RESEARCH SOFTWARE · ALON GORENSHTEIN, MD
Research projects in clinical AI, evidence synthesis, and neurology, developed by Alon Gorenshtein and collaborators.
Alon Gorenshtein and collaborators developed INSPIRE, an agent-guided research system for interpreting and reporting nerve conduction studies and electromyography.
Project details →LITERAS is a multi-agent biomedical literature retrieval and review framework developed by Alon Gorenshtein and colleagues using PubMed-based search and citation validation.
Project details →LitBench is a research benchmark by Alon Gorenshtein and colleagues for retrieval-grounded, multi-paper evidence synthesis in epilepsy.
Project details →Neuro-Copilot is a clinical AI research framework studied by Alon Gorenshtein and colleagues for neurological decision support in the emergency department.
Project details →Each project links its public code to the corresponding article or preprint. Repository documentation provides the requirements for reuse, including licenses, dependencies, and any separately controlled data access.
A multi-agent framework for biomedical literature review and citation retrieval. The public repository accompanies the 2025 paper in Computers in Biology and Medicine.
The paper evaluates reference retrieval and literature-review generation. Consult the publication for its comparison systems, evaluation design, and limitations.
Analysis code for the study of recovery and instability of bedside command-following, published in Neurocritical Care.
The repository describes the analysis pipeline and access requirements for the source ICU datasets. Raw patient data are not distributed in the repository.
A benchmark for retrieval-grounded, multi-paper evidence synthesis in epilepsy, with a public repository maintained by Goldenholz Lab.
The linked medRxiv preprint tests identifying source papers, retrieving supporting passages, combining evidence, and abstaining when evidence is absent. The work is a research benchmark.