{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T11:52:13Z","timestamp":1790682733072,"version":"4.1.0"},"reference-count":28,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"10","license":[{"start":{"date-parts":[[2022,9,6]],"date-time":"2022-09-06T00:00:00Z","timestamp":1662422400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["www.ahajournals.org"],"crossmark-restriction":true},"short-container-title":["Circulation"],"published-print":{"date-parts":[[2022,9,6]]},"abstract":"<jats:sec>\n                    <jats:title>Background:<\/jats:title>\n                    <jats:p>Novel targeted treatments increase the need for prompt hypertrophic cardiomyopathy (HCM) detection. However, its low prevalence (0.5%) and resemblance to common diseases present challenges that may benefit from automated machine learning\u2013based approaches. We aimed to develop machine learning models to detect HCM and to differentiate it from other cardiac conditions using ECGs and echocardiograms, with robust generalizability across multiple cohorts.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods:<\/jats:title>\n                    <jats:p>Single-institution HCM ECG models were trained and validated on external data. Multi-institution models for ECG and echocardiogram were trained on data from 3 academic medical centers in the United States and Japan using a federated learning approach, which enables training on distributed data without data sharing. Models were validated on held-out test sets for each institution and from a fourth academic medical center and were further evaluated for discrimination of HCM from aortic stenosis, hypertension, and cardiac amyloidosis. Last, automated detection was compared with manual interpretation by 3 cardiologists on a data set with a realistic HCM prevalence.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>We identified 74\u2009376 ECGs for 56\u2009129 patients and 8392 echocardiograms for 6825 patients at the 4 academic medical centers. Although ECG models trained on data from each institution displayed excellent discrimination of HCM on internal test data (C statistics, 0.88\u20130.93), the generalizability was limited, most notably for a model trained in Japan and tested in the United States (C statistic, 0.79\u20130.82). When trained in a federated manner, discrimination of HCM was excellent across all institutions (C statistics, 0.90\u20130.96 and 0.90\u20130.96 for ECG and echocardiogram model, respectively), including for phenotypic subgroups. The models further discriminated HCM from hypertension, aortic stenosis, and cardiac amyloidosis (C statistics, 0.84, 0.83, and 0.88, respectively, for ECG and 0.93, 0.94, 0.85, respectively, for echocardiogram). Analysis of electrocardiography-echocardiography paired data from 11\u2009823 patients from an external institution indicated a higher sensitivity of automated HCM detection at a given positive predictive value compared with cardiologists (0.98 versus 0.81 at a positive predictive value of 0.01 for ECG and 0.78 versus 0.59 at a positive predictive value of 0.24 for echocardiogram).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions:<\/jats:title>\n                    <jats:p>Federated learning improved the generalizability of models that use ECGs and echocardiograms to detect and differentiate HCM from other causes of hypertrophy compared with training within a single institution.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1161\/circulationaha.121.058696","type":"journal-article","created":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T05:00:33Z","timestamp":1659416433000},"page":"755-769","update-policy":"https:\/\/doi.org\/10.1161\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":138,"title":["Multinational Federated Learning Approach to Train ECG and Echocardiogram Models for Hypertrophic Cardiomyopathy Detection"],"prefix":"10.1161","volume":"146","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0450-0331","authenticated-orcid":true,"given":"Shinichi","family":"Goto","sequence":"first","affiliation":[{"name":"One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women\u2019s Hospital, Boston, MA (S.G., D.S., J.E.J., R.Y., M.H., C.A.M., R.C.D.)."},{"name":"Harvard Medical School, Boston, MA (S.G., J.E.J., R.Y., M.H., H.K.G., C.A.M., R.C.D.)."},{"name":"Department of Cardiology, Keio University School of Medicine, Shinjuku, Tokyo, Japan (S.G., G.I., Y.K., Y.I.)."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Divyarajsinhji","family":"Solanki","sequence":"additional","affiliation":[{"name":"One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women\u2019s Hospital, Boston, MA (S.G., D.S., J.E.J., R.Y., M.H., C.A.M., R.C.D.)."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7174-9858","authenticated-orcid":true,"given":"Jenine E.","family":"John","sequence":"additional","affiliation":[{"name":"One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women\u2019s Hospital, Boston, MA (S.G., D.S., J.E.J., R.Y., M.H., C.A.M., R.C.D.)."},{"name":"Harvard Medical School, Boston, MA (S.G., J.E.J., R.Y., M.H., H.K.G., C.A.M., R.C.D.)."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryuichiro","family":"Yagi","sequence":"additional","affiliation":[{"name":"One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women\u2019s Hospital, Boston, MA (S.G., D.S., J.E.J., R.Y., M.H., C.A.M., R.C.D.)."},{"name":"Harvard Medical School, Boston, MA (S.G., J.E.J., R.Y., M.H., H.K.G., C.A.M., R.C.D.)."