BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20241120T082409Z
LOCATION:HG F 26.5
DTSTART;TZID=Europe/Stockholm:20240604T113000
DTEND;TZID=Europe/Stockholm:20240604T120000
UID:submissions.pasc-conference.org_PASC24_sess162_msa117@linklings.com
SUMMARY:Image Based Precision Medicine Using Artificial Intelligence
DESCRIPTION:Minisymposium\n\nJudy Gichoya (Emory University)\n\nRecent stu
 dies have shown that both biologic and non-biologic disease-based characte
 ristics can be predicted from medical imaging. For instance, self-reported
  race, sex, and age can be predicted from chest X-rays and other imaging m
 odalities, as well as disease conditions, such as ICD code diagnoses. Addi
 tional research has indicated that disease risk, such as the risk of breas
 t cancer, can be predicted from medical imaging with better performance th
 an clinical and traditional scoring systems like the Tyrer-Cuzick and Gail
  breast cancer risk prediction. These models prove to be powerful even whe
 n they lack high precision labels from radiologists.   \n\nHowever, these 
 image models face challenges due to the inadequacy of existing explanatory
  techniques. Furthermore, given the known issue of shortcut learning causi
 ng bias, there is increased concern over the use of image-only models.\nCo
 nversely, if properly leveraged, image-only models can be successful, part
 icularly for opportunistic screenings and mining information for populatio
 n health, even if their initial intent was not for subsequent use.\n\nI wi
 ll discuss image-only models and their methodologies that have demonstrate
 d superior performance over non-traditional imaging-only models, as well a
 s the challenges and limitations of scaling imaging for precision medicine
 , specifically shortcut learning and limited explainability techniques.\n\
 nDomain: Applied Social Sciences and Humanities, Life Sciences, Computatio
 nal Methods and Applied Mathematics\n\nSession Chair: Destinee Morrow (Law
 rence Berkeley National Laboratory)
END:VEVENT
END:VCALENDAR