A Novel Machine Learning Predictive Tool Assessing Outpatient or Inpatient Designation for Medicare Patients Undergoing Total Hip Arthroplasty
Background: The Centers for Medicare and Medicaid Services removed total hip arthroplasty (THA) from the inpatient-only list. This has created significant confusion regarding which patients qualify for an inpatient designation. The purpose of this study is to develop and validate a novel predictive...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2021-04-01
|
Series: | Arthroplasty Today |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2352344121000376 |
id |
doaj-da00f03f2dd646f4910420474173d52e |
---|---|
record_format |
Article |
spelling |
doaj-da00f03f2dd646f4910420474173d52e2021-05-16T04:24:03ZengElsevierArthroplasty Today2352-34412021-04-018194199A Novel Machine Learning Predictive Tool Assessing Outpatient or Inpatient Designation for Medicare Patients Undergoing Total Hip ArthroplastyDavid N. Kugelman, MD0Greg Teo, MD1Shengnan Huang, MS2Michael G. Doran, MD3Vivek Singh, MD4William J. Long, MD, FRCSC5New York University Langone Orthopaedic Hospital, New York, NYNew York University Langone Orthopaedic Hospital, New York, NYNew York University Langone Orthopaedic Hospital, New York, NYNew York University Langone Orthopaedic Hospital, New York, NYNew York University Langone Orthopaedic Hospital, New York, NYCorresponding author. 301 East 17 St, Manhattan, New York 10003. Tel.: 212-598-6000.; New York University Langone Orthopaedic Hospital, New York, NYBackground: The Centers for Medicare and Medicaid Services removed total hip arthroplasty (THA) from the inpatient-only list. This has created significant confusion regarding which patients qualify for an inpatient designation. The purpose of this study is to develop and validate a novel predictive tool for preoperatively objectively determining “outpatient” vs “inpatient” status for THA in the Medicare population. Methods: A cohort of Medicare patients undergoing primary THA between January 2017 and September 2019 was retrospectively reviewed. A machine learning model was trained using 80% of the THA patients, and the remaining 20% was used for testing the model performance in terms of accuracy and the average area under the receiver operating characteristic curve. Feature importance was obtained for each feature used in the model. Results: One thousand ninety-one patients had outpatient stays, and 318 qualified for inpatient designation. Significant associations were demonstrated between inpatient designations and the following: higher BMI, increased patient age, better preoperative functional scores, higher American Society of Anesthesiologist Physical Status Classification, higher Modified Frailty Index, higher Charlson Comorbidity Index, female gender, and numerous comorbidities. The XGBoost model for predicting an inpatient or outpatient stay was 78.7% accurate with the area under the receiver operating characteristic curve to be 81.5%. Conclusions: Using readily available key baseline characteristics, functional scores and comorbidities, this machine-learning model accurately predicts an “outpatient” or “inpatient” stay after THA in the Medicare population. BMI, age, functional scores, and American Society of Anesthesiologist Physical Status Classification had the highest influence on this predictive model.http://www.sciencedirect.com/science/article/pii/S2352344121000376Total hip arthroplastyMedicare total hipMedicare bundle paymentMedicare inpatient only listArthroplasty inpatient onlyPredictive model |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
David N. Kugelman, MD Greg Teo, MD Shengnan Huang, MS Michael G. Doran, MD Vivek Singh, MD William J. Long, MD, FRCSC |
spellingShingle |
David N. Kugelman, MD Greg Teo, MD Shengnan Huang, MS Michael G. Doran, MD Vivek Singh, MD William J. Long, MD, FRCSC A Novel Machine Learning Predictive Tool Assessing Outpatient or Inpatient Designation for Medicare Patients Undergoing Total Hip Arthroplasty Arthroplasty Today Total hip arthroplasty Medicare total hip Medicare bundle payment Medicare inpatient only list Arthroplasty inpatient only Predictive model |
author_facet |
David N. Kugelman, MD Greg Teo, MD Shengnan Huang, MS Michael G. Doran, MD Vivek Singh, MD William J. Long, MD, FRCSC |
author_sort |
David N. Kugelman, MD |
title |
A Novel Machine Learning Predictive Tool Assessing Outpatient or Inpatient Designation for Medicare Patients Undergoing Total Hip Arthroplasty |
title_short |
A Novel Machine Learning Predictive Tool Assessing Outpatient or Inpatient Designation for Medicare Patients Undergoing Total Hip Arthroplasty |
