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:Abstract: Real-world data (RWD) studies and target trial emula
 tion (TTE) are becoming increasingly important for comparative effectiven
 ess\, safety evaluation\, and regulatory-grade real-world evidence. Yet i
 n practice\, turning a clinical question into a credible TTE still requir
 es substantial manual effort: investigators must define cohorts\, compose
  statistical analysis plans (SAPs)\, align time zero and follow-up\, exec
 ute analyses\, and document design decisions in a form that is both revie
 w-ready and interpretable. Recent agentic systems automate parts of this 
 workflow\, but they often remain fragmented and rarely treat debiasing—es
 pecially negative-control-based adjustment for residual and potentially u
 nmeasured confounding—as a core design objective.We present MATTE (Multi-
 agent Target Trial Emulation)\, an end-to-end agentic TTE framework that 
 links hypothesis interpretation\, protocol and SAP generation\, cohort co
 nstruction\, effect estimation\, negative control outcome (NCO)-guided de
 biasing\, and FDA-aware compliance auditing within a single traceable wor
 kflow. By integrating study design\, bias assessment\, and compliance aud
 iting into one human-reviewable pipeline\, MATTE aims to make RWD-based e
 vidence generation more scalable\, interpretable\, and audit-ready for tr
 anslational and regulatory use. This talk describes the current MATTE sys
 tem snapshot and its expected evaluation behavior while full benchmarking
  is ongoing. Howard Chan Tsai Hor\, PhD \, is a Postdoctoral Researcher i
 n the Department of Biostatistics\, Epidemiology and Informatics at the P
 erelman School of Medicine\, University of Pennsylvania\, working with Dr
 . Yong Chen. His research focuses on agentic AI for biomedical evidence g
 eneration\, real-world data analysis\, and target trial emulation using l
 arge-scale electronic health records. He develops methods that combine ca
 usal inference\, trustworthy machine learning\, negative control outcome 
 calibration\, and automated statistical analysis planning to support scal
 able\, interpretable\, and audit-ready real-world evidence workflows. How
 ard has authored more than 16 peer-reviewed papers at leading AI/ML venue
 s\, including the International Conference on Learning Representations (I
 CLR)\, and in journals including IEEE Transactions on Medical Imaging (TM
 I) and IEEE Transactions on Pattern Analysis and Machine Intelligence (TP
 AMI).\n\nSpeaker:\nHoward Chan\, PhD\n\nAdmission:\nFree\n\nFood:\n\n\nDe
 tails URL:\nhttps://medicine.yale.edu/event/nlpllm-interest-group-36/\n
DTEND;TZID=America/New_York:20260518T170000
DTSTAMP:20260514T233126Z
DTSTART;TZID=America/New_York:20260518T160000
LOCATION:Join our mailing list to receive Zoom Passcode: https://mailman.y
 ale.edu/mailman/listinfo/nlp-llm-ig\, URL: https://yale.zoom.us/j/9359994
 1969
SEQUENCE:0
STATUS:Confirmed
SUMMARY:🤖 AI Frontiers hosted by NLP/LLM Interest Group
UID:ce4ea51d-5fc1-4ab2-a4cf-7cdfd3873d6e
END:VEVENT
END:VCALENDAR