BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260422T000605Z
LOCATION:DEF Concourse
DTSTART;TZID=America/Denver:20231116T100000
DTEND;TZID=America/Denver:20231116T170000
UID:submissions.supercomputing.org_SC23_sess300_spostg130@linklings.com
SUMMARY:Utilizing Large Language Models for Disease Phenotyping in Obstruc
 tive Sleep Apnea
DESCRIPTION:Ifrah Khurram (San Juan Bautista School of Medicine, Lawrence 
 Berkeley National Laboratory (LBNL))\n\nObstructive sleep apnea (OSA) impa
 cts millions, linking to severe complications yet understanding its influe
 nce on comorbidities lags. Complications can be avoided by using expensive
  continuous positive airway pressure (CPAP) machines, but physicians canno
 t identify those at risk. Large language models (LLMs) have recently made 
 impressive advancements in sequence modeling, and clinical applications ar
 e quickly emerging. However, the medical relevance of pre-trained LLM late
 nt spaces remains uncertain.\n\nThis study gauges 12 pre-trained clinical 
 LLMs, clustering OSA-related phenotypes and comorbidities (atrial fibrilla
 tion, coronary artery disease, heart failure, hypertension, stroke, type 2
  diabetes). Using 40 A100 GPUs on NERSC’s Perlmutter, document-level embed
 dings for 331,793 MIMIC-IV discharge reports were computed for each LLM. K
 -Means models were ranked by clustering entropy of phenotype classes, guid
 ing model selection. The top models successfully subset patients with simi
 lar histories and outcomes. This work will support ongoing OSA research by
  identifying phenotypes and assist physicians by informing CPAP allocation
 .\n\nRegistration Category: Tech Program Reg Pass, Exhibits Reg Pass\n\n
END:VEVENT
END:VCALENDAR