Cargando…
Machine-learning vs. logistic regression for preoperative prediction of medical morbidity after fast-track hip and knee arthroplasty—a comparative study
BACKGROUND: Machine-learning models may improve prediction of length of stay (LOS) and morbidity after surgery. However, few studies include fast-track programs, and most rely on administrative coding with limited follow-up and information on perioperative care. This study investigates potential ben...
Autores principales: | , , , , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
BioMed Central
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10685559/ https://www.ncbi.nlm.nih.gov/pubmed/38030979 http://dx.doi.org/10.1186/s12871-023-02354-z |
_version_ | 1785151660014698496 |
---|---|
author | Michelsen, Christian Jørgensen, Christoffer C. Heltberg, Mathias Jensen, Mogens H. Lucchetti, Alessandra Petersen, Pelle B. Petersen, Troels Kehlet, Henrik Madsen, Frank Hansen, Torben B. Gromov, Kirill Jakobsen, Thomas Varnum, Claus Overgaard, Soren Rathsach, Mikkel Hansen, Lars |
author_facet | Michelsen, Christian Jørgensen, Christoffer C. Heltberg, Mathias Jensen, Mogens H. Lucchetti, Alessandra Petersen, Pelle B. Petersen, Troels Kehlet, Henrik Madsen, Frank Hansen, Torben B. Gromov, Kirill Jakobsen, Thomas Varnum, Claus Overgaard, Soren Rathsach, Mikkel Hansen, Lars |
author_sort | Michelsen, Christian |
collection | PubMed |
description | BACKGROUND: Machine-learning models may improve prediction of length of stay (LOS) and morbidity after surgery. However, few studies include fast-track programs, and most rely on administrative coding with limited follow-up and information on perioperative care. This study investigates potential benefits of a machine-learning model for prediction of postoperative morbidity in fast-track total hip (THA) and knee arthroplasty (TKA). METHODS: Cohort study in consecutive unselected primary THA/TKA between 2014–2017 from seven Danish centers with established fast-track protocols. Preoperative comorbidity and prescribed medication were recorded prospectively and information on length of stay and readmissions was obtained through the Danish National Patient Registry and medical records. We used a machine-learning model (Boosted Decision Trees) based on boosted decision trees with 33 preoperative variables for predicting “medical” morbidity leading to LOS > 4 days or 90-days readmissions and compared to a logistical regression model based on the same variables. We also evaluated two parsimonious models, using the ten most important variables in the full machine-learning and logistic regression models. Data collected between 2014–2016 (n:18,013) was used for model training and data from 2017 (n:3913) was used for testing. Model performances were analyzed using precision, area under receiver operating (AUROC) and precision recall curves (AUPRC), as well as the Mathews Correlation Coefficient. Variable importance was analyzed using Shapley Additive Explanations values. RESULTS: Using a threshold of 20% “risk-patients” (n:782), precision, AUROC and AUPRC were 13.6%, 76.3% and 15.5% vs. 12.4%, 74.7% and 15.6% for the machine-learning and logistic regression model, respectively. The parsimonious machine-learning model performed better than the full logistic regression model. Of the top ten variables, eight were shared between the machine-learning and logistic regression models, but with a considerable age-related variation in importance of specific types of medication. CONCLUSION: A machine-learning model using preoperative characteristics and prescriptions slightly improved identification of patients in high-risk of “medical” complications after fast-track THA and TKA compared to a logistic regression model. Such algorithms could help find a manageable population of patients who may benefit most from intensified perioperative care. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1186/s12871-023-02354-z. |
format | Online Article Text |
id | pubmed-10685559 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | BioMed Central |
record_format | MEDLINE/PubMed |
spelling | pubmed-106855592023-11-30 Machine-learning vs. logistic regression for preoperative prediction of medical morbidity after fast-track hip and knee arthroplasty—a comparative study Michelsen, Christian Jørgensen, Christoffer C. Heltberg, Mathias Jensen, Mogens H. Lucchetti, Alessandra Petersen, Pelle B. Petersen, Troels Kehlet, Henrik Madsen, Frank Hansen, Torben B. Gromov, Kirill Jakobsen, Thomas Varnum, Claus Overgaard, Soren Rathsach, Mikkel Hansen, Lars BMC Anesthesiol Research BACKGROUND: Machine-learning models may improve prediction of length of stay (LOS) and morbidity after surgery. However, few studies include fast-track programs, and most rely on administrative coding with limited follow-up and information on perioperative care. This study investigates potential benefits of a machine-learning model for prediction of postoperative morbidity in fast-track total hip (THA) and knee arthroplasty (TKA). METHODS: Cohort study in consecutive unselected primary THA/TKA between 2014–2017 from seven Danish centers with established fast-track protocols. Preoperative comorbidity and prescribed medication were recorded prospectively and information on length of stay and readmissions was obtained through the Danish National Patient Registry and medical records. We used a machine-learning model (Boosted Decision Trees) based on boosted decision trees with 33 preoperative variables for predicting “medical” morbidity leading to LOS > 4 days or 90-days readmissions and compared to a logistical regression model based on the same variables. We also evaluated two parsimonious models, using the ten most important variables in the full machine-learning and logistic regression models. Data collected between 2014–2016 (n:18,013) was used for model training and data