BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
DTSTART:20260308T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20261101T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260615T185038Z
UID:6A4F985A-5F33-4392-9A20-D4855B58F664
DTSTART;TZID=America/New_York:20260708T120000
DTEND;TZID=America/New_York:20260708T130000
DESCRIPTION:[]\n\nIn the field of mental health\, the vast majority of meas
 urements are intrinsically "messy". This messiness stems from the difficul
 ty in measuring ground-truth phenomena which are inaccessible. This result
 s in off-target variations due to human interpretations\, difficult-to-cha
 racterize biases\, and widespread infrastructure inefficiencies. However\,
  rather than viewing these factors solely as a hindrance\, this talk explo
 res the distinct opportunities they present to improve research robustness
  in research and clinical care. Drawing on concrete examples across MRI\, 
 biometrics\, and clinical assessments\, this presentation highlights how r
 obust computational infrastructure can turn analytical variation into a to
 ol for improving the generalizability of brain-behavior models. It also de
 monstrates how engaging the broader data science community through open da
 ta initiatives and competitions can help solve complex challenges\, such a
 s accurately detecting sleep states from wrist-worn actigraphy data. Final
 ly\, the talk illustrates how leveraging open data\, software engineering\
 , and carefully constrained Artificial Intelligence tools can transform un
 structured clinical assessments into scalable\, accessible tools for publi
 c good. Ultimately\, this presentation outlines a principled framework for
  using software engineering and AI in mental health research and care in a
  way that can accelerate discovery and increase access without increasing 
 the risk of harm.\n\nZoom link\n[https://mcgill.zoom.us/j/4937377259](http
 s://mcgill.zoom.us/j/4937377259#success)\n\nRoom: 321\, Bldg: Duff Medical
  Building\, 3775 Rue University\, Montreal\, Quebec\, Canada\, Virtual: ht
 tps://events.vtools.ieee.org/m/561886
LOCATION:Room: 321\, Bldg: Duff Medical Building\, 3775 Rue University\, Mo
 ntreal\, Quebec\, Canada\, Virtual: https://events.vtools.ieee.org/m/56188
 6
ORGANIZER:milad.mokhtari@mail.mcgill.ca
SEQUENCE:4
SUMMARY:Messy measurements…and the opportunities they provide in mental h
 ealth
URL;VALUE=URI:https://events.vtools.ieee.org/m/561886
X-ALT-DESC:Description: <br /><p><img src="https://events.vtools.ieee.org/v
 tools_ui/media/display/052aa2d8-ceff-41c1-ba46-b0124e421c4c" alt="" width=
 "987" height="400"></p>\n<p style="text-align: justify\;">In the field of 
 mental health\, the vast majority of measurements are intrinsically "messy
 ". This messiness stems from the difficulty in measuring ground-truth phen
 omena which are inaccessible. This results in off-target variations due to
  human interpretations\, difficult-to-characterize biases\, and widespread
  infrastructure inefficiencies. However\, rather than viewing these factor
 s solely as a hindrance\, this talk explores the distinct opportunities th
 ey present to improve research robustness in research and clinical care. D
 rawing on concrete examples across MRI\, biometrics\, and clinical assessm
 ents\, this presentation highlights how robust computational infrastructur
 e can turn analytical variation into a tool for improving the generalizabi
 lity of brain-behavior models. It also demonstrates how engaging the broad
 er data science community through open data initiatives and competitions c
 an help solve complex challenges\, such as accurately detecting sleep stat
 es from wrist-worn actigraphy data. Finally\, the talk illustrates how lev
 eraging open data\, software engineering\, and carefully constrained Artif
 icial Intelligence tools can transform unstructured clinical assessments i
 nto scalable\, accessible tools for public good. Ultimately\, this present
 ation outlines a principled framework for using software engineering and A
 I in mental health research and care in a way that can accelerate discover
 y and increase access without increasing the risk of harm.</p>\n<p>Zoom li
 nk<br><a href="https://mcgill.zoom.us/j/4937377259#success">https://mcgill
 .zoom.us/j/4937377259</a></p>\n<p>&nbsp\;</p>
END:VEVENT
END:VCALENDAR