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7240-0028","authenticated-orcid":true,"given":"Max","family":"Homilius","sequence":"additional","affiliation":[{"name":"One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women\u2019s Hospital, Boston, MA (S.G., D.S., J.E.J., R.Y., M.H., C.A.M., R.C.D.)."},{"name":"Harvard Medical School, Boston, MA (S.G., J.E.J., R.Y., M.H., H.K.G., C.A.M., R.C.D.)."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Genki","family":"Ichihara","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Keio University School of Medicine, Shinjuku, Tokyo, Japan (S.G., G.I., Y.K., Y.I.)."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoshinori","family":"Katsumata","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Keio University School of Medicine, Shinjuku, Tokyo, Japan (S.G., G.I., Y.K., Y.I.)."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanna K.","family":"Gaggin","sequence":"additional","affiliation":[{"name":"Harvard Medical School, Boston, MA (S.G., J.E.J., R.Y., M.H., H.K.G., C.A.M., R.C.D.)."},{"name":"Division of Cardiology, Massachusetts General Hospital, Boston (H.K.G.)."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5236-1236","authenticated-orcid":true,"given":"Yuji","family":"Itabashi","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Keio University School of Medicine, Shinjuku, Tokyo, Japan (S.G., G.I., Y.K., Y.I.)."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5181-2664","authenticated-orcid":true,"given":"Calum A.","family":"MacRae","sequence":"additional","affiliation":[{"name":"One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women\u2019s Hospital, Boston, MA (S.G., D.S., J.E.J., R.Y., M.H., C.A.M., R.C.D.)."},{"name":"Harvard Medical School, Boston, MA (S.G., J.E.J., R.Y., M.H., H.K.G., C.A.M., R.C.D.)."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2791-9434","authenticated-orcid":true,"given":"Rahul C.","family":"Deo","sequence":"additional","affiliation":[{"name":"One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women\u2019s Hospital, Boston, MA (S.G., D.S., J.E.J., R.Y., M.H., C.A.M., R.C.D.)."},{"name":"Harvard Medical School, Boston, MA (S.G., J.E.J., R.Y., M.H., H.K.G., C.A.M., R.C.D.)."},{"name":"Center for Digital Health Innovation and Department of Medicine, University of California San Francisco (R.C.D.)."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCRESAHA.117.311059"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/s0092-8674(01)00242-2"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMra1710575"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1161\/CIR.0000000000000937"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(20)31792-X"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2020.03.064"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2021.12.002"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2559.2004.01835.x"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijcard.2015.11.071"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCIMAGING.116.005372"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/0735-1097(90)90587-f"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/s0002-9149(83)80034-4"},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/s0002-8703(07)80026-3"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCOUTCOMES.118.005289"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2021.669860"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2019.12.030"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.118.034338"},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1602.05629"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32692-0_16"},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-021-01506-3"},{"key":"e_1_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamacardio.2016.5670"},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.03426"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1610.02391"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-22877-8"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2021.669860"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2012.07805"},{"key":"e_1_3_3_28_2","first-page":"1322","article-title":"Model inversion attacks that exploit confidence information and basic countermeasures.","author":"Ray I","year":"2015","unstructured":"Ray, I, Li, N, Kruegel, C, Fredrikson, M, Jha, S, Ristenpart, T. Model inversion attacks that exploit confidence information and basic countermeasures. Proc 22nd Acm Sigsac Conf Comput Commun Secur. 2015:1322\u20131333.","journal-title":"Proc 22nd Acm Sigsac Conf Comput Commun Secur"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.001.1900506"}],"container-title":["Circulation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ahajournals.org\/doi\/full\/10.1161\/CIRCULATIONAHA.121.058696","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T03:58:59Z","timestamp":1715572739000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ahajournals.org\/doi\/10.1161\/CIRCULATIONAHA.121.058696"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,6]]},"references-count":28,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2022,9,6]]}},"alternative-id":["10.1161\/CIRCULATIONAHA.121.058696"],"URL":"https:\/\/doi.org\/10.1161\/circulationaha.121.058696","relation":{},"ISSN":["0009-7322","1524-4539"],"issn-type":[{"value":"0009-7322","type":"print"},{"value":"1524-4539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,6]]},"assertion":[{"value":"2021-12-09","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-06-14","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-08-02","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}