Arthroplasty Care Redesign Impacts the Predictive Accuracy of the Risk Assessment and Prediction Tool

Safety Considerations for Outpatient Arthroplasty

Since 2018, the number of total joint arthroplasties (TJAs) performed on an outpatient basis has dramatically increased. Both surgeon and anesthesiologist should be aware of the implications for the safety of outpatient TJAs and potential patient risk factors that could alter this safety profile. Although smaller studies suggest that the risk of negative outcomes is equivalent when comparing outpatient and inpatient arthroplasty, larger database analyses suggest that, even when matched for comorbidities, patients undergoing outpatient arthroplasty may be at increased risk of surgical or medical complications. Appropriate patient selection is critical for the success of any outpatient arthroplasty program. Potential exclusion criteria for outpatient TJA may include age greater than 75 years, bleeding disorder, history of deep vein thrombosis, uncontrolled diabetes mellitus, and hypoalbuminemia, among others. Patient optimization before surgery is also warranted. The potential risks of same-day versus next-day discharge have yet to be elicited in a large-scale manner.

Evaluation of Preoperative Variables that Improve the Predictive Accuracy of the Risk Assessment and Prediction Tool in Primary Total Hip Arthroplasty

INTRODUCTION

Discharge disposition after total joint arthroplasty may be predictable. Previous literature has attempted to improve upon models such as the Risk Assessment and Prediction Tool (RAPT) in an effort to optimize postoperative planning. The purpose of this study was to determine whether preoperative laboratory values and other previously unstudied demographic factors could improve the predictive accuracy of the RAPT.

METHODS

All patients included had RAPT scores in addition to the following preoperative laboratory values: red blood cell count, albumin, and vitamin D. All values were recorded within 90 days of surgery. Demographic variables including marital status, American Society of Anesthesiologists (ASA) scores, body mass index, Charlson Comorbidity Index, and depression were also evaluated. Binary logistic regression was used to determine the significance of each factor in association with discharge disposition.

RESULTS

Univariate logistic regression found significant associations between discharge disposition and all original RAPT factors as well as nonmarried patients (P < 0.001), ASA class 3 to 4 (P < 0.001), body mass index >30 kg/m2 (P = 0.065), red blood cell count <4 million/mm3 (P < 0.001), albumin <3.5 g/dL (P < 0.001), Charlson Comorbidity Index (P < 0.001), and a history of depression (P < 0.001). All notable univariate models were used to create a multivariate model with an overall predictive accuracy of 90.1%.

CONCLUSIONS

The addition of preoperative laboratory values and additional demographic data to the RAPT may improve its PA. Orthopaedic surgeons could benefit from incorporating these values as part of their discharge planning in THA. Machine learning may be able to identify other factors to make the model even more predictive.

RAPT and AM-PAC "6-Clicks": Do They Correlate on Predicting Discharge Destination After Total Joint Arthroplasty?

Background: The Risk Assessment and Prediction Tool (RAPT) and the Activity Measure for Post-Acute Care "6-Clicks" Mobility Score (AM-PAC) are validated discharge planning tools for patients undergoing total hip arthroplasty (THA) and total knee arthroplasty (TKA). Planning for discharge with these tools considers very different factors and it is important to determine if they relate. Purpose: We sought to determine whether the preoperative RAPT score would correlate with postoperative AM-PAC score for predicting discharge destination for THA and TKA populations. Secondarily, we sought to examine whether the AM-PAC and RAPT scores would remain statistically significant predictors of discharge destination despite covariates. Methods: A retrospective cohort study was performed for patients who underwent THA or TKA from January 2020 to December 2022 at a specialty orthopedic hospital. Primary variables included the RAPT score, the AM-PAC score, and discharge disposition. Correlation between AM-PAC and RAPT scores was tested using Pearson's correlation coefficient, and association between both scores and discharge destination was tested using chi-square tests and multivariable logistic regression. Results: Our comparison of AM-PAC scores and RAPT scores found a statistically significant, positive correlation in both THA and TKA patients. Regression analysis found that increased RAPT and AM-PAC scores resulted in higher odds of being discharged home for both populations, after adjusting for all other variables. In both cohorts, patients discharged to a facility were more likely to be female, be over the age of 70 years, have Medicare/Medicaid insurance, and have a higher number of preoperative social work visits or any incidence of an intraoperative or hospital complication. Conclusions: This retrospective study found that RAPT score correlated with AM-PAC score for predicting discharge destination for elective THA and TKA populations, suggesting that these scores may be predictors of home discharge destination even when accounting for covariates. Further study is recommended.

