Prediction of diagnosis and diastolic filling pressure by AI-enhanced cardiac MRI: a modelling study of hospital data.
Autor: | Lehmann DH; Precision Digital Health and Informatics for Life, Clinic of Internal Medicine III, Interdisciplinary Center for Scientific Computing, University of Heidelberg, Heidelberg, Germany; German Center for Cardiovascular Research, Berlin, Germany., Gomes B; Precision Digital Health and Informatics for Life, Clinic of Internal Medicine III, Interdisciplinary Center for Scientific Computing, University of Heidelberg, Heidelberg, Germany; Department of Medicine, Department of Genetics, and Department of Biomedical Data Science, Stanford University, Stanford, CA, USA., Vetter N; Precision Digital Health and Informatics for Life, Clinic of Internal Medicine III, Interdisciplinary Center for Scientific Computing, University of Heidelberg, Heidelberg, Germany., Braun O; Department of Cardiology, Angiology and Pulmology, Center of Internal Medicine, Interdisciplinary Center for Scientific Computing, University of Heidelberg, Heidelberg, Germany., Amr A; Precision Digital Health and Informatics for Life, Clinic of Internal Medicine III, Interdisciplinary Center for Scientific Computing, University of Heidelberg, Heidelberg, Germany., Hilbel T; Department of Cardiology, Angiology and Pulmology, Center of Internal Medicine, Interdisciplinary Center for Scientific Computing, University of Heidelberg, Heidelberg, Germany., Müller J; Computer Vision and Learning Lab, Interdisciplinary Center for Scientific Computing, University of Heidelberg, Heidelberg, Germany., Köthe U; Computer Vision and Learning Lab, Interdisciplinary Center for Scientific Computing, University of Heidelberg, Heidelberg, Germany., Reich C; Precision Digital Health and Informatics for Life, Clinic of Internal Medicine III, Interdisciplinary Center for Scientific Computing, University of Heidelberg, Heidelberg, Germany., Kayvanpour E; Precision Digital Health and Informatics for Life, Clinic of Internal Medicine III, Interdisciplinary Center for Scientific Computing, University of Heidelberg, Heidelberg, Germany; German Center for Cardiovascular Research, Berlin, Germany., Sedaghat-Hamedani F; Precision Digital Health and Informatics for Life, Clinic of Internal Medicine III, Interdisciplinary Center for Scientific Computing, University of Heidelberg, Heidelberg, Germany; German Center for Cardiovascular Research, Berlin, Germany., Meder M; Precision Digital Health and Informatics for Life, Clinic of Internal Medicine III, Interdisciplinary Center for Scientific Computing, University of Heidelberg, Heidelberg, Germany., Haas J; Precision Digital Health and Informatics for Life, Clinic of Internal Medicine III, Interdisciplinary Center for Scientific Computing, University of Heidelberg, Heidelberg, Germany; German Center for Cardiovascular Research, Berlin, Germany., Ashley E; Department of Medicine, Department of Genetics, and Department of Biomedical Data Science, Stanford University, Stanford, CA, USA., Rottbauer W; Department of Cardiology, Ulm University Heart Center, Ulm, Germany., Felbel D; Department of Cardiology, Ulm University Heart Center, Ulm, Germany., Bekeredjian R; Clinic for Cardiology and Angiology, Robert-Bosch Krankenhaus, Stuttgart, Germany., Mahrholdt H; Clinic for Cardiology and Angiology, Robert-Bosch Krankenhaus, Stuttgart, Germany., Keller A; Clinical Bioinformatics, Saarland University, Saarbrücken, Germany., Ong P; Clinic for Cardiology and Angiology, Robert-Bosch Krankenhaus, Stuttgart, Germany., Seitz A; Clinic for Cardiology and Angiology, Robert-Bosch Krankenhaus, Stuttgart, Germany., Hund H; Department of Cardiology, Angiology and Pulmology, Center of Internal Medicine, Interdisciplinary Center for Scientific Computing, University of Heidelberg, Heidelberg, Germany., Geis N; Department of Cardiology, Angiology and Pulmology, Center of Internal Medicine, Interdisciplinary Center for Scientific Computing, University of Heidelberg, Heidelberg, Germany., André F; Department of Cardiology, Angiology and Pulmology, Center of Internal Medicine, Interdisciplinary Center for Scientific Computing, University of Heidelberg, Heidelberg, Germany; German Center for Cardiovascular Research, Berlin, Germany., Engelhardt S; Department of Cardiology, Angiology and Pulmology, Center of Internal Medicine, Interdisciplinary Center for Scientific Computing, University of Heidelberg, Heidelberg, Germany; German Center for Cardiovascular Research, Berlin, Germany., Katus HA; Department of Cardiology, Angiology and Pulmology, Center of Internal Medicine, Interdisciplinary