TY - JOUR
T1 - Development and Validation of Machine Learning-Based Race-Specific Models to Predict 10-Year Risk of Heart Failure
T2 - A Multicohort Analysis
AU - Segar, Matthew W.
AU - Jaeger, Byron C.
AU - Patel, Kershaw V.
AU - Nambi, Vijay
AU - Ndumele, Chiadi E.
AU - Correa, Adolfo
AU - Butler, Javed
AU - Chandra, Alvin
AU - Ayers, Colby
AU - Rao, Shreya
AU - Lewis, Alana A.
AU - Raffield, Laura M.
AU - Rodriguez, Carlos J.
AU - Michos, Erin D.
AU - Ballantyne, Christie M.
AU - Hall, Michael E.
AU - Mentz, Robert J.
AU - De Lemos, James A.
AU - Pandey, Ambarish
N1 - Funding Information:
The authors thank the participants, staff, and investigators of the ARIC, DHS, JHS, and MESA studies for their important contributions. This research was supported in part by the computational resources provided by the BioHPC supercomputing facility located in the Lyda Hill Department of Bioinformatics, UT Southwestern Medical Center, Dallas, TX (https://portal.biohpc.swmed.edu).
Funding Information:
The ARIC study is conducted as a collaborative study supported by National Heart, Lung, and Blood Institute contracts (HHSN268201100005C, HHSN2 68201100006C, HHSN268201100007C, HHSN268201100008C, HHSN26820 1100009C, HHSN268201100010C, HHSN268201100011C, and HHSN268201 100012C) and R01HL 134320 to Dr Ballantyne. Reagents for NT-proBNP were provided by Roche and hs-TnI by Abbott. The DHS was funded by a grant from the Donald W. Reynolds Foundation. Research reported in this publication was supported by the National Center for Advancing Translational Sciences of the National Institutes of Health under award UL1TR001105 to the University of Texas Southwestern Medical Center. The JHS is supported by and conducted in collaboration with Jackson State University (HHSN268201800013I), Tougaloo College (HHSN268201800014I), the Mississippi State Department of Health (HHSN268201800015I), and the University of Mississippi Medical Center (HHSN268201800010I, HHSN268201800011I and HHSN268201800012I) and contracts from the National Heart, Lung, and Blood Institute and the National Institute on Minority Health and Health Disparities. A full list of participating MESA investigators and institutions can be found at http://www.mesa-nhlbi.org. MESA was supported by contracts N01-HC-95159, N01-HC-95160, N01-HC-95161, N01-HC-95162, N01-HC-95163, N01-HC-95164, N01-HC-95165, and N01HC 95169 from the National Heart, Lung, and Blood Institute. Reagents for the NT-proBNP and hs-cTnT assays were donated by Roche Diagnostics.
Publisher Copyright:
© 2020 American Heart Association, Inc.