Artificial intelligence-based analysis of associations between learning curve and clinical outcomes in endoscopic and microsurgical lumbar decompression surgery

PURPOSE

A common spine surgery procedure involves decompression of the lumbar spine. The impact of the surgeon's learning curve on relevant clinical outcomes is currently not well examined in the literature. A variety of machine learning algorithms have been investigated in this study to determine how a surgeon's learning curve and other clinical parameters will influence prolonged lengths of stay (LOS), extended operating times (OT), and complications, as well as whether these clinical parameters can be reliably predicted.

METHODS

A retrospective monocentric cohort study of patients with lumbar spinal stenosis treated with microsurgical (MSD) and full-endoscopic (FED) decompression was conducted. The study included 206 patients with lumbar spinal stenosis who underwent FED (63; 30.6%) and MSD (118; 57.3%). Prolonged LOS and OT were defined as those exceeding the 75th percentile of the cohort. Furthermore, complications were assessed as a dependent variable. Using unsupervised learning, clusters were identified in the data, which helped distinguish between the early learning curve (ELC) and the late learning curve (LLC). From 15 algorithms, the top five algorithms that best fit the data were selected for each prediction task. We calculated the accuracy of prediction (Acc) and the area under the curve (AUC). The most significant predictors were determined using a feature importance analysis.

RESULTS

For the FED group, the median number of surgeries with case surgery type at the time of surgery was 72 in the ELC group and 274 in the LLC group. FED patients did not significantly differ in outcome variables (LOS, OT, complication rate) between the ELC and LLC group. The random forest model demonstrated the highest mean accuracy and AUC across all folds for each classification task. For OT, it achieved an accuracy of 76.08% and an AUC of 0.89. For LOS, the model reached an accuracy of 83.83% and an AUC of 0.91. Lastly, in predicting complications, the random forest model attained the highest accuracy of 89.90% and an AUC of 0.94. Feature importance analysis indicated that LOS, OT, and complications were more significantly affected by patient characteristics than the surgical technique (FED versus MSD) or the surgeon's learning curve.

CONCLUSIONS

A median of 72 cases of FED surgeries led to comparable clinical outcomes in the early learning curve phase compared to experienced surgeons. These outcomes seem to be more significantly affected by patient characteristics than the learning curve or the surgical technique. Several study variables, including the learning curve, can be used to predict whether lumbar decompression surgery will result in an increased LOS, OT, or complications. To introduce the provided prediction tools into clinics, the algorithms need to be implemented into open-source software and externally validated through large-scale randomized controlled trials.

Lessons Learned From the Comprehensive Care for Joint Replacement Model at an Academic Tertiary Center: The Good, the Bad, and the Ugly

BACKGROUND

Our institution participated in the Comprehensive Care for Joint Replacement (CJR) model from 2016 to 2020. Here we review lessons learned from a total joint arthroplasty (TJA) care redesign at a tertiary academic center amid changing: (1) CJR rules; (2) inpatient only rules; and (3) outpatient trends.

METHODS

Quality, financial, and patient demographic data from the years prior to and during participation in CJR were obtained from institutional and Medicare reconciled CJR performance data.

