Prediction of Stroke Outcome After Endovascular Thrombectomy From Clinical Characteristics: A Machine Learning Approach
Journal of the American Heart Association · 12.11.2026
DOI: 10.1161/jaha.125.047479 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the American Heart Association, online erschienen am 12.11.2026. Verfasst von Tomohide Yoshie und 16 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cerebrovascular Medicine National Cerebral and Cardiovascular Center Suita, Osaka Japan. Die Arbeit nennt 31 Literaturangaben.
Abstract (Originalsprache)
Background
Predicting outcomes after endovascular thrombectomy (EVT) for acute ischemic stroke is challenging. This study aimed to develop a machine learning model to predict outcomes after EVT using only clinical characteristics available shortly after hospital arrival, excluding imaging, laboratory, and angiographic data.
Methods
We analyzed data from the JSDB (Japan Stroke Data Bank), a multicenter, prospective registry of patients with acute stroke. A total of 4353 patients who underwent EVT between 2016 and 2020 were included, with those from 2016 to 2019 assigned to the derivation cohort and those from 2020 to the validation cohort. The model was developed using 132 routinely collected clinical variables that can be rapidly obtained on patient arrival. Feature selection was performed using the Boruta algorithm, and the model was built using CatBoost. The primary outcome was a modified Rankin Scale (mRS) score of 0 to 2 at discharge.
Results
Among 4353 patients treated with EVT, the derivation cohort included 2764 patients and the validation cohort, 1589 patients. In these cohorts, 973 (35.2%) and 547 (34.4%) achieved mRS 0 to 2, respectively. Boruta selected 47 predictors. CatBoost achieved an area under the receiver operating characteristic curve of 0.744 (95% CI, 0.710–0.776) in the derivation test set and 0.781 (95% CI, 0.755–0.803) in the validation cohort. Validation areas under the receiver operating characteristic curves were 0.792 (95% CI, 0.765–0.815) for mRS 0 to 1, 0.766 (95% CI, 0.744–0.787) for mRS 0 to 3, and 0.680 (95% CI, 0.631–0.729) for mRS 6.
Conclusions
Our machine learning model predicted outcomes following EVT using only admission clinical data. This imaging‐independent machine learning approach may support early prognostication and facilitate discussions of expected clinical courses.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Cerebrovascular Medicine National Cerebral and Cardiovascular Center Suita, Osaka Japan.
- Technology Unit AI Strategy Office, SoftBank Corp Tokyo Japan.
- Department of Medical and Health Information Management National Cerebral and Cardiovascular Center Suita, Osaka Japan.
- Public Health, Department of Social Medicine Osaka University Graduate School of Medicine Osaka Japan.
- Department of Neurosurgery Nakamura Memorial Hospital Sapporo Japan.
- Department of Neurosurgery Aizawa Hospital Matsumoto Japan.
ORCID-Profile: Tomohide Yoshie, Sohei Yoshimura, Shinichi Wada, Kaori Miwa, Junpei Koge, Junji Miyazaki, Toshiichi Watanabe, Nobuyuki Sakai, Ken Johkura, Koji Iihara, Yoshihiro Miyamoto, Kazunori Toyoda, Masatoshi Koga
Zitieren
APA
Yoshie, T., Yoshimura, S., Sakuraba, M., Wada, S., Miwa, K., Koge, J., Miyazaki, J., Watanabe, T., Kitazawa, K., Sakai, N., Yanagisawa, T., Johkura, K., Iihara, K., Miyamoto, Y., Minematsu, K., Toyoda, K., & Koga, M. (2026). Prediction of Stroke Outcome After Endovascular Thrombectomy From Clinical Characteristics: A Machine Learning Approach. Journal of the American Heart Association. https://doi.org/10.1161/jaha.125.047479
Vancouver
Yoshie T, Yoshimura S, Sakuraba M, Wada S, Miwa K, Koge J, et al. Prediction of Stroke Outcome After Endovascular Thrombectomy From Clinical Characteristics: A Machine Learning Approach. Journal of the American Heart Association. 2026. doi:10.1161/jaha.125.047479
BibTeX
@article{Yoshie2026,
author = {Yoshie, Tomohide and Yoshimura, Sohei and Sakuraba, Makino and Wada, Shinichi and Miwa, Kaori and Koge, Junpei and Miyazaki, Junji and Watanabe, Toshiichi and Kitazawa, Kazuo and Sakai, Nobuyuki and Yanagisawa, Toshiharu and Johkura, Ken and Iihara, Koji and Miyamoto, Yoshihiro and Minematsu, Kazuo and Toyoda, Kazunori and Koga, Masatoshi},
title = {Prediction of Stroke Outcome After Endovascular Thrombectomy From Clinical Characteristics: A Machine Learning Approach},
journal = {Journal of the American Heart Association},
year = {2026},
doi = {10.1161/jaha.125.047479}
}
EUVIMED