{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T03:39:04Z","timestamp":1787974744028,"version":"build-2784847793"},"reference-count":30,"publisher":"MDPI AG","issue":"15","license":[{"start":{"date-parts":[[2024,7,30]],"date-time":"2024-07-30T00:00:00Z","timestamp":1722297600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Qure.AI","award":["239717"],"award-info":[{"award-number":["239717"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>The opportunistic use of radiological examinations for disease detection can potentially enable timely management. We assessed if an index created by an AI software to quantify chest radiography (CXR) findings associated with heart failure (HF) could distinguish between patients who would develop HF or not within a year of the examination. Our multicenter retrospective study included patients who underwent CXR without an HF diagnosis. We included 1117 patients (age 67.6 \u00b1 13 years; m:f 487:630) that underwent CXR. A total of 413 patients had the CXR image taken within one year of their HF diagnosis. The rest (n = 704) were patients without an HF diagnosis after the examination date. All CXR images were processed with the model (qXR-HF, Qure.AI) to obtain information on cardiac silhouette, pleural effusion, and the index. We calculated the accuracy, sensitivity, specificity, and area under the curve (AUC) of the index to distinguish patients who developed HF within a year of the CXR and those who did not. We report an AUC of 0.798 (95%CI 0.77\u20130.82), accuracy of 0.73, sensitivity of 0.81, and specificity of 0.68 for the overall AI performance. AI AUCs by lead time to diagnosis (&lt;3 months: 0.85; 4\u20136 months: 0.82; 7\u20139 months: 0.75; 10\u201312 months: 0.71), accuracy (0.68\u20130.72), and specificity (0.68) remained stable. Our results support the ongoing investigation efforts for opportunistic screening in radiology.<\/jats:p>","DOI":"10.3390\/diagnostics14151635","type":"journal-article","created":{"date-parts":[[2024,7,30]],"date-time":"2024-07-30T08:51:42Z","timestamp":1722329502000},"page":"1635","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Early Detection of Heart Failure with Autonomous AI-Based Model Using Chest Radiographs: A Multicenter Study"],"prefix":"10.3390","volume":"14","author":[{"given":"Emiliano","family":"Garza-Frias","sequence":"first","affiliation":[{"name":"Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114, USA"},{"name":"Mass General Brigham Data Science Office, Boston, MA 02114, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0911-7507","authenticated-orcid":false,"given":"Parisa","family":"Kaviani","sequence":"additional","affiliation":[{"name":"Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114, USA"},{"name":"Mass General Brigham Data Science Office, Boston, MA 02114, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lina","family":"Karout","sequence":"additional","affiliation":[{"name":"Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114, USA"},{"name":"Mass General Brigham Data Science Office, Boston, MA 02114, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roshan","family":"Fahimi","sequence":"additional","affiliation":[{"name":"Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114, USA"},{"name":"Mass General Brigham Data Science Office, Boston, MA 02114, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seyedehelaheh","family":"Hosseini","sequence":"additional","affiliation":[{"name":"Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114, USA"},{"name":"Mass General Brigham Data Science Office, Boston, MA 02114, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Preetham","family":"Putha","sequence":"additional","affiliation":[{"name":"Qure AI, Mumbai 400063, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8632-9231","authenticated-orcid":false,"given":"Manoj","family":"Tadepalli","sequence":"additional","affiliation":[{"name":"Qure AI, Mumbai 400063, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sai","family":"Kiran","sequence":"additional","affiliation":[{"name":"Qure AI, Mumbai 400063, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Charu","family":"Arora","sequence":"additional","affiliation":[{"name":"Qure AI, Mumbai 400063, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8539-6408","authenticated-orcid":false,"given":"Dennis","family":"Robert","sequence":"additional","affiliation":[{"name":"Qure AI, Mumbai 400063, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bernardo","family":"Bizzo","sequence":"additional","affiliation":[{"name":"Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114, USA"},{"name":"Mass General Brigham Data Science Office, Boston, MA 02114, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keith J.","family":"Dreyer","sequence":"additional","affiliation":[{"name":"Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114, USA"},{"name":"Mass General Brigham Data Science Office, Boston, MA 