BEGIN:VCALENDAR
PRODID:-//github.com/ical-org/ical.net//NONSGML ical.net 4.0//EN
VERSION:2.0
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:STANDARD
DTSTART:20241103T020000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20250309T020000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
DESCRIPTION:NOTE: You are invited to attend in person\, but may also atten
 d via Zoom. SPEAKER : Pratik Shah\, PhD\, Assistant Professor\, Departmen
 ts of Pathology\, Biomedical Engineering\, Electrical Engineering & Compu
 ter Science\, University of California\, Irvine TITLE : “Validating gener
 ative deep learning with uncertainty estimations for health informatics" 
 ABSTRACT: The rapid advancement of deep learning and artificial intellige
 nce (AI) presents transformative opportunities for health informatics\, y
 et clinical deployment remains constrained by data scarcity and the need 
 for rigorous validation frameworks for measuring public health impact. Th
 is seminar details methodological innovations in two key areas: deep lear
 ning for translational biomedical imaging and bioinformatics\, and decisi
 on support for real-world time-varying clinical data. We explore 'virtual
  staining and sequencing' frameworks based on generative AI methods that 
 can infer molecular and genomic information directly from standard medica
 l images\, bridging the gap between low-cost imaging and high-cost genomi
 cs. We then examine the development of Reinforcement Learning (RL) agents
  designed to optimize treatment regimens using electronic medical records
  and clinical trial data\, ensuring algorithmic recommendations are stati
 stically and clinically valid. The discussion will conclude with a focus 
 on biostatistical standards\, uncertainty estimations\, and regulatory sc
 ience perspectives for validating and approving complex\, AI-enabled medi
 cal software and devices to ensure their safe and effective integration i
 nto biomedical education and clinical informatics workflows. YSPH values 
 inclusion and access for all participants. If you have questions about ac
 cessibility or would like to request an accommodation\, please contact ch
 armila.fernandes@yale.edu by March 25\, 2026.\n\nSpeaker:\nPratik Shah\, 
 PhD\n\nAdmission:\nFree\n\nDetails URL:\nhttps://medicine.yale.edu/event/
 ysph-biostatistics-seminar-tba-3-31-26/\n
DTEND;TZID=America/New_York:20260331T113000
DTSTAMP:20260409T150525Z
DTSTART;TZID=America/New_York:20260331T103000
GEO:41.303509;-72.931937
LOCATION:LEPH 101\, 60 College Street\, New Haven\, CT\, United States
SEQUENCE:0
STATUS:Confirmed
SUMMARY:YSPH Biostatistics-Health Informatics Seminar: “Validating Generat
 ive Deep Learning with Uncertainty Estimations for Health Informatics"
UID:8447baf4-61b1-4232-acc9-5801351596d8
END:VEVENT
END:VCALENDAR