title":"BMJ Open"},{"key":"2025120116480622300_ooaf158-B23","doi-asserted-by":"publisher","first-page":"260","DOI":"10.17269\/s41997-021-00552-1","article-title":"The 2011 and 2016 iterations of the Ontario marginalization index: updates, consistency and a cross-sectional study of health outcome associations","volume":"113","author":"van Ingen","year":"2022","journal-title":"Can J of Public Health"},{"key":"2025120116480622300_ooaf158-B24","doi-asserted-by":"publisher","DOI":"10.1136\/bmjhci-2020-100289","article-title":"Equity in essence: a call for operationalising fairness in machine learning for healthcare","author":"Wawira Gichoya","journal-title":"BMJ Health Care Inform"},{"key":"2025120116480622300_ooaf158-B25","doi-asserted-by":"publisher","first-page":"e2335377","DOI":"10.1001\/jamanetworkopen.2023.35377","article-title":"APPRAISE-AI tool for quantitative evaluation of AI studies for clinical decision support","volume":"6","author":"Kwong","year":"2023","journal-title":"JAMA Netw Open"},{"key":"2025120116480622300_ooaf158-B26","doi-asserted-by":"publisher","first-page":"1552","DOI":"10.1136\/bmj.308.6943.1552","article-title":"Statistics notes: diagnostic tests 1: sensitivity and specificity","volume":"308","author":"Altman","year":"1994","journal-title":"BMJ"},{"key":"2025120116480622300_ooaf158-B27","doi-asserted-by":"publisher","DOI":"10.1101\/2024.02.05.24301960","article-title":"Causes, diagnostic testing, and treatments related to clinical deterioration events among High-Risk ward patients","author":"Churpek","year":"2024","journal-title":"medRxiv"},{"key":"2025120116480622300_ooaf158-B28","doi-asserted-by":"publisher","first-page":"2170","DOI":"10.1002\/sim.2677","article-title":"Confidence intervals for predictive values with an emphasis to case-control studies","volume":"26","author":"Mercaldo","year":"2007","journal-title":"Stat Med"},{"key":"2025120116480622300_ooaf158-B29","doi-asserted-by":"publisher","first-page":"390","DOI":"10.1080\/01621459.2016.1260466","article-title":"Balancing covariates via propensity score weighting","volume":"113","author":"Li","year":"2018","journal-title":"J Am Stat Assoc"},{"key":"2025120116480622300_ooaf158-B30","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1093\/aje\/kwy201","article-title":"Addressing extreme propensity scores via the overlap weights","volume":"188","author":"Li","year":"2019","journal-title":"Am J Epidemiol"},{"key":"2025120116480622300_ooaf158-B31","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","article-title":"Controlling the false discovery rate: a practical and powerful approach to multiple testing","volume":"57","author":"Benjamini","year":"1995","journal-title":"J R Stat Soc Series B Stat Methodol"},{"key":"2025120116480622300_ooaf158-B32","doi-asserted-by":"publisher","first-page":"4189","DOI":"10.1007\/s11606-022-07533-1","article-title":"My goals are not their goals: Barriers and facilitators to delivery of patient-centered care for patients with multimorbidity","volume":"37","author":"Schuttner","year":"2022","journal-title":"J Gen Intern Med"},{"key":"2025120116480622300_ooaf158-B33","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1016\/j.cvdhj.2021.03.003","article-title":"Large-scale identification of aortic stenosis and its severity using natural language processing on electronic health records","volume":"2","author":"Solomon","year":"2021","journal-title":"Cardiovasc Digit Health J"},{"key":"2025120116480622300_ooaf158-B34","doi-asserted-by":"publisher","first-page":"e028131","DOI":"10.1161\/JAHA.122.028131","article-title":"Racial and ethnic disparities in aortic stenosis","volume":"11","author":"Parikh","year":"2022","journal-title":"J Am Heart Assoc"},{"key":"2025120116480622300_ooaf158-B35","doi-asserted-by":"publisher","first-page":"1364","DOI":"10.1038\/s41591-020-1034-x","article-title":"Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension","volume":"26","author":"Liu","year":"2020","journal-title":"Nat Med"},{"key":"2025120116480622300_ooaf158-B36","doi-asserted-by":"publisher","first-page":"1503","DOI":"10.1093\/jamia\/ocad088","article-title":"Implementation frameworks for end-to-end clinical AI: derivation of the SALIENT framework","volume":"30","author":"Van Der Vegt","year":"2023","journal-title":"J Am Med Inform Assoc"},{"key":"2025120116480622300_ooaf158-B37","doi-asserted-by":"publisher","first-page":"617","DOI":"10.1093\/aje\/kwy250","article-title":"Some desirable properties of the bonferroni correction: is the bonferroni correction really so bad?","volume":"188","author":"Van der Weele","year":"2019","journal-title":"Am J Epidemiol"},{"key":"2025120116480622300_ooaf158-B38","doi-asserted-by":"publisher","first-page":"1725","DOI":"10.21037\/jtd.2017.05.34","article-title":"A general introduction to adjustment for multiple comparisons","volume":"9","author":"Chen","year":"2017","journal-title":"J Thorac Dis"}],"container-title":["JAMIA Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamiaopen\/article-pdf\/8\/6\/ooaf158\/65667892\/ooaf158.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamiaopen\/article-pdf\/8\/6\/ooaf158\/65667892\/ooaf158.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T21:48:13Z","timestamp":1764625693000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamiaopen\/article\/doi\/10.1093\/jamiaopen\/ooaf158\/8362324"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,3]]},"references-count":38,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,11,3]]}},"URL":"https:\/\/doi.org\/10.1093\/jamiaopen\/ooaf158","relation":{},"ISSN":["2574-2531"],"issn-type":[{"value":"2574-2531","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,12]]},"published":{"date-parts":[[2025,11,3]]},"article-number":"ooaf158"}}