Utilizing machine learning to improve clinical trial design for acute respiratory distress syndrome

Abstract Heterogeneous patient populations, complex pharmacology and low recruitment rates in the Intensive Care Unit (ICU) have led to the failure of many clinical trials. Recently, machine learning (ML) emerged as a new technology to process and identify big data relationships, enabling a new era...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	E. Schwager, K. Jansson, A. Rahman, S. Schiffer, Y. Chang, G. Boverman, B. Gross, M. Xu-Wilson, P. Boehme, H. Truebel, J. J. Frassica
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Computer applications to medicine. Medical informatics R858-859.7
Acceso en línea:	https://doaj.org/article/539b553a776342559af5a398b474ad15
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:539b553a776342559af5a398b474ad15
record_format	dspace
spelling	oai:doaj.org-article:539b553a776342559af5a398b474ad152021-12-02T17:19:10ZUtilizing machine learning to improve clinical trial design for acute respiratory distress syndrome10.1038/s41746-021-00505-52398-6352https://doaj.org/article/539b553a776342559af5a398b474ad152021-09-01T00:00:00Zhttps://doi.org/10.1038/s41746-021-00505-5https://doaj.org/toc/2398-6352Abstract Heterogeneous patient populations, complex pharmacology and low recruitment rates in the Intensive Care Unit (ICU) have led to the failure of many clinical trials. Recently, machine learning (ML) emerged as a new technology to process and identify big data relationships, enabling a new era in clinical trial design. In this study, we designed a ML model for predictively stratifying acute respiratory distress syndrome (ARDS) patients, ultimately reducing the required number of patients by increasing statistical power through cohort homogeneity. From the Philips eICU Research Institute (eRI) database, no less than 51,555 ARDS patients were extracted. We defined three subpopulations by outcome: (1) rapid death, (2) spontaneous recovery, and (3) long-stay patients. A retrospective univariate analysis identified highly predictive variables for each outcome. All 220 variables were used to determine the most accurate and generalizable model to predict long-stay patients. Multiclass gradient boosting was identified as the best-performing ML model. Whereas alterations in pH, bicarbonate or lactate proved to be strong predictors for rapid death in the univariate analysis, only the multivariate ML model was able to reliably differentiate the disease course of the long-stay outcome population (AUC of 0.77). We demonstrate the feasibility of prospective patient stratification using ML algorithms in the by far largest ARDS cohort reported to date. Our algorithm can identify patients with sufficiently long ARDS episodes to allow time for patients to respond to therapy, increasing statistical power. Further, early enrollment alerts may increase recruitment rate.E. SchwagerK. JanssonA. RahmanS. SchifferY. ChangG. BovermanB. GrossM. Xu-WilsonP. BoehmeH. TruebelJ. J. FrassicaNature PortfolioarticleComputer applications to medicine. Medical informaticsR858-859.7ENnpj Digital Medicine, Vol 4, Iss 1, Pp 1-9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer applications to medicine. Medical informatics R858-859.7
spellingShingle	Computer applications to medicine. Medical informatics R858-859.7 E. Schwager K. Jansson A. Rahman S. Schiffer Y. Chang G. Boverman B. Gross M. Xu-Wilson P. Boehme H. Truebel J. J. Frassica Utilizing machine learning to improve clinical trial design for acute respiratory distress syndrome
description	Abstract Heterogeneous patient populations, complex pharmacology and low recruitment rates in the Intensive Care Unit (ICU) have led to the failure of many clinical trials. Recently, machine learning (ML) emerged as a new technology to process and identify big data relationships, enabling a new era in clinical trial design. In this study, we designed a ML model for predictively stratifying acute respiratory distress syndrome (ARDS) patients, ultimately reducing the required number of patients by increasing statistical power through cohort homogeneity. From the Philips eICU Research Institute (eRI) database, no less than 51,555 ARDS patients were extracted. We defined three subpopulations by outcome: (1) rapid death, (2) spontaneous recovery, and (3) long-stay patients. A retrospective univariate analysis identified highly predictive variables for each outcome. All 220 variables were used to determine the most accurate and generalizable model to predict long-stay patients. Multiclass gradient boosting was identified as the best-performing ML model. Whereas alterations in pH, bicarbonate or lactate proved to be strong predictors for rapid death in the univariate analysis, only the multivariate ML model was able to reliably differentiate the disease course of the long-stay outcome population (AUC of 0.77). We demonstrate the feasibility of prospective patient stratification using ML algorithms in the by far largest ARDS cohort reported to date. Our algorithm can identify patients with sufficiently long ARDS episodes to allow time for patients to respond to therapy, increasing statistical power. Further, early enrollment alerts may increase recruitment rate.
format	article
author	E. Schwager K. Jansson A. Rahman S. Schiffer Y. Chang G. Boverman B. Gross M. Xu-Wilson P. Boehme H. Truebel J. J. Frassica
author_facet	E. Schwager K. Jansson A. Rahman S. Schiffer Y. Chang G. Boverman B. Gross M. Xu-Wilson P. Boehme H. Truebel J. J. Frassica
author_sort	E. Schwager
title	Utilizing machine learning to improve clinical trial design for acute respiratory distress syndrome
title_short	Utilizing machine learning to improve clinical trial design for acute respiratory distress syndrome
title_full	Utilizing machine learning to improve clinical trial design for acute respiratory distress syndrome
title_fullStr	Utilizing machine learning to improve clinical trial design for acute respiratory distress syndrome
title_full_unstemmed	Utilizing machine learning to improve clinical trial design for acute respiratory distress syndrome
title_sort	utilizing machine learning to improve clinical trial design for acute respiratory distress syndrome
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/539b553a776342559af5a398b474ad15
work_keys_str_mv	AT eschwager utilizingmachinelearningtoimproveclinicaltrialdesignforacuterespiratorydistresssyndrome AT kjansson utilizingmachinelearningtoimproveclinicaltrialdesignforacuterespiratorydistresssyndrome AT arahman utilizingmachinelearningtoimproveclinicaltrialdesignforacuterespiratorydistresssyndrome AT sschiffer utilizingmachinelearningtoimproveclinicaltrialdesignforacuterespiratorydistresssyndrome AT ychang utilizingmachinelearningtoimproveclinicaltrialdesignforacuterespiratorydistresssyndrome AT gboverman utilizingmachinelearningtoimproveclinicaltrialdesignforacuterespiratorydistresssyndrome AT bgross utilizingmachinelearningtoimproveclinicaltrialdesignforacuterespiratorydistresssyndrome AT mxuwilson utilizingmachinelearningtoimproveclinicaltrialdesignforacuterespiratorydistresssyndrome AT pboehme utilizingmachinelearningtoimproveclinicaltrialdesignforacuterespiratorydistresssyndrome AT htruebel utilizingmachinelearningtoimproveclinicaltrialdesignforacuterespiratorydistresssyndrome AT jjfrassica utilizingmachinelearningtoimproveclinicaltrialdesignforacuterespiratorydistresssyndrome
_version_	1718381084837675008

Utilizing machine learning to improve clinical trial design for acute respiratory distress syndrome

Ejemplares similares