BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Asia/Kolkata
BEGIN:STANDARD
DTSTART:19451014T230000
TZOFFSETFROM:+0630
TZOFFSETTO:+0530
TZNAME:IST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260721T105716Z
UID:7AAEAFED-8428-4EB3-B852-ED8202A800A8
DTSTART;TZID=Asia/Kolkata:20260717T190000
DTEND;TZID=Asia/Kolkata:20260717T200000
DESCRIPTION:The integration of Artificial Intelligence (AI) into healthcare
  systems promises transformative improvements in diagnostics\, treatment p
 lanning\, and patient monitoring. However\, the opacity of many machine le
 arning models raises concerns about safety\, accountability\, and trust. E
 xplainable AI (XAI) addresses these challenges by providing transparent re
 asoning behind predictions and decisions\, enabling clinicians to validate
  outcomes and patients to understand recommendations. By combining interpr
 etability techniques such as feature attribution\, rule extraction\, and v
 isualization\, XAI enhances confidence in AI‑driven healthcare solutions
 . Trustworthy systems further require adherence to ethical principles\, fa
 irness\, and regulatory compliance to ensure unbiased and reliable care. A
 pplications include clinical decision support\, personalized medicine\, an
 d predictive analytics\, where explainability fosters collaboration betwee
 n human expertise and machine intelligence. Ultimately\, XAI serves as a c
 ornerstone for building healthcare systems that are not only intelligent b
 ut also transparent\, ethical\, and aligned with patient‑centric values.
 \n\nSpeaker(s): Dr. Abhilash Pati\, \n\nVirtual: https://events.vtools.iee
 e.org/m/565762
LOCATION:Virtual: https://events.vtools.ieee.org/m/565762
ORGANIZER:amiya87@gmail.com
SEQUENCE:12
SUMMARY:Explainable AI for Trustworthy Healthcare Systems
URL;VALUE=URI:https://events.vtools.ieee.org/m/565762
X-ALT-DESC:Description: <br /><p>The integration of Artificial Intelligence
  (AI) into healthcare systems promises transformative improvements in diag
 nostics\, treatment planning\, and patient monitoring. However\, the opaci
 ty of many machine learning models raises concerns about safety\, accounta
 bility\, and trust. Explainable AI (XAI) addresses these challenges by pro
 viding transparent reasoning behind predictions and decisions\, enabling c
 linicians to validate outcomes and patients to understand recommendations.
  By combining interpretability techniques such as feature attribution\, ru
 le extraction\, and visualization\, XAI enhances confidence in AI‑driven
  healthcare solutions. Trustworthy systems further require adherence to et
 hical principles\, fairness\, and regulatory compliance to ensure unbiased
  and reliable care. Applications include clinical decision support\, perso
 nalized medicine\, and predictive analytics\, where explainability fosters
  collaboration between human expertise and machine intelligence. Ultimatel
 y\, XAI serves as a cornerstone for building healthcare systems that are n
 ot only intelligent but also transparent\, ethical\, and aligned with pati
 ent‑centric values.</p>
END:VEVENT
END:VCALENDAR