Center for Scientific Computing, University of Heidelberg, Heidelberg, Germany; eCardiology, German Cardiac Society, Düsseldorf, Germany; German Center for Cardiovascular Research, Berlin, Germany., Frey N; Department of Cardiology, Angiology and Pulmology, Center of Internal Medicine, Interdisciplinary Center for Scientific Computing, University of Heidelberg, Heidelberg, Germany; eCardiology, German Cardiac Society, Düsseldorf, Germany; German Center for Cardiovascular Research, Berlin, Germany., Heuveline V; Engineering Mathematics and Computing Lab, Interdisciplinary Center for Scientific Computing, University of Heidelberg, Heidelberg, Germany., Meder B; Precision Digital Health and Informatics for Life, Clinic of Internal Medicine III, Interdisciplinary Center for Scientific Computing, University of Heidelberg, Heidelberg, Germany; Department of Cardiology, Angiology and Pulmology, Center of Internal Medicine, Interdisciplinary Center for Scientific Computing, University of Heidelberg, Heidelberg, Germany; eCardiology, German Cardiac Society, Düsseldorf, Germany; German Center for Cardiovascular Research, Berlin, Germany. Electronic address: benjamin.meder@med.uni-heidelberg.de. |
---|---|
Jazyk: | angličtina |
Zdroj: | The Lancet. Digital health [Lancet Digit Health] 2024 Jun; Vol. 6 (6), pp. e407-e417. |
DOI: | 10.1016/S2589-7500(24)00063-3 |
Abstrakt: | Background: With increasing numbers of patients and novel drugs for distinct causes of systolic and diastolic heart failure, automated assessment of cardiac function is important. We aimed to provide a non-invasive method to predict diagnosis of patients undergoing cardiac MRI (cMRI) and to obtain left ventricular end-diastolic pressure (LVEDP). Methods: For this modelling study, patients who had undergone cardiac catheterisation at University Hospital Heidelberg (Heidelberg, Germany) between July 15, 2004 and March 16, 2023, were identified, as were individual left ventricular pressure measurements. We used existing patient data from routine cardiac diagnostics. From this initial group, we extracted patients who had been diagnosed with ischaemic cardiomyopathy, dilated cardiomyopathy, hypertrophic cardiomyopathy, or amyloidosis, as well as control individuals with no structural phenotype. Data were pseudonymised and only processed within the university hospital's AI infrastructure. We used the data to build different models to predict either demographic (ie, AI-age and AI-sex), diagnostic (ie, AI-coronary artery disease and AI-cardiomyopathy [AI-CMP]), or functional parameters (ie, AI-LVEDP). We randomly divided our datasets via computer into training, validation, and test datasets. AI-CMP was not compared with other models, but was validated in a prospective setting. Benchmarking was also done. Findings: 66 936 patients who had undergone cardiac catheterisation at University Hospital Heidelberg were identified, with more than 183 772 individual left ventricular pressure measurements. We extracted 4390 patients from this initial group, of whom 1131 (25·8%) had been diagnosed with ischaemic cardiomyopathy, 1064 (24·2%) had been diagnosed with dilated cardiomyopathy, 816 (18·6%) had been diagnosed with hypertrophic cardiomyopathy, 202 (4·6%) had been diagnosed with amyloidosis, and 1177 (26·7%) were control individuals with no structural phenotype. The core cohort only included patients with cardiac catherisation and cMRI within 30 days, and emergency cases were excluded. AI-sex was able to predict patient sex with areas under the receiver operating characteristic curves (AUCs) of 0·78 (95% CI 0·77-0·78) and AI-age was able to predict patient age with a mean absolute error of 7·86 years (7·77-7·95), with a Pearson correlation of 0·57 (95% CI 0·56-0·57). The AUCs for the classification tasks ranged between 0·82 (95% CI 0·79-0·84) for ischaemic cardiomyopathy and 0·92 (0·91-0·94) for hypertrophic cardiomyopathy. Interpretation: Our AI models could be easily integrated into clinical practice and provide added value to the information content of cMRI, allowing for disease classification and prediction of diastolic function. Funding: Informatics for Life initiative of the Klaus-Tschira Foundation, German Center for Cardiovascular Research, eCardiology section of the German Cardiac Society, and AI Health Innovation Cluster Heidelberg. Competing Interests: Declaration of interests We declare no competing interests. (Copyright © 2024 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY-NC 4.0 license. Published by Elsevier Ltd.. All rights reserved.) |
Databáze: | MEDLINE |
Externí odkaz: |