Forecasting the Acute Heart Failure Admissions: Development of Deep Learning Prediction Model Incorporating the Climate Information.

Acute heart failure climate deep learning prediction model

Journal

Journal of cardiac failure
ISSN: 1532-8414
Titre abrégé: J Card Fail
Pays: United States
ID NLM: 9442138

Informations de publication

Date de publication:
10 Nov 2023
Historique:
received: 05 09 2023
revised: 08 10 2023
accepted: 08 10 2023
pubmed: 13 11 2023
medline: 13 11 2023
entrez: 12 11 2023
Statut: aheadofprint

Résumé

Climate is known to influence the incidence of cardiovascular events. However, their prediction with traditional statistical models remains imprecise. We analyzed 27,799 acute heart failure (AHF) admissions within the Tokyo CCU Network Database from January 2014 to December 2019. High-risk AHF (HR-AHF) day was defined as a day with the upper 10th percentile of AHF admission volume. Deep neural network (DNN) and traditional regression models were developed using the admissions in 2014-2018 and tested in 2019. Explanatory variables included 17 meteorological parameters. Shapley additive explanations were used to evaluate their importance. The median number of incidences of AHF was 12 (9-16) per day in 2014-2018 and 11 (9-15) per day in 2019. The predicted AHF admissions correlated well with the observed numbers (DNN: R The DNN model had good prediction ability for incident AHF using climate information. Forecasting AHF admissions could be useful for the effective management of AHF.

Sections du résumé

BACKGROUND BACKGROUND
Climate is known to influence the incidence of cardiovascular events. However, their prediction with traditional statistical models remains imprecise.
METHODS AND RESULTS RESULTS
We analyzed 27,799 acute heart failure (AHF) admissions within the Tokyo CCU Network Database from January 2014 to December 2019. High-risk AHF (HR-AHF) day was defined as a day with the upper 10th percentile of AHF admission volume. Deep neural network (DNN) and traditional regression models were developed using the admissions in 2014-2018 and tested in 2019. Explanatory variables included 17 meteorological parameters. Shapley additive explanations were used to evaluate their importance. The median number of incidences of AHF was 12 (9-16) per day in 2014-2018 and 11 (9-15) per day in 2019. The predicted AHF admissions correlated well with the observed numbers (DNN: R
CONCLUSIONS CONCLUSIONS
The DNN model had good prediction ability for incident AHF using climate information. Forecasting AHF admissions could be useful for the effective management of AHF.

Identifiants

pubmed: 37952642
pii: S1071-9164(23)00866-7
doi: 10.1016/j.cardfail.2023.10.476
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Informations de copyright

Copyright © 2023 Elsevier Inc. All rights reserved.

Auteurs

Takahiro Jimba (T)

Tokyo CCU Network Scientific Committee, Tokyo, Japan; Department of Cardiovascular Medicine, Graduate School of Medicine and Faculty of Medicine, The University of Tokyo, Tokyo, Japan. Electronic address: blackjtaka@yahoo.co.jp.

Satoshi Kodera (S)

Tokyo CCU Network Scientific Committee, Tokyo, Japan; Department of Cardiovascular Medicine, Graduate School of Medicine and Faculty of Medicine, The University of Tokyo, Tokyo, Japan.

Shun Kohsaka (S)

Tokyo CCU Network Scientific Committee, Tokyo, Japan.

Toshiaki Otsuka (T)

Tokyo CCU Network Scientific Committee, Tokyo, Japan; Department of Hygiene and Public Health, Nippon Medical School, Tokyo, Japan.

Kazumasa Harada (K)

Tokyo CCU Network Scientific Committee, Tokyo, Japan.

Akito Shindo (A)

Tokyo CCU Network Scientific Committee, Tokyo, Japan.

Yasuyuki Shiraishi (Y)

Tokyo CCU Network Scientific Committee, Tokyo, Japan.

Takashi Kohno (T)

Tokyo CCU Network Scientific Committee, Tokyo, Japan.

Makoto Takei (M)

Tokyo CCU Network Scientific Committee, Tokyo, Japan.

Hiroki Nakano (H)

Tokyo CCU Network Scientific Committee, Tokyo, Japan.

Junya Matsuda (J)

Tokyo CCU Network Scientific Committee, Tokyo, Japan.

Takeshi Yamamoto (T)

Tokyo CCU Network Scientific Committee, Tokyo, Japan.

Ken Nagao (K)

Tokyo CCU Network Scientific Committee, Tokyo, Japan.

Morimasa Takayama (M)

Tokyo CCU Network Scientific Committee, Tokyo, Japan.

Classifications MeSH