RESULTS

Despite an increase in true outpatients and new challenges that arose from changing inpatient-only rules, there was significant improvement in quality metrics: decreased length of stay (3.48-1.52 days, P < .001), increased home discharge rate (70.2-85.5%, P < .001), decreased readmission rate (17.7%-5.1%, P < .001), decreased complication rate (6.5%-2.0%, P < .001), and the Centers for Medicare and Medicaid Services (CMS) Composite Quality Score increased from 4.4 to 17.6. Over the five year period, CMS saved an estimated $8.3 million on 1,486 CJR cases, $7.5 million on 1,351 non-CJR cases, and $600,000 from the voluntary classification of 371 short-stay inpatients as outpatient-a total savings of $16.4 million. Despite major physician time and effort leading to marked improvements in efficiency, quality, and large cost savings for CMS, CJR participation resulted in a net penalty of $304,456 to our institution, leading to zero physician gainsharing opportunities.

CONCLUSION

The benefits of CJR were tempered by malalignment of incentives among payer, hospital, and physician as well as a lack of transparency. Future payment models should be refined based on the successes and challenges of CJR.

The Risk Assessment and Prediction Tool (RAPT) Score Predicts Discharge Destination, Length of Stay, and Postoperative Mobility after Total Joint Arthroplasty

INTRODUCTION

Predicting an arthroplasty patient's discharge disposition, length of stay, and physical function is helpful because it allows for preoperative patient optimization, expectation management, and discharge planning. The goal of this study was to evaluate the ability of the Risk Assessment and Prediction Tool (RAPT) score to predict discharge destination, length of stay, and postoperative mobility in patients undergoing primary total knee arthroplasty (TKA) and total hip arthroplasty (THA).

METHODS

Primary unilateral TKAs (n=9,064) and THAs (n=8,649) performed for primary osteoarthritis at our institution from 2018 to 2021 (excluding March to June 2020) were identified using a prospectively maintained institutional registry. We evaluated the associations between preoperative RAPT score and (1) discharge destination, (2) length of stay, and postoperative mobility as measured by (3) successful ambulation on the day of surgery and (4) Activity Measure for Post-Acute Care (AM-PAC) "6-Clicks" score.

RESULTS

On multivariable analyses adjusting for multiple covariates, every one-point increase in RAPT score among TKA patients was associated with a 1.82-fold increased odds of home discharge (P<0.001), 0.22 days shorter length of stay (P<0.001), 1.13-fold increased odds of ambulating on postoperative day 0 (P<0.001), and 0.25-point higher AM-PAC score (P<0.001). Similar findings were seen among THAs. A RAPT score of 8 or higher was the most sensitive and specific cutoff to predict home discharge.

CONCLUSION

Among nearly 18,000 TKA and THA patients, RAPT score was predictive of discharge disposition, length of stay, and postoperative mobility. A RAPT score of 8 or higher was the most sensitive and specific cutoff to predict discharge to home. In contrast to prior studies of the RAPT score which have grouped TKAs and THAs together, this study ran separate analyses for TKAs and THAs and found that THA patients seemed to perform better than TKA patients with equal RAPT scores, suggesting that RAPT may behave differently between TKAs and THAs, particularly in the intermediate risk RAPT range.

The Use of Risk Scores in Patient Preoperative Optimization for Total Joint Arthroplasty: A Survey of Orthopaedic Nurse Navigators

Preoperative optimization of patients seeking total joint arthroplasty is becoming more common, and risk scores, which provide an estimate for the risk of complications following procedures, are often used to assist with the preoperative decision-making process. The aim of this study was to characterize the use of risk scores at institutions that utilize nurse navigators in the preoperative optimization process. The survey included 207 nurse navigators identified via the National Association of Orthopaedic Nurses to better understand the use of risk scores in preoperative optimization and the different factors that are included in these risk scores. The study found that 48% of responding nurse navigators utilized risk scores in the preoperative optimization process. These risk scores often included patient comorbidities such as diabetes (85%) and body mass index (87%). Risk scores are commonly used by nurse navigators in preoperative optimization and involve a variety of comorbidities and patient-specific factors.

Validation of a Predictive Tool for Discharge to Rehabilitation or a Skilled Nursing Facility After TJA

BACKGROUND

Cost excess in bundled payment models for total joint arthroplasty (TJA) is driven by discharge to rehabilitation or a skilled nursing facility (SNF). A recently published preoperative risk prediction tool showed very good internal accuracy in stratifying patients on the basis of likelihood of discharge to an SNF or rehabilitation. The purpose of the present study was to test the accuracy of this predictive tool through external validation with use of a large cohort from an outside institution.

