Deep learning survival model predicts outcome after intracerebral hemorrhage from initial CT scan
European Stroke Journal · 2025
DOI: 10.1177/23969873241260154 ↗Kurz gefasst
Fachartikel in der Zeitschrift European Stroke Journal, 2025. Verfasst von Yutong Chen und 10 weiteren Autor:innen. Beteiligte Einrichtung: Center for Genomic Medicine, Massachusetts General Hospital, Boston, MA, USA. Hauptthemen laut MEDLINE: Deep Learning, Cerebral Hemorrhage, Tomography, X-Ray Computed. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: American Heart Association-American Stroke Association, NINDS NIH HHS, NCATS NIH HHS.
Abstract (Originalsprache)
Background
Predicting functional impairment after intracerebral hemorrhage (ICH) provides valuable information for planning of patient care and rehabilitation strategies. Current prognostic tools are limited in making long term predictions and require multiple expert-defined inputs and interpretation that make their clinical implementation challenging. This study aimed to predict long term functional impairment of ICH patients from admission non-contrast CT scans, leveraging deep learning models in a survival analysis framework.
Methods
We used the admission non-contrast CT scans from 882 patients from the Massachusetts General Hospital ICH Study for training, hyperparameter optimization, and model selection, and 146 patients from the Yale New Haven ICH Study for external validation of a deep learning model predicting functional outcome. Disability (modified Rankin scale [mRS] > 2), severe disability (mRS > 4), and dependent living status were assessed via telephone interviews after 6, 12, and 24 months. The prediction methods were evaluated by the c-index and compared with ICH score and FUNC score.
Results
Using non-contrast CT, our deep learning model achieved higher prediction accuracy of post-ICH dependent living, disability, and severe disability by 6, 12, and 24 months (c-index 0.742 [95% CI –0.700 to 0.778], 0.712 [95% CI –0.674 to 0.752], 0.779 [95% CI –0.733 to 0.832] respectively) compared with the ICH score (c-index 0.673 [95% CI –0.662 to 0.688], 0.647 [95% CI –0.637 to 0.661] and 0.697 [95% CI –0.675 to 0.717]) and FUNC score (c-index 0.701 [95% CI– 0.698 to 0.723], 0.668 [95% CI –0.657 to 0.680] and 0.727 [95% CI –0.708 to 0.753]). In the external independent Yale-ICH cohort, similar performance metrics were obtained for disability and severe disability (c-index 0.725 [95% CI –0.673 to 0.781] and 0.747 [95% CI –0.676 to 0.807], respectively). Similar AUC of predicting each outcome at 6 months, 1 and 2 years after ICH was achieved compared with ICH score and FUNC score.
Conclusion
We developed a generalizable deep learning model to predict onset of dependent living and disability after ICH, which could help to guide treatment decisions, advise relatives in the acute setting, optimize rehabilitation strategies, and anticipate long-term care needs.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Center for Genomic Medicine, Massachusetts General Hospital, Boston, MA, USA.
- Broad Institute of Harvard and MIT, Cambridge, MA, USA.
- Henry and Allison McCance Center for Brain Health, Massachusetts General Hospital, Boston, MA, USA.
- Department of Neurology, Yale School of Medicine, New Haven, CT, USA.
- Yale Center for Brain and Mind Health, New Haven, CT, USA.
- Department of Neurology, University of Freiburg, Freiburg, Germany.
ORCID-Profile: Yutong Chen, Cyprien A Rivier, Ernst Mayerhofer
Förderung
- American Heart Association-American Stroke Association
- NINDS NIH HHS
- NCATS NIH HHS
- AHA
- Berta-Ottenstein-Program for Advanced Clinician Scientists
- MGH McCance Center for Brain Health
- AHA-Bugher
- NIH
Zitieren
APA
Chen, Y., Rivier, C. A., Mora, S. A., Torres Lopez, V., Payabvash, S., Sheth, K. N., Harloff, A., Falcone, G. J., Rosand, J., Mayerhofer, E., & Anderson, C. D. (2025). Deep learning survival model predicts outcome after intracerebral hemorrhage from initial CT scan. European Stroke Journal. https://doi.org/10.1177/23969873241260154
Vancouver
Chen Y, Rivier CA, Mora SA, Torres Lopez V, Payabvash S, Sheth KN, et al. Deep learning survival model predicts outcome after intracerebral hemorrhage from initial CT scan. European Stroke Journal. 2025. doi:10.1177/23969873241260154
BibTeX
@article{Chen2025,
author = {Chen, Yutong and Rivier, Cyprien A and Mora, Samantha A and Torres Lopez, Victor and Payabvash, Sam and Sheth, Kevin N and Harloff, Andreas and Falcone, Guido J and Rosand, Jonathan and Mayerhofer, Ernst and Anderson, Christopher D},
title = {Deep learning survival model predicts outcome after intracerebral hemorrhage from initial CT scan},
journal = {European Stroke Journal},
year = {2025},
doi = {10.1177/23969873241260154}
}
EUVIMED