BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//compute-paris-2026//speaker//CLYAUD
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20251126T000000
TZNAME:CET
TZOFFSETFROM:+0100
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20260329T030000
RDATE:20270328T030000
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20261025T030000
RDATE:20271031T030000
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Supporting Reliable Clinical Prediction Through Interactive Open-S
 ource Tools - Justine Leclerc
DTSTART;TZID=Europe/Paris:20261126T151500
DTEND;TZID=Europe/Paris:20261126T154500
DTSTAMP:20260930T113503Z
UID:pretalx-compute-paris-2026-DECXTH@pretalx.com
DESCRIPTION:Clinical researchers increasingly rely on AI coding tools to d
 evelop prediction models\, as these tools can substantially accelerate dat
 a analysis. However\, they also introduce new challenges. While AI can gen
 erate thousands of lines of code within seconds\, thoroughly reviewing and
  validating such code is often infeasible for humans within a reasonable t
 imeframe. As a result\, prediction workflows may become overwhelming and u
 nnecessarily complex\, making it difficult to understand the original anal
 ytical intent.\n\nIn this talk\, we present an R Shiny application develop
 ed in collaboration with clinicians. The platform provides an interactive 
 and user-friendly environment for clinical prediction analyses without req
 uiring advanced programming skills. Users upload cleaned datasets\, explor
 e visualizations\, adjust analysis parameters\, and download results direc
 tly through the interface.\n\nThe application includes key analysis steps 
 such as missing value handling\, imputation\, model fitting\, prediction\,
  and visualization. Users can choose models from the ([parsnip](https://pa
 rsnip.tidymodels.org)) R ecosystem . The interface guides them toward suit
 able methodological choices depending on the data structure and study obje
 ctives. Predictive outputs come with uncertainty assessment through confor
 mal prediction methods. Those provide prediction intervals with statistica
 l coverage guarantees\, not only point predictions.\n\nThe talk includes a
  live demonstration on a clinical use case. The presentation is practical 
 and application-oriented\, with limited mathematical content.\n\nAttendees
  will discover how open-source and interactive tools can support transpare
 nt\, reproducible\, and uncertainty-aware prediction workflows in healthca
 re research. The project also encourages responsible AI use and helps clin
 icians adopt more reliable statistical practices.
LOCATION:Auditorium
URL:https://pretalx.com/compute-paris-2026/talk/DECXTH/
END:VEVENT
END:VCALENDAR