{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T12:22:16Z","timestamp":1768566136908,"version":"3.49.0"},"posted":{"date-parts":[[2024,10,10]]},"group-title":"Cardiovascular Medicine","reference-count":25,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T00:00:00Z","timestamp":1728518400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.medrxiv.org\/about\/FAQ#license"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,6,24]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>Delays in the diagnosis of transthyretin amyloid cardiomyopathy (ATTR-CM) contribute to the significant morbidity of the condition, especially in the era of disease-modifying therapies. Screening for ATTR-CM with AI and other algorithms may improve timely diagnosis, but these algorithms have not been directly compared.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Objectives<\/jats:title>\n                  <jats:p>The aim of this study was to compare the performance of four algorithms for ATTR-CM detection in a heart failure population and assess the risk for harms due to model bias.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>\n                    We identified patients in an integrated health system from 2010-2022 with ATTR-CM and age- and sex-matched them to controls with heart failure to target 5% prevalence. We compared the performance of a claims-based random forest model (Huda et al. model), a regression-based score (Mayo ATTR-CM), and two deep learning echo models (EchoNet-LVH and EchoGo\n                    <jats:sup>\u00ae<\/jats:sup>\n                    Amyloidosis). We evaluated for bias using standard fairness metrics.\n                  <\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>\n                    The analytical cohort included 176 confirmed cases of ATTR-CM and 3192 control patients with 79.2% self-identified as White and 9.0% as Black. The Huda et al. model performed poorly (AUC 0.49). Both deep learning echo models had a higher AUC when compared to the Mayo ATTR-CM Score (EchoNet-LVH 0.88; EchoGo Amyloidosis 0.92; Mayo ATTR-CM Score 0.79; DeLong P&lt;0.001 for both). Bias auditing met fairness criteria for\n                    <jats:italic>equal opportunity<\/jats:italic>\n                    among patients who identified as Black.\n                  <\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>Deep learning, echo-based models to detect ATTR-CM demonstrated best overall discrimination when compared to two other models in external validation with low risk of harms due to racial bias.<\/jats:p>\n                <\/jats:sec>","DOI":"10.1101\/2024.10.09.24315202","type":"posted-content","created":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T19:10:28Z","timestamp":1728587428000},"source":"Crossref","is-referenced-by-count":1,"title":["Evaluating the performance and potential bias of predictive models for detection of transthyretin cardiac amyloidosis"],"prefix":"10.64898","author":[{"given":"Jonathan","family":"Hourmozdi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicholas","family":"Easton","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"Benigeri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James D.","family":"Thomas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akhil","family":"Narang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Ouyang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Grant","family":"Duffy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ross","family":"Upton","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Will","family":"Hawkes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ashley","family":"Akerman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ike","family":"Okwuosa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adrienne","family":"Kline","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abel N.","family":"Kho","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanjiv J.","family":"Shah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2613-2541","authenticated-orcid":false,"given":"Faraz S.","family":"Ahmad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"issue":"24","key":"2025062503200864000_2024.10.09.24315202v3.1","doi-asserted-by":"crossref","first-page":"2472","DOI":"10.1016\/j.jacc.2024.03.400","article-title":"Artificial intelligence for cardiovascular care-part 1: Advances: JACC review topic of the week","volume":"83","year":"2024","journal-title":"J Am Coll Cardiol"},{"key":"2025062503200864000_2024.10.09.24315202v3.2","doi-asserted-by":"publisher","DOI":"10.1007\/s12170-021-00670-y"},{"key":"2025062503200864000_2024.10.09.24315202v3.3","doi-asserted-by":"publisher","DOI":"10.1161\/cir.0000000000000792"},{"key":"2025062503200864000_2024.10.09.24315202v3.4","doi-asserted-by":"publisher","DOI":"10.1161\/circulationaha.118.038169"},{"issue":"1","key":"2025062503200864000_2024.10.09.24315202v3.5","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1016\/j.cpcardiol.2017.04.003","article-title":"Cardiac amyloidosis: An updated review with emphasis on diagnosis and future