Computational medication regimen for Parkinson’s disease using reinforcement learning

Abstract Our objective is to derive a sequential decision-making rule on the combination of medications to minimize motor symptoms using reinforcement learning (RL). Using an observational longitudinal cohort of Parkinson’s disease patients, the Parkinson’s Progression Markers Initiative database, w...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yejin Kim, Jessika Suescun, Mya C. Schiess, Xiaoqian Jiang
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/31c5e5c270414017a3711587b00d9e9a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:31c5e5c270414017a3711587b00d9e9a
record_format	dspace
spelling	oai:doaj.org-article:31c5e5c270414017a3711587b00d9e9a2021-12-02T16:55:46ZComputational medication regimen for Parkinson’s disease using reinforcement learning10.1038/s41598-021-88619-42045-2322https://doaj.org/article/31c5e5c270414017a3711587b00d9e9a2021-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-88619-4https://doaj.org/toc/2045-2322Abstract Our objective is to derive a sequential decision-making rule on the combination of medications to minimize motor symptoms using reinforcement learning (RL). Using an observational longitudinal cohort of Parkinson’s disease patients, the Parkinson’s Progression Markers Initiative database, we derived clinically relevant disease states and an optimal combination of medications for each of them by using policy iteration of the Markov decision process (MDP). We focused on 8 combinations of medications, i.e., Levodopa, a dopamine agonist, and other PD medications, as possible actions and motor symptom severity, based on the Unified Parkinson Disease Rating Scale (UPDRS) section III, as reward/penalty of decision. We analyzed a total of 5077 visits from 431 PD patients with 55.5 months follow-up. We excluded patients without UPDRS III scores or medication records. We derived a medication regimen that is comparable to a clinician’s decision. The RL model achieved a lower level of motor symptom severity scores than what clinicians did, whereas the clinicians’ medication rules were more consistent than the RL model. The RL model followed the clinician’s medication rules in most cases but also suggested some changes, which leads to the difference in lowering symptoms severity. This is the first study to investigate RL to improve the pharmacological approach of PD patients. Our results contribute to the development of an interactive machine-physician ecosystem that relies on evidence-based medicine and can potentially enhance PD management.Yejin KimJessika SuescunMya C. SchiessXiaoqian JiangNature 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 Yejin Kim Jessika Suescun Mya C. Schiess Xiaoqian Jiang Computational medication regimen for Parkinson’s disease using reinforcement learning
description	Abstract Our objective is to derive a sequential decision-making rule on the combination of medications to minimize motor symptoms using reinforcement learning (RL). Using an observational longitudinal cohort of Parkinson’s disease patients, the Parkinson’s Progression Markers Initiative database, we derived clinically relevant disease states and an optimal combination of medications for each of them by using policy iteration of the Markov decision process (MDP). We focused on 8 combinations of medications, i.e., Levodopa, a dopamine agonist, and other PD medications, as possible actions and motor symptom severity, based on the Unified Parkinson Disease Rating Scale (UPDRS) section III, as reward/penalty of decision. We analyzed a total of 5077 visits from 431 PD patients with 55.5 months follow-up. We excluded patients without UPDRS III scores or medication records. We derived a medication regimen that is comparable to a clinician’s decision. The RL model achieved a lower level of motor symptom severity scores than what clinicians did, whereas the clinicians’ medication rules were more consistent than the RL model. The RL model followed the clinician’s medication rules in most cases but also suggested some changes, which leads to the difference in lowering symptoms severity. This is the first study to investigate RL to improve the pharmacological approach of PD patients. Our results contribute to the development of an interactive machine-physician ecosystem that relies on evidence-based medicine and can potentially enhance PD management.
format	article
author	Yejin Kim Jessika Suescun Mya C. Schiess Xiaoqian Jiang
author_facet	Yejin Kim Jessika Suescun Mya C. Schiess Xiaoqian Jiang
author_sort	Yejin Kim
title	Computational medication regimen for Parkinson’s disease using reinforcement learning
title_short	Computational medication regimen for Parkinson’s disease using reinforcement learning
title_full	Computational medication regimen for Parkinson’s disease using reinforcement learning
title_fullStr	Computational medication regimen for Parkinson’s disease using reinforcement learning
title_full_unstemmed	Computational medication regimen for Parkinson’s disease using reinforcement learning
title_sort	computational medication regimen for parkinson’s disease using reinforcement learning
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/31c5e5c270414017a3711587b00d9e9a
work_keys_str_mv	AT yejinkim computationalmedicationregimenforparkinsonsdiseaseusingreinforcementlearning AT jessikasuescun computationalmedicationregimenforparkinsonsdiseaseusingreinforcementlearning AT myacschiess computationalmedicationregimenforparkinsonsdiseaseusingreinforcementlearning AT xiaoqianjiang computationalmedicationregimenforparkinsonsdiseaseusingreinforcementlearning
_version_	1718382792012726272

Computational medication regimen for Parkinson’s disease using reinforcement learning

Ejemplares similares