Objective We sought to augment the presurgical workup of medically refractory temporal lobe epilepsy by creating a supervised machine learning technique that uses diffusion-weighted imaging to classify patient-specific seizure onset laterality and surgical outcome.
Methods 151 subjects were included in this analysis: 62 patients (aged 18–68 years, 36 women) and 89 healthy controls (aged 18–71 years, 47 women). We created a supervised machine learning technique that uses diffusion-weighted metrics to classify subject groups. Specifically, we sought to classify patients versus healthy controls, unilateral versus bilateral temporal lobe epilepsy, left versus right temporal lobe epilepsy and seizure-free versus not seizure-free surgical outcome. We then reduced the dimensionality of derived features with community detection for ease of interpretation.
Results We classified the subject groups in withheld testing data sets with a cross-fold average testing areas under the receiver operating characteristic curve of 0.745 for patients versus healthy controls, 1.000 for unilateral versus bilateral seizure onset, 0.662 for left versus right seizure onset, 0.800 for left-sided seizure-free vsersu not seizure-free surgical outcome and 0.775 for right-sided seizure-free versus not seizure-free surgical outcome.
Conclusions This technique classifies important clinical decisions in the presurgical workup of temporal lobe epilepsy by generating discerning white-matter features. We believe that this work augments existing network connectivity findings in the field by further elucidating important white-matter pathology in temporal lobe epilepsy. We hope that this work contributes to recent efforts aimed at using diffusion imaging as an augmentation to the presurgical workup of this devastating neurological disorder.
- epilepsy, surgery
- image analysis
Data availability statement
Data are available upon reasonable request.
Statistics from Altmetric.com
If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.
Twitter @SB_Narasimhan, @VickyLMorgan
Contributors All listed authors made significant contributions to this work. GWJ participated in data collection, data preprocessing, lead data analysis and manuscript preparation. LYC made significant contributions in machine learning methods development and manuscript preparation. SN, HFJG and KEW aided in data collection, preprocessing, data analysis and manuscript preparation. VLM lead data collection, aided in data analysis and manuscript preparation. DJE made significant contributions to data collection, data analysis, manuscript preparation, and serves as the guarantor.
Funding This work was supported by the following funding sources: NINDS R00-NS097618-05, NINDS R01-NS112252-02, NINDS R01-NS075270, NINDS R01-NS110130, NINDS R01-NS108445, NINDS F31-NS106735, F31NS120401 and NIH Training Grants: NIGMS T32-GM007347, NIBIB T32-EB021937 and NIBIB T32EB001628.
Competing interests None declared.
Provenance and peer review Not commissioned; externally peer reviewed.
Supplemental material This content has been supplied by the author(s). It has not been vetted by BMJ Publishing Group Limited (BMJ) and may not have been peer-reviewed. Any opinions or recommendations discussed are solely those of the author(s) and are not endorsed by BMJ. BMJ disclaims all liability and responsibility arising from any reliance placed on the content. Where the content includes any translated material, BMJ does not warrant the accuracy and reliability of the translations (including but not limited to local regulations, clinical guidelines, terminology, drug names and drug dosages), and is not responsible for any error and/or omissions arising from translation and adaptation or otherwise.