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:20211207T055411Z
LOCATION:223
DTSTART;TZID=America/Chicago:20211114T144500
DTEND;TZID=America/Chicago:20211114T150000
UID:submissions.supercomputing.org_SC21_sess434_ws_cafcws104@linklings.com
SUMMARY:Predicting Tumor Time to Recurrence from Free-Text Notes
DESCRIPTION:Workshop\n\nPredicting Tumor Time to Recurrence from Free-Text
  Notes\n\nNagaraj\n\nElectronic medical records contain a significant amou
 nt of unstructured patient information from free text, but crucial informa
 tion can be difficult to find within lengthy notes. Thus, we develop an au
 tomated tool that can detect mentions of tumor recurrence and progression 
 in clinical, radiology, and pathology notes to infer time to recurrence an
 d progression. This approach avoids the need for re-training models and is
  flexible enough to be applied to a variety of institutions and note types
 . \n\nWe tested this approach with a cohort of pediatric and adult brain t
 umor patients with 27,137 clinical, radiology, and pathology notes from St
 anford University Hospital, creating cumulative patient trajectory graphs 
 and fine-tuning models to predict time to recurrence. To assess initial ac
 curacy, we compared the patient trajectories to their diagnosis from the I
 CD-10 codes associated with the notes and found high accuracy from the wea
 k labeling pipeline.\n\nTag: Applications, Computational Science, Educatio
 n and Training and Outreach, HPC Community Collaboration, HPC Training and
  Education, Machine Learning and Artificial Intelligence, Performance, Wor
 kforce\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR