Predicting in-hospital length of stay: a two-stage modeling approach to account for highly skewed data
Abstract Background In the early stages of the COVID-19 pandemic our institution was interested in forecasting how long surgical patients receiving elective procedures would spend in the hospital. Initial examination of our models indicated that, due to the skewed nature of the length of stay, accur...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2022-04-01
|
Series: | BMC Medical Informatics and Decision Making |
Subjects: | |
Online Access: | https://doi.org/10.1186/s12911-022-01855-0 |
_version_ | 1811338795904139264 |
---|---|
author | Zhenhui Xu Congwen Zhao Charles D. Scales Ricardo Henao Benjamin A. Goldstein |
author_facet | Zhenhui Xu Congwen Zhao Charles D. Scales Ricardo Henao Benjamin A. Goldstein |
author_sort | Zhenhui Xu |
collection | DOAJ |
description | Abstract Background In the early stages of the COVID-19 pandemic our institution was interested in forecasting how long surgical patients receiving elective procedures would spend in the hospital. Initial examination of our models indicated that, due to the skewed nature of the length of stay, accurate prediction was challenging and we instead opted for a simpler classification model. In this work we perform a deeper examination of predicting in-hospital length of stay. Methods We used electronic health record data on length of stay from 42,209 elective surgeries. We compare different loss-functions (mean squared error, mean absolute error, mean relative error), algorithms (LASSO, Random Forests, multilayer perceptron) and data transformations (log and truncation). We also assess the performance of two stage hybrid classification-regression approach. Results Our results show that while it is possible to accurately predict short length of stays, predicting longer length of stay is extremely challenging. As such, we opt for a two-stage model that first classifies patients into long versus short length of stays and then a second stage that fits a regresssor among those predicted to have a short length of stay. Discussion The results indicate both the challenges and considerations necessary to applying machine-learning methods to skewed outcomes. Conclusions Two-stage models allow those developing clinical decision support tools to explicitly acknowledge where they can and cannot make accurate predictions. |
first_indexed | 2024-04-13T18:16:51Z |
format | Article |
id | doaj.art-30ddaaf267fb48a383780783ddf0c5be |
institution | Directory Open Access Journal |
issn | 1472-6947 |
language | English |
last_indexed | 2024-04-13T18:16:51Z |
publishDate | 2022-04-01 |
publisher | BMC |
record_format | Article |
series | BMC Medical Informatics and Decision Making |
spelling | doaj.art-30ddaaf267fb48a383780783ddf0c5be2022-12-22T02:35:39ZengBMCBMC Medical Informatics and Decision Making1472-69472022-04-0122111210.1186/s12911-022-01855-0Predicting in-hospital length of stay: a two-stage modeling approach to account for highly skewed dataZhenhui Xu0Congwen Zhao1Charles D. Scales2Ricardo Henao3Benjamin A. Goldstein4Department of Biostatistics and Bioinformatics, Duke UniversityDepartment of Biostatistics and Bioinformatics, Duke UniversityDuke Clinical Research Institute, Duke UniversityDepartment of Biostatistics and Bioinformatics, Duke UniversityDepartment of Biostatistics and Bioinformatics, Duke UniversityAbstract Background In the early stages of the COVID-19 pandemic our institution was interested in forecasting how long surgical patients receiving elective procedures would spend in the hospital. Initial examination of our models indicated that, due to the skewed nature of the length of stay, accurate prediction was challenging and we instead opted for a simpler classification model. In this work we perform a deeper examination of predicting in-hospital length of stay. Methods We used electronic health record data on length of stay from 42,209 elective surgeries. We compare different loss-functions (mean squared error, mean absolute error, mean relative error), algorithms (LASSO, Random Forests, multilayer perceptron) and data transformations (log and truncation). We also assess the performance of two stage hybrid classification-regression approach. Results Our results show that while it is possible to accurately predict short length of stays, predicting longer length of stay is extremely challenging. As such, we opt for a two-stage model that first classifies patients into long versus short length of stays and then a second stage that fits a regresssor among those predicted to have a short length of stay. Discussion The results indicate both the challenges and considerations necessary to applying machine-learning methods to skewed outcomes. Conclusions Two-stage models allow those developing clinical decision support tools to explicitly acknowledge where they can and cannot make accurate predictions.https://doi.org/10.1186/s12911-022-01855-0Electronic health recordsMachine learningClinical decision supportSurgical outcomes |
spellingShingle | Zhenhui Xu Congwen Zhao Charles D. Scales Ricardo Henao Benjamin A. Goldstein Predicting in-hospital length of stay: a two-stage modeling approach to account for highly skewed data BMC Medical Informatics and Decision Making Electronic health records Machine learning Clinical decision support Surgical outcomes |
title | Predicting in-hospital length of stay: a two-stage modeling approach to account for highly skewed data |
title_full | Predicting in-hospital length of stay: a two-stage modeling approach to account for highly skewed data |
title_fullStr | Predicting in-hospital length of stay: a two-stage modeling approach to account for highly skewed data |
title_full_unstemmed | Predicting in-hospital length of stay: a two-stage modeling approach to account for highly skewed data |
title_short | Predicting in-hospital length of stay: a two-stage modeling approach to account for highly skewed data |
title_sort | predicting in hospital length of stay a two stage modeling approach to account for highly skewed data |
topic | Electronic health records Machine learning Clinical decision support Surgical outcomes |
url | https://doi.org/10.1186/s12911-022-01855-0 |
work_keys_str_mv | AT zhenhuixu predictinginhospitallengthofstayatwostagemodelingapproachtoaccountforhighlyskeweddata AT congwenzhao predictinginhospitallengthofstayatwostagemodelingapproachtoaccountforhighlyskeweddata AT charlesdscales predictinginhospitallengthofstayatwostagemodelingapproachtoaccountforhighlyskeweddata AT ricardohenao predictinginhospitallengthofstayatwostagemodelingapproachtoaccountforhighlyskeweddata AT benjaminagoldstein predictinginhospitallengthofstayatwostagemodelingapproachtoaccountforhighlyskeweddata |