Publications

Papers & code

Selected work on knowledge-guided agents, causal discovery, and evidence verification. Full publication record on Google Scholar.

LLM health responseEvidence gatedeterministic checks against explicit requirementsKnowledgegraphEvidence metrequired evidence checkedEvidence missingresponse revisedBenchmark: 100 structured type 2 diabetes cases
Evidence verification · 2026

T2D-Bench: Evidence-Gated Evaluation of LLM Outputs for Type 2 Diabetes Using a Multi-Layer Clinical-Lifestyle Knowledge Graph

Saba A. Farahani, Hung Cao, Ramesh Jain, Amir M. Rahmani

A benchmark and evidence gate for checking required support in personalized health responses.

Patient health queryDetect missing patient contextAsk a targeted clarifying questionMissing context acquiredGrounded responsedownstream LLM uses acquired contextKnowledgegraph
Knowledge-guided agents · 2026 · Preprint

A knowledge-guided agentic framework for mitigating patient-context ambiguity in health queries

Mahyar Abbasian, Saba A. Farahani, Arshia Ilaty, Hung Cao, Ramesh Jain, Amir M. Rahmani

Targeted clarification acquires missing patient context before a downstream model answers.

Sleep & physiological signalsMESA and MrOS cohorts · 2,365 participantsPhysiology-guided causal discoveryInterpretable sleep-recovery frameworkbeyond the apnea–hypopnea index (AHI)
Causal & multimodal learning · 2026

Beyond AHI: An Interpretable Causal-Discovery-Guided Framework for Sleep Recovery in Connected Health

Saba A. Farahani, Elahe Khatibi, Manoj Vishwanath, Amir M. Rahmani, Hung Cao

Designed and implemented a physiology-guided causal-discovery pipeline, evaluated across MESA and MrOS cohorts totaling 2,365 participants.

Further research

More work

  • When Clean Signals Are Not Enough: Detecting Structural Ambiguity for Safe Wearable Stress Classification
  • Event-Aligned Analysis of Multi-Rater Pain Assessments Using Continuous Wearable Physiology
  • Personal Care Utility: Health as Everyday Infrastructure

Full record on Google Scholar

Get in touch

Building trustworthy AI for health? Let’s talk.

I’m interested in research roles in health AI, LLM agents, and wearable and clinical data.