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:20250422T064947Z UID:121478E0-F98F-481E-8479-C0E8690BAFCB DTSTART;TZID=Asia/Kolkata:20250409T100000 DTEND;TZID=Asia/Kolkata:20250409T110000 DESCRIPTION:Brain stimulation shows significant potential in treating neuro logical disorders\, but the challenge lies in personalizing these therapie s effectively. Traditionally\, identifying the optimal stimulation paramet ers\, such as amplitude\, frequency\, and pulse width\, requires extensive trial-and-error testing\, which is both time-consuming and costly. To str eamline this process\, we developed an active learning framework that effi ciently identifies the most effective relationships between stimulation pa rameters and brain responses\, reducing the need for numerous experiments. We conducted three types of validation for our framework: in silico exper iments using synthetic data from a Parkinson’s disease model\, in silico tests with real data from a non-human primate model\, and in vivo tests t hrough real-time optogenetic stimulation in rats. In each scenario\, our a ctive learning models demonstrated superior performance over traditional r andom sampling methods\, achieving significantly lower errors in predictin g brain responses. This innovative approach enhances the efficiency and ef ficacy of research and clinical applications in brain stimulation\, offeri ng a more cost-effective pathway to developing personalized therapies for neurological disorders.\n\nSpeaker(s): Dr Mohammed Sendi\n\nVirtual: https ://events.vtools.ieee.org/m/480226 LOCATION:Virtual: https://events.vtools.ieee.org/m/480226 ORGANIZER:uttaranb417@gmail.com SEQUENCE:12 SUMMARY:Refining Brain Stimulation Therapies: An Active Learning Approach t o Personalization URL;VALUE=URI:https://events.vtools.ieee.org/m/480226 X-ALT-DESC:Description: <br /><p><span style="font-size: 14.6667px\;">Brain stimulation shows significant potential in treating neurological disorder s\, but the challenge lies in personalizing these therapies effectively. T raditionally\, identifying the optimal stimulation parameters\, such as am plitude\, frequency\, and pulse width\, requires extensive trial-and-error testing\, which is both time-consuming and costly. To streamline this pro cess\, we developed an active learning framework that efficiently identifi es the most effective relationships between stimulation parameters and bra in responses\, reducing the need for numerous experiments. We conducted th ree types of validation for our framework: in silico experiments using syn thetic data from a Parkinson&rsquo\;s disease model\, in silico tests with real data from a non-human primate model\, and in vivo tests through real -time optogenetic stimulation in rats. In each scenario\, our active learn ing models demonstrated superior performance over traditional random sampl ing methods\, achieving significantly lower errors in predicting brain res ponses. This innovative approach enhances the efficiency and efficacy of r esearch and clinical applications in brain stimulation\, offering a more c ost-effective pathway to developing personalized therapies for neurologica l disorders.</span></p> END:VEVENT END:VCALENDAR