BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251016T135143Z
LOCATION:Grand C/D North
DTSTART;TZID=America/Chicago:20251015T150000
DTEND;TZID=America/Chicago:20251015T152000
UID:HFESAM_ASPIRE 2025_sess192_LECT686@linklings.com
SUMMARY:Evaluating Large Language Models for Clinical Heuristic Extraction
  Under Increasing Data Noise
DESCRIPTION:Alina Hyk and Joseph Slade (Oregon State University)\n\nThis s
 tudy evaluates the ability of large language models (LLMs) to extract clin
 ically relevant heuristics from increasingly noisy medical data, supportin
 g their integration into decision support systems. We compare GPT-3.5, GPT
 -4o, and a custom o1 model across three experimental settings of escalatin
 g complexity: (1) identifying key symptom-lab combinations in low-noise sy
 nthetic cases, (2) recovering multi-step decision protocols with embedded 
 logic noise, and (3) extracting reasoning from highly noisy, unstructured 
 clinical notes. Each model is assessed for accuracy, conciseness, and resi
 lience to misleading features using a standardized prompt framework across
  10 diagnostic scenarios per experiment. Quantitative metrics—such as feat
 ure precision, step completeness, and confounding error rates—are analyzed
  using ANOVA and post-hoc comparisons. Preliminary hypotheses suggest that
  GPT-4o and o1 will outperform GPT-3.5, particularly under high-noise cond
 itions. Our findings aim to clarify the strengths and limitations of curre
 nt LLMs in extracting interpretable, actionable medical rules, a necessary
  step toward transparent, trustworthy AI deployment in clinical workflows.
  This work informs future strategies to reduce AI hallucinations, enhance 
 model interpretability, and build clinician confidence in AI-assisted deci
 sion-making. Ultimately, it contributes to the development of safer, more 
 explainable AI systems for healthcare.\n\nTrack: Health Care\n\nSession Ch
 air: YIFAN LI (University of Michigan)\n\n
END:VEVENT
END:VCALENDAR