Multimodal ensemble machine learning predicts neurological outcome within three hours after out of hospital cardiac arrest
Abstract This study aimed to determine if an ensemble (stacking) model that integrates three independently developed base models can reliably predict patients’ neurological outcomes following out-of-hospital cardiac arrest (OHCA) within 3 h of arrival and outperform each individual model. This retro...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-08-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-15160-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849342540155715584 |
|---|---|
| author | Yasuyuki Kawai Koji Yamamoto Keisuke Tsuruta Keita Miyazaki Hideki Asai Hidetada Fukushima |
| author_facet | Yasuyuki Kawai Koji Yamamoto Keisuke Tsuruta Keita Miyazaki Hideki Asai Hidetada Fukushima |
| author_sort | Yasuyuki Kawai |
| collection | DOAJ |
| description | Abstract This study aimed to determine if an ensemble (stacking) model that integrates three independently developed base models can reliably predict patients’ neurological outcomes following out-of-hospital cardiac arrest (OHCA) within 3 h of arrival and outperform each individual model. This retrospective study included patients with OHCA (≥ 18 years) admitted directly to Nara Medical University between April 2015 and March 2024 who remained comatose for ≥ 3 h after arrival and had suitable head computed tomography (CT) images. The area under the receiver operating characteristic curve (AUC) and Briers scores were used to evaluate the performance of four models (resuscitation-related background OHCA score factors, bilateral pupil diameter, single-slice head CT within 3 h of arrival, and an ensemble stacked model combining these three models) in predicting favourable neurological outcomes at hospital discharge or 1 month, as defined by a Cerebral Performance Category scale of 1–2. Among 533 patients, 82 (15%) had favourable outcomes. The OHCA, pupil, and head CT models yielded AUCs of 0.76, 0.65, and 0.68 with Brier scores of 0.11, 0.13, and 0.12, respectively. The ensemble model outperformed the other models (AUC, 0.82; Brier score, 0.10), thereby supporting its application for early clinical decision-making and optimising resource allocation. |
| format | Article |
| id | doaj-art-aa265258fa8f414eaad8a77864ea1ed4 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-aa265258fa8f414eaad8a77864ea1ed42025-08-20T03:43:21ZengNature PortfolioScientific Reports2045-23222025-08-0115111010.1038/s41598-025-15160-zMultimodal ensemble machine learning predicts neurological outcome within three hours after out of hospital cardiac arrestYasuyuki Kawai0Koji Yamamoto1Keisuke Tsuruta2Keita Miyazaki3Hideki Asai4Hidetada Fukushima5Department of Emergency and Critical Care Medicine, Nara Medical UniversityDepartment of Emergency and Critical Care Medicine, Nara Medical UniversityDepartment of Emergency and Critical Care Medicine, Nara Medical UniversityDepartment of Emergency and Critical Care Medicine, Nara Medical UniversityDepartment of Emergency and Critical Care Medicine, Nara Medical UniversityDepartment of Emergency and Critical Care Medicine, Nara Medical UniversityAbstract This study aimed to determine if an ensemble (stacking) model that integrates three independently developed base models can reliably predict patients’ neurological outcomes following out-of-hospital cardiac arrest (OHCA) within 3 h of arrival and outperform each individual model. This retrospective study included patients with OHCA (≥ 18 years) admitted directly to Nara Medical University between April 2015 and March 2024 who remained comatose for ≥ 3 h after arrival and had suitable head computed tomography (CT) images. The area under the receiver operating characteristic curve (AUC) and Briers scores were used to evaluate the performance of four models (resuscitation-related background OHCA score factors, bilateral pupil diameter, single-slice head CT within 3 h of arrival, and an ensemble stacked model combining these three models) in predicting favourable neurological outcomes at hospital discharge or 1 month, as defined by a Cerebral Performance Category scale of 1–2. Among 533 patients, 82 (15%) had favourable outcomes. The OHCA, pupil, and head CT models yielded AUCs of 0.76, 0.65, and 0.68 with Brier scores of 0.11, 0.13, and 0.12, respectively. The ensemble model outperformed the other models (AUC, 0.82; Brier score, 0.10), thereby supporting its application for early clinical decision-making and optimising resource allocation.https://doi.org/10.1038/s41598-025-15160-zMultimodal ensemble modelEarly neurological prognosticationOut-of-hospital cardiac arrest |
| spellingShingle | Yasuyuki Kawai Koji Yamamoto Keisuke Tsuruta Keita Miyazaki Hideki Asai Hidetada Fukushima Multimodal ensemble machine learning predicts neurological outcome within three hours after out of hospital cardiac arrest Scientific Reports Multimodal ensemble model Early neurological prognostication Out-of-hospital cardiac arrest |
| title | Multimodal ensemble machine learning predicts neurological outcome within three hours after out of hospital cardiac arrest |
| title_full | Multimodal ensemble machine learning predicts neurological outcome within three hours after out of hospital cardiac arrest |
| title_fullStr | Multimodal ensemble machine learning predicts neurological outcome within three hours after out of hospital cardiac arrest |
| title_full_unstemmed | Multimodal ensemble machine learning predicts neurological outcome within three hours after out of hospital cardiac arrest |
| title_short | Multimodal ensemble machine learning predicts neurological outcome within three hours after out of hospital cardiac arrest |
| title_sort | multimodal ensemble machine learning predicts neurological outcome within three hours after out of hospital cardiac arrest |
| topic | Multimodal ensemble model Early neurological prognostication Out-of-hospital cardiac arrest |
| url | https://doi.org/10.1038/s41598-025-15160-z |
| work_keys_str_mv | AT yasuyukikawai multimodalensemblemachinelearningpredictsneurologicaloutcomewithinthreehoursafteroutofhospitalcardiacarrest AT kojiyamamoto multimodalensemblemachinelearningpredictsneurologicaloutcomewithinthreehoursafteroutofhospitalcardiacarrest AT keisuketsuruta multimodalensemblemachinelearningpredictsneurologicaloutcomewithinthreehoursafteroutofhospitalcardiacarrest AT keitamiyazaki multimodalensemblemachinelearningpredictsneurologicaloutcomewithinthreehoursafteroutofhospitalcardiacarrest AT hidekiasai multimodalensemblemachinelearningpredictsneurologicaloutcomewithinthreehoursafteroutofhospitalcardiacarrest AT hidetadafukushima multimodalensemblemachinelearningpredictsneurologicaloutcomewithinthreehoursafteroutofhospitalcardiacarrest |