collaborators

6 papers

cs.AI2026

When Clean Signals Are Not Enough: Detecting Structural Ambiguity for Safe Wearable Stress Classification

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

Wearable stress classifiers can achieve strong average performance while failing completely for a particular individual. On WESAD, a Random Forest reaches 93.0% mean accuracy yet y…

cs.LG2026

PerCaM-Health: Personalized Dynamic Causal Graphs for Healthcare Reasoning

Elahe Khatibi, Ziyu Wang, Saba A. Farahani +4

Personalized healthcare decisions require reasoning about how physiological and behavioral variables influence an individual patient over time. Existing temporal causal discovery m…

cs.AI2026

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 +1

Large language models (LLMs) can produce clinically fluent recommendations for type 2 diabetes while failing to satisfy guideline constraints or explicitly justify lifestyle-relate…

cs.LG2026

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

Saba A. Farahani, Elahe Khatibi, Manoj Vishwanath +2

Objective sleep assessment relies on polysomnography (PSG), yet clinical impact is often better reflected in patient-reported outcomes (PROs) such as sleepiness and fatigue. Existi…

cs.CL2026

Personal Care Utility: Health as Everyday Infrastructure

Mahyar Abbasian, Elahe Khatibi, Saba A. Farahani +5

Healthcare is essential, expert, and episodic by design - built around the roughly one hour per year a person spends with a clinician. The 8,759 hours outside clinical settings, wh…

stat.AP2026

Event-Aligned Analysis of Multi-Rater Pain Assessments Using Continuous Wearable Physiology

Saba A. Farahani, Elahe Khatibi, Thomas D. Hughes +3

Pain is assessed differently by patients, nurses, and clinicians, yet most computational approaches assume a single ground-truth label - effectively ignoring who is doing the ratin…