Generalizability of machine learning models predicting 30-day unplanned readmission after primary total knee arthroplasty using a nationally representative database.

Unplanned readmission after primary total knee arthroplasty (TKA) costs an average of US $39,000 per episode and negatively impacts patient outcomes. Although predictive machine learning (ML) models show promise for risk stratification in specific populations, existing studies do not address model generalizability. This study aimed to establish the generalizability of previous institutionally developed ML models to predict 30-day readmission following primary TKA using a national database. Data from 424,354 patients from the ACS-NSQIP database was used to develop and validate four ML models to predict 30-day readmission risk after primary TKA. Individual model performance was assessed and compared based on discrimination, accuracy, calibration, and clinical utility. Length of stay (> 2.5 days), body mass index (BMI) (> 33.21 kg/m2), and operation time (> 93 min) were important determinants of 30-day readmission. All ML models demonstrated equally good accuracy, calibration, and discriminatory ability (Brier score, ANN = RF = HGB = NEPLR = 0.03; ANN, slope = 0.90, intercept = - 0.11; RF, slope = 0.93, intercept = - 0.12; HGB, slope = 0.90, intercept = - 0.12; NEPLR, slope = 0.77, intercept = 0.01; AUCANN = AUCRF = AUCHGB = AUCNEPLR = 0.78). This study validates the generalizability of four previously developed ML algorithms in predicting readmission risk in patients undergoing TKA and offers surgeons an opportunity to reduce readmissions by optimizing discharge planning, BMI, and surgical efficiency.

Predicting 30-day unplanned hospital readmission after revision total knee arthroplasty: machine learning model analysis of a national patient cohort.

Revision total knee arthroplasty (TKA) is associated with a higher risk of readmission than primary TKA. Identifying individual patients predisposed to readmission can facilitate proactive optimization and increase care efficiency. This study developed machine learning (ML) models to predict unplanned readmission following revision TKA using a national-scale patient dataset. A total of 17,443 revision TKA cases (2013-2020) were acquired from the ACS NSQIP database. Four ML models (artificial neural networks, random forest, histogram-based gradient boosting, and k-nearest neighbor) were developed on relevant patient variables to predict readmission following revision TKA. The length of stay, operation time, body mass index (BMI), and laboratory test results were the strongest predictors of readmission. Histogram-based gradient boosting was the best performer in distinguishing readmission (AUC: 0.95) and estimating the readmission probability for individual patients (calibration slope: 1.13; calibration intercept: -0.00; Brier score: 0.064). All models produced higher net benefit than the default strategies of treating all or no patients, supporting the clinical utility of the models. ML demonstrated excellent performance for the prediction of readmission following revision TKA. Optimization of important predictors highlighted by our model may decrease preventable hospital readmission following surgery, thereby leading to reduced financial burden and improved patient satisfaction.

Evaluating the safe zone for lumbar pedicle screws: are midline crossing screws indicative of pedicle breach?

BACKGROUND CONTEXT: Pedicle screw breach (PSB) is not uncommon following lumbar instrumentation, and in some instances, it may lead to vascular and/or neurologic complications. Previous literature suggested that screws crossing the vertebral midline on an anterior-posterior (AP) radiograph (or midsagittal on CT) are concerning for medial pedicle breach. OBJECTIVE: Our primary aim was to map out the safe zones (SZ) of bilateral pedicle instrumentation and their relationship at each lumbar vertebral level. Our secondary aim was to evaluate the presence of SZs' intersection at each lumbar level, denoting safe midline pedicle screw crossing not otherwise associated with medial pedicle breach. STUDY DESIGN/SETTING: Retrospective Anatomical Study. PATIENT SAMPLE: Adult patients in the from "The Cancer Imaging Archive" (TCIA) database who have not had thoraco-lumbo-sacral fusion. OUTCOME MEASURES: Physiologic measures obtained through 3D analysis of CT images and virtual pedicle screws. METHOD: CT scans of 51 patients were randomly selected from "The Cancer Imaging Archive" (TCIA) online database for analysis. The Sectra 3D Spine software was used to create 3D renderings, place virtual screws, and make measurements. At each lumbar vertebra, the right and left pedicle corridors were mapped. At each pedicle, two screw positions were templated, the "medial limit screw" (MLS) and the "lateral limit screw" (LLS). Each limit screw was the most extreme position that the screw could exist in without causing a medial or lateral breach. The safe zone was defined as the zone between MLS and LLS. Measurements were taken for each level (between L1 and L5) and side (Left, Right). RESULTS: A total of 253 lumbar vertebrae from 51 patients (mean age 53.1, 56.9% male) were included. Two vertebrae from two patients were removed for poor image quality. Out of the 506 screw positions analyzed in our study, 97.4% had overlapping SZ and crossed the midplane without medial pedicle breach. The significant factors (p<.01) for safe midplane-crossing screws included: the screw length (L1-L5); the laterality of the screw entry point (L1-L4); and the pedicle diameter (L2 and L5). CONCLUSIONS: A midline crossing pedicle screw on a lumbar AP radiograph is not necessarily indicative of a medial pedicle screw breach. Anatomical (ie, larger pedicle diameter) and technical (ie, longer screws, and lateral entry points) factors allow for safety zone intersections and indicate safe midline crossing by pedicle screws.

