Machine Learning Model Developed to Aid in Patient Selection for Outpatient Total Joint Arthroplasty

Abstract

Background: Patient selection for outpatient total joint arthroplasty (TJA) is important for optimizing patient outcomes. This study develops machine learning models that may aid in patient selection for outpatient TJA based on medical comorbidities and demographic factors. Methods: This study queried elective total knee arthroplasty (TKA) and total hip arthroplasty (THA) cases during 2010-2018 in the American College of Surgeons National Surgical Quality Improvement Program. Artificial neural network models predicted same-day discharge and length of stay (LOS) fewer than 2 days (short LOS). Multiple linear and logistic regression analyses were used to identify variables significantly associated with predicted outcomes. Results: A total of 284,731 TKA cases and 153,053 THA cases met inclusion criteria. For TKA, prediction of short LOS had an area under the receiver operating characteristic curve (AUC) of 0.767 and accuracy of 84.1%; prediction of same-day discharge had an AUC of 0.802 and accuracy of 89.2%. For THA, prediction of short LOS had an AUC of 0.757 and accuracy of 70.6%; prediction of same-day discharge had an AUC of 0.814 and accuracy of 78.8%. Conclusion: This study developed machine learning models for aiding patient selection for outpatient TJA, through accurately predicting short LOS or outpatient vs inpatient cases. As outpatient TJA expands, it will be important to optimize preoperative patient selection and effectively screen surgical candidates from a broader patient population. Incorporating models such as these into electronic medical records could aid in decision-making and resource planning in real time.

Assessing ChatGPT Responses to Common Patient Questions Regarding Total Hip Arthroplasty

“…Despite some patients' safety concerns 28 and prior reports of higher rates of adverse outcomes 29 , contemporary evidence supports the safety and efficacy of outpatient surgery in appropriate patient populations [30][31][32] . Retrospective reviews of outpatient procedures [33][34][35] and development of patient-selection models [36][37][38] have assisted with patient selection. Ultimately, the chatbot recommends that the patient's surgeon make the decision regarding individual suitability for outpatient surgery.…”

Adapting Physical Therapy Practice for the “Short-Stay” Total Joint Arthroplasty Patient: A Commentary

“…Information is gathered on an ongoing basis, so that, staff schedules may be re-evaluated and adapted to match. Stratification models for patient selection for outpatient surgery and for SDD exist [1,21,24,29,46] but may not yet be integrated into the pre-surgical decisionmaking process for all providers. Improving the accuracy of the patient classification during the preoperative period would enhance the ability of PT departments to meet the unique care demands of this population.…”

Same-Day Outpatient Lower-Extremity Joint Replacement

“…These indices were not developed specifically for outpatient TJA, and their use for this purpose has recently been called into question 23,24 . As a result, many groups have attempted to use predictive modeling to aid in this difficult process 19,20,23,25,26 . To date, the most widely recognized and utilized tool is the Outpatient Arthroplasty Risk Assessment (OARA) score 23 .…”

“…These indices were not developed specifically for outpatient TJA, and their use for this purpose has recently been called into question 23,24 . As a result, many groups have attempted to use predictive modeling to aid in this difficult process 19,20,23,25,26 26 . These risk scores have not been specifically tailored to the ASC setting, and additional studies to verify the results from the hospital outpatient setting would be valuable.…”