Risk of Mortality Prediction Involving Time-Varying Covariates for Patients with Heart Failure Using Deep Learning
Heart failure (HF) is challenging public medical and healthcare systems. This study aimed to develop and validate a novel deep learning-based prognostic model to predict the risk of all-cause mortality for patients with HF. We also compared the performance of the proposed model with those of classic...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/12/12/2947 |
| _version_ | 1827641057704148992 |
|---|---|
| author | Keijiro Nakamura Xue Zhou Naohiko Sahara Yasutake Toyoda Yoshinari Enomoto Hidehiko Hara Mahito Noro Kaoru Sugi Ming Huang Masao Moroi Masato Nakamura Xin Zhu |
| author_facet | Keijiro Nakamura Xue Zhou Naohiko Sahara Yasutake Toyoda Yoshinari Enomoto Hidehiko Hara Mahito Noro Kaoru Sugi Ming Huang Masao Moroi Masato Nakamura Xin Zhu |
| author_sort | Keijiro Nakamura |
| collection | DOAJ |
| description | Heart failure (HF) is challenging public medical and healthcare systems. This study aimed to develop and validate a novel deep learning-based prognostic model to predict the risk of all-cause mortality for patients with HF. We also compared the performance of the proposed model with those of classical deep learning- and traditional statistical-based models. The present study enrolled 730 patients with HF hospitalized at Toho University Ohashi Medical Center between April 2016 and March 2020. A recurrent neural network-based model (RNNSurv) involving time-varying covariates was developed and validated. The proposed RNNSurv showed better prediction performance than those of a deep feed-forward neural network-based model (referred as “DeepSurv”) and a multivariate Cox proportional hazard model in view of discrimination (C-index: 0.839 vs. 0.755 vs. 0.762, respectively), calibration (better fit with a 45-degree line), and ability of risk stratification, especially identifying patients with high risk of mortality. The proposed RNNSurv demonstrated an improved prediction performance in consideration of temporal information from time-varying covariates that could assist clinical decision-making. Additionally, this study found that significant risk and protective factors of mortality were specific to risk levels, highlighting the demand for an individual-specific clinical strategy instead of a uniform one for all patients. |
| first_indexed | 2024-03-09T17:08:02Z |
| format | Article |
| id | doaj.art-1181fc7a716a41e5bb6bddedf8e872ed |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-09T17:08:02Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-1181fc7a716a41e5bb6bddedf8e872ed2023-11-24T14:15:59ZengMDPI AGDiagnostics2075-44182022-11-011212294710.3390/diagnostics12122947Risk of Mortality Prediction Involving Time-Varying Covariates for Patients with Heart Failure Using Deep LearningKeijiro Nakamura0Xue Zhou1Naohiko Sahara2Yasutake Toyoda3Yoshinari Enomoto4Hidehiko Hara5Mahito Noro6Kaoru Sugi7Ming Huang8Masao Moroi9Masato Nakamura10Xin Zhu11Division of Cardiovascular Medicine, Toho University Ohashi Medical Center, Tokyo 153-8515, JapanGraduate School of Science and Technology, Nara Institute of Science and Technology, Ikoma 630-0192, JapanDivision of Cardiovascular Medicine, Toho University Ohashi Medical Center, Tokyo 153-8515, JapanDivision of Cardiovascular Medicine, Toho University Ohashi Medical Center, Tokyo 153-8515, JapanDivision of Cardiovascular Medicine, Toho University Ohashi Medical Center, Tokyo 153-8515, JapanDivision of Cardiovascular Medicine, Toho University Ohashi Medical Center, Tokyo 153-8515, JapanDivision of Cardiovascular Medicine, Odawara Cardiovascular Hospital, Odawara 250-0873, JapanDivision of Cardiovascular Medicine, Odawara Cardiovascular Hospital, Odawara 250-0873, JapanGraduate School of Science and Technology, Nara Institute of Science and Technology, Ikoma 630-0192, JapanDivision of Cardiovascular Medicine, Toho University Ohashi Medical Center, Tokyo 153-8515, JapanDivision of Cardiovascular Medicine, Toho University Ohashi Medical Center, Tokyo 153-8515, JapanGraduate Department of Computer and Information Systems, The University of Aizu, Aizuwakamatsu 965-8580, JapanHeart failure (HF) is challenging