Do preoperative PROMIS scores independently predict 90-day readmission following primary total knee arthroplasty?

INTRODUCTION: The rising demand for total knee arthroplasty (TKA) is expected to increase the total number of TKA-related readmissions, presenting significant public health and economic burden. With the increasing use of Patient-Reported Outcomes Measurement Information System (PROMIS) scores to inform clinical decision-making, this study aimed to investigate whether preoperative PROMIS scores are predictive of 90-day readmissions following primary TKA. MATERIALS AND METHODS: We retrospectively reviewed a consecutive series of 10,196 patients with preoperative PROMIS scores who underwent primary TKA. Two comparison groups, readmissions (n = 79; 3.6%) and non-readmissions (n = 2091; 96.4%) were established. Univariate and multivariate logistic regression analyses were then performed with readmission as the outcome variable to determine whether preoperative PROMIS scores could predict 90-day readmission. RESULTS: The study cohort consisted of 2170 patients overall. Non-white patients (OR = 3.53, 95% CI [1.16, 10.71], p = 0.026) and patients with cardiovascular or cerebrovascular disease (CVD) (OR = 1.66, 95% CI [1.01, 2.71], p = 0.042) were found to have significantly higher odds of 90-day readmission after TKA. Preoperative PROMIS-PF10a (p = 0.25), PROMIS-GPH (p = 0.38), and PROMIS-GMH (p = 0.07) scores were not significantly associated with 90-day readmission. CONCLUSION: This study demonstrates that preoperative PROMIS scores may not be used to predict 90-day readmission following primary TKA. Non-white patients and patients with CVD are 3.53 and 1.66 times more likely to be readmitted, highlighting existing racial disparities and medical comorbidities contributing to readmission in patients undergoing TKA.

Can machine learning models predict prolonged length of hospital stay following primary total knee arthroplasty based on a national patient cohort data?

INTRODUCTION: The total length of stay (LOS) is one of the biggest determinators of overall care costs associated with total knee arthroplasty (TKA). An accurate prediction of LOS could aid in optimizing discharge strategy for patients in need and diminishing healthcare expenditure. The aim of this study was to predict LOS following TKA using machine learning models developed on a national-scale patient cohort. METHODS: The ACS-NSQIP database was queried to acquire 267,966 TKA cases from 2013 to 2020. Four machine learning models-artificial neural network (ANN), random forest, histogram-based gradient boosting, and k-nearest neighbor were trained and tested on the dataset for the prediction of prolonged LOS (LOS exceeded the 75th of all values in the cohort). The model performance was assessed by discrimination (area under the receiver operating characteristic curve [AUC]), calibration, and clinical utility. RESULTS: ANN delivered the best performance among the four models. ANN distinguished prolonged LOS in the study cohort with an AUC of 0.71 and accurately predicted the probability of prolonged LOS for individual patients (calibration slope: 0.82; calibration intercept: 0.03; Brier score: 0.089). All models demonstrated clinical utility by generating positive net benefits in decision curve analyses. Operation time, pre-operative transfusion, pre-operative laboratory tests (hematocrit, platelet count, and white blood cell count), and BMI were the strongest predictors of prolonged LOS. CONCLUSION: ANN demonstrated modest discrimination capacity and excellent performance in calibration and clinical utility for the prediction of prolonged LOS following TKA. Clinical application of the machine learning models has the potential to improve care coordination and discharge planning for patients at high risk of extended hospitalization after surgery. Incorporating more relevant patient factors may further increase the models' prediction strength.

Validation of Machine Learning Model Performance in Predicting Blood Transfusion After Primary and Revision Total Hip Arthroplasty.

