The neural interfaces lab headed by Prof. Izhar Bar-Gad targets the research of bidirectional interaction between computerized systems and the central nervous system. The long-term goal of the lab is to use this interaction to provide a deeper understanding of the pathophysiology of neural disorders and to create the electrophysiological basis for the treatment of their symptoms. The research utilizes a comprehensive approach which combines broad usage of animal models for the different diseases, electrophysiological recordings from human subjects undergoing neurosurgery and computational models.
The current focus of the lab is shedding light on the neurophysiology of motor and behavioral disorders associated with basal ganglia malfunction such as Parkinson's disease, Obsessive Compulsive Disorder (OCD), Tourette Syndrome and the amendment of their symptoms using electrical or magnetic modulation. This goal combines basic and clinical research, which on one hand unravels the information processing pathways of the cortico-basal ganglia loop and on the other hand attempts a direct intervention for improving the severe motor and behavioral disabilities associated with the aforementioned disorders.
Current projects
Ongoing project
NabuPD
AI-Augmented Treatment of Parkinson's Disease Patients
NabuPD is an active clinical pilot being developed with Hadassah Medical Center to address gaps created by infrequent clinic visits and retrospective reporting. It uses a familiar messaging interface and a multi-agent backend to collect and interpret symptom and medication information shared in conversation.
The system is designed to turn routine messages into longitudinal clinical context, route concerns to specialized agents, schedule follow-ups, and give clinicians concise summaries and red alerts. Its design emphasizes identity anonymization before clinical processing, protocol-constrained reasoning, clinician oversight, and guardrails that validate responses and escalate urgent cases. Current research directions include latent-state analysis, longitudinal memory, and multimodal interaction data.
Read the full NabuPD poster (PDF)Ongoing project
LoCoPD
A Framework for Longitudinal Conversational Modeling in Parkinson's Disease
LoCoPD is a Parkinson's disease-grounded framework for developing and evaluating conversational agents that follow a patient across multiple sessions. It represents a stable baseline profile and persona alongside a dynamic patient state that can change over days, weeks, and months, allowing generated conversations to reflect reported symptoms as well as partially observed changes.
The project targets three reusable research components: a dynamic longitudinal conversation generator, a curated frozen evaluation dataset, and state-and-memory benchmarks. Together, these are intended to test whether companion agents can track, recall, and reason over evolving patient context, while the frozen dataset lets different systems be evaluated on identical transcripts.
Read the full LoCoPD poster (PDF)