Innovation
Data Science Programs
Data Science Scholar Program
The use of advanced data science techniques for research and practice improvement in neurosurgery continues to expand. Obtaining training in basic and advanced data science requires both mentorship and financial support, and the CNS Scholarship in Data Science provides both on an individual basis as we seek to create a cadre of neurosurgeons with expertise in this subject.
Sponsored by ATEC
Goals & Objectives
- Give a small group of future neurosurgeons’ expertise in the application of advanced data science techniques to the field of neurosurgery
- Provide those future leaders a platform within the CNS to build additional educational content and technology broadly applicable to the entire CNS membership
- Improve the quality of data science research presented at the CNS Annual Meeting and published in Neurosurgery, aiming to remain at the forefront of this field
The application period for the 2026–2027 scholarship is currently closed.
CNS Scholarship in Data Science
Computational techniques are poised to revolutionize healthcare. CNS is an integral part of the movement! Apply for our Data Science Scholarship, sponsored by ATEC.
Program Description
The program will be overseen by a mentor and the CNS Data Science and AI Committee, and once the scholar is selected and a research mentor is chosen, that person will join as the final member of the committee. The Scholarship will run through the academic year July 2026–June 2027, during which time the scholar will complete approved coursework, meet physically and remotely with his/her mentor, attend scientific meetings, and complete a research project.
After completion of the scholarship, the expectation is that this work will be submitted for presentation at the 2027 CNS Annual Meeting and a manuscript based on this work will be submitted to Neurosurgery. During the scholarship year, the scholar will join the CNS Data Science Committee to help with broader aspects of data science education for the entire membership and he/she will continue to serve on this committee for at least 1 year after completion of the scholarship.
Application Process
The application opens April 15, 2026. Applicants should be neurosurgical residents in good standing with residency program located in the United States who have support to spend 5-10 hrs/week on this project during the upcoming academic year. The committee will review applications and choose a CNS Data Science Scholar for a term which will begin July 15, 2026. During their term, the committee will work with the selected scholar to identify a research mentor who will join as the final member of this mentorship committee. Together, this group will help the scholar craft his/her curriculum and research questions based on prior experience and career goals. Financial support of up to $15,000 will be available to support coursework, technical materials, and travel for research meetings and conferences.
Rationale
The use of advanced data science techniques for research and practice improvement in neurosurgery is in its infancy. Most neurosurgeons are unfamiliar with topics like Machine Learning, Deep Learning, and Artificial Intelligence (AI). However, these computational techniques are poised to revolutionize healthcare. Currently there are limited formal training opportunities available to neurosurgeons interested in gaining expertise in data science. Specialty-naïve courses do exist, but are often difficult to undertake within the confines of the neurosurgical workload. Additionally, neurosurgeons engaged in such coursework lack mentors within the specialty to help guide their scholarship, and coursework can seem distant from neurosurgical care.
Obtaining training in basic and advanced data science requires both mentorship and financial support, and the CNS Scholarship in Data Science will provide both on an individual basis as we seek to create a cadre of neurosurgeons with expertise in this subject. This training program will benefit both the individual neurosurgeons who take part in the program, as well as the field as a whole as these future leaders work through the CNS to shape the ways in which data science will be integrated into neurosurgical research and practice.
The use of advanced data science techniques for research and practice improvement in neurosurgery is in its infancy. Most neurosurgeons are unfamiliar with topics like Machine Learning, Deep Learning, and Artificial Intelligence (AI). However, these computational techniques are poised to revolutionize healthcare. Currently there are limited formal training opportunities available to neurosurgeons interested in gaining expertise in data science. Specialty-naïve courses do exist, but are often difficult to undertake within the confines of the neurosurgical workload. Additionally, neurosurgeons engaged in such coursework lack mentors within the specialty to help guide their scholarship, and coursework can seem distant from neurosurgical care.
Obtaining training in basic and advanced data science requires both mentorship and financial support, and the CNS Scholarship in Data Science will provide both on an individual basis as we seek to create a cadre of neurosurgeons with expertise in this subject. This training program will benefit both the individual neurosurgeons who take part in the program, as well as the field as a whole as these future leaders work through the CNS to shape the ways in which data science will be integrated into neurosurgical research and practice.
Funding: Sponsored by ATEC.
Data Science Scholar Program Awardees
Andrew Abumoussa, MD MSc
University of North Carolina at Chapel Hill
Dr. Abumoussa is currently studying how to apply machine learning and computer vision techniques to create a global motion-artifact reduction algorithm for Digital Subtraction Angiography. In his main project, multiple angiograms with motion artifact will be coupled with pre-angiographic 3D scans to attempt a global alignment and reconstruction. In the first phase, angiograms were registered – frame by frame – to the appropriate x-ray projection through a prior scan and in the second phase, the angiogram will be digitally reconstructed and resampled to provide eradication of all motion. Dr. Abumoussa will also complete multiple professional courses for AI as well as work towards achieving certification as a Google Tensor Flow Engineer.
Daniel Sexton, MD
Duke University
Dr. Sexton used machine learning techniques to complete two projects using electrophysiological (EEG) data. For his main project, he collected and analyzed intracranial EEG data from patients with medication refractory epilepsy. He was able to use a novel interpretable technique developed at Duke to identify network components involved in the period following seizures. For his other project, he used EEG data from a mouse model of traumatic brain injury to determine injury severity. Both projects were accepted for poster presentations at this the CNS Annual Meeting with manuscripts in preparation. Dr. Sexton also completed two Stanford Professional classes for AI specialization and submitted a review article to Neurosurgical Focus on resting state connectivity.
Matthew Pease, MD
Fellow in Neurosurgical Oncology, Memorial Sloan Kettering
Dr. Pease used machine learning techniques to complete two projects related to imaging analysis during his time as the CNS data science fellow. For his main project, he led a multi-institutional, radiomics project where he successfully differentiated between solitary primary CNS lymphoma, glioblastoma, and metastatic disease based on pre-operative MRI. His model, built with nearly 1000 patients, achieved an AUC of 0.95, was accepted for an oral presentation at CNS 2021, and the manuscript is under review. Dr. Pease also completed a project using deep learning to prognose long- term outcomes in severe TBI based on admission clinical information and CT head scans. This project served as the basis for an application for an R01 and was published in Radiology.
Eric Karl Oermann, MD
NYU Langone Health, New York
We’re Here to Help