public medical and healthcare systems. This study aimed to develop and validate a novel deep learning-based prognostic model to predict the risk of all-cause mortality for patients with HF. We also compared the performance of the proposed model with those of classical deep learning- and traditional statistical-based models. The present study enrolled 730 patients with HF hospitalized at Toho University Ohashi Medical Center between April 2016 and March 2020. A recurrent neural network-based model (RNNSurv) involving time-varying covariates was developed and validated. The proposed RNNSurv showed better prediction performance than those of a deep feed-forward neural network-based model (referred as “DeepSurv”) and a multivariate Cox proportional hazard model in view of discrimination (C-index: 0.839 vs. 0.755 vs. 0.762, respectively), calibration (better fit with a 45-degree line), and ability of risk stratification, especially identifying patients with high risk of mortality. The proposed RNNSurv demonstrated an improved prediction performance in consideration of temporal information from time-varying covariates that could assist clinical decision-making. Additionally, this study found that significant risk and protective factors of mortality were specific to risk levels, highlighting the demand for an individual-specific clinical strategy instead of a uniform one for all patients.https://www.mdpi.com/2075-4418/12/12/2947deep learningheart failuremortalityrisk predictiontime-varying covariates |
| spellingShingle | Keijiro Nakamura Xue Zhou Naohiko Sahara Yasutake Toyoda Yoshinari Enomoto Hidehiko Hara Mahito Noro Kaoru Sugi Ming Huang Masao Moroi Masato Nakamura Xin Zhu Risk of Mortality Prediction Involving Time-Varying Covariates for Patients with Heart Failure Using Deep Learning Diagnostics deep learning heart failure mortality risk prediction time-varying covariates |
| title | Risk of Mortality Prediction Involving Time-Varying Covariates for Patients with Heart Failure Using Deep Learning |
| title_full | Risk of Mortality Prediction Involving Time-Varying Covariates for Patients with Heart Failure Using Deep Learning |
| title_fullStr | Risk of Mortality Prediction Involving Time-Varying Covariates for Patients with Heart Failure Using Deep Learning |
| title_full_unstemmed | Risk of Mortality Prediction Involving Time-Varying Covariates for Patients with Heart Failure Using Deep Learning |
| title_short | Risk of Mortality Prediction Involving Time-Varying Covariates for Patients with Heart Failure Using Deep Learning |
| title_sort | risk of mortality prediction involving time varying covariates for patients with heart failure using deep learning |
| topic | deep learning heart failure mortality risk prediction time-varying covariates |
| url | https://www.mdpi.com/2075-4418/12/12/2947 |
| work_keys_str_mv | AT keijironakamura riskofmortalitypredictioninvolvingtimevaryingcovariatesforpatientswithheartfailureusingdeeplearning AT xuezhou riskofmortalitypredictioninvolvingtimevaryingcovariatesforpatientswithheartfailureusingdeeplearning AT naohikosahara riskofmortalitypredictioninvolvingtimevaryingcovariatesforpatientswithheartfailureusingdeeplearning AT yasutaketoyoda riskofmortalitypredictioninvolvingtimevaryingcovariatesforpatientswithheartfailureusingdeeplearning AT yoshinarienomoto riskofmortalitypredictioninvolvingtimevaryingcovariatesforpatientswithheartfailureusingdeeplearning AT hidehikohara riskofmortalitypredictioninvolvingtimevaryingcovariatesforpatientswithheartfailureusingdeeplearning AT mahitonoro riskofmortalitypredictioninvolvingtimevaryingcovariatesforpatientswithheartfailureusingdeeplearning AT kaorusugi riskofmortalitypredictioninvolvingtimevaryingcovariatesforpatientswithheartfailureusingdeeplearning AT minghuang riskofmortalitypredictioninvolvingtimevaryingcovariatesforpatientswithheartfailureusingdeeplearning AT masaomoroi riskofmortalitypredictioninvolvingtimevaryingcovariatesforpatientswithheartfailureusingdeeplearning AT masatonakamura riskofmortalitypredictioninvolvingtimevaryingcovariatesforpatientswithheartfailureusingdeeplearning AT xinzhu riskofmortalitypredictioninvolvingtimevaryingcovariatesforpatientswithheartfailureusingdeeplearning |