PY - 2021/6/15
Y1 - 2021/6/15
N2 - Background: Heart failure (HF) risk and the underlying risk factors vary by race. Traditional models for HF risk prediction treat race as a covariate in risk prediction and do not account for significant parameters such as cardiac biomarkers. Machine learning (ML) may offer advantages over traditional modeling techniques to develop race-specific HF risk prediction models and to elucidate important contributors of HF development across races. Methods: We performed a retrospective analysis of 4 large, community cohort studies (ARIC [Atherosclerosis Risk in Communities], DHS [Dallas Heart Study], JHS [Jackson Heart Study], and MESA [Multi-Ethnic Study of Atherosclerosis]) with adjudicated HF events. The study included participants who were >40 years of age and free of HF at baseline. Race-specific ML models for HF risk prediction were developed in the JHS cohort (for Black race-specific model) and White adults from ARIC (for White race-specific model). The models included 39 candidate variables across demographic, anthropometric, medical history, laboratory, and electrocardiographic domains. The ML models were externally validated and compared with prior established traditional and non-race-specific ML models in race-specific subgroups of the pooled MESA/DHS cohort and Black participants of ARIC. The Harrell C-index and Greenwood-Nam-D'Agostino χ2 tests were used to assess discrimination and calibration, respectively. Results: The ML models had excellent discrimination in the derivation cohorts for Black (n=4141 in JHS, C-index=0.88) and White (n=7858 in ARIC, C-index=0.89) participants. In the external validation cohorts, the race-specific ML model demonstrated adequate calibration and superior discrimination (Black individuals, C-index=0.80-0.83; White individuals, C-index=0.82) compared with established HF risk models or with non-race-specific ML models derived with race included as a covariate. Among the risk factors, natriuretic peptide levels were the most important predictor of HF risk across both races, followed by troponin levels in Black and ECG-based Cornell voltage in White individuals. Other key predictors of HF risk among Black individuals were glycemic parameters and socioeconomic factors. In contrast, prevalent cardiovascular disease and traditional cardiovascular risk factors were stronger predictors of HF risk in White adults. Conclusions: Race-specific and ML-based HF risk models that integrate clinical, laboratory, and biomarker data demonstrated superior performance compared with traditional HF risk and non-race-specific ML models. This approach identifies distinct race-specific contributors of HF.
AB - Background: Heart failure (HF) risk and the underlying risk factors vary by race. Traditional models for HF risk prediction treat race as a covariate in risk prediction and do not account for significant parameters such as cardiac biomarkers. Machine learning (ML) may offer advantages over traditional modeling techniques to develop race-specific HF risk prediction models and to elucidate important contributors of HF development across races. Methods: We performed a retrospective analysis of 4 large, community cohort studies (ARIC [Atherosclerosis Risk in Communities], DHS [Dallas Heart Study], JHS [Jackson Heart Study], and MESA [Multi-Ethnic Study of Atherosclerosis]) with adjudicated HF events. The study included participants who were >40 years of age and free of HF at baseline. Race-specific ML models for HF risk prediction were developed in the JHS cohort (for Black race-specific model) and White adults from ARIC (for White race-specific model). The models included 39 candidate variables across demographic, anthropometric, medical history, laboratory, and electrocardiographic domains. The ML models were externally validated and compared with prior established traditional and non-race-specific ML models in race-specific subgroups of the pooled MESA/DHS cohort and Black participants of ARIC. The Harrell C-index and Greenwood-Nam-D'Agostino χ2 tests were used to assess discrimination and calibration, respectively. Results: The ML models had excellent discrimination in the derivation cohorts for Black (n=4141 in JHS, C-index=0.88) and White (n=7858 in ARIC, C-index=0.89) participants. In the external validation cohorts, the race-specific ML model demonstrated adequate calibration and superior discrimination (Black individuals, C-index=0.80-0.83; White individuals, C-index=0.82) compared with established HF risk models or with non-race-specific ML models derived with race included as a covariate. Among the risk factors, natriuretic peptide levels were the most important predictor of HF risk across both races, followed by troponin levels in Black and ECG-based Cornell voltage in White individuals. Other key predictors of HF risk among Black individuals were glycemic parameters and socioeconomic factors. In contrast, prevalent cardiovascular disease and traditional cardiovascular risk factors were stronger predictors of HF risk in White adults. Conclusions: Race-specific and ML-based HF risk models that integrate clinical, laboratory, and biomarker data demonstrated superior performance compared with traditional HF risk and non-race-specific ML models. This approach identifies distinct race-specific contributors of HF.
KW - epidemiology
KW - heart failure
KW - machine learning
KW - risk
UR - http://www.scopus.com/inward/record.url?scp=85108107154&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85108107154&partnerID=8YFLogxK
U2 - 10.1161/CIRCULATIONAHA.120.053134
DO - 10.1161/CIRCULATIONAHA.120.053134
M3 - Article
C2 - 33845593
AN - SCOPUS:85108107154
SN - 0009-7322
VL - 143
SP - 2370
EP - 2383
JO - Circulation
JF - Circulation
IS - 24
ER -