Predicting Early Hospital Discharge Following Revision Total Hip Arthroplasty: An Analysis of a Large National Database Using Machine Learning.

IF 3.4 2区 医学 Q1 ORTHOPEDICS
Teja Yeramosu, Jacob M Farrar, Avni Malik, Jibanananda Satpathy, Gregory J Golladay, Nirav K Patel
{"title":"Predicting Early Hospital Discharge Following Revision Total Hip Arthroplasty: An Analysis of a Large National Database Using Machine Learning.","authors":"Teja Yeramosu, Jacob M Farrar, Avni Malik, Jibanananda Satpathy, Gregory J Golladay, Nirav K Patel","doi":"10.1016/j.arth.2024.12.006","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Revision total hip arthroplasty (rTHA) was recently removed from the Medicare inpatient-only list. However, appropriate candidate selection for outpatient rTHA remains paramount. The purpose of this study was to evaluate the utility of a large national database using machine learning (ML) and traditional multivariable logistic regression (MLR) models in predicting early hospital discharge (EHD) (< 24 hours) following rTHA. Furthermore, this study aimed to use the trained ML models, cross-referenced with traditional MLR, to determine key perioperative variables predictive of EHD following rTHA.</p><p><strong>Methods: </strong>Data were obtained from a large national database from 2021. Patients who had unilateral rTHA procedures were included. Demographic, preoperative, and operative variables were analyzed as inputs for the models. An ML regression model and various ML techniques were used to predict EHD and were compared using the area under the curve, calibration, Brier score, and decision curve analysis. Feature importance was identified from the overall best-performing model. Of the 3,097 patients in this study, 866 (27.96%) underwent EHD.</p><p><strong>Results: </strong>The random forest model performed the best overall and identified aseptic surgical indication, operative time < three hours, absence of anemia (hematocrit < 40% in men and < 35% in women), neuraxial anesthesia type, White race, men, independent functional status, body mass index > 20, age < 75 years, and the presence of home support as factors predictive of EHD. Each of these variables was also significant in the MLR model.</p><p><strong>Conclusions: </strong>Each ML model and MLR displayed good performance and identified clinically important variables for determining candidates for EHD following rTHA. Machine learning (ML) techniques such as random forest may allow clinicians to accurately risk stratify their patients preoperatively to optimize resources and improve patient outcomes.</p>","PeriodicalId":51077,"journal":{"name":"Journal of Arthroplasty","volume":" ","pages":""},"PeriodicalIF":3.4000,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Arthroplasty","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1016/j.arth.2024.12.006","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ORTHOPEDICS","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Revision total hip arthroplasty (rTHA) was recently removed from the Medicare inpatient-only list. However, appropriate candidate selection for outpatient rTHA remains paramount. The purpose of this study was to evaluate the utility of a large national database using machine learning (ML) and traditional multivariable logistic regression (MLR) models in predicting early hospital discharge (EHD) (< 24 hours) following rTHA. Furthermore, this study aimed to use the trained ML models, cross-referenced with traditional MLR, to determine key perioperative variables predictive of EHD following rTHA.

Methods: Data were obtained from a large national database from 2021. Patients who had unilateral rTHA procedures were included. Demographic, preoperative, and operative variables were analyzed as inputs for the models. An ML regression model and various ML techniques were used to predict EHD and were compared using the area under the curve, calibration, Brier score, and decision curve analysis. Feature importance was identified from the overall best-performing model. Of the 3,097 patients in this study, 866 (27.96%) underwent EHD.

Results: The random forest model performed the best overall and identified aseptic surgical indication, operative time < three hours, absence of anemia (hematocrit < 40% in men and < 35% in women), neuraxial anesthesia type, White race, men, independent functional status, body mass index > 20, age < 75 years, and the presence of home support as factors predictive of EHD. Each of these variables was also significant in the MLR model.

Conclusions: Each ML model and MLR displayed good performance and identified clinically important variables for determining candidates for EHD following rTHA. Machine learning (ML) techniques such as random forest may allow clinicians to accurately risk stratify their patients preoperatively to optimize resources and improve patient outcomes.

预测翻修全髋关节置换术后早期出院:使用机器学习对大型国家数据库的分析。
背景:翻修全髋关节置换术(rTHA)最近从医疗保险住院患者名单中删除。然而,门诊rTHA患者的合适选择仍然是至关重要的。本研究的目的是评估使用机器学习(ML)和传统多变量逻辑回归(MLR)模型的大型国家数据库在预测rTHA术后早期出院(< 24小时)方面的效用。此外,本研究旨在使用训练后的ML模型,与传统MLR交叉参考,确定预测rTHA术后早期出院(EHD)的关键围手术期变量。方法:数据来自2021年起的大型国家数据库。包括单侧rTHA手术的患者。人口统计学、术前和手术变量作为模型的输入进行分析。使用机器学习回归模型和各种机器学习技术来预测EHD,并使用曲线下面积(AUC),校准,Brier评分和决策曲线分析进行比较。特征的重要性是从整体表现最好的模型中确定出来的。在本研究的3097例患者中,866例(27.96%)发生了EHD。结果:随机森林(RF)模型总体上表现最好,并确定了无菌手术指征、手术时间< 3小时、无贫血(男性红细胞压比< 40%,女性< 35%)、轴向麻醉类型、白人、男性、独立功能状态、体重指数(BMI) bb20、年龄< 75岁、是否有家庭支持作为EHD的预测因素。这些变量中的每一个在MLR模型中也是显著的。结论:每个ML模型和MLR都表现出良好的性能,并确定了确定rTHA后EHD候选人的临床重要变量。RF等机器学习技术可以使临床医生在手术前准确地对患者进行风险分层,以优化资源并改善患者预后。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Journal of Arthroplasty
Journal of Arthroplasty 医学-整形外科
CiteScore
7.00
自引率
20.00%
发文量
734
审稿时长
48 days
期刊介绍: The Journal of Arthroplasty brings together the clinical and scientific foundations for joint replacement. This peer-reviewed journal publishes original research and manuscripts of the highest quality from all areas relating to joint replacement or the treatment of its complications, including those dealing with clinical series and experience, prosthetic design, biomechanics, biomaterials, metallurgy, biologic response to arthroplasty materials in vivo and in vitro.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信