directions","volume":"43","year":"2018","journal-title":"Curr Probl Cardiol"},{"key":"2025062503200864000_2024.10.09.24315202v3.6","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCHEARTFAILURE.119.006075"},{"key":"2025062503200864000_2024.10.09.24315202v3.7","doi-asserted-by":"publisher","DOI":"10.1136\/heartjnl-2012-302353"},{"issue":"6","key":"2025062503200864000_2024.10.09.24315202v3.8","doi-asserted-by":"crossref","first-page":"718","DOI":"10.1001\/jamacardio.2020.6623","article-title":"Association of the V122I transthyretin amyloidosis genetic variant with cardiac structure and function in middle-aged Black adults: Coronary Artery Risk Development in Young Adults (CARDIA) study: Coronary artery risk development in young adults (CARDIA) study","volume":"6","year":"2021","journal-title":"JAMA Cardiol"},{"key":"2025062503200864000_2024.10.09.24315202v3.9","doi-asserted-by":"crossref","unstructured":"Donnelly JP , Hanna M . Cardiac amyloidosis: An update on diagnosis and treatment. Cleve Clin J Med. 2017;84(12 Suppl 3):12-26.","DOI":"10.3949\/ccjm.84.s3.02"},{"key":"2025062503200864000_2024.10.09.24315202v3.10","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378"},{"key":"2025062503200864000_2024.10.09.24315202v3.11","first-page":"1354","article-title":"PsmPy: A package for retrospective cohort matching in python","volume":"2022","year":"2022","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"issue":"1","key":"2025062503200864000_2024.10.09.24315202v3.12","doi-asserted-by":"crossref","first-page":"2725","DOI":"10.1038\/s41467-021-22876-9","article-title":"A machine learning model for identifying patients at risk for wild-type transthyretin amyloid cardiomyopathy","volume":"12","year":"2021","journal-title":"Nat Commun"},{"issue":"10","key":"2025062503200864000_2024.10.09.24315202v3.13","doi-asserted-by":"crossref","first-page":"1036","DOI":"10.1001\/jamacardio.2022.1781","article-title":"A simple score to identify increased risk of transthyretin amyloid cardiomyopathy in heart failure with preserved ejection fraction","volume":"7","year":"2022","journal-title":"JAMA Cardiol"},{"issue":"4","key":"2025062503200864000_2024.10.09.24315202v3.14","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1001\/jamacardio.2021.6059","article-title":"High-throughput precision phenotyping of left ventricular hypertrophy with cardiovascular deep learning","volume":"7","year":"2022","journal-title":"JAMA Cardiol"},{"key":"2025062503200864000_2024.10.09.24315202v3.15","unstructured":"U.S. Food & Drug Administration. Re: K2340860. 2024. Available at: https:\/\/www.accessdata.fda.gov\/cdrh_docs\/pdf24\/K240860.pdf. Accessed 16 Mar 2025."},{"key":"2025062503200864000_2024.10.09.24315202v3.16","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2015.02.010"},{"key":"2025062503200864000_2024.10.09.24315202v3.17","doi-asserted-by":"publisher","DOI":"10.2307\/2531595"},{"key":"2025062503200864000_2024.10.09.24315202v3.18","doi-asserted-by":"publisher","DOI":"10.1016\/j.echo.2015.05.002"},{"issue":"6","key":"2025062503200864000_2024.10.09.24315202v3.19","doi-asserted-by":"crossref","first-page":"719","DOI":"10.1038\/s41551-023-01056-8","article-title":"Algorithmic fairness in artificial intelligence for medicine and healthcare","volume":"7","year":"2023","journal-title":"Nat Biomed Eng"},{"key":"2025062503200864000_2024.10.09.24315202v3.20","unstructured":"Saleiro P , Kuester B , Hinkson L , et al. Aequitas: A bias and fairness audit toolkit. arXiv [csLG]. Published online November 13, 2018. http:\/\/arxiv.org\/abs\/1811.05577"},{"key":"2025062503200864000_2024.10.09.24315202v3.21","doi-asserted-by":"publisher","DOI":"10.1002\/ejhf.3455"},{"issue":"9","key":"2025062503200864000_2024.10.09.24315202v3.22","doi-asserted-by":"crossref","first-page":"100998","DOI":"10.1016\/j.jacadv.2024.100998","article-title":"Impact of case and control selection on training artificial intelligence screening of cardiac amyloidosis","volume":"3","year":"2024","journal-title":"JACC Adv"},{"key":"2025062503200864000_2024.10.09.24315202v3.23","doi-asserted-by":"publisher","DOI":"10.1097\/MLR.0b013e3182408812"},{"key":"2025062503200864000_2024.10.09.24315202v3.24","doi-asserted-by":"publisher","DOI":"10.1186\/s13012-019-0861-y"},{"key":"2025062503200864000_2024.10.09.24315202v3.25","doi-asserted-by":"crossref","unstructured":"Shelton RC , Chambers DA , Glasgow RE . An extension of RE-AIM to enhance sustainability: Addressing dynamic context and promoting health equity over time. Front Public Health. 2020;8:134.","DOI":"10.3389\/fpubh.2020.00134"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2024.10.09.24315202","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:14:25Z","timestamp":1768508065000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2024.10.09.24315202"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,10]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1101\/2024.10.09.24315202","relation":{"is-preprint-of":[{"id-type":"doi","id":"10.1016\/j.jacadv.2025.101901","asserted-by":"subject"}]},"subject":[],"published":{"date-parts":[[2024,10,10]]},"subtype":"preprint"}}