Dr. Bilal Naved, PhD, is a Faculty (Instructor) and Schmidt AI Fellow at the Icahn School of Medicine at Mount Sinai. He is an MD/PhD physician scientist trainee in the Northwestern Medical Scientist Training Program (MSTP) with a PhD in Biomedical Engineering and postdoctoral training focused on patient-facing AI agents for clinically intelligent triage and navigation. Over the past three years, he has led or co-led national scale observational analyses of self-triage adoption and performance, developed supervised and large language model-enabled Natural Language Processing (NLP) for symptom and intent classification, validated triage quality against clinician or gold standard outcomes, and quantified how inaccurate patient intent and avoidable visit load contribute to access and capacity constraints.
For his proposal, A Clinical Domain-Specific Language with Independent Expert Validation to Translate Evidence-Based Care Guidance into Patient-Facing Digital Triage Logic, his mentors will be Dr. Girish Nadkarni, MD, MPH; Dr. Robert Freeman, DNP, RN; and Dr. Nicholas Gavin, MD, MBA.
Dr. Naved’s team proposes a clinical domain-specific language (DSL) and language-model-assisted workflow that translates evidence-based care guidance into structured, clinician-reviewable triage logic; carries embedded literature citations so every rule is traceable to its evidence; and is validated by independent Mount Sinai clinicians who did not author the underlying content. The product of this proposal is a method, not a single clinical pathway; the DSL, the independent-reviewer workflow, and the LLM-assisted extraction pipeline together generate generalizable knowledge about converting clinical evidence into auditable, patient-facing logic.
His proposal aims to:
- Develop a clinician-reviewable, citation-linked domain-specific language for digital triage logic.
- Pilot a large language model-assisted extraction into the domain-specific language with independent clinical expert validation.
ConduITS is supported by NCATS of the NIH’s CTSA Program. Any use of CTSA-supported resources requires citation of grant number UL1TR004419 awarded to ISMMS in the acknowledgment section of every publication resulting from this support. Adherence to the NIH Public Access Policy is also required.
