Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Application of Sparse Autoencoders to Enhance Mechanistic Interpretability of Large Language Models in Medicine.

JMIR AI·2026

Same author

A protocol for developing screening criteria for degenerative cervical myelopathy: AO Spine Myelopathy.org RECODE-DCM.

Spinal cord·2026

Same author

Radiological analysis correlated with neurological outcomes following resection of myxopapillary ependymoma: patient series.

Journal of neurosurgery. Case lessons·2026

Same author

Clinical Outcomes and Future Directions of Endoscopic Cervical Spine Surgery: A Systematic Review With Narrative Insights.

Global spine journal·2026

Same author

Validity of a Smartphone App to Objectively Monitor Performance Outcomes in Degenerative Cervical Myelopathy: Preliminary Findings From a Longitudinal Observational Study.

JMIR neurotechnology·2025

Same author

Inpatient Outcomes in Geriatric Complete Cervical Spinal Cord Injury: Associations Between Surgical Management and Reduced Mortality Despite Increased Morbidity.

Global spine journal·2025

Search research articles

Related Experiment Video

Updated: May 27, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Machine Learning-Driven Prognostication in Traumatic Subdural Hematoma: Development of a Predictive Web Application.

Mert Karabacak¹, Konstantinos Margetis¹

¹Department of Neurosurgery, Mount Sinai Health System, New York, New York, USA.

Neurosurgery Practice

|February 17, 2025

Summary

Machine learning models effectively predict in-hospital outcomes for acute traumatic subdural hematoma (atSDH) patients. A developed web application integrates these models for potential clinical use.

Keywords:

Artificial intelligence Machine learning Outcome prediction Subdural hematoma Traumatic brain injury Web application

More Related Videos

Systems Analysis of the Neuroinflammatory and Hemodynamic Response to Traumatic Brain Injury

Systems Analysis of the Neuroinflammatory and Hemodynamic Response to Traumatic Brain Injury

Published on: May 27, 2022

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Related Experiment Videos

Last Updated: May 27, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Systems Analysis of the Neuroinflammatory and Hemodynamic Response to Traumatic Brain Injury

Systems Analysis of the Neuroinflammatory and Hemodynamic Response to Traumatic Brain Injury

Published on: May 27, 2022

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Area of Science:

Medical Informatics
Machine Learning in Medicine
Trauma Surgery

Background:

Acute traumatic subdural hematoma (atSDH) is a critical condition with significant in-hospital morbidity and mortality.
Predicting outcomes in atSDH patients is crucial for timely intervention and resource allocation.

Purpose of the Study:

To develop and validate machine learning (ML) models for predicting unfavorable in-hospital outcomes in atSDH patients.
To create an accessible web application for deploying these predictive ML models.

Main Methods:

Utilized data from the American College of Surgeons Trauma Quality Program database for patients with atSDH.
Employed five ML algorithms (TabPFN, TabNET, XGBoost, LightGBM, Random Forest) with hyperparameter tuning.
Assessed in-hospital mortality, nonhome discharges, prolonged length of stay (LOS), ICU-LOS, and major complications.

Main Results:

TabPFN demonstrated the highest predictive performance for mortality (AUROC 0.934) and major complications.
LightGBM excelled in predicting nonhome discharges, prolonged LOS, and ICU-LOS.
The top-performing models were integrated into a web application for outcome prediction.

Conclusions:

Machine learning tools show significant promise in predicting diverse outcomes for atSDH patients.
The developed web application offers a practical platform for integrating these ML models into clinical workflows.