from 2017 (n:3913) was used for testing. Model performances were analyzed using precision, area under receiver operating (AUROC) and precision recall curves (AUPRC), as well as the Mathews Correlation Coefficient. Variable importance was analyzed using Shapley Additive Explanations values. RESULTS: Using a threshold of 20% “risk-patients” (n:782), precision, AUROC and AUPRC were 13.6%, 76.3% and 15.5% vs. 12.4%, 74.7% and 15.6% for the machine-learning and logistic regression model, respectively. The parsimonious machine-learning model performed better than the full logistic regression model. Of the top ten variables, eight were shared between the machine-learning and logistic regression models, but with a considerable age-related variation in importance of specific types of medication. CONCLUSION: A machine-learning model using preoperative characteristics and prescriptions slightly improved identification of patients in high-risk of “medical” complications after fast-track THA and TKA compared to a logistic regression model. Such algorithms could help find a manageable population of patients who may benefit most from intensified perioperative care. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1186/s12871-023-02354-z. BioMed Central 2023-11-29 /pmc/articles/PMC10685559/ /pubmed/38030979 http://dx.doi.org/10.1186/s12871-023-02354-z Text en © The Author(s) 2023 https://creativecommons.org/licenses/by/4.0/Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) . The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/ (https://creativecommons.org/publicdomain/zero/1.0/) ) applies to the data made available in this article, unless otherwise stated in a credit line to the data. |
spellingShingle | Research Michelsen, Christian Jørgensen, Christoffer C. Heltberg, Mathias Jensen, Mogens H. Lucchetti, Alessandra Petersen, Pelle B. Petersen, Troels Kehlet, Henrik Madsen, Frank Hansen, Torben B. Gromov, Kirill Jakobsen, Thomas Varnum, Claus Overgaard, Soren Rathsach, Mikkel Hansen, Lars Machine-learning vs. logistic regression for preoperative prediction of medical morbidity after fast-track hip and knee arthroplasty—a comparative study |
title | Machine-learning vs. logistic regression for preoperative prediction of medical morbidity after fast-track hip and knee arthroplasty—a comparative study |
title_full | Machine-learning vs. logistic regression for preoperative prediction of medical morbidity after fast-track hip and knee arthroplasty—a comparative study |
title_fullStr | Machine-learning vs. logistic regression for preoperative prediction of medical morbidity after fast-track hip and knee arthroplasty—a comparative study |
title_full_unstemmed | Machine-learning vs. logistic regression for preoperative prediction of medical morbidity after fast-track hip and knee arthroplasty—a comparative study |
title_short | Machine-learning vs. logistic regression for preoperative prediction of medical morbidity after fast-track hip and knee arthroplasty—a comparative study |
title_sort | machine-learning vs. logistic regression for preoperative prediction of medical morbidity after fast-track hip and knee arthroplasty—a comparative study |
topic | Research |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10685559/ https://www.ncbi.nlm.nih.gov/pubmed/38030979 http://dx.doi.org/10.1186/s12871-023-02354-z |
work_keys_str_mv | AT michelsenchristian machinelearningvslogisticregressionforpreoperativepredictionofmedicalmorbidityafterfasttrackhipandkneearthroplastyacomparativestudy AT jørgensenchristofferc machinelearningvslogisticregressionforpreoperativepredictionofmedicalmorbidityafterfasttrackhipandkneearthroplastyacomparativestudy AT heltbergmathias machinelearningvslogisticregressionforpreoperativepredictionofmedicalmorbidityafterfasttrackhipandkneearthroplastyacomparativestudy AT jensenmogensh machinelearningvslogisticregressionforpreoperativepredictionofmedicalmorbidityafterfasttrackhipandkneearthroplastyacomparativestudy AT lucchettialessandra machinelearningvslogisticregressionforpreoperativepredictionofmedicalmorbidityafterfasttrackhipandkneearthroplastyacomparativestudy AT petersenpelleb machinelearningvslogisticregressionforpreoperativepredictionofmedicalmorbidityafterfasttrackhipandkneearthroplastyacomparativestudy AT petersentroels machinelearningvslogisticregressionforpreoperativepredictionofmedicalmorbidityafterfasttrackhipandkneearthroplastyacomparativestudy AT kehlethenrik machinelearningvslogisticregressionforpreoperativepredictionofmedicalmorbidityafterfasttrackhipandkneearthroplastyacomparativestudy AT machinelearningvslogisticregressionforpreoperativepredictionofmedicalmorbidityafterfasttrackhipandkneearthroplastyacomparativestudy AT madsenfrank machinelearningvslogisticregressionforpreoperativepredictionofmedicalmorbidityafterfasttrackhipandkneearthroplastyacomparativestudy AT hansentorbenb machinelearningvslogisticregressionforpreoperativepredictionofmedicalmorbidityafterfasttrackhipandkneearthroplastyacomparativestudy AT gromovkirill machinelearningvslogisticregressionforpreoperativepredictionofmedicalmorbidityafterfasttrackhipandkneearthroplastyacomparativestudy AT jakobsenthomas machinelearningvslogisticregressionforpreoperativepredictionofmedicalmorbidityafterfasttrackhipandkneearthroplastyacomparativestudy AT varnumclaus machinelearningvslogisticregressionforpreoperativepredictionofmedicalmorbidityafterfasttrackhipandkneearthroplastyacomparativestudy AT overgaardsoren machinelearningvslogisticregressionforpreoperativepredictionofmedicalmorbidityafterfasttrackhipandkneearthroplastyacomparativestudy AT rathsachmikkel machinelearningvslogisticregressionforpreoperativepredictionofmedicalmorbidityafterfasttrackhipandkneearthroplastyacomparativestudy AT hansenlars machinelearningvslogisticregressionforpreoperativepredictionofmedicalmorbidityafterfasttrackhipandkneearthroplastyacomparativestudy |