BACKGROUND: The rates of blood transfusion following primary and revision total hip arthroplasty (THA) remain as high as 9% and 18%, respectively, contributing to patient morbidity and healthcare costs. Existing predictive tools are limited to specific populations, thereby diminishing their clinical applicability. This study aimed to externally validate our previous institutionally developed machine learning (ML) algorithms to predict the risk of postoperative blood transfusion following primary and revision THA using national inpatient data. METHODS: Five ML algorithms were trained and validated using data from 101,266 primary THA and 8,594 revision THA patients from a large national database to predict postoperative transfusion risk after primary and revision THA. Models were assessed and compared based on discrimination, calibration, and decision curve analysis. RESULTS: The most important predictors of transfusion following primary and revision THA were preoperative hematocrit (<39.4%) and operation time (>157 minutes), respectively. All ML models demonstrated excellent discrimination (area under the curve (AUC) >0.8) in primary and revision THA patients, with artificial neural network (AUC = 0.84, slope = 1.11, intercept = -0.04, Brier score = 0.04), and elastic-net-penalized logistic regression (AUC = 0.85, slope = 1.08, intercept = -0.01, and Brier score = 0.12) performing best, respectively. On decision curve analysis, all 5 models demonstrated a higher net benefit than the conventional strategy of intervening for all or no patients in both patient cohorts. CONCLUSIONS: This study successfully validated our previous institutionally developed ML algorithms for the prediction of blood transfusion following primary and revision THA. Our findings highlight the potential generalizability of predictive ML tools developed using nationally representative data in THA patients.

Machine Learning Models Based on a National-Scale Cohort Identify Patients at High Risk for Prolonged Lengths of Stay Following Primary Total Hip Arthroplasty.

BACKGROUND: Existing machine learning models that predicted prolonged lengths of stay (LOS) following primary total hip arthroplasty (THA) were limited by the small training volume and exclusion of important patient factors. This study aimed to develop machine learning models using a national-scale data set and examine their performance in predicting prolonged LOS following THA. METHODS: A total of 246,265 THAs were analyzed from a large database. Prolonged LOS was defined as exceeding the 75th percentile of all LOSs in the cohort. Candidate predictors of prolonged LOS were selected by recursive feature elimination and used to construct four machine learning models-artificial neural network, random forest, histogram-based gradient boosting, and k-nearest neighbor. The model performance was assessed by discrimination, calibration, and utility. RESULTS: All models exhibited excellent performance in discrimination (area under the receiver operating characteristic curve [AUC] = 0.72 to 0.74) and calibration (slope: 0.83 to 1.18, intercept: -0.01 to 0.11, Brier score: 0.185 to 0.192) during both training and testing sessions. The artificial neural network was the best performer with an AUC of 0.73, calibration slope of 0.99, calibration intercept of -0.01, and Brier score of 0.185. All models showed great utility by producing higher net benefits than the default treatment strategies in the decision curve analyses. Age, laboratory tests, and surgical variables were the strongest predictors of prolonged LOS. CONCLUSION: The excellent prediction performance of machine learning models demonstrated their capacity to identify patients prone to prolonged LOS. Many factors contributing to prolonged LOS can be optimized to minimize hospital stay for high-risk patients.

Internal and External Validation of the Generalizability of Machine Learning Algorithms in Predicting Non-home Discharge Disposition Following Primary Total Knee Joint Arthroplasty.

BACKGROUND: Nonhome discharge disposition following primary total knee arthroplasty (TKA) is associated with a higher rate of complications and constitutes a socioeconomic burden on the health care system. While existing algorithms predicting nonhome discharge disposition varied in degrees of mathematical complexity and prediction power, their capacity to generalize predictions beyond the development dataset remains limited. Therefore, this study aimed to establish the machine learning model generalizability by performing internal and external validations using nation-scale and institutional cohorts, respectively. METHODS: Four machine learning models were trained using the national cohort. Recursive feature elimination and hyper-parameter tuning were applied. Internal validation was achieved through five-fold cross-validation during model training. The trained models' performance was externally validated using the institutional cohort and assessed by discrimination, calibration, and clinical utility. RESULTS: The national (424,354 patients) and institutional (10,196 patients) cohorts had non-home discharge rates of 19.4 and 36.4%, respectively. The areas under the receiver operating curve of the model predictions were 0.83 to 0.84 during internal validation and increased to 0.88 to 0.89 during external validation. Artificial neural network and histogram-based gradient boosting elicited the best performance with a mean area under the receiver operating curve of 0.89, calibration slope of 1.39, and Brier score of 0.14, which indicated that the two models were robust in distinguishing non-home discharge and well-calibrated with accurate predictions of the probabilities. The low inter-dataset similarity indicated reliable external validation. Length of stay, age, body mass index, and sex were the strongest predictors of discharge destination after primary TKA. CONCLUSION: The machine learning models demonstrated excellent predictive performance during both internal and external validations, supporting their generalizability across different patient cohorts and potential applicability in the clinical workflow.