Accelerating Psychometric Screening Tests with Prior Information

Accelerating Psychometric Screening Tests with Prior Information. Larsen, T., Malkomes, G., & Barbour, D. L. In Shaban-Nejad, A., Michalowski, M., & Buckeridge, D. L., editors, Explainable AI in Healthcare and Medicine: Building a Culture of Transparency and Accountability, of Studies in Computational Intelligence, pages 305–311. Springer International Publishing, Cham, 2021.

Paper doi abstract bibtex

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.

@incollection{larsen_accelerating_2021,
	address = {Cham},
	series = {Studies in {Computational} {Intelligence}},
	title = {Accelerating {Psychometric} {Screening} {Tests} with {Prior} {Information}},
	isbn = {978-3-030-53352-6},
	url = {https://doi.org/10.1007/978-3-030-53352-6_29},
	abstract = {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.},
	language = {en},
	urldate = {2020-11-11},
	booktitle = {Explainable {AI} in {Healthcare} and {Medicine}: {Building} a {Culture} of {Transparency} and {Accountability}},
	publisher = {Springer International Publishing},
	author = {Larsen, Trevor and Malkomes, Gustavo and {Barbour, D. L.}},
	editor = {Shaban-Nejad, Arash and Michalowski, Martin and Buckeridge, David L.},
	year = {2021},
	doi = {10.1007/978-3-030-53352-6_29},
	pages = {305--311},
}

Downloads: 0

{"_id":"gAjcTrZKttpf3rThH","bibbaseid":"larsen-malkomes-barbour-acceleratingpsychometricscreeningtestswithpriorinformation-2021","author_short":["Larsen, T.","Malkomes, G.","Barbour, D. L."],"bibdata":{"bibtype":"incollection","type":"incollection","address":"Cham","series":"Studies in Computational Intelligence","title":"Accelerating Psychometric Screening Tests with Prior Information","isbn":"978-3-030-53352-6","url":"https://doi.org/10.1007/978-3-030-53352-6_29","abstract":"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.","language":"en","urldate":"2020-11-11","booktitle":"Explainable AI in Healthcare and Medicine: Building a Culture of Transparency and Accountability","publisher":"Springer International Publishing","author":[{"propositions":[],"lastnames":["Larsen"],"firstnames":["Trevor"],"suffixes":[]},{"propositions":[],"lastnames":["Malkomes"],"firstnames":["Gustavo"],"suffixes":[]},{"firstnames":[],"propositions":[],"lastnames":["Barbour, D. L."],"suffixes":[]}],"editor":[{"propositions":[],"lastnames":["Shaban-Nejad"],"firstnames":["Arash"],"suffixes":[]},{"propositions":[],"lastnames":["Michalowski"],"firstnames":["Martin"],"suffixes":[]},{"propositions":[],"lastnames":["Buckeridge"],"firstnames":["David","L."],"suffixes":[]}],"year":"2021","doi":"10.1007/978-3-030-53352-6_29","pages":"305–311","bibtex":"@incollection{larsen_accelerating_2021,\n\taddress = {Cham},\n\tseries = {Studies in {Computational} {Intelligence}},\n\ttitle = {Accelerating {Psychometric} {Screening} {Tests} with {Prior} {Information}},\n\tisbn = {978-3-030-53352-6},\n\turl = {https://doi.org/10.1007/978-3-030-53352-6_29},\n\tabstract = {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.},\n\tlanguage = {en},\n\turldate = {2020-11-11},\n\tbooktitle = {Explainable {AI} in {Healthcare} and {Medicine}: {Building} a {Culture} of {Transparency} and {Accountability}},\n\tpublisher = {Springer International Publishing},\n\tauthor = {Larsen, Trevor and Malkomes, Gustavo and {Barbour, D. L.}},\n\teditor = {Shaban-Nejad, Arash and Michalowski, Martin and Buckeridge, David L.},\n\tyear = {2021},\n\tdoi = {10.1007/978-3-030-53352-6_29},\n\tpages = {305--311},\n}\n\n","author_short":["Larsen, T.","Malkomes, G.","Barbour, D. L."],"editor_short":["Shaban-Nejad, A.","Michalowski, M.","Buckeridge, D. L."],"key":"larsen_accelerating_2021","id":"larsen_accelerating_2021","bibbaseid":"larsen-malkomes-barbour-acceleratingpsychometricscreeningtestswithpriorinformation-2021","role":"author","urls":{"Paper":"https://doi.org/10.1007/978-3-030-53352-6_29"},"metadata":{"authorlinks":{}}},"bibtype":"incollection","biburl":"https://api.zotero.org/groups/2607247/items?key=t9TdC3rOErveu1tiJ6HpRRuh&format=bibtex&limit=100","dataSources":["Fo9Jzk7YWDoEzAMys"],"keywords":[],"search_terms":["accelerating","psychometric","screening","tests","prior","information","larsen","malkomes","barbour"],"title":"Accelerating Psychometric Screening Tests with Prior Information","year":2021}