RESUMO
OBJECTIVES: : Although numerous risk prediction models have been proposed, few such models have been developed using neural network-based survival analysis. We developed risk prediction models for three cardiovascular disease risk factors (diabetes mellitus, hypertension, and dyslipidemia) among a working-age population in Japan using DeepSurv, a deep feed-forward neural network. METHODS: : Data were obtained from the Japan Epidemiology Collaboration on Occupational Health Study. A total of 51â258, 44â197, and 31â452 individuals were included in the development of risk models for diabetes mellitus, hypertension, and dyslipidemia, respectively; two-thirds of whom were used to develop prediction models, and the rest were used to validate the models. We compared the performances of DeepSurv-based models with those of prediction models based on the Cox proportional hazards model. RESULTS: : The area under the receiver-operating characteristic curve was 0.878 [95% confidence interval (CI)â=â0.864-0.892] for diabetes mellitus, 0.835 (95% CIâ=â0.826-0.845) for hypertension, and 0.826 (95% CIâ=â0.817-0.835) for dyslipidemia. Compared with the Cox proportional hazards-based models, the DeepSurv-based models had better reclassification performance [diabetes mellitus: net reclassification improvement (NRI)â=â0.474, P â≤â0.001; hypertension: NRIâ=â0.194, P â≤â0.001; dyslipidemia: NRIâ=â0.397, P â≤â0.001] and discrimination performance [diabetes mellitus: integrated discrimination improvement (IDI)â=â0.013, P â≤â0.001; hypertension: IDIâ=â0.007, P â≤â0.001; and dyslipidemia: IDIâ=â0.043, P â≤â0.001]. CONCLUSION: : This study suggests that DeepSurv has the potential to improve the performance of risk prediction models for cardiovascular disease risk factors.