Development of a Novel Prospective Model to Predict Unplanned 90-Day Readmissions After Total Hip Arthroplasty

A preoperative risk assessment tool for predicting adverse outcomes among total shoulder arthroplasty patients

BACKGROUND

With the increased utilization of Total Shoulder Arthroplasty (TSA) in the outpatient setting, understanding the risk factors associated with complications and hospital readmissions becomes a more significant consideration. Prior developed assessment metrics in the literature either consisted of hard-to-implement tools or relied on postoperative data to guide decision-making. This study aimed to develop a preoperative risk assessment tool to help predict the risk of hospital readmission and other postoperative adverse outcomes.

METHODS

We retrospectively evaluated the 2019-2022(Q2) Medicare fee-for-service inpatient and outpatient claims data to identify primary anatomic or reserve TSAs and to predict postoperative adverse outcomes within 90 days postdischarge, including all-cause hospital readmissions, postoperative complications, emergency room visits, and mortality. We screened 108 candidate predictors, including demographics, social determinants of health, TSA indications, prior 12-month hospital, and skilled nursing home admissions, comorbidities measured by hierarchical conditional categories, and prior orthopedic device-related complications. We used two approaches to reduce the number of predictors based on 80% of the data: 1) the Least Absolute Shrinkage and Selection Operator logistic regression and 2) the machine-learning-based cross-validation approach, with the resulting predictor sets being assessed in the remaining 20% of the data. A scoring system was created based on the final regression models' coefficients, and score cutoff points were determined for low, medium, and high-risk patients.

RESULTS

A total of 208,634 TSA cases were included. There was a 6.8% hospital readmission rate with 11.2% of cases having at least one postoperative adverse outcome. Fifteen covariates were identified for predicting hospital readmission with the area under the curve of 0.70, and 16 were selected to predict any adverse postoperative outcome (area under the curve = 0.75). The Least Absolute Shrinkage and Selection Operator and machine learning approaches had similar performance. Advanced age and a history of fracture due to orthopedic devices are among the top predictors of hospital readmissions and other adverse outcomes. The score range for hospital readmission and an adverse postoperative outcome was 0 to 48 and 0 to 79, respectively. The cutoff points for the low, medium, and high-risk categories are 0-9, 10-14, ≥15 for hospital readmissions, and 0-11, 12-16, ≥17 for the composite outcome.

CONCLUSION

Based on Medicare fee-for-service claims data, this study presents a preoperative risk stratification tool to assess hospital readmission or adverse surgical outcomes following TSA. Further investigation is warranted to validate these tools in a variety of diverse demographic settings and improve their predictive performance.

Early Readmission and Revision After Total Joint Arthroplasty: An Analysis of Cause and Cost

Background: Bundled payments for total joint arthroplasty (TJA) were instituted by the Centers for Medicare and Medicaid Services (CMS) to reimburse providers a lump sum for operative and 90-day postoperative costs. Gaining a better understanding of which TJA patients are at risk for early return to the operating room (OR) is critical in preoperative optimization of those with modifiable risks, which could improve bundled-payment performance. Purpose: We sought to identify the most common reason for readmissions, as well as patient characteristics and costs, associated with early return to the OR among TJA patients. Methods: This was a retrospective cohort study of Medicare patients who had undergone primary total hip or knee arthroplasty (THA or TKA) between 2013 and 2018 at a tertiary care hospital. We used the CMS research identifiable files database to identify the most common reasons for readmissions and revisions within 90 days of surgery. Total billing claims were used to determine the cost of early readmissions and revisions. Multivariate regression analysis was used to determine the characteristics associated with early readmission or revision. Results: Out of 20 166 primary TJA patients identified, we found 1349 readmissions (5.6%) and 163 (0.8%) revisions within 90 days of surgery. Dislocation was the most common indication for readmission, and periprosthetic joint infection was the most common indication for revision. Early return to the OR was associated with a mean $105,988 (standard deviation [SD] = $76,865) in CMS claims for the inpatient stay. Factors associated with a higher risk of early reoperation were female sex, THA, longer length of stay, and discharge to long-term care facility. Conclusions: This retrospective cohort study found that early return to the OR after TJA increased overall 90-day costs by 260%, suggesting that early reoperation might have a significant impact on bundled payments. Further study is warranted.

Machine Learning-Based Predictive Models for 90-Day Readmission of Total Joint Arthroplasty Using Comprehensive Electronic Health Records and Patient-Reported Outcome Measures

Background

The Centers for Medicare & Medicaid Services currently incentivizes hospitals to reduce postdischarge adverse events such as unplanned hospital readmissions for patients who underwent total joint arthroplasty (TJA). This study aimed to predict 90-day TJA readmissions from our comprehensive electronic health record data and routinely collected patient-reported outcome measures.

Methods

We retrospectively queried all TJA-related readmissions in our tertiary care center between 2016 and 2019. A total of 104-episode care characteristics and preoperative patient-reported outcome measures were used to develop several machine learning models for prediction performance evaluation and comparison. For interpretability, a logistic regression model was built to investigate the statistical significance, magnitudes, and directions of associations between risk factors and readmission.

Results

Given the significant imbalanced outcome (5.8% of patients were readmitted), our models robustly predicted the outcome, yielding areas under the receiver operating characteristic curves over 0.8, recalls over 0.5, and precisions over 0.5. In addition, the logistic regression model identified risk factors predicting readmission: diabetes, preadmission medication prescriptions (ie, nonsteroidal anti-inflammatory drug, corticosteroid, and narcotic), discharge to a skilled nursing facility, and postdischarge care behaviors within 90 days. Notably, low self-reported confidence to carry out social activities accurately predicted readmission.

Conclusions

A machine learning model can help identify patients who are at substantially increased risk of a readmission after TJA. This finding may allow for health-care providers to increase resources targeting these patients. In addition, a poor response to the "social activities" question may be a useful indicator that predicts a significant increased risk of readmission after TJA.