BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/New_York BEGIN:DAYLIGHT DTSTART:20250309T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20251102T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20251110T140437Z UID:E39AF281-9919-48EA-87F7-0A0496F52103 DTSTART;TZID=America/New_York:20251007T120000 DTEND;TZID=America/New_York:20251107T130000 DESCRIPTION:​This event offers a detailed\, clinically oriented examinati on of the integration of artificial intelligence (AI) and machine learning (ML) into medical diagnostics and healthcare delivery. Designed as a prac tical resource for clinicians\, researchers\, and healthcare administrator s\, it systematically explores how AI technologies are being adopted\, whi le critically addressing the challenges and opportunities presented by the ir real-world implementation.\n\nA central focus of the event is its detai led exploration of the technical underpinnings of ML in medicine. It explo res model evaluation\, emphasizing the limitations of traditional metrics like accuracy\, the importance of robust validation\, and the need for com prehensive performance measures such as learning curves\, confusion matric es\, and external testing. Special attention is given to the evaluation of ML algorithms for image classification and to the selection of appropriat e models for specific diagnostic tasks.\n\nThe event also introduces a sta ndardized validation framework aligned with regulatory guidance\, includin g clinically oriented composite utility metrics and protocols for ongoing model monitoring. It critically examines the impact of feature selection a nd data leakage through case studies\, demonstrating how methodological pi tfalls can lead to misleading claims of performance.\n\nRecognizing the co mplexity of real-world deployment\, the event provides practical tools and checklists for clinicians to appraise AI solutions\, operational framewor ks for safe integration\, and guidance on governance and continuous learni ng.\n\nBy combining technical rigor with clinical relevance\, the event em powers healthcare professionals to critically evaluate\, safely integrate\ , and effectively leverage AI tools for improved patient outcomes. It serv es as an essential resource for navigating the evolving landscape of AI-as sisted medical diagnostics\, supporting responsible and equitable innovati on in healthcare.\n\n​This event is part of #AIWeekNY by Pulse NYC — a community-led festival celebrating innovation across the AI ecosystem. Mo re at https://pulse.nyc/ai-week/\n\nSpeaker(s): Dr. Toma\n\nVirtual: https ://events.vtools.ieee.org/m/503554 LOCATION:Virtual: https://events.vtools.ieee.org/m/503554 ORGANIZER:mtoma@nyit.edu SEQUENCE:12 SUMMARY:AI-Assisted Medical Diagnostics URL;VALUE=URI:https://events.vtools.ieee.org/m/503554 X-ALT-DESC:Description: <br /><p class="">​This event offers a detailed\, clinically oriented examination of the integration of artificial intellig ence (AI) and machine learning (ML) into medical diagnostics and healthcar e delivery. Designed as a practical resource for clinicians\, researchers\ , and healthcare administrators\, it systematically explores how AI techno logies are being adopted\, while critically addressing the challenges and opportunities presented by their real-world implementation.<br><br>A centr al focus of the event is its detailed exploration of the technical underpi nnings of ML in medicine. It explores model evaluation\, emphasizing the l imitations of traditional metrics like accuracy\, the importance of robust validation\, and the need for comprehensive performance measures such as learning curves\, confusion matrices\, and external testing. Special atten tion is given to the evaluation of ML algorithms for image classification and to the selection of appropriate models for specific diagnostic tasks.< br><br>The event also introduces a standardized validation framework align ed with regulatory guidance\, including clinically oriented composite util ity metrics and protocols for ongoing model monitoring. It critically exam ines the impact of feature selection and data leakage through case studies \, demonstrating how methodological pitfalls can lead to misleading claims of performance.<br><br>Recognizing the complexity of real-world deploymen t\, the event provides practical tools and checklists for clinicians to ap praise AI solutions\, operational frameworks for safe integration\, and gu idance on governance and continuous learning.<br><br>By combining technica l rigor with clinical relevance\, the event empowers healthcare profession als to critically evaluate\, safely integrate\, and effectively leverage A I tools for improved patient outcomes. It serves as an essential resource for navigating the evolving landscape of AI-assisted medical diagnostics\, supporting responsible and equitable innovation in healthcare.</p>\n<p cl ass="">​<em>This event is part of #AIWeekNY by Pulse NYC &mdash\; a comm unity-led festival celebrating innovation across the AI ecosystem. More at &nbsp\;</em><em><a href="https://pulse.nyc/ai-week/" target="_blank" rel=" nofollow noopener">https://pulse.nyc/ai-week/</a></em></p> END:VEVENT END:VCALENDAR