METHODS

A total of 20,294 primary unilateral total hip (48%) and knee (52%) arthroplasty cases at a tertiary health system were extracted from the institutional electronic medical record. Discharge location and the 9 preoperative variables required by the predictive model were collected. All cases were run through the model to generate risk scores for those patients, which were compared with the actual discharge locations to evaluate the cutoff originally proposed in the derivation paper. The proportion of correct classifications at this threshold was evaluated, as well as the sensitivity, specificity, positive and negative predictive values, number needed to screen, and area under the receiver operating characteristic curve (AUC), in order to determine the predictive accuracy of the model.

RESULTS

A total of 3,147 (15.5%) of the patients who underwent primary, unilateral total hip or knee arthroplasty were discharged to rehabilitation or an SNF. Despite considerable differences between the present and original model derivation cohorts, predicted scores demonstrated very good accuracy (AUC, 0.734; 95% confidence interval, 0.725 to 0.744). The threshold simultaneously maximizing sensitivity and specificity was 0.1745 (sensitivity, 0.672; specificity, 0.679), essentially identical to the proposed cutoff of the original paper (0.178). The proportion of correct classifications was 0.679. Positive and negative predictive values (0.277 and 0.919, respectively) were substantially better than those of random selection based only on event prevalence (0.155 and 0.845), and the number needed to screen was 3.6 (random selection, 6.4).

CONCLUSIONS

A previously published online predictive tool for discharge to rehabilitation or an SNF performed well under external validation, demonstrating a positive predictive value 79% higher and number needed to screen 56% lower than simple random selection. This tool consists of exclusively preoperative parameters that are easily collected. Based on a successful external validation, this tool merits consideration for clinical implementation because of its value for patient counseling, preoperative optimization, and discharge planning.

LEVEL OF EVIDENCE

Prognostic Level III . See Instructions for Authors for a complete description of levels of evidence.

Performance of Artificial Intelligence-Based Algorithms to Predict Prolonged Length of Stay after Lumbar Decompression Surgery

Background: Decompression of the lumbar spine is one of the most common procedures performed in spine surgery. Hospital length of stay (LOS) is a clinically relevant metric used to assess surgical success, patient outcomes, and socioeconomic impact. This study aimed to investigate a variety of machine learning and deep learning algorithms to reliably predict whether a patient undergoing decompression of lumbar spinal stenosis will experience a prolonged LOS. Methods: Patients undergoing treatment for lumbar spinal stenosis with microsurgical and full-endoscopic decompression were selected within this retrospective monocentric cohort study. Prolonged LOS was defined as an LOS greater than or equal to the 75th percentile of the cohort (normal versus prolonged stay; binary classification task). Unsupervised learning with K-means clustering was used to find clusters in the data. Hospital stay classes were predicted with logistic regression, RandomForest classifier, stochastic gradient descent (SGD) classifier, K-nearest neighbors, Decision Tree classifier, Gaussian Naive Bayes (GaussianNB), support vector machines (SVM), a custom-made convolutional neural network (CNN), multilayer perceptron artificial neural network (MLP), and radial basis function neural network (RBNN) in Python. Prediction accuracy and area under the curve (AUC) were calculated. Feature importance analysis was utilized to find the most important predictors. Further, we developed a decision tree based on the Chi-square automatic interaction detection (CHAID) algorithm to investigate cut-offs of predictors for clinical decision-making. Results: 236 patients and 14 feature variables were included. K-means clustering separated data into two clusters distinguishing the data into two patient risk characteristic groups. The algorithms reached AUCs between 67.5% and 87.3% for the classification of LOS classes. Feature importance analysis of deep learning algorithms indicated that operation time was the most important feature in predicting LOS. A decision tree based on CHAID could predict 84.7% of the cases. Conclusions: Machine learning and deep learning algorithms can predict whether patients will experience an increased LOS following lumbar decompression surgery. Therefore, medical resources can be more appropriately allocated to patients who are at risk of prolonged LOS.

