Machine learning-based prediction of 1-year mortality for acute coronary syndrome


Journal

Journal of cardiology
ISSN: 1876-4738
Titre abrégé: J Cardiol
Pays: Netherlands
ID NLM: 8804703

Informations de publication

Date de publication:
03 2022
Historique:
received: 21 06 2021
revised: 20 09 2021
accepted: 13 10 2021
pubmed: 4 12 2021
medline: 3 3 2022
entrez: 3 12 2021
Statut: ppublish

Résumé

Clinical risk assessment with quantitative formal risk scores may add to intuitive physician risk assessment and are advised by the international guidelines for the management of acute coronary syndrome (ACS) patients. Most previous studies have used the binary regression/classification approach (dead/alive) for long-term mortality post-ACS, without considering the time-to-event as in survival analysis. The use of machine learning (ML)-based survival models has yet to be validated. The primary objective was to compare survival prediction performance of 1-year mortality following ACS of two newly developed ML-based models [random survival forest (RSF) and deep learning (DeepSurv)] with the traditional Cox-proportional hazard (CPH) model. The secondary objective was external validation of the findings. This was a retrospective, supervised learning data mining study based on the Acute Coronary Syndrome Israeli Survey (ACSIS) and the Myocardial Ischemia National Audit Project (MINAP). The ACSIS data were divided to train/test in a 70/30 fashion. Next, the models were externally validated on the MINAP data. Harrell's C-index, inverse probability of censoring weighting (IPCW), and the Brier-score were used for models' performance comparison. RSF performed best among the three models, with Harrell's C-index on training and testing sets reaching 0.953 and 0.924 respectively, followed by CPH multivariate selected model (0.805/0.849), CPH Univariate selected model (0.828/0.806), DeepSurv model (0.801/0.804), and the traditional CPH model (0.826/0.738). The RSF model also had the highest performance on the validation data set with 0.811 for Harrell's C-index, 0.844 for IPCW, and 0.093 for Brier score. The CPH model performance on the validation set had C-index range between 0.689 to 0.790, 0.713 to 0.826 for IPCW, and 0.094 to 0.103 Brier score. RSF survival predictions for long-term mortality post-ACS show improved model performance compared with the classic statistical method. This may benefit patients by allowing better risk stratification and tailored therapy, however further prospective evaluations are required.

Sections du résumé

BACKGROUND
Clinical risk assessment with quantitative formal risk scores may add to intuitive physician risk assessment and are advised by the international guidelines for the management of acute coronary syndrome (ACS) patients. Most previous studies have used the binary regression/classification approach (dead/alive) for long-term mortality post-ACS, without considering the time-to-event as in survival analysis. The use of machine learning (ML)-based survival models has yet to be validated. The primary objective was to compare survival prediction performance of 1-year mortality following ACS of two newly developed ML-based models [random survival forest (RSF) and deep learning (DeepSurv)] with the traditional Cox-proportional hazard (CPH) model. The secondary objective was external validation of the findings.
METHODS
This was a retrospective, supervised learning data mining study based on the Acute Coronary Syndrome Israeli Survey (ACSIS) and the Myocardial Ischemia National Audit Project (MINAP). The ACSIS data were divided to train/test in a 70/30 fashion. Next, the models were externally validated on the MINAP data. Harrell's C-index, inverse probability of censoring weighting (IPCW), and the Brier-score were used for models' performance comparison.
RESULTS
RSF performed best among the three models, with Harrell's C-index on training and testing sets reaching 0.953 and 0.924 respectively, followed by CPH multivariate selected model (0.805/0.849), CPH Univariate selected model (0.828/0.806), DeepSurv model (0.801/0.804), and the traditional CPH model (0.826/0.738). The RSF model also had the highest performance on the validation data set with 0.811 for Harrell's C-index, 0.844 for IPCW, and 0.093 for Brier score. The CPH model performance on the validation set had C-index range between 0.689 to 0.790, 0.713 to 0.826 for IPCW, and 0.094 to 0.103 Brier score.
CONCLUSIONS
RSF survival predictions for long-term mortality post-ACS show improved model performance compared with the classic statistical method. This may benefit patients by allowing better risk stratification and tailored therapy, however further prospective evaluations are required.

