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...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| 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 |