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:20260605T154541Z
LOCATION:Bldg. 6 - Room 104
DTSTART;TZID=Europe/Stockholm:20260701T090000
DTEND;TZID=Europe/Stockholm:20260701T110000
UID:submissions.pasc-conference.org_PASC26_sess154@linklings.com
SUMMARY:MS4F - HPC and the Health Sciences: Co-Design for Trust, Robustnes
 s, and Communication
DESCRIPTION:Organizer(s): Justin M. Wozniak, Thomas Brettin (Argonne Natio
 nal Laboratory, University of Chicago), and Eric Stahlberg (MD Anderson)\n
 \nHPC-powered AI applications are increasingly accurate and robust, but ch
 allenges remain when translating these capabilities into real-world preven
 tion and treatment routines. Central to this issue is the notion of trust,
  which is essential to all stakeholders in the health care complex: patien
 ts, providers, management, and governance. Trustworthy AI systems use tran
 sparent reasoning processes, are explainable, accountable, robust, fair, h
 onest, privacy-preserving, and amenable to human goals. In the context of 
 health, all of these aspects are potential blockers to future adoption. In
  this minisymposium, we will bring in experts from AI model development, h
 ealth systems analysis, and the clinical translation of AI-integrated canc
 er treatments.\n\nCo-Designing Trustworthy Scientific Agents: From Closed-
 Loop Validation to Self-Improving Discovery\n\nThe Transformational AI Mod
 els Consortium (ModCon) is a foundational initiative of the Genesis Missio
 n, advancing the nation's scientific and technological resources to develo
 p and deploy AI models that revolutionize scientific discovery. In this ta
 lk, I'll discuss how we co-design trustworthy scien...\n\n\nNeeraj Kumar (
 Pacific Northwest National Laboratory)\n---------------------\nComputation
 al Prediction of Anti-Cancer Drug Response in Preclinical Cancer Models Us
 ing Deep Learning and High-Performance Computing\n\nCancer is a complex an
 d heterogeneous disease. Tumors of the same histological type can respond 
 differently to the same anti-cancer therapy. Therefore, accurate predictio
 n of anti-cancer drug response is of paramount importance for both patient
  treatment design and therapeutic development. We have d...\n\n\nYitan Zhu
 , Justin Wozniak, Alexander Partin, and Thomas Brettin (Argonne National L
 aboratory) and Rick Stevens (Argonne National Laboratory, The University o
 f Chicago)\n---------------------\nTrust and Transparency From Pipeline to
  Practice: Foundations for Robust Clinical AI\n\nDeployment of AI in clini
 cal environments demands more than computational capabilities, it requires
  systematic commitment to data integrity and a deliberate strategy for bui
 lding clinician trust. This talk examines two interdependent pillars of re
 sponsible clinical AI: the critical role of data in c...\n\n\nCaroline Chu
 ng (UT MD Anderson Cancer Center)\n---------------------\nToward Participa
 tory Co-Design in HPC-Powered Health Sciences\n\nEmerging HPC-powered AI s
 ystems for the health sciences must be trustworthy: they must be explainab
 le, accountable, robust, fair, honest, privacy-preserving, and amenable to
  human goals.  These attributes are currently difficult to achieve, as cur
 rent technologies often use opaque methods that are n...\n\n\nJustin Wozni
 ak (Argonne National Laboratory)\n\nDomain: Applied Social Sciences and Hu
 manities, Life Sciences, Computational Methods and Applied Mathematics\n\n
 Session Chairs: Justin M. Wozniak (Argonne National Laboratory, University
  of Chicago) and Thomas Brettin (Argonne National Laboratory, University o
 f Chicago)
END:VEVENT
END:VCALENDAR