Machine Learning Prediction of Seizure Outcome with Presurgical Resting-State fMRI Data

Authors

Xiaosong He, Thomas Jefferson UniversityFollow
Dorian Pustina, Department of Neurology, Thomas Jefferson UniversityFollow
Michael R Sperling, Thomas Jefferson UniversityFollow
Ashwini Sharan, Thomas Jefferson UniversityFollow
Joseph I Tracy, Department of Neurology, Thomas Jefferson UniversityFollow

Files

Description

Rationale:

Developing a quantitative algorithm for predicting seizure outcome following anterior temporal lobectomy (ATL) in temporal lobe epilepsy (TLE) patient would constitute a significant advance for presurgical decision making. In this project, we tested the ability of topographic properties extracted from presurgical resting-state (rsfMRI) data to predict surgical outcome, using two separate maching learning classification methods (support vector machine, SVM, and random forest RF).

Publication Date

12-4-2016

Keywords

Machine Learning Prediction of Seizure Outcome with Presurgical Resting-State fMRI Data

Disciplines

Medicine and Health Sciences

Comments

Poster presented at 2016 Annual Meeting of American Epilepsy Society in Houston TX.

Recommended Citation

He, Xiaosong; Pustina, Dorian; Sperling, Michael R; Sharan, Ashwini; and Tracy, Joseph I, "Machine Learning Prediction of Seizure Outcome with Presurgical Resting-State fMRI Data" (2016). Department of Neurosurgery Posters. 7.
https://jdc.jefferson.edu/neurosurgeryposters/7