Loading…

Insights from a machine learning model for predicting the hospital Length of Stay (LOS) at the time of admission

•A Cubist model for hospital Length of Stay (LOS) is proposed.•The groups of cases covered by the Cubist rules differ in their characteristics.•The LOS primarily depends on historical variables such as number of admissions.•Applying CARMA algorithm allows discovery of important relations among varia...

Full description

Saved in:
Bibliographic Details
Published in:Expert systems with applications 2017-07, Vol.78, p.376-385
Main Authors: Turgeman, Lior, May, Jerrold H., Sciulli, Roberta
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c457t-5fe9f314d74734767834a9980abed8aa8e3216529a7c416764afe8e013d45d783
cites cdi_FETCH-LOGICAL-c457t-5fe9f314d74734767834a9980abed8aa8e3216529a7c416764afe8e013d45d783
container_end_page 385
container_issue
container_start_page 376
container_title Expert systems with applications
container_volume 78
creator Turgeman, Lior
May, Jerrold H.
Sciulli, Roberta
description •A Cubist model for hospital Length of Stay (LOS) is proposed.•The groups of cases covered by the Cubist rules differ in their characteristics.•The LOS primarily depends on historical variables such as number of admissions.•Applying CARMA algorithm allows discovery of important relations among variables.•A method to separate the cases by their level of Cubist error. A model that accurately predicts, at the time of admission, the Length of Stay (LOS) for hospitalized patients could be an effective tool for healthcare providers. It could enable early interventions to prevent complications, enabling more efficient utilization of manpower and facilities in hospitals. In this study, we apply a regression tree (Cubist) model for predicting the LOS, based on static inputs, that is, values that are known at the time of admission and that do not change during patient's hospital stay. The model was trained and validated on de-identified administrative data from the Veterans Health Administration (VHA) hospitals in Pittsburgh, PA. We chose to use a Cubist model because it produced more accurate predictions than did alternative techniques. In addition, tree models enable us to examine the classification rules learned from the data, in order to better understand the factors that are most correlated with hospital LOS. Cubist recursively partitions the data set as it estimates linear regressions for each partition, and the error level differs for different partitions, so that it is possible to deduce what are the characteristics of patients whose LOS can be accurately predicted at admission, and what are the characteristics of patients for whom the LOS estimate at that point in time is more highly uncertain. For example, our model indicates that the prediction error is greater for patients who had more admissions in the recent past, and for those who had longer previous hospital stays. Our approach suggests that mapping the cases into a higher dimensional space, using a Radial Basis Function (RBF) kernel, helps to separate them by their level of Cubist error, using a Support Vector Machine (SVM).
doi_str_mv 10.1016/j.eswa.2017.02.023
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_1932190877</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0957417417301057</els_id><sourcerecordid>1932190877</sourcerecordid><originalsourceid>FETCH-LOGICAL-c457t-5fe9f314d74734767834a9980abed8aa8e3216529a7c416764afe8e013d45d783</originalsourceid><addsrcrecordid>eNp9kE9LxDAQxYMouK5-AU8BL3poTZq0acGLLP5ZKOxh9RxiO92mtE1Nssp-e1PXs_BgYOb3ZoaH0DUlMSU0u-9icN8qTggVMUmC2Ala0FywKBMFO0ULUqQi4lTwc3ThXEcCSIhYoGk9Or1rvcONNQNWeFBVq0fAPSg76nGHB1NDjxtj8WSh1pWfm74F3Bo3aa96XMK48y02Dd56dcC35WZ7h5X_hbweYJ6oetDOaTNeorNG9Q6u_uoSvT8_va1eo3Lzsl49llHFU-GjtIGiYZTXggvGRSZyxlVR5ER9QJ0rlQNLaJYmhRIVp5nIuGogB0JZzdM60Et0c9w7WfO5B-dlZ_Z2DCclLYK3ILkQgUqOVGWNcxYaOVk9KHuQlMg5WdnJOVk5JytJEsSC6eFogvD_lwYrXaVhrEI6Fiova6P_s_8ADPKBJg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1932190877</pqid></control><display><type>article</type><title>Insights from a machine learning model for predicting the hospital Length of Stay (LOS) at the time of admission</title><source>ScienceDirect Freedom Collection</source><creator>Turgeman, Lior ; May, Jerrold H. ; Sciulli, Roberta</creator><creatorcontrib>Turgeman, Lior ; May, Jerrold H. ; Sciulli, Roberta</creatorcontrib><description>•A Cubist model for hospital Length of Stay (LOS) is proposed.