Effect of Algoplaque Hydrocolloid Dressing Combined with Nanosilver Antibacterial Gel under Predictive Nursing in the Treatment of Medical Device-Related Pressure Injury

It was aimed at the clinical value of predictive nursing and Algoplaque hydrocolloid dressing (AHD) combined with nanosilver antibacterial gel in treating medical device-related pressure injury (MDRPI). 100 patients, who underwent surgery in Chongqing Qijiang District People's Hospital from February 2019 to February 2020, were selected as the research objects and were randomly divided into the experimental group (50 cases) and the control group (50 cases). For the characterization test, a nanosilver antibacterial gel was created first. Patients in both groups received predictive nursing, but those in the experimental group received AHD and nanosilver antibacterial gel, and those in the control group received gauzes. MDRPI incidence, pressed skin injury severity, comfort level, clothing changes, nursing satisfaction, and other factors were all compared. The particle size of the nanosilver gel was 45-85 nm, with a relatively homogeneous distribution with the medium size, according to the findings. The incidence of MDRPI in the experimental group was lower than that in the control group significantly (6% vs. 30%, P < 0.05). The degree of injury of pressured skin in the experimental group was milder than that in the control group (P < 0.05), the degree of comfort and nursing satisfaction was higher in the experimental group than in the control group (P < 0.05), and dressing change count was lower than that in the control group (P < 0.05). In the treatment of MDRPI, predictive nursing and AHD using nanosilver antibacterial gel showed high clinical application value.

RAPT score and preoperative factors to predict discharge location following adult spinal deformity surgery

PURPOSE

To assess factors, including RAPT score, predictive of non-home discharges following adult spinal deformity (ASD) operations.

METHODS

Adults who underwent thoracolumbar instrumented fusions to the pelvis for ASD (1/2019-1/2020) were reviewed. Patient demographics, RAPT metrics, hospital length of stay (LOS), operative details, and complications were compared between patients discharged home and non-home. Univariate and multivariate analyses were performed using logistic regression to determine the relative risk of non-home discharge. Area Under the Receiver Operating Characteristic curve (AUROC) for RAPT score and non-home discharge was also determined.

RESULTS

Ninety-nine patients (average age 68 ± 9 years; female-64; average RAPT 8.6 ± 2.2) were analyzed. Operations had the following characteristics: average # levels fused 11 ± 3, revisions 54%, anterior-posterior 70%, 3-column osteotomies 23%. Average LOS was 8.5 ± 3.6 days. The majority of patients (75.8%) had non-home discharges. Non-home discharges had significantly lower RAPT scores (8.3 vs. 9.6; p = 0.02), more advanced age (70 vs. 63 years; p = 0.01), and higher Charlson Comorbidity Index (CCI) scores (3.6 vs. 2.5; p < 0.01) compared to home discharges. On univariate analysis, factors significantly associated with non-home discharge were older age [relative risk (RR) 1.09, p < 0.01], higher CCI (RR 1.73, p = 0.01), total # levels fused (RR 1.24, p = 0.04), and lower RAPT scores (RR 0.71, p = 0.01). RAPT score < 8 was most predictive of non-home discharge (RR 4.87, p = 0.04). An AUROC relating RAPT scores and non-home discharge was 0.7.

CONCLUSIONS

Non-home discharges after ASD operations are common. Of the four factors associated with non-home discharges (elderly age, higher CCI, total number of levels fused, RAPT score), a RAPT score < 8 was most predictive. The RAPT score holds promising utility for pre-operative patient counseling and discharge planning for adults undergoing operations for spinal deformity.

