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. 8 - Room B 101
DTSTART;TZID=Europe/Stockholm:20260629T133000
DTEND;TZID=Europe/Stockholm:20260629T153000
UID:submissions.pasc-conference.org_PASC26_sess110@linklings.com
SUMMARY:MS1G - Advancing Medical AI: Challenges for Developing AI-Driven I
 n-Silico Clinical Trials for Accelerating Translational Medicine
DESCRIPTION:Organizer(s): John Garcia-Henao (Balgrist University Hospital)
 , and Carlos Barrios Hernandez (Universidad Industrial de Santander, LIG/I
 NRIA - CITI Laboratory)\n\nArtificial intelligence (AI) has achieved major
  success in medicine, particularly in diagnostic imaging, pathology classi
 fication, and clinical report generation, accelerating research translatio
 n and improving care. However, most deployed systems remain task-specific,
  lack biomedical reasoning, and generalize poorly across data modalities a
 nd clinical settings. The Advancing Medical AI minisymposium explores how 
 emerging approaches, especially large multimodal models (LMMs), can enable
  AI-driven in-silico clinical trials (ISCTs) that better connect research 
 innovation with clinical application. Recent LMMs integrate medical images
 , text, and structured data to support diagnosis, segmentation, and report
 ing, enabling the simulation of biological and clinical processes and adva
 ncing virtual patient modeling. Key challenges remain in explainability, c
 omputational efficiency, privacy protection, and integration with hospital
  infrastructure, highlighting the need for transparent data governance and
  verifiable systems. In parallel, ISCTs are gaining momentum as computer-b
 ased experiments that model disease progression and therapy response in vi
 rtual patient cohorts. Built on digital twins-dynamic computational models
  continuously updated with clinical data, ISCTs promise lower costs, faste
 r development, and improved safety. Despite their potential, barriers such
  as data heterogeneity, limited interpretability, validation gaps, regulat
 ory constraints, and infrastructure demands persist.\n\nHPC Infrastructure
  for Multimodal Medical AI: Lessons from Bridges-2 and Neocortex\n\nLarge 
 multimodal models (LMMs) are rapidly transforming medical AI by enabling i
 ntegrated analysis across imaging, clinical text, structured health record
 s, and biomedical data. These models are reshaping how researchers approac
 h diagnostics, clinical decision support, and biomedical discovery by co..
 .\n\n\nPaola Buitrago (Pittsburgh Supercomputing Center)\n----------------
 -----\nDigital Twins Meet the HPC Continuum: Distributed Systems Challenge
 s for Scalable and Privacy-Aware In-Silico Medicine\n\nThe convergence of 
 AI and computational modeling is redefining scientific workflows, moving f
 rom centralized HPC platforms toward a distributed, heterogeneous computin
 g continuum. In healthcare, this evolution is exemplified by medical digit
 al twins, which integrate multimodal patient data, simulati...\n\n\nFrédér
 ic Le Mouël (University of Lyon, INSA Lyon; CITI Laboratory)\n------------
 ---------\nA Hospital-Integrated Digital Twin Ecosystem for Translational 
 Musculoskeletal AI\n\nArtificial intelligence is rapidly transforming musc
 uloskeletal (MSK) medicine through advances in multimodal imaging, segment
 ation foundation models, and clinical data integration. However, translati
 ng these systems from research into clinical practice remains limited by f
 ragmented infrastructures,...\n\n\nJohn Garcia-Henao (Balgrist University 
 Hospital)\n---------------------\nCarbon-Aware Compression Evaluation for 
 Sustainable Medical Image Classification\n\nDeep learning models for medic
 al imaging often require substantial computational resources, resulting in
  high energy consumption and carbon emissions that limit deployment in res
 ource-constrained clinical environments. We propose a carbon-aware evaluat
 ion framework for assessing deep learning compre...\n\n\nCarlos Barrios He
 rnandez (Universidad Industrial de Santander, LIG/INRIA - CITI Laboratory)
 \n\nDomain: Engineering, Life Sciences, Computational Methods and Applied 
 Mathematics\n\nSession Chairs: John Anderson Garcia Henao (University of B
 ern, ARTORG Center for Biomedical Engineering Research) and Carlos Barrios
  Hernandez (Universidad Industrial de Santander, LIG/INRIA - CITI Laborato
 ry)
END:VEVENT
END:VCALENDAR