•The groups of cases covered by the Cubist rules differ in their characteristics.•The LOS primarily depends on historical variables such as number of admissions.•Applying CARMA algorithm allows discovery of important relations among variables.•A method to separate the cases by their level of Cubist error. A model that accurately predicts, at the time of admission, the Length of Stay (LOS) for hospitalized patients could be an effective tool for healthcare providers. It could enable early interventions to prevent complications, enabling more efficient utilization of manpower and facilities in hospitals. In this study, we apply a regression tree (Cubist) model for predicting the LOS, based on static inputs, that is, values that are known at the time of admission and that do not change during patient's hospital stay. The model was trained and validated on de-identified administrative data from the Veterans Health Administration (VHA) hospitals in Pittsburgh, PA. We chose to use a Cubist model because it produced more accurate predictions than did alternative techniques. In addition, tree models enable us to examine the classification rules learned from the data, in order to better understand the factors that are most correlated with hospital LOS. Cubist recursively partitions the data set as it estimates linear regressions for each partition, and the error level differs for different partitions, so that it is possible to deduce what are the characteristics of patients whose LOS can be accurately predicted at admission, and what are the characteristics of patients for whom the LOS estimate at that point in time is more highly uncertain. For example, our model indicates that the prediction error is greater for patients who had more admissions in the recent past, and for those who had longer previous hospital stays. Our approach suggests that mapping the cases into a higher dimensional space, using a Radial Basis Function (RBF) kernel, helps to separate them by their level of Cubist error, using a Support Vector Machine (SVM).</description><identifier>ISSN: 0957-4174</identifier><identifier>EISSN: 1873-6793</identifier><identifier>DOI: 10.1016/j.eswa.2017.02.023</identifier><language>eng</language><publisher>New York: Elsevier Ltd</publisher><subject>Algorithms ; Continuous association rule mining algorithm (CARMA) ; Cubist decision tree ; Decision function ; Error distribution ; Errors ; Hospitalization ; Hospitals ; Length of Stay (LOS) ; Machine learning ; Manpower ; Mapping ; Mathematical models ; Partitions ; Patient admissions ; Patients ; Predictions ; Radial basis function ; Regression analysis ; Support vector machine (SVM) ; Support vector machines</subject><ispartof>Expert systems with applications, 2017-07, Vol.78, p.376-385</ispartof><rights>2017 Elsevier Ltd</rights><rights>Copyright Elsevier BV Jul 15, 2017</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c457t-5fe9f314d74734767834a9980abed8aa8e3216529a7c416764afe8e013d45d783</citedby><cites>FETCH-LOGICAL-c457t-5fe9f314d74734767834a9980abed8aa8e3216529a7c416764afe8e013d45d783</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Turgeman, Lior</creatorcontrib><creatorcontrib>May, Jerrold H.</creatorcontrib><creatorcontrib>Sciulli, Roberta</creatorcontrib><title>Insights from a machine learning model for predicting the hospital Length of Stay (LOS) at the time of admission</title><title>Expert systems with applications</title><description>•A Cubist model for hospital Length of Stay (LOS) is proposed.•The groups of cases covered by the Cubist rules differ in their characteristics.•The LOS primarily depends on historical variables such as number of admissions.•Applying CARMA algorithm allows discovery of important relations among variables.