{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:44:01Z","timestamp":1785545041339,"version":"3.56.0"},"reference-count":26,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Res Protoc"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Clinical triage requires integrating multiple information sources to identify patients at risk of deterioration. Tools capturing global health assessments beyond disease-specific scores are being developed using either bottom-up aggregation of simple indicators or top-down machine learning from large datasets. Their alignment with expert clinical judgment remains poorly characterized.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study evaluates 2 latent health measurement approaches: Frailty Index-laboratory, a transparent bottom-up tool aggregating laboratory abnormalities via deficit accumulation theory, and ETHOS-ARES (Enhanced Transformer for Health Outcome Simulation-Adaptive Risk Estimation System), a transformer-based foundation model generating multidimensional patient representations from electronic health records. We assess whether each tool\u2019s severity rankings align with clinical consensus and whether they offer utility in triage decisions.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n In this 3-phase mixed methods study, at least 30 clinicians across hospital specialties reviewed 20 emergency department presentations derived from Medical Information Mart for Intensive Care IV-Emergency Department. Phase 1 compared unaided clinician severity and urgency judgments against model outputs using Spearman rank correlation, with a Turing-inspired indistinguishability test assessing whether model rankings fell within the distribution of clinician assessments. Phase 2 allocated clinicians to receive Frailty Index-laboratory or ETHOS-ARES outputs, measuring anchoring effects via within-person pre-post comparisons and exploring clinical utility through semistructured interviews analyzed using the Framework Method.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n Ethics approval was granted in June 2025 (KCL Research Ethics Office; MRSP-24\/25\u201048707). Recruitment began in October 2025 (32 clinicians recruited as of manuscript submission), with data collection expected to be completed in January 2026 and analysis planned for March or April 2026.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n This study will quantify model-clinician agreement, measure anchoring effects, and generate qualitative insights on utility, trust, and adoption. The findings will inform the implementation of latent health measurement tools in clinical practice and provide a framework for the early-stage evaluation of artificial intelligence\u2013based clinical decision support systems.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/85437","type":"journal-article","created":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T16:00:05Z","timestamp":1776873605000},"page":"e85437-e85437","source":"Crossref","is-referenced-by-count":0,"title":["Evaluation and Comparison of Latent Health Risk Prediction Models for Clinical Triage: Protocol for a Mixed Methods Study"],"prefix":"10.2196","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0351-7410","authenticated-orcid":false,"given":"Morgan","family":"Roberts","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8460-0133","authenticated-orcid":false,"given":"Otso","family":"Pelkonen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2434-3641","authenticated-orcid":false,"given":"Diana","family":"Shamsutdinova","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8427-724X","authenticated-orcid":false,"given":"Saskia C","family":"Sanderson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0487-7454","authenticated-orcid":false,"given":"Pawel","family":"Renc","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6428-0158","authenticated-orcid":false,"given":"Hugh","family":"Logan Ellis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,7,3]]},"reference":[{"key":"R1","doi-asserted-by":"crossref","unstructured":"McDermid RC Bagshaw SM . Physiological reserve and frailty in critical illness. In: Stevens RD Hart N Herridge MS , editors. Textbook of Post-ICU Medicine: The Legacy of Critical Care. Oxford Academic; 2014:303-316. [doi: 10.1093\/med\/9780199653461.003.0028]","DOI":"10.1093\/med\/9780199653461.003.0028"},{"issue":"1","key":"R2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01408-x","article-title":"The early warning paradox","volume":"8","author":"Logan Ellis","journal-title":"NPJ Digit Med"},{"key":"R3","unstructured":"Munakomi S Margetis K Iverson LM . Glasgow Coma Scale. In: StatPearls. StatPearls Publishing; 2025. URL: https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK513298\/ [Accessed 03-06-2026]"},{"issue":"11","key":"R4","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1136\/emermed-2020-209698","article-title":"Identification of very low-risk acute chest pain patients without troponin testing","volume":"37","author":"Smith","journal-title":"Emerg Med J"},{"issue":"6","key":"R5","doi-asserted-by":"publisher","first-page":"499","DOI":"10.7861\/clinmed.2022-news-concept","article-title":"The national early warning score: from concept to NHS implementation","volume":"22","author":"Williams","journal-title":"Clin Med (Lond)"},{"issue":"1","key":"R6","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01543-z","article-title":"A systematic review and meta-analysis of diagnostic performance comparison between generative AI and physicians","volume":"8","author":"Takita","journal-title":"NPJ Digit Med"},{"issue":"1","key":"R7","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-025-03048-x","article-title":"AI-powered early warning systems for clinical deterioration significantly improve patient outcomes: a meta-analysis","volume":"25","author":"Yuan","journal-title":"BMC Med Inform Decis Mak"},{"issue":"7","key":"R8","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1093\/jamia\/ocad085","article-title":"Bottom-up and top-down paradigms of artificial intelligence research approaches to healthcare data science using growing real-world big data","volume":"30","author":"Wang","journal-title":"J Am Med Inform Assoc"},{"key":"R9","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-014-0171-9","article-title":"Standard laboratory tests to identify older adults at increased risk of death","volume":"12","author":"Howlett","journal-title":"BMC Med"},{"issue":"7","key":"R10","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1093\/gerona\/62.7.722","article-title":"Frailty in relation to the accumulation of deficits","volume":"62","author":"Rockwood","journal-title":"J Gerontol A Biol Sci Med Sci"},{"issue":"1","key":"R11","doi-asserted-by":"publisher","DOI":"10.1093\/ageing\/afac309","article-title":"The Frailty Index based on laboratory test data as a tool to investigate the impact of frailty on health outcomes: a systematic review and meta-analysis","volume":"52","author":"Sapp","journal-title":"Age Ageing"},{"key":"R12","doi-asserted-by":"publisher","DOI":"10.2196\/70204","article-title":"Association between the Frailty Index based on laboratory tests and all-cause mortality in hospitalized older adults: retrospective cohort study","volume":"8","author":"Pasternak","journal-title":"JMIR Aging"},{"key":"R13","doi-asserted-by":"publisher","DOI":"10.1093\/gigascience\/giaf107","article-title":"Foundation model of electronic medical records for adaptive risk estimation","volume":"14","author":"Renc","journal-title":"Gigascience"},{"issue":"1","key":"R14","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01235-0","article-title":"Zero shot health trajectory prediction using transformer","volume":"7","author":"Renc","journal-title":"NPJ Digit Med"},{"key":"R15","doi-asserted-by":"publisher","DOI":"10.2196\/69678","article-title":"Trust in artificial intelligence-based clinical decision support systems among health care workers: systematic review","volume":"27","author":"Tun","journal-title":"J Med Internet Res"},{"key":"R16","unstructured":"Korom R Kiptinness S Adan N et al. AI-based clinical decision support for primary care: a real-world study. arXiv. Preprint posted online on Jul 22, 2025. [doi: 10.48550\/arXiv.2507.16947]"},{"issue":"2","key":"R17","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1136\/bmjinnov-2019-000359","article-title":"Bridging the implementation gap of machine learning in healthcare","volume":"6","author":"Seneviratne","journal-title":"BMJ Innov"},{"issue":"11","key":"R18","doi-asserted-by":"publisher","first-page":"2730","DOI":"10.1093\/jamia\/ocae209","article-title":"Toward a responsible future: recommendations for AI-enabled clinical decision support","volume":"31","author":"Labkoff","journal-title":"J Am Med Inform Assoc"},{"key":"R19","doi-asserted-by":"crossref","unstructured":"Ellis HL Alabdallat L Futrell E et al. What clinicians want AI to measure, and how they want it done. Research Square. Preprint posted online on Apr 22, 2025. [doi: 10.21203\/rs.3.rs-6346779\/v1]","DOI":"10.21203\/rs.3.rs-6346779\/v1"},{"issue":"1","key":"R20","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01899-x","article-title":"MIMIC-IV, a freely accessible electronic health record dataset","volume":"10","author":"Johnson","journal-title":"Sci Data"},{"key":"R21","unstructured":"Pwr: basic functions for power analysis. CRAN. URL: https:\/\/CRAN.R-project.org\/package=pwr [Accessed 03-06-2026]"},{"key":"R22","unstructured":"Pwrss: statistical power and sample size calculation tools. CRAN. URL: https:\/\/cran.r-project.org\/web\/packages\/pwrss\/index.html [Accessed 03-06-2026]"},{"issue":"2","key":"R23","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1191\/1478088706qp063oa","article-title":"Using thematic analysis in psychology","volume":"3","author":"Braun","journal-title":"Qual Res Psychol"},{"key":"R24","doi-asserted-by":"publisher","DOI":"10.1177\/16094069231205789","article-title":"A step-by-step process of thematic analysis to develop a conceptual model in qualitative research","volume":"22","author":"Naeem","journal-title":"Int J Qual Methods"},{"key":"R25","unstructured":"Lumivero. 2023. URL: https:\/\/www.lumivero.com [Accessed 03-06-2026]"},{"issue":"6","key":"R26","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1093\/intqhc\/mzm042","article-title":"Consolidated Criteria for Reporting Qualitative Research (COREQ): a 32-item checklist for interviews and focus groups","volume":"19","author":"Tong","journal-title":"Int J Qual Health Care"}],"container-title":["JMIR Research Protocols"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.researchprotocols.org\/2026\/1\/e85437","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:25:47Z","timestamp":1785536747000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.researchprotocols.org\/2026\/1\/e85437"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,3]]},"references-count":26,"URL":"https:\/\/doi.org\/10.2196\/85437","relation":{},"ISSN":["1929-0748"],"issn-type":[{"value":"1929-0748","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,3]]},"article-number":"v15i1e85437"}}