Machine Learning–Based Prediction for In‐Hospital Mortality After Acute Intracerebral Hemorrhage Using Real‐World Clinical and Image Data

BACKGROUND Machine learning (ML) techniques are widely employed across various domains to achieve accurate predictions. This study assessed the effectiveness of ML in predicting early mortality risk among patients with acute intracerebral hemorrhage (ICH) in real‐world settings. METHODS AND RESULTS...

Full description

Saved in:
Bibliographic Details
Main Authors: Koutarou Matsumoto, Kazuaki Ishihara, Katsuhiko Matsuda, Koki Tokunaga, Shigeo Yamashiro, Hidehisa Soejima, Naoki Nakashima, Masahiro Kamouchi
Format: Article
Language:English
Published: Wiley 2024-12-01
Series:Journal of the American Heart Association: Cardiovascular and Cerebrovascular Disease
Subjects:
Online Access:https://www.ahajournals.org/doi/10.1161/JAHA.124.036447
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850063331227860992
author Koutarou Matsumoto
Kazuaki Ishihara
Katsuhiko Matsuda
Koki Tokunaga
Shigeo Yamashiro
Hidehisa Soejima
Naoki Nakashima
Masahiro Kamouchi
author_facet Koutarou Matsumoto
Kazuaki Ishihara
Katsuhiko Matsuda
Koki Tokunaga
Shigeo Yamashiro
Hidehisa Soejima
Naoki Nakashima
Masahiro Kamouchi
author_sort Koutarou Matsumoto
collection DOAJ
description BACKGROUND Machine learning (ML) techniques are widely employed across various domains to achieve accurate predictions. This study assessed the effectiveness of ML in predicting early mortality risk among patients with acute intracerebral hemorrhage (ICH) in real‐world settings. METHODS AND RESULTS ML‐based models were developed to predict in‐hospital mortality in 527 patients with ICH using raw brain imaging data from brain computed tomography and clinical data. The models' performances were evaluated using the area under the receiver operating characteristic curves and calibration plots, comparing them with traditional risk scores such as the ICH score and ICH grading scale. Kaplan–Meier curves were used to examine the post‐ICH survival rates, stratified by ML‐based risk assessment. The net benefit of ML‐based models was evaluated using decision curve analysis. The area under the receiver operating characteristic curves were 0.91 (95% CI, 0.86–0.95) for the ICH score, 0.93 (95% CI, 0.89–0.97) for the ICH grading scale, 0.83 (95% CI, 0.71–0.91) for the ML‐based model fitted with raw image data only, and 0.87 (95% CI, 0.76–0.93) for the ML‐based model fitted using clinical data without specialist expertise. The area under the receiver operating characteristic curve increased significantly to 0.97 (95% CI, 0.94–0.99) when the ML model was fitted using clinical and image data assessed by specialists. All ML‐based models demonstrated good calibration, and the survival rates showed significant differences between risk groups. Decision curve analysis indicated the highest net benefit when utilizing the findings assessed by specialists. CONCLUSIONS ML‐based prediction models exhibit satisfactory performance in predicting post‐ICH in‐hospital mortality when utilizing raw imaging data or nonspecialist input. Nevertheless, incorporating specialist expertise notably improves performance.
format Article
id doaj-art-bda0f681abb24e7c8478cc759f65b662
institution DOAJ
issn 2047-9980
language English
publishDate 2024-12-01
publisher Wiley
record_format Article
series Journal of the American Heart Association: Cardiovascular and Cerebrovascular Disease
spelling doaj-art-bda0f681abb24e7c8478cc759f65b6622025-08-20T02:49:39ZengWileyJournal of the American Heart Association: Cardiovascular and Cerebrovascular Disease2047-99802024-12-01132410.1161/JAHA.124.036447Machine Learning–Based Prediction for In‐Hospital Mortality After Acute Intracerebral Hemorrhage Using Real‐World Clinical and Image DataKoutarou Matsumoto0Kazuaki Ishihara1Katsuhiko Matsuda2Koki Tokunaga3Shigeo Yamashiro4Hidehisa Soejima5Naoki Nakashima6Masahiro Kamouchi7Department of Health Care Administration and Management, Graduate School of Medical Sciences Kyushu University Fukuoka JapanBiostatistics Center Kurume University Kurume JapanDepartment of Radiology Saiseikai Kumamoto Hospital Kumamoto JapanDepartment of Pharmacy Saiseikai Kumamoto Hospital Kumamoto JapanDivision of Neurosurgery Saiseikai Kumamoto Hospital Kumamoto JapanInstitute for Medical Information Research and Analysis Saiseikai Kumamoto Hospital Kumamoto JapanMedical Information Center Kyushu University Hospital Fukuoka JapanDepartment of Health Care Administration and Management, Graduate School of Medical Sciences Kyushu University Fukuoka JapanBACKGROUND