Use of a machine learning framework to predict substance use disorder treatment success
There are several methods for building prediction models. The wealth of currently available modeling techniques usually forces the researcher to judge, a priori, what will likely be the best method. Super learning (SL) is a methodology that facilitates this decision by combining all identified predi...
Guardado en:
Autor principal: | |
---|---|
Publicado: |
2017
|
Materias: | |
Acceso en línea: | https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_19326203_v12_n4_p_Acion http://hdl.handle.net/20.500.12110/paper_19326203_v12_n4_p_Acion |
Aporte de: |
id |
paper:paper_19326203_v12_n4_p_Acion |
---|---|
record_format |
dspace |
spelling |
paper:paper_19326203_v12_n4_p_Acion2023-06-08T16:30:39Z Use of a machine learning framework to predict substance use disorder treatment success Kelmansky, Diana M. adult algorithm area under the curve Article artificial neural network controlled study decision making drug dependence education employment status female Hispanic human length of stay machine learning major clinical study male methodology prediction receiver operating characteristic sensitivity analysis substance abuse super learning treatment outcome adolescent computer assisted diagnosis drug dependence factual database middle aged prognosis regression analysis socioeconomics young adult Adolescent Adult Area Under Curve Databases, Factual Diagnosis, Computer-Assisted Female Humans Length of Stay Machine Learning Male Middle Aged Neural Networks (Computer) Prognosis Regression Analysis ROC Curve Socioeconomic Factors Substance-Related Disorders Treatment Outcome Young Adult There are several methods for building prediction models. The wealth of currently available modeling techniques usually forces the researcher to judge, a priori, what will likely be the best method. Super learning (SL) is a methodology that facilitates this decision by combining all identified prediction algorithms pertinent for a particular prediction problem. SL generates a final model that is at least as good as any of the other models considered for predicting the outcome. The overarching aim of this work is to introduce SL to analysts and practitioners. This work compares the performance of logistic regression, penalized regression, random forests, deep learning neural networks, and SL to predict successful substance use disorders (SUD) treatment. A nationwide database including 99,013 SUD treatment patients was used. All algorithms were evaluated using the area under the receiver operating characteristic curve (AUC) in a test sample that was not included in the training sample used to fit the prediction models. AUC for the models ranged between 0.793 and 0.820. SL was superior to all but one of the algorithms compared. An explanation of SL steps is provided. SL is the first step in targeted learning, an analytic framework that yields double robust effect estimation and inference with fewer assumptions than the usual parametric methods. Different aspects of SL depending on the context, its function within the targeted learning framework, and the benefits of this methodology in the addiction field are discussed. © 2017 Acion et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Fil:Kelmansky, D. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. 2017 https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_19326203_v12_n4_p_Acion http://hdl.handle.net/20.500.12110/paper_19326203_v12_n4_p_Acion |
institution |
Universidad de Buenos Aires |
institution_str |
I-28 |
repository_str |
R-134 |
collection |
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) |
topic |
adult algorithm area under the curve Article artificial neural network controlled study decision making drug dependence education employment status female Hispanic human length of stay machine learning major clinical study male methodology prediction receiver operating characteristic sensitivity analysis substance abuse super learning treatment outcome adolescent computer assisted diagnosis drug dependence factual database middle aged prognosis regression analysis socioeconomics young adult Adolescent Adult Area Under Curve Databases, Factual Diagnosis, Computer-Assisted Female Humans Length of Stay Machine Learning Male Middle Aged Neural Networks (Computer) Prognosis Regression Analysis ROC Curve Socioeconomic Factors Substance-Related Disorders Treatment Outcome Young Adult |
spellingShingle |
adult algorithm area under the curve Article artificial neural network controlled study decision making drug dependence education employment status female Hispanic human length of stay machine learning major clinical study male methodology prediction receiver operating characteristic sensitivity analysis substance abuse super learning treatment outcome adolescent computer assisted diagnosis drug dependence factual database middle aged prognosis regression analysis socioeconomics young adult Adolescent Adult Area Under Curve Databases, Factual Diagnosis, Computer-Assisted Female Humans Length of Stay Machine Learning Male Middle Aged Neural Networks (Computer) Prognosis Regression Analysis ROC Curve Socioeconomic Factors Substance-Related Disorders Treatment Outcome Young Adult Kelmansky, Diana M. Use of a machine learning framework to predict substance use disorder treatment success |
topic_facet |
adult algorithm area under the curve Article artificial neural network controlled study decision making drug dependence education employment status female Hispanic human length of stay machine learning major clinical study male methodology prediction receiver operating characteristic sensitivity analysis substance abuse super learning treatment outcome adolescent computer assisted diagnosis drug dependence factual database middle aged prognosis regression analysis socioeconomics young adult Adolescent Adult Area Under Curve Databases, Factual Diagnosis, Computer-Assisted Female Humans Length of Stay Machine Learning Male Middle Aged Neural Networks (Computer) Prognosis Regression Analysis ROC Curve Socioeconomic Factors Substance-Related Disorders Treatment Outcome Young Adult |
description |
There are several methods for building prediction models. The wealth of currently available modeling techniques usually forces the researcher to judge, a priori, what will likely be the best method. Super learning (SL) is a methodology that facilitates this decision by combining all identified prediction algorithms pertinent for a particular prediction problem. SL generates a final model that is at least as good as any of the other models considered for predicting the outcome. The overarching aim of this work is to introduce SL to analysts and practitioners. This work compares the performance of logistic regression, penalized regression, random forests, deep learning neural networks, and SL to predict successful substance use disorders (SUD) treatment. A nationwide database including 99,013 SUD treatment patients was used. All algorithms were evaluated using the area under the receiver operating characteristic curve (AUC) in a test sample that was not included in the training sample used to fit the prediction models. AUC for the models ranged between 0.793 and 0.820. SL was superior to all but one of the algorithms compared. An explanation of SL steps is provided. SL is the first step in targeted learning, an analytic framework that yields double robust effect estimation and inference with fewer assumptions than the usual parametric methods. Different aspects of SL depending on the context, its function within the targeted learning framework, and the benefits of this methodology in the addiction field are discussed. © 2017 Acion et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
author |
Kelmansky, Diana M. |
author_facet |
Kelmansky, Diana M. |
author_sort |
Kelmansky, Diana M. |
title |
Use of a machine learning framework to predict substance use disorder treatment success |
title_short |
Use of a machine learning framework to predict substance use disorder treatment success |
title_full |
Use of a machine learning framework to predict substance use disorder treatment success |
title_fullStr |
Use of a machine learning framework to predict substance use disorder treatment success |
title_full_unstemmed |
Use of a machine learning framework to predict substance use disorder treatment success |
title_sort |
use of a machine learning framework to predict substance use disorder treatment success |
publishDate |
2017 |
url |
https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_19326203_v12_n4_p_Acion http://hdl.handle.net/20.500.12110/paper_19326203_v12_n4_p_Acion |
work_keys_str_mv |
AT kelmanskydianam useofamachinelearningframeworktopredictsubstanceusedisordertreatmentsuccess |
_version_ |
1768542665360539648 |