title_full |
A Novel Machine Learning Predictive Tool Assessing Outpatient or Inpatient Designation for Medicare Patients Undergoing Total Hip Arthroplasty |
title_fullStr |
A Novel Machine Learning Predictive Tool Assessing Outpatient or Inpatient Designation for Medicare Patients Undergoing Total Hip Arthroplasty |
title_full_unstemmed |
A Novel Machine Learning Predictive Tool Assessing Outpatient or Inpatient Designation for Medicare Patients Undergoing Total Hip Arthroplasty |
title_sort |
novel machine learning predictive tool assessing outpatient or inpatient designation for medicare patients undergoing total hip arthroplasty |
publisher |
Elsevier |
series |
Arthroplasty Today |
issn |
2352-3441 |
publishDate |
2021-04-01 |
description |
Background: The Centers for Medicare and Medicaid Services removed total hip arthroplasty (THA) from the inpatient-only list. This has created significant confusion regarding which patients qualify for an inpatient designation. The purpose of this study is to develop and validate a novel predictive tool for preoperatively objectively determining “outpatient” vs “inpatient” status for THA in the Medicare population. Methods: A cohort of Medicare patients undergoing primary THA between January 2017 and September 2019 was retrospectively reviewed. A machine learning model was trained using 80% of the THA patients, and the remaining 20% was used for testing the model performance in terms of accuracy and the average area under the receiver operating characteristic curve. Feature importance was obtained for each feature used in the model. Results: One thousand ninety-one patients had outpatient stays, and 318 qualified for inpatient designation. Significant associations were demonstrated between inpatient designations and the following: higher BMI, increased patient age, better preoperative functional scores, higher American Society of Anesthesiologist Physical Status Classification, higher Modified Frailty Index, higher Charlson Comorbidity Index, female gender, and numerous comorbidities. The XGBoost model for predicting an inpatient or outpatient stay was 78.7% accurate with the area under the receiver operating characteristic curve to be 81.5%. Conclusions: Using readily available key baseline characteristics, functional scores and comorbidities, this machine-learning model accurately predicts an “outpatient” or “inpatient” stay after THA in the Medicare population. BMI, age, functional scores, and American Society of Anesthesiologist Physical Status Classification had the highest influence on this predictive model. |
topic |
Total hip arthroplasty Medicare total hip Medicare bundle payment Medicare inpatient only list Arthroplasty inpatient only Predictive model |
url |
http://www.sciencedirect.com/science/article/pii/S2352344121000376 |
work_keys_str_mv |
AT davidnkugelmanmd anovelmachinelearningpredictivetoolassessingoutpatientorinpatientdesignationformedicarepatientsundergoingtotalhiparthroplasty AT gregteomd anovelmachinelearningpredictivetoolassessingoutpatientorinpatientdesignationformedicarepatientsundergoingtotalhiparthroplasty AT shengnanhuangms anovelmachinelearningpredictivetoolassessingoutpatientorinpatientdesignationformedicarepatientsundergoingtotalhiparthroplasty AT michaelgdoranmd anovelmachinelearningpredictivetoolassessingoutpatientorinpatientdesignationformedicarepatientsundergoingtotalhiparthroplasty AT viveksinghmd anovelmachinelearningpredictivetoolassessingoutpatientorinpatientdesignationformedicarepatientsundergoingtotalhiparthroplasty AT williamjlongmdfrcsc anovelmachinelearningpredictivetoolassessingoutpatientorinpatientdesignationformedicarepatientsundergoingtotalhiparthroplasty AT davidnkugelmanmd novelmachinelearningpredictivetoolassessingoutpatientorinpatientdesignationformedicarepatientsundergoingtotalhiparthroplasty AT gregteomd novelmachinelearningpredictivetoolassessingoutpatientorinpatientdesignationformedicarepatientsundergoingtotalhiparthroplasty AT shengnanhuangms novelmachinelearningpredictivetoolassessingoutpatientorinpatientdesignationformedicarepatientsundergoingtotalhiparthroplasty AT michaelgdoranmd novelmachinelearningpredictivetoolassessingoutpatientorinpatientdesignationformedicarepatientsundergoingtotalhiparthroplasty AT viveksinghmd novelmachinelearningpredictivetoolassessingoutpatientorinpatientdesignationformedicarepatientsundergoingtotalhiparthroplasty AT williamjlongmdfrcsc novelmachinelearningpredictivetoolassessingoutpatientorinpatientdesignationformedicarepatientsundergoingtotalhiparthroplasty |
_version_ |
1721439965288595456 |