Accelerating Psychometric Screening Tests with Prior Information

Trevor Larsen, Gustavo Malkomes, Dennis Barbour

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations


Classical methods for psychometric function estimation either require excessive measurements or produce only a low-resolution approximation of the target psychometric function. In this paper, we propose solutions for rapid high-resolution approximation of the psychometric function of a patient given her or his prior exam. We develop a rapid screening algorithm for a change in the psychometric function estimation of a patient. We use Bayesian active model selection to perform an automated pure-tone audiometry test with the goal of quickly finding if the current estimation will be different from the previous one. We validate our methods using audiometric data from the National Institute for Occupational Safety and Health (niosh). Initial results indicate that with a few tones we can (i) detect if the patient’s audiometric function has changed between the two test sessions with high confidence, and (ii) learn high-resolution approximations of the target psychometric function.

Original languageEnglish
Title of host publicationExplainable AI in Healthcare and Medicine - Building a Culture of Transparency and Accountability
EditorsArash Shaban-Nejad, Martin Michalowski, David L. Buckeridge
PublisherSpringer Science and Business Media Deutschland GmbH
Number of pages7
ISBN (Print)9783030533519
StatePublished - 2021
EventAAAI International Workshop on Health Intelligence, W3PHIAI 2020 - New York City, United States
Duration: Feb 7 2020Feb 7 2020

Publication series

NameStudies in Computational Intelligence
ISSN (Print)1860-949X
ISSN (Electronic)1860-9503


ConferenceAAAI International Workshop on Health Intelligence, W3PHIAI 2020
Country/TerritoryUnited States
CityNew York City


Dive into the research topics of 'Accelerating Psychometric Screening Tests with Prior Information'. Together they form a unique fingerprint.

Cite this