02114, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mannudeep K.","family":"Kalra","sequence":"additional","affiliation":[{"name":"Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114, USA"},{"name":"Mass General Brigham Data Science Office, Boston, MA 02114, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Subba R.","family":"Digumarthy","sequence":"additional","affiliation":[{"name":"Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114, USA"},{"name":"Mass General Brigham Data Science Office, Boston, MA 02114, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,7,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"e139","DOI":"10.1161\/CIR.0000000000000757","article-title":"Heart Disease and Stroke Statistics-2020 Update: A Report from the American Heart Association","volume":"141","author":"Virani","year":"2020","journal-title":"Circulation"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"3272","DOI":"10.1093\/cvr\/cvac013","article-title":"Global burden of heart failure: A comprehensive and updated review of epidemiology","volume":"118","author":"Savarese","year":"2023","journal-title":"Cardiovasc. Res."},{"key":"ref_3","unstructured":"Malik, A., Brito, D., Vaqar, S., and Chhabra, L. (2024, June 17). Congestive Heart Failure. [Updated 2023 Nov 5], StatPearls [Internet], Available online: https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK430873\/."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"e008538","DOI":"10.1161\/CIRCHEARTFAILURE.121.008538","article-title":"Disparity in the Setting of Incident Heart Failure Diagnosis","volume":"14","author":"Sandhu","year":"2021","journal-title":"Circ. Heart Fail."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2154","DOI":"10.1007\/s00125-012-2579-0","article-title":"High prevalence of previously unknown heart failure and left ventricular dysfunction in patients with type 2 diabetes","volume":"55","author":"Rutten","year":"2012","journal-title":"Diabetologia"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"213","DOI":"10.4103\/0975-3583.89805","article-title":"Diastolic dysfunction in asymptomatic type 2 diabetes mellitus with normal systolic function","volume":"2","author":"Patil","year":"2011","journal-title":"J. Cardiovasc. Dis. Res."},{"key":"ref_7","first-page":"548","article-title":"Left ventricular systolic and diastolic dysfunction and their relationship with microvascular complications in normotensive, asymptomatic patients with type 2 diabetes mellitus","volume":"60","author":"Mishra","year":"2008","journal-title":"Indian Heart J."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"434","DOI":"10.1111\/dom.14236","article-title":"Asymptomatic left ventricular dysfunction in patients with type 2 diabetes free of cardiovascular disease and its relationship with clinical characteristics: The DIACAR cohort study","volume":"23","author":"Moeuf","year":"2021","journal-title":"Diabetes Obes. Metab."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1007\/s00125-023-06068-2","article-title":"Epidemiology of heart failure in diabetes: A disease in disguise","volume":"67","author":"Hoek","year":"2024","journal-title":"Diabetologia"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Swiatkiewicz, I., Patel, N.T., Villarreal-Gonzalez, M., and Taub, P.R. (2024). Prevalence of diabetic cardiomyopathy in patients with type 2 diabetes in a large academic medical center. BMC Med., 22.","DOI":"10.1186\/s12916-024-03401-3"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"301","DOI":"10.3109\/08037051.2010.488051","article-title":"Detection of unrecognized clinical heart failure in elderly hypertensive women attended in primary care setting","volume":"19","author":"Barrios","year":"2010","journal-title":"Blood Press."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1887","DOI":"10.1093\/eurheartj\/ehi291","article-title":"Unrecognized heart failure in elderly patients with stable chronic obstructive pulmonary disease","volume":"26","author":"Rutten","year":"2005","journal-title":"Eur. Heart J."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"925","DOI":"10.1016\/j.cardfail.2021.05.014","article-title":"Misdiagnosis of Heart Failure: A Systematic Review of the Literature","volume":"27","author":"Wong","year":"2021","journal-title":"J. Card. Fail."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"e006513","DOI":"10.1161\/CIRCHEARTFAILURE.119.006513","article-title":"Continuous Wearable Monitoring Analytics Predict Heart Failure Hospitalization: The LINK-HF Multicenter Study","volume":"13","author":"Stehlik","year":"2020","journal-title":"Circ. Heart Fail."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"e004669","DOI":"10.1161\/CIRCHEARTFAILURE.117.004669","article-title":"HeartLogic Multisensor Algorithm Identifies Patients During Periods of Significantly Increased Risk of Heart Failure Events: Results from the MultiSENSE Study","volume":"11","author":"Gardner","year":"2018","journal-title":"Circ. Heart Fail."