Comparison of Machine Learning Methods to Predict Early Mortality After Evacuation of Chronic Subdural Hematoma.
The LR model demonstrated the best performance of discriminative ability, balanced accuracy, and recall, whereas DT modeling performed worst. Using an automated segmentation software, our models demonstrate an ability to identify patients at high risk of mortality after treatment for cSDH.
Authors
- Barnabas Obeng-Gyasi (ORCID: https://orcid.org/0000-0003-3346-1631)
- Matthew Pease (ORCID: https://orcid.org/0000-0001-6125-9858)
- David O. Okonkwo (ORCID: https://orcid.org/0000-0002-7444-2851)
- Jan Vargas (ORCID: https://orcid.org/0000-0001-7164-1479)
- Trenton A. Line (ORCID: https://orcid.org/0000-0003-3443-6964)
- Jamie Bradbury
- Gordon Mao (ORCID: https://orcid.org/0000-0003-3259-7481)
- Enyinna L. Nwachuku (ORCID: https://orcid.org/0000-0002-4945-3647)
- Anoop S. Chinthala (ORCID: https://orcid.org/0000-0002-6065-1177)
- Ryan Thomson Kellogg (ORCID: https://orcid.org/0000-0001-6491-5443)
- Aditya M. Mittal (ORCID: https://orcid.org/0000-0002-4346-4337)
Institutions
- Prisma Health (US)
- Cleveland Clinic (US)
- Proteogenomics Research Institute for Systems Medicine (US)
- University of Pittsburgh Medical Center (US)
- Neurological Surgery (US)
- Indiana University School of Medicine
- University of Virginia (US)
- Indiana University – Purdue University Indianapolis (US)
Publication Details
- Journal
- PubMed
- Published
- 2025-09-01
- DOI
- https://doi.org/10.1227/neuprac.0000000000000151
- Primary Topic
- Neurosurgical Procedures and Complications
- Type
- article
- Field-Weighted Citation Impact
- 0.00