Identifiants

pubmed: 34857429
pii: S0914-5087(21)00316-6
doi: 10.1016/j.jjcc.2021.11.006
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

342-351

Informations de copyright

Copyright © 2021. Published by Elsevier Ltd.

Déclaration de conflit d'intérêts

Conflict of interests The authors had no conflict of interests.

Auteurs

Amir Hadanny (A)

The Mina and Everard Goodman Faculty of Life Sciences, Bar-Ilan University, Ramat-Gan, Israel; Sackler School of Medicine, Tel-Aviv University, Tel-Aviv, Israel. Electronic address: amir.had@gmail.com.

Roni Shouval (R)

The Mina and Everard Goodman Faculty of Life Sciences, Bar-Ilan University, Ramat-Gan, Israel; Sackler School of Medicine, Tel-Aviv University, Tel-Aviv, Israel; Adult Bone Marrow Transplantation Service, Memorial Sloan Kettering Cancer Center, New York, NY, United States of America.

Jianhua Wu (J)

Leeds Institute for Data Analytics, University of Leeds, Leeds, United Kingdom.

Chris P Gale (CP)

Leeds Institute for Data Analytics, University of Leeds, Leeds, United Kingdom; Leeds Institute of Cardiovascular and Metabolic Medicine, School of Medicine, University of Leeds, Leeds, United Kingdom; Department of Cardiology, Leeds Teaching Hospitals NHS Trust, Leeds, United Kingdom.

Ron Unger (R)

The Mina and Everard Goodman Faculty of Life Sciences, Bar-Ilan University, Ramat-Gan, Israel.

Doron Zahger (D)

Department of Cardiology, Soroka University Medical Center, Faculty of Health Sciences, Ben Gurion University of the Negev, Beer Sheva, Israel.

Shmuel Gottlieb (S)

Sackler School of Medicine, Tel-Aviv University, Tel-Aviv, Israel; Jesselson Integrated Heart Center, Shaare Zedek Medical Center, Jerusalem, Israel.

Shlomi Matetzky (S)

Sackler School of Medicine, Tel-Aviv University, Tel-Aviv, Israel; The Heart Institute, Sheba Medical Center, Tel Hashomer, Israel.

Ilan Goldenberg (I)

Sackler School of Medicine, Tel-Aviv University, Tel-Aviv, Israel; The Heart Institute, Sheba Medical Center, Tel Hashomer, Israel; Israeli Association for Cardiovascular Trials, Sheba Medical Center, Tel Hashomer, Israel.

Roy Beigel (R)

Sackler School of Medicine, Tel-Aviv University, Tel-Aviv, Israel; Department of Cardiology, The Cardiovascular Division, Sheba Medical Center, Tel Hashomer, Israel.

Zaza Iakobishvili (Z)

Department of Cardiology, Soroka University Medical Center, Faculty of Health Sciences, Ben Gurion University of the Negev, Beer Sheva, Israel; Department of Cardiology, Tel Aviv Jaffa district, Clalit Health Services, Israel; Department of Cardiology, Samson Assuta Ashdod Hospital, Israel.

Articles similaires

[Redispensing of expensive oral anticancer medicines: a practical application].

Lisanne N van Merendonk, Kübra Akgöl, Bastiaan Nuijen
1.00
Humans Antineoplastic Agents Administration, Oral Drug Costs Counterfeit Drugs

Smoking Cessation and Incident Cardiovascular Disease.

Jun Hwan Cho, Seung Yong Shin, Hoseob Kim et al.
1.00
Humans Male Smoking Cessation Cardiovascular Diseases Female
Humans United States Aged Cross-Sectional Studies Medicare Part C
1.00
Humans Yoga Low Back Pain Female Male

Classifications MeSH