Artificial Intelligence Monitoring of Neurological Status From Patient Videos in the Neuroscience Intensive Care Unit
We show that AI pose estimation can provide minimally invasive, continuous, and clinically relevant neuromonitoring in critically ill patients. Neurological conditions account for the highest global disease burden and AI pose estimation may be a low-cost, explainable, and scalable AI solution to address this pressing need for neuro-telemetry.
Authors
- Madeline Fields (ORCID: https://orcid.org/0000-0003-0661-4153)
- R Feng
- Christopher P. Kellner (ORCID: https://orcid.org/0000-0003-4604-8205)
- B Rapoport
- Neha Dangayach (ORCID: https://orcid.org/0000-0002-6485-350X)
- Eric E. Schadt (ORCID: https://orcid.org/0000-0002-7892-8808)
- Raj Shrivastava (ORCID: https://orcid.org/0000-0001-6894-5666)
- Chi Le (ORCID: https://orcid.org/0000-0001-9686-4206)
- Benjamin S. Glicksberg
- Florian Richter
- Alec Gleason
- Felix Richter
Institutions
- Albert Einstein College of Medicine (US)
- Program for Appropriate Technology in Health (US)
- Children's Hospital of Philadelphia (US)
- San Francisco Art Institute (US)
- Icahn School of Medicine at Mount Sinai (US)
Publication Details
- Journal
- Neurosurgery
- Published
- 2026-01-14
- DOI
- https://doi.org/10.1227/neu.0000000000003899
- Primary Topic
- EEG and Brain-Computer Interfaces
- Type
- article
- Field-Weighted Citation Impact
- 0.00