Robust diagnostic classification via Q-learning

Abstract Machine learning (ML) models have demonstrated the power of utilizing clinical instruments to provide tools for domain experts in gaining additional insights toward complex clinical diagnoses. In this context these tools desire two additional properties: interpretability, being able to audi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Victor Ardulov, Victor R. Martinez, Krishna Somandepalli, Shuting Zheng, Emma Salzman, Catherine Lord, Somer Bishop, Shrikanth Narayanan
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/adb330cbb8564a788d5c113e60e8c783
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:adb330cbb8564a788d5c113e60e8c783
record_format	dspace
spelling	oai:doaj.org-article:adb330cbb8564a788d5c113e60e8c7832021-12-02T17:50:42ZRobust diagnostic classification via Q-learning10.1038/s41598-021-90000-42045-2322https://doaj.org/article/adb330cbb8564a788d5c113e60e8c7832021-06-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-90000-4https://doaj.org/toc/2045-2322Abstract Machine learning (ML) models have demonstrated the power of utilizing clinical instruments to provide tools for domain experts in gaining additional insights toward complex clinical diagnoses. In this context these tools desire two additional properties: interpretability, being able to audit and understand the decision function, and robustness, being able to assign the correct label in spite of missing or noisy inputs. This work formulates diagnostic classification as a decision-making process and utilizes Q-learning to build classifiers that meet the aforementioned desired criteria. As an exemplary task, we simulate the process of differentiating Autism Spectrum Disorder from Attention Deficit-Hyperactivity Disorder in verbal school aged children. This application highlights how reinforcement learning frameworks can be utilized to train more robust classifiers by jointly learning to maximize diagnostic accuracy while minimizing the amount of information required.Victor ArdulovVictor R. MartinezKrishna SomandepalliShuting ZhengEmma SalzmanCatherine LordSomer BishopShrikanth NarayananNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Victor Ardulov Victor R. Martinez Krishna Somandepalli Shuting Zheng Emma Salzman Catherine Lord Somer Bishop Shrikanth Narayanan Robust diagnostic classification via Q-learning
description	Abstract Machine learning (ML) models have demonstrated the power of utilizing clinical instruments to provide tools for domain experts in gaining additional insights toward complex clinical diagnoses. In this context these tools desire two additional properties: interpretability, being able to audit and understand the decision function, and robustness, being able to assign the correct label in spite of missing or noisy inputs. This work formulates diagnostic classification as a decision-making process and utilizes Q-learning to build classifiers that meet the aforementioned desired criteria. As an exemplary task, we simulate the process of differentiating Autism Spectrum Disorder from Attention Deficit-Hyperactivity Disorder in verbal school aged children. This application highlights how reinforcement learning frameworks can be utilized to train more robust classifiers by jointly learning to maximize diagnostic accuracy while minimizing the amount of information required.
format	article
author	Victor Ardulov Victor R. Martinez Krishna Somandepalli Shuting Zheng Emma Salzman Catherine Lord Somer Bishop Shrikanth Narayanan
author_facet	Victor Ardulov Victor R. Martinez Krishna Somandepalli Shuting Zheng Emma Salzman Catherine Lord Somer Bishop Shrikanth Narayanan
author_sort	Victor Ardulov
title	Robust diagnostic classification via Q-learning
title_short	Robust diagnostic classification via Q-learning
title_full	Robust diagnostic classification via Q-learning
title_fullStr	Robust diagnostic classification via Q-learning
title_full_unstemmed	Robust diagnostic classification via Q-learning
title_sort	robust diagnostic classification via q-learning
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/adb330cbb8564a788d5c113e60e8c783
work_keys_str_mv	AT victorardulov robustdiagnosticclassificationviaqlearning AT victorrmartinez robustdiagnosticclassificationviaqlearning AT krishnasomandepalli robustdiagnosticclassificationviaqlearning AT shutingzheng robustdiagnosticclassificationviaqlearning AT emmasalzman robustdiagnosticclassificationviaqlearning AT catherinelord robustdiagnosticclassificationviaqlearning AT somerbishop robustdiagnosticclassificationviaqlearning AT shrikanthnarayanan robustdiagnosticclassificationviaqlearning
_version_	1718379305446146048

Robust diagnostic classification via Q-learning

Ejemplares similares