Safety Considerations for Outpatient Arthroplasty

Since 2018, the number of total joint arthroplasties (TJAs) performed on an outpatient basis has dramatically increased. Both surgeon and anesthesiologist should be aware of the implications for the safety of outpatient TJAs and potential patient risk factors that could alter this safety profile. Although smaller studies suggest that the risk of negative outcomes is equivalent when comparing outpatient and inpatient arthroplasty, larger database analyses suggest that, even when matched for comorbidities, patients undergoing outpatient arthroplasty may be at increased risk of surgical or medical complications. Appropriate patient selection is critical for the success of any outpatient arthroplasty program. Potential exclusion criteria for outpatient TJA may include age greater than 75 years, bleeding disorder, history of deep vein thrombosis, uncontrolled diabetes mellitus, and hypoalbuminemia, among others. Patient optimization before surgery is also warranted. The potential risks of same-day versus next-day discharge have yet to be elicited in a large-scale manner.

The Predictive Accuracy of the CareMOSAIC Risk Assessment for Discharge Disposition in Medicare Bundle Patients After Total Joint Arthroplasty

Background

This article evaluates the predictive accuracy of the CareMOSAIC Risk Assessment for discharge disposition in Medicare patients undergoing total joint arthroplasty.

Methods

Retrospectively collected data from a single institution on 499 consecutive Medicare patients who underwent primary total hip arthroplasty or total knee arthroplasty were reviewed. The CareMOSAIC Risk Assessment was completed by each patient during the preoperative period. The CareMOSAIC Risk Assessment scores were calculated via the CareMOSAIC software, and the scores indicate a risk category for each patient as it relates to post–acute care discharge needs.

Results

The CareMOSAIC Risk Assessment with a binary logistic regression area under the receiver operating characteristic curve of 0.798 appears to be a reliable tool for predicting discharge disposition. The assessment had a positive predictive value of 90.0% and negative predictive value of 76.3% for discharge disposition.

Conclusions

The CareMOSAIC Risk Assessment effectively predicts the discharge disposition for Medicare patients undergoing total hip or total knee arthroplasty.

Machine Learning Prediction of Length of Stay in Adult Spinal Deformity Patients Undergoing Posterior Spine Fusion Surgery

(1) Background: Length of stay (LOS) is a commonly reported metric used to assess surgical success, patient outcomes, and economic impact. The focus of this study is to use a variety of machine learning algorithms to reliably predict whether a patient undergoing posterior spinal fusion surgery treatment for Adult Spine Deformity (ASD) will experience a prolonged LOS. (2) Methods: Patients undergoing treatment for ASD with posterior spinal fusion surgery were selected from the American College of Surgeon's NSQIP dataset. Prolonged LOS was defined as a LOS greater than or equal to 9 days. Data was analyzed with the Logistic Regression, Decision Tree, Random Forest, XGBoost, and Gradient Boosting functions in Python with the Sci-Kit learn package. Prediction accuracy and area under the curve (AUC) were calculated. (3) Results: 1281 posterior patients were analyzed. The five algorithms had prediction accuracies between 68% and 83% for posterior cases (AUC: 0.566-0.821). Multivariable regression indicated that increased Work Relative Value Units (RVU), elevated American Society of Anesthesiologists (ASA) class, and longer operating times were linked to longer LOS. (4) Conclusions: Machine learning algorithms can predict if patients will experience an increased LOS following ASD surgery. Therefore, medical resources can be more appropriately allocated towards patients who are at risk of prolonged LOS.

Readmission, Complication, and Disposition Calculators in Total Joint Arthroplasty: A Systemic Review

BACKGROUND

Predictive tools are useful adjuncts in surgical planning. They help guide patient selection, candidacy for inpatient vs outpatient surgery, and discharge disposition as well as predict the probability of readmissions and complications after total joint arthroplasty (TJA). Surgeons may find it difficult due to significant variation among risk calculators to decide which tool is best suited for a specific patient for optimal decision-based care. Our aim is to perform a systematic review of the literature to determine the existing post-TJA readmission calculators and compare the specific elements that comprise their formula. Second, we intend to evaluate the pros and cons of each calculator.

METHODS

Using a Preferred Reporting Items for Systematic Reviews and Meta-Analysis Protocols protocol, we conducted a systematic search through 3 major databases for publications addressing TJA risk stratification tools for readmission, discharge disposition, and early complications. We excluded those manuscripts that were not comprehensive for hips and knees, did not list discharge, readmission or complication as the primary outcome, or were published outside the North America.

