{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["2(6)"],"submitter":["Hamatani Y"],"pubmed_abstract":["<h4>Background</h4>Atrial fibrillation (AF) increases the risk of heart failure (HF); however, little focus is placed on the risk stratification for, and prevention of, incident HF in patients with AF.<h4>Objectives</h4>This study aimed to construct and validate a machine learning (ML) prediction model for HF hospitalization in patients with AF.<h4>Methods</h4>The Fushimi AF Registry is a community-based prospective survey of patients with AF in Fushimi-ku, Kyoto, Japan. We divided the data set of the registry into derivation (n = 2,383) and validation (n = 2,011) cohorts. An ML model was built to predict the incidence of HF hospitalization using the derivation cohort, and predictive ability was examined using the validation cohort.<h4>Results</h4>HF hospitalization occurred in 606 patients (14%) during a median follow-up period of 4.4 years in the entire registry. Data of transthoracic echocardiography and biomarkers were frequently nominated as important predictive variables across all 6 ML models. The ML model based on a random forest algorithm using 7 variables (age, history of HF, creatinine clearance, cardiothoracic ratio on x-ray, left ventricular [LV] ejection fraction, LV end-systolic diameter, and LV asynergy) had high prediction performance (area under the receiver operating characteristics curve [AUC]: 0.75) and was significantly superior to the Framingham HF risk model (AUC: 0.67; <i>P</i> < 0.001). Based on Kaplan-Meier curves, the ML model could stratify the risk of HF hospitalization during the follow-up period (log-rank; <i>P</i> < 0.001).<h4>Conclusions</h4>The ML model revealed important predictors and helped us to stratify the risk of HF, providing opportunities for the prevention of HF in patients with AF."],"journal":["JACC. Asia"],"pagination":["706-716"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC9700042"],"repository":["biostudies-literature"],"pubmed_title":["Machine Learning Risk Prediction for Incident Heart Failure in Patients With Atrial Fibrillation."],"pmcid":["PMC9700042"],"pubmed_authors":["Hamatani Y","Fushimi AF Registry Investigators","Esato M","Abe M","Wada H","Tsuji H","Ogawa H","Iguchi M","Fukuda S","Nishi H","Akao M","Hasegawa K"],"additional_accession":[]},"is_claimable":false,"name":"Machine Learning Risk Prediction for Incident Heart Failure in Patients With Atrial Fibrillation.","description":"<h4>Background</h4>Atrial fibrillation (AF) increases the risk of heart failure (HF); however, little focus is placed on the risk stratification for, and prevention of, incident HF in patients with AF.<h4>Objectives</h4>This study aimed to construct and validate a machine learning (ML) prediction model for HF hospitalization in patients with AF.<h4>Methods</h4>The Fushimi AF Registry is a community-based prospective survey of patients with AF in Fushimi-ku, Kyoto, Japan. We divided the data set of the registry into derivation (n = 2,383) and validation (n = 2,011) cohorts. An ML model was built to predict the incidence of HF hospitalization using the derivation cohort, and predictive ability was examined using the validation cohort.<h4>Results</h4>HF hospitalization occurred in 606 patients (14%) during a median follow-up period of 4.4 years in the entire registry. Data of transthoracic echocardiography and biomarkers were frequently nominated as important predictive variables across all 6 ML models. The ML model based on a random forest algorithm using 7 variables (age, history of HF, creatinine clearance, cardiothoracic ratio on x-ray, left ventricular [LV] ejection fraction, LV end-systolic diameter, and LV asynergy) had high prediction performance (area under the receiver operating characteristics curve [AUC]: 0.75) and was significantly superior to the Framingham HF risk model (AUC: 0.67; <i>P</i> < 0.001). Based on Kaplan-Meier curves, the ML model could stratify the risk of HF hospitalization during the follow-up period (log-rank; <i>P</i> < 0.001).<h4>Conclusions</h4>The ML model revealed important predictors and helped us to stratify the risk of HF, providing opportunities for the prevention of HF in patients with AF.","dates":{"release":"2022-01-01T00:00:00Z","publication":"2022 Nov","modification":"2025-04-25T20:50:51.152Z","creation":"2025-04-06T08:34:49.957Z"},"accession":"S-EPMC9700042","cross_references":{"pubmed":["36444329"],"doi":["10.1016/j.jacasi.2022.07.007"]}}