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"11","DOI":"10.36628\/ijhf.2023.0050","article-title":"Application and Potential of Artificial Intelligence in Heart Failure: Past, Present, and Future","volume":"6","author":"Yoon","year":"2023","journal-title":"Int. J. Heart Fail."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1038\/s41746-020-0261-3","article-title":"Artificial intelligence for the diagnosis of heart failure","volume":"3","author":"Choi","year":"2020","journal-title":"NPJ Digit. Med."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1007\/s40471-020-00259-w","article-title":"Heart Failure Diagnosis, Readmission, and Mortality Prediction Using Machine Learning and Artificial Intelligence Models","volume":"7","author":"Guo","year":"2020","journal-title":"Curr. Epidemiol. Rep."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1562","DOI":"10.1002\/clc.24105","article-title":"The diagnostic value of chest X-ray scanning by the help of Artificial Intelligence in Heart Failure (ART-IN-HF)","volume":"46","author":"Celik","year":"2023","journal-title":"Clin. Cardiol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"781","DOI":"10.1536\/ihj.19-714","article-title":"Diagnosing Heart Failure from Chest X-Ray Images Using Deep Learning","volume":"61","author":"Matsumoto","year":"2020","journal-title":"Int. Heart J."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1387","DOI":"10.1007\/s00380-022-02043-w","article-title":"Quantitative estimation of pulmonary artery wedge pressure from chest radiographs by a regression convolutional neural network","volume":"37","author":"Saito","year":"2022","journal-title":"Heart Vessel."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1198","DOI":"10.1016\/j.cjca.2021.02.007","article-title":"Deep Learning for Detection of Elevated Pulmonary Artery Wedge Pressure Using Standard Chest X-Ray","volume":"37","author":"Hirata","year":"2021","journal-title":"Can. J. Cardiol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"e525","DOI":"10.1016\/S2589-7500(23)00107-3","article-title":"Artificial intelligence-based model to classify cardiac functions from chest radiographs: A multi-institutional, retrospective model development and validation study","volume":"5","author":"Ueda","year":"2023","journal-title":"Lancet Digit. Health"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1007\/s12576-014-0314-y","article-title":"Cardiac thin filament regulation and the Frank\u2013Starling mechanism","volume":"64","author":"Inoue","year":"2014","journal-title":"J. Physiol. Sci."},{"key":"ref_25","unstructured":"Delicce, A.V., and Makaryus, A.N. (2024, June 17). Physiology, Frank Starling Law. [Updated 2023 Jan 30], StatPearls [Internet], Available online: https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK470295\/."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"4444","DOI":"10.1002\/ehf2.13646","article-title":"\u2018Time is prognosis\u2019 in heart failure: Time-to-treatment initiation as a modifiable risk factor","volume":"8","author":"Abdin","year":"2021","journal-title":"ESC Heart Fail."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"649","DOI":"10.1161\/CIRCOUTCOMES.116.002797","article-title":"Early Detection of Heart Failure Using Electronic Health Records: Practical Implications for Time Before Diagnosis, Data Diversity, Data Quantity, and Data Density","volume":"9","author":"Ng","year":"2016","journal-title":"Circ. Cardiovasc. Qual. Outcomes"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1093\/eurheartj\/ehi559","article-title":"What is the most cost-effective strategy to screen for left ventricular systolic dysfunction: Natriuretic peptides, the electrocardiogram, hand-held echocardiography, traditional echocardiography, or their combination?","volume":"27","author":"Galasko","year":"2006","journal-title":"Eur. Heart J."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1007\/5584_2017_137","article-title":"Optimizing Management of Heart Failure by Using Echo and Natriuretic Peptides in the Outpatient Unit","volume":"1067","author":"Dini","year":"2018","journal-title":"Adv. Exp. Med. Biol."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1007\/s10741-021-10105-w","article-title":"Biomarkers for the diagnosis and management of heart failure","volume":"27","author":"Castiglione","year":"2022","journal-title":"Heart Fail Rev."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/14\/15\/1635\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:26:09Z","timestamp":1760109969000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/14\/15\/1635"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,30]]},"references-count":30,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2024,8]]}},"alternative-id":["diagnostics14151635"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics14151635","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,30]]}}}