Machine learning (ML) techniques are widely employed across various domains to achieve accurate predictions. This study assessed the effectiveness of ML in predicting early mortality risk among patients with acute intracerebral hemorrhage (ICH) in real‐world settings. METHODS AND RESULTS ML‐based models were developed to predict in‐hospital mortality in 527 patients with ICH using raw brain imaging data from brain computed tomography and clinical data. The models' performances were evaluated using the area under the receiver operating characteristic curves and calibration plots, comparing them with traditional risk scores such as the ICH score and ICH grading scale. Kaplan–Meier curves were used to examine the post‐ICH survival rates, stratified by ML‐based risk assessment. The net benefit of ML‐based models was evaluated using decision curve analysis. The area under the receiver operating characteristic curves were 0.91 (95% CI, 0.86–0.95) for the ICH score, 0.93 (95% CI, 0.89–0.97) for the ICH grading scale, 0.83 (95% CI, 0.71–0.91) for the ML‐based model fitted with raw image data only, and 0.87 (95% CI, 0.76–0.93) for the ML‐based model fitted using clinical data without specialist expertise. The area under the receiver operating characteristic curve increased significantly to 0.97 (95% CI, 0.94–0.99) when the ML model was fitted using clinical and image data assessed by specialists. All ML‐based models demonstrated good calibration, and the survival rates showed significant differences between risk groups. Decision curve analysis indicated the highest net benefit when utilizing the findings assessed by specialists. CONCLUSIONS ML‐based prediction models exhibit satisfactory performance in predicting post‐ICH in‐hospital mortality when utilizing raw imaging data or nonspecialist input. Nevertheless, incorporating specialist expertise notably improves performance.https://www.ahajournals.org/doi/10.1161/JAHA.124.036447deep learningintracerebral hemorrhagemachine learningprognostic score
spellingShingle Koutarou Matsumoto
Kazuaki Ishihara
Katsuhiko Matsuda
Koki Tokunaga
Shigeo Yamashiro
Hidehisa Soejima
Naoki Nakashima
Masahiro Kamouchi
Machine Learning–Based Prediction for In‐Hospital Mortality After Acute Intracerebral Hemorrhage Using Real‐World Clinical and Image Data
Journal of the American Heart Association: Cardiovascular and Cerebrovascular Disease
deep learning
intracerebral hemorrhage
machine learning
prognostic score
title Machine Learning–Based Prediction for In‐Hospital Mortality After Acute Intracerebral Hemorrhage Using Real‐World Clinical and Image Data
title_full Machine Learning–Based Prediction for In‐Hospital Mortality After Acute Intracerebral Hemorrhage Using Real‐World Clinical and Image Data
title_fullStr Machine Learning–Based Prediction for In‐Hospital Mortality After Acute Intracerebral Hemorrhage Using Real‐World Clinical and Image Data
title_full_unstemmed Machine Learning–Based Prediction for In‐Hospital Mortality After Acute Intracerebral Hemorrhage Using Real‐World Clinical and Image Data
title_short Machine Learning–Based Prediction for In‐Hospital Mortality After Acute Intracerebral Hemorrhage Using Real‐World Clinical and Image Data
title_sort machine learning based prediction for in hospital mortality after acute intracerebral hemorrhage using real world clinical and image data
topic deep learning
intracerebral hemorrhage
machine learning
prognostic score
url https://www.ahajournals.org/doi/10.1161/JAHA.124.036447
work_keys_str_mv AT koutaroumatsumoto machinelearningbasedpredictionforinhospitalmortalityafteracuteintracerebralhemorrhageusingrealworldclinicalandimagedata
AT kazuakiishihara machinelearningbasedpredictionforinhospitalmortalityafteracuteintracerebralhemorrhageusingrealworldclinicalandimagedata
AT katsuhikomatsuda machinelearningbasedpredictionforinhospitalmortalityafteracuteintracerebralhemorrhageusingrealworldclinicalandimagedata
AT kokitokunaga machinelearningbasedpredictionforinhospitalmortalityafteracuteintracerebralhemorrhageusingrealworldclinicalandimagedata
AT shigeoyamashiro machinelearningbasedpredictionforinhospitalmortalityafteracuteintracerebralhemorrhageusingrealworldclinicalandimagedata
AT hidehisasoejima machinelearningbasedpredictionforinhospitalmortalityafteracuteintracerebralhemorrhageusingrealworldclinicalandimagedata
AT naokinakashima machinelearningbasedpredictionforinhospitalmortalityafteracuteintracerebralhemorrhageusingrealworldclinicalandimagedata
AT masahirokamouchi machinelearningbasedpredictionforinhospitalmortalityafteracuteintracerebralhemorrhageusingrealworldclinicalandimagedata