RESULTS

Ten publications met our criteria and were compared on their sourced data, variable types, and overall algorithm quality. Seven of these were generated with single institution data and 3 from large administrative datasets. Three tools determined readmission risk, 5 calculated discharge disposition, and 2 predicted early complications. Only 4 prediction tools were validated by external studies. Seven studies utilized preoperative data points in their risk equations while 3 utilized intraoperative or postsurgical data to delineate risk.

CONCLUSION

The extensive variation among TJA risk calculators underscores the need for tools with more individualized stratification capabilities and verification. The transition to outpatient and same-day discharge TJA may preclude or change the need for many of these calculators. Further studies are needed to develop more streamlined risk calculator tools that predict readmission and surgical complications.

Predictive Value of the Risk Assessment and Prediction Tool (RAPT) Score for Primary Hip and Knee Arthroplasty Patients: A Single-Center Study

The Risk Assessment and Prediction Tool (RAPT) was developed to predict patient discharge destination for arthroplasty operations. However, since Enhanced Recovery After Surgery (ERAS) programs have been utilized in the UK, the RAPT score has not been validated for use. The aim of the current study was to evaluate the predictive validity of the RAPT score in an ERAS environment with short length of stay. Data were compiled from 545 patients receiving a primary elective total hip or total knee arthroplasty in a district general hospital over 12 months. RAPT scores, length of stay, and discharge destinations were recorded. Patients were classified as low, intermediate, or high risk as per their RAPT score. Length of stay was significantly different between groups (p = 0.008), with low-risk patients having shorter length of stay. However, RAPT scores did not predict discharge destination; the overall correct prediction was only 31.9%. Furthermore, the most likely discharge destination was directly home in ≤3 days in all groups (68.5%, 60.2%, and 40% for the low-, intermediate-, and high-risk groups, respectively). The RAPT score is not an adequate tool to predict the discharge disposition following primary total knee and hip replacement surgery in a UK hospital with a standardized modern ERAS program. Alternative predictive tools are required.

Modifying the RAPT Score to Reflect Discharge Destination in Current Practice

Background

The Risk Assessment Prediction Tool (RAPT) is a validated 6-question survey designed to predict primary total joint arthroplasty (TJA) patients’ discharge disposition. It is scored from 1 to 12 with patients stratified into high-, intermediate-, and low-risk groups. Given recent advancements in rapid-discharge protocols and increasing utilization of home services, the RAPT score may require modified scoring cutoffs.

Methods

A retrospective chart review of all patients undergoing primary TJA at a single academic center over 14 months was performed. The RAPT score was implemented during the sixth month. Patients undergoing revision TJA, complex TJA, and TJA after resection of malignancy were excluded. Outcomes before and after RAPT implementation were analyzed with additional subanalysis investigating of post-RAPT data.

Results

A total of 1264 patients (624 Pre-RAPT and 640 Post-RAPT) were evaluated. The post-RAPT group (245 total hip arthroplasty and 395 total knee arthroplasty) experienced significant decreases in mean hospital length of stay (2.22 days pre-RAPT to 1.82 days post-RAPT, P < .001) and the proportion of patients discharged to facility (21.8% pre-RAPT to 15.2% post-RAPT, P = .002). The modified system demonstrated the highest overall predictive accuracy at 92% and was found to be predictive of hospital length of stay.

Conclusion

Owing to the recent trends favoring in-home services over rehab facility after discharge, previously published RAPT scoring cutoffs are inaccurate for modern practice. Using mRAPT cutoffs maximizes the number of patients for whom a discharge prediction can be made, while maintaining excellent predictive accuracy.