•A method to separate the cases by their level of Cubist error. A model that accurately predicts, at the time of admission, the Length of Stay (LOS) for hospitalized patients could be an effective tool for healthcare providers. It could enable early interventions to prevent complications, enabling more efficient utilization of manpower and facilities in hospitals. In this study, we apply a regression tree (Cubist) model for predicting the LOS, based on static inputs, that is, values that are known at the time of admission and that do not change during patient's hospital stay. The model was trained and validated on de-identified administrative data from the Veterans Health Administration (VHA) hospitals in Pittsburgh, PA. We chose to use a Cubist model because it produced more accurate predictions than did alternative techniques. In addition, tree models enable us to examine the classification rules learned from the data, in order to better understand the factors that are most correlated with hospital LOS. Cubist recursively partitions the data set as it estimates linear regressions for each partition, and the error level differs for different partitions, so that it is possible to deduce what are the characteristics of patients whose LOS can be accurately predicted at admission, and what are the characteristics of patients for whom the LOS estimate at that point in time is more highly uncertain. For example, our model indicates that the prediction error is greater for patients who had more admissions in the recent past, and for those who had longer previous hospital stays. Our approach suggests that mapping the cases into a higher dimensional space, using a Radial Basis Function (RBF) kernel, helps to separate them by their level of Cubist error, using a Support Vector Machine (SVM).</description><subject>Algorithms</subject><subject>Continuous association rule mining algorithm (CARMA)</subject><subject>Cubist decision tree</subject><subject>Decision function</subject><subject>Error distribution</subject><subject>Errors</subject><subject>Hospitalization</subject><subject>Hospitals</subject><subject>Length of Stay (LOS)</subject><subject>Machine learning</subject><subject>Manpower</subject><subject>Mapping</subject><subject>Mathematical models</subject><subject>Partitions</subject><subject>Patient admissions</subject><subject>Patients</subject><subject>Predictions</subject><subject>Radial basis function</subject><subject>Regression analysis</subject><subject>Support vector machine (SVM)</subject><subject>Support vector machines</subject><issn>0957-4174</issn><issn>1873-6793</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><recordid>eNp9kE9LxDAQxYMouK5-AU8BL3poTZq0acGLLP5ZKOxh9RxiO92mtE1Nssp-e1PXs_BgYOb3ZoaH0DUlMSU0u-9icN8qTggVMUmC2Ala0FywKBMFO0ULUqQi4lTwc3ThXEcCSIhYoGk9Or1rvcONNQNWeFBVq0fAPSg76nGHB1NDjxtj8WSh1pWfm74F3Bo3aa96XMK48y02Dd56dcC35WZ7h5X_hbweYJ6oetDOaTNeorNG9Q6u_uoSvT8_va1eo3Lzsl49llHFU-GjtIGiYZTXggvGRSZyxlVR5ER9QJ0rlQNLaJYmhRIVp5nIuGogB0JZzdM60Et0c9w7WfO5B-dlZ_Z2DCclLYK3ILkQgUqOVGWNcxYaOVk9KHuQlMg5WdnJOVk5JytJEsSC6eFogvD_lwYrXaVhrEI6Fiova6P_s_8ADPKBJg</recordid><startdate>20170715</startdate><enddate>20170715</enddate><creator>Turgeman, Lior</creator><creator>May, Jerrold H.</creator><creator>Sciulli, Roberta</creator><general>Elsevier Ltd</general><general>Elsevier BV</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>20170715</creationdate><title>Insights from a machine learning model for predicting the hospital Length of Stay (LOS) at the time of admission</title><author>Turgeman, Lior ; May, Jerrold H. ; Sciulli, Roberta</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c457t-5fe9f314d74734767834a9980abed8aa8e3216529a7c416764afe8e013d45d783</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Algorithms</topic><topic>Continuous association rule mining algorithm (CARMA)</topic><topic>Cubist decision tree</topic><topic>Decision function</topic><topic>Error distribution</topic><topic>Errors</topic><topic>Hospitalization</topic><topic>Hospitals</topic><topic>Length of Stay (LOS)</topic><topic>Machine learning</topic><topic>Manpower</topic><topic>Mapping</topic><topic>Mathematical models</topic><topic>Partitions</topic><topic>Patient admissions</topic><topic>Patients</topic><topic>Predictions</topic><topic>Radial basis function</topic><topic>Regression analysis</topic><topic>Support vector machine (SVM)</topic><topic>Support vector machines</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Turgeman, Lior</creatorcontrib><creatorcontrib>May, Jerrold H.