EUVIMEDEUVIMED entdecken
Multizentrische StudieOpen Access

Clinically Applicable Machine Learning Approach to Predict Intracerebral Hematoma Expansion

Shogo Watanabe iD, Nice Ren iD, Yukihiro Imaoka iD, Kento Morita iD, Syoji Kobashi iD, Nobutaka Mukae iD, Koichi Arimura iD, Kunihiro Nishimura iD, Koji Iihara iD, J‐ASPECT study collaborators

Journal of the American Heart Association · 2026

DOI: 10.1161/jaha.125.042387 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Journal of the American Heart Association, 2026. Verfasst von Shogo Watanabe und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Stroke and Cardiovascular Disease Next Generation Medical Research National Cerebral and Cardiovascular Center Osaka Japan. Hauptthemen laut MEDLINE: Machine Learning, Cerebral Hemorrhage, Hematoma. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Hematoma expansion (HE) is a significant risk factor for poor prognosis in patients with intracerebral hemorrhage (ICH). Accurately predicting HE is crucial for determining optimal treatment strategies.

Methods

This study enrolled 452 patients with ICH from 10 hospitals. To predict HE, 28 clinical variables available on patient arrival (including medical history, ICH location, and ICH volume) and 1142 radiomics features extracted from noncontrast computed tomography images of the ICH regions were used. Clinical variables and radiomics features were selected using gradient boosting and the least absolute shrinkage and selection operator. Three HE prediction models were built on clinical variables alone, radiomics features alone, and a third combining both. The models were compared using 5‐fold cross‐validation, and the mean area under the receiver operating characteristic curve was calculated for each. Additionally, the important features of HE prediction in the combined model were explored.

Results

The combined model demonstrated the highest performance for predicting HE with a 5‐fold mean area under the receiver operating characteristic curve of 0.77±0.05, compared with 0.70±0.06 for the clinical variables alone and 0.73±0.04 for the radiomics features alone. Permutation feature importance analysis suggested that anticoagulant treatment was the most predictive of HE.

Conclusions

A predictive model for HE was developed using the medical history, clinical features available on the patient’s arrival, imaging, and radiomics features extracted from computed tomography images. This prediction model will assist non–stroke care specialists in making treatment decisions for ICH in emergency settings.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningCerebral HemorrhageHematomaHumansMaleFemaleAgedTomography, X-Ray ComputedMiddle AgedRisk FactorsPredictive Value of TestsRetrospective StudiesROC CurvePrognosisRisk AssessmentDisease ProgressionAged, 80 and over

Stichwörter der Autor:innen

hematoma expansionimaging biomarkersintracerebral hemorrhagemachine learningprediction modelradiomics

Autor:innen und Institutionen

  • Department of Stroke and Cardiovascular Disease Next Generation Medical Research National Cerebral and Cardiovascular Center Osaka Japan.
  • Graduate School of Engineering Mie University Tsu Mie Japan.
  • Graduate School of Engineering University of Hyogo Kobe Hyogo Japan.
  • Department of Neurosurgery, Graduate School of Medical Sciences Kyushu University Fukuoka Japan.
  • Department of Preventive Medicine and Epidemiology National Cerebral and Cardiovascular Center Osaka Japan.
  • Center of Stroke and Cardiovascular Disease Informatics National Cerebral and Cardiovascular Center Hospital Osaka Japan.

ORCID-Profile: Shogo Watanabe, Nice Ren, Yukihiro Imaoka, Kento Morita, Syoji Kobashi, Nobutaka Mukae, Koichi Arimura, Kunihiro Nishimura, Koji Iihara

Zitieren

APA

Watanabe, S., Ren, N., Imaoka, Y., Morita, K., Kobashi, S., Mukae, N., Arimura, K., Nishimura, K., Iihara, K., & J‐ASPECT study collaborators (2026). Clinically Applicable Machine Learning Approach to Predict Intracerebral Hematoma Expansion. Journal of the American Heart Association. https://doi.org/10.1161/jaha.125.042387

Vancouver

Watanabe S, Ren N, Imaoka Y, Morita K, Kobashi S, Mukae N, et al. Clinically Applicable Machine Learning Approach to Predict Intracerebral Hematoma Expansion. Journal of the American Heart Association. 2026. doi:10.1161/jaha.125.042387

BibTeX
@article{Watanabe2026,
  author = {Watanabe, Shogo and Ren, Nice and Imaoka, Yukihiro and Morita, Kento and Kobashi, Syoji and Mukae, Nobutaka and Arimura, Koichi and Nishimura, Kunihiro and Iihara, Koji and J‐ASPECT study collaborators, J‐ASPECT study collaborators},
  title = {Clinically Applicable Machine Learning Approach to Predict Intracerebral Hematoma Expansion},
  journal = {Journal of the American Heart Association},
  year = {2026},
  doi = {10.1161/jaha.125.042387}
}
Kostenlos starten →