Compilation and Analysis of Web-Based Orthopedic Personalized Predictive Tools: A Scoping Review

Web-based personalized predictive tools in orthopedic surgery are becoming more widely available. Despite rising numbers of these tools, many orthopedic surgeons may not know what tools are available, how these tools were developed, and how they can be utilized. The aim of this scoping review is to compile and synthesize the profile of existing web-based orthopedic tools. We conducted two separate PubMed searches-one a broad search and the second a more targeted one involving high impact journals-with the aim of comprehensively identifying all existing tools. These articles were then screened for functional tool URLs, methods regarding the tool's creation, and general inputs and outputs required for the tool to function. We identified 57 articles, which yielded 31 unique web-based tools. These tools involved various orthopedic conditions (e.g., fractures, osteoarthritis, musculoskeletal neoplasias); interventions (e.g., fracture fixation, total joint arthroplasty); outcomes (e.g., mortality, clinical outcomes). This scoping review highlights the availability and utility of a vast array of web-based personalized predictive tools for orthopedic surgeons. Increased awareness and access to these tools may allow for better decision support, surgical planning, post-operative expectation management, and improved shared decision-making.

An Electronic Medical Record-Based Discharge Disposition Tool Gets Bundle Busted: Decaying Relevance of Clinical Data Accuracy in Machine Learning

Background

Determining discharge disposition after total joint arthroplasty (TJA) has been a challenge. Advances in machine learning (ML) have produced computer models that learn by example to generate predictions on future events. We hypothesized a trained ML algorithm’s diagnostic accuracy will be better than that of current predictive tools to predict discharge disposition after primary TJA.

Methods

This study was a retrospective cohort study from a single, tertiary referral center for primary TJA. We trained and validated an artificial neural network (ANN) based on 4368 distinct surgical encounters between 1/1/2013 and 6/28/2016. The ANN’s ability to identify discharge disposition was then tested on 1452 distinct surgical encounters between 1/3/17 and 11/30/17.

Results

The area under the curve and accuracy achieved during model validation were 0.973 and 91.7%, respectively, with 25% of patients being discharged to skilled nursing facilities (SNFs). Within our testing data set, 6.7% of patients went to SNFs. The performance in the testing set included an area under the curve of 0.804, accuracy of 61.3%, sensitivity of 28.9%, and specificity of 93.8%.

Conclusions

This is the first prediction tool using an electronic medical record–integrated ANN to predict discharge disposition after TJA based on locally generated data. Dramatically reduced numbers of patients discharged to SNFs due to implementation of a bundled payment model lead to poor recall in the testing model. This model serves as a proof of concept for developing an ML prediction tool using a relatively small data set and subsequent integration into the electronic medical record.

The Risk Assessment and Prediction Tool Accurately Predicts Discharge Destination After Revision Hip and Knee Arthroplasty

BACKGROUND

The Risk Assessment and Prediction Tool (RAPT) was developed and validated to predict discharge disposition after primary total hip and knee arthroplasty (THA/TKA). To date, there are no studies evaluating the applicability and accuracy of RAPT for revision THA/TKA. This study aims to determine the predictive accuracy of the RAPT for revision THA/TKA.

METHODS

Prospectively collected data from a single tertiary academic medical center were retrospectively analyzed for patients undergoing revision THA/TKA between January 2016 and July 2019. RAPT score was used to predict their postoperative discharge destination and its predictive accuracy was calculated. Patient risk (low, intermediate, and high) for postoperative inpatient rehabilitation facilities or skilled nursing facilities were determined based on the predictive accuracy of each RAPT score. Other factors evaluated included patient-reported discharge expectation, body mass index, and American Society of Anesthesiologists scores.

RESULTS

A total of 716 consecutive revision THA/TKA episodes were analyzed. Overall, predictive accuracy of RAPT for discharge disposition was 83%. RAPT scores <3 and >8 were deemed high and low risk of discharge to a post-acute care facility, respectively. RAPT scores of 4 to 7 were still accurate 65%-71% of the time and were deemed to be intermediate-risk. RAPT score and patient-reported discharge expectation had the strongest correlation with actual discharge disposition.

CONCLUSION

The RAPT has high predictive accuracy for discharge planning in revision THA/TKA patients. Patient-expected discharge destination is a powerful modulator of the RAPT score and we suggest that it be taken into consideration for preoperative discharge planning.