</creatorcontrib><creatorcontrib>Sciulli, Roberta</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>Expert systems with applications</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Turgeman, Lior</au><au>May, Jerrold H.</au><au>Sciulli, Roberta</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Insights from a machine learning model for predicting the hospital Length of Stay (LOS) at the time of admission</atitle><jtitle>Expert systems with applications</jtitle><date>2017-07-15</date><risdate>2017</risdate><volume>78</volume><spage>376</spage><epage>385</epage><pages>376-385</pages><issn>0957-4174</issn><eissn>1873-6793</eissn><abstract>•A Cubist model for hospital Length of Stay (LOS) is proposed.•The groups of cases covered by the Cubist rules differ in their characteristics.•The LOS primarily depends on historical variables such as number of admissions.•Applying CARMA algorithm allows discovery of important relations among variables.•A method to separate the cases by their level of Cubist error. A model that accurately predicts, at the time of admission, the Length of Stay (LOS) for hospitalized patients could be an effective tool for healthcare providers. It could enable early interventions to prevent complications, enabling more efficient utilization of manpower and facilities in hospitals. In this study, we apply a regression tree (Cubist) model for predicting the LOS, based on static inputs, that is, values that are known at the time of admission and that do not change during patient's hospital stay. The model was trained and validated on de-identified administrative data from the Veterans Health Administration (VHA) hospitals in Pittsburgh, PA. We chose to use a Cubist model because it produced more accurate predictions than did alternative techniques. In addition, tree models enable us to examine the classification rules learned from the data, in order to better understand the factors that are most correlated with hospital LOS. Cubist recursively partitions the data set as it estimates linear regressions for each partition, and the error level differs for different partitions, so that it is possible to deduce what are the characteristics of patients whose LOS can be accurately predicted at admission, and what are the characteristics of patients for whom the LOS estimate at that point in time is more highly uncertain. For example, our model indicates that the prediction error is greater for patients who had more admissions in the recent past, and for those who had longer previous hospital stays. Our approach suggests that mapping the cases into a higher dimensional space, using a Radial Basis Function (RBF) kernel, helps to separate them by their level of Cubist error, using a Support Vector Machine (SVM).</abstract><cop>New York</cop><pub>Elsevier Ltd</pub><doi>10.1016/j.eswa.2017.02.023</doi><tpages>10</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0957-4174
ispartof Expert systems with applications, 2017-07, Vol.78, p.376-385
issn 0957-4174
1873-6793
language eng
recordid cdi_proquest_journals_1932190877
source ScienceDirect Freedom Collection
subjects Algorithms
Continuous association rule mining algorithm (CARMA)
Cubist decision tree
Decision function
Error distribution
Errors
Hospitalization
Hospitals
Length of Stay (LOS)
Machine learning
Manpower
Mapping
Mathematical models
Partitions
Patient admissions
Patients
Predictions
Radial basis function
Regression analysis
Support vector machine (SVM)
Support vector machines
title Insights from a machine learning model for predicting the hospital Length of Stay (LOS) at the time of admission
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T00%3A17%3A43IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Insights%20from%20a%20machine%20learning%20model%20for%20predicting%20the%20hospital%20Length%20of%20Stay%20(LOS)%20at%20the%20time%20of%20admission&rft.jtitle=Expert%20systems%20with%20applications&rft.au=Turgeman,%20Lior&rft.date=2017-07-15&rft.volume=78&rft.spage=376&rft.epage=385&rft.pages=376-385&rft.issn=0957-4174&rft.eissn=1873-6793&rft_id=info:doi/10.1016/j.eswa.2017.02.023&rft_dat=%3Cproquest_cross%3E1932190877%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c457t-5fe9f314d74734767834a9980abed8aa8e3216529a7c416764afe8e013d45d783%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=1932190877&rft_id=info:pmid/&rfr_iscdi=true