BEGIN:VCALENDAR VERSION:2.0 X-WR-CALNAME:EventsCalendar PRODID:-//hacksw/handcal//NONSGML v1.0//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/New_York LAST-MODIFIED:20240422T053451Z TZURL:https://www.tzurl.org/zoneinfo-outlook/America/New_York X-LIC-LOCATION:America/New_York BEGIN:DAYLIGHT TZNAME:EDT TZOFFSETFROM:-0500 TZOFFSETTO:-0400 DTSTART:19700308T020000 RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU END:DAYLIGHT BEGIN:STANDARD TZNAME:EST TZOFFSETFROM:-0400 TZOFFSETTO:-0500 DTSTART:19701101T020000 RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU END:STANDARD END:VTIMEZONE BEGIN:VEVENT CATEGORIES:Academic Affairs,Charlton College of Business,College of Arts an d Sciences,College of Engineering,Lectures and Seminars DESCRIPTION:Title: From Multiple Testing to Machine Learning: Ranking Adver se Events Using LambdaMART Multiplicity adjustment is essential in pharmac eutical research due to the simultaneous testing of multiple hypotheses ac ross endpoints, treatment groups, and safety outcomes. Without appropriate control, the risk of inflated Type I error may lead to false conclusions regarding drug efficacy and safety. This presentation reviews key multipli city adjustment methods, including Hochberg, and gatekeeping procedures fo r controlling the family-wise error rate, as well as False Discovery Rate (FDR) approaches such as the Benjamini–Hochberg procedure. Adverse event (AE) analysis is a critical component of clinical trial safety evaluation , traditionally relying on descriptive statistics and multiplicity-adjuste d hypothesis testing procedures. While methods such as the Benjamini–Hoc hberg procedure control the false discovery rate, they are not inherently designed to prioritize events based on clinical relevance or overall impor tance. As the volume and complexity of safety data continue to grow, there is an increasing need for advanced methodologies that can effectively ran k adverse events at the population level. In this presentation, we propose the use of LambdaMART, a gradient boosting–based learning-to-rank algor ithm, to systematically prioritize adverse events in clinical trial data. LambdaMART directly optimizes ranking metrics and can produce a clinically meaningful ordering of events.\nEvent page: https://www.umassd.edu/events /cms/data-science-seminar-series---talk-by-dr-thakur-director-of-biostatis tics--frontage-lab.php X-ALT-DESC;FMTTYPE=text/html:

Title: From Multiple Testing to Machine Learning: Ranking Adverse Events Using LambdaMART

Multipl icity adjustment is essential in pharmaceutical research due to the simult aneous testing of multiple hypotheses across endpoints\, treatment groups\ , and safety outcomes. Without appropriate control\, the risk of inflated Type I error may lead to false conclusions regarding drug efficacy and saf ety.

This presentation reviews key multiplicity adjustment methods \, including Hochberg\, and gatekeeping procedures for controlling the fam ily-wise error rate\, as well as False Discovery Rate (FDR) approaches suc h as the Benjamini–Hochberg procedure.

Adverse event (AE) analys is is a critical component of clinical trial safety evaluation\, tradition ally relying on descriptive statistics and multiplicity-adjusted hypothesi s testing procedures. While methods such as the Benjamini–Hochberg proce dure control the false discovery rate\, they are not inherently designed t o prioritize events based on clinical relevance or overall importance. As the volume and complexity of safety data continue to grow\, there is an in creasing need for advanced methodologies that can effectively rank adverse events at the population level.

In this presentation\, we propose the use of LambdaMART\, a gradient boosting–based learning-to-rank algo rithm\, to systematically prioritize adverse events in clinical trial data . LambdaMART directly optimizes ranking metrics and can produce a clinical ly meaningful ordering of events.

Event page: https://www.umassd.edu/events/cms/ data-science-seminar-series---talk-by-dr-thakur-director-of-biostatistics- -frontage-lab.php

DTSTAMP:20260519T025243 DTSTART;TZID=America/New_York:20260408T143000 DTEND;TZID=America/New_York:20260408T143000 LOCATION:Textile 105A SUMMARY;LANGUAGE=en-us:Data Science Seminar Series - Talk by Dr. Thakur (Di rector of Biostatistics @ Frontage Lab) UID:84f78f1e14718e5befe61359d09d8b88@www.umassd.edu END:VEVENT END:VCALENDAR