To construct a risk prediction model for poor discharge readiness in patients undergoing elective unilateral lower extremity joint replacement based on clinical and psychosocial factors
This study successfully developed a high-precision and interpretable machine learning prediction tool that can effectively identify high-risk patients with poor discharge readiness and highlights the critical impact of shortening hospital stay, preoperative psychological state, and socioeconomic status on rehabilitation outcomes.
Abstract
Objective To construct and validate a machine learning model integrating clinical and psychosocial factors for predicting the risk of poor discharge preparation (PDP) in patients undergoing elective unilateral lower extremity joint replacement surgery. Methods This study adopted a retrospective observational cohort design, enrolling 265 adult patients who underwent elective unilateral total hip or knee arthroplasty at a tertiary grade A hospital in Fujian Province from December 2022 to April 2023. Patients were divided into the PDP group and the well-prepared group based on the median total score of the Readiness for Hospital Discharge Scale (RHDS) (97.0 points). A total of 25 variables, including demographic, clinical, fear of movement (TSK-13), and socioeconomic factors, were collected. Variable selection was performed using strongly regularized Elastic Net logistic regression, and XGBoost and Elastic Net logistic regression models were constructed, respectively. Model performance was evaluated using 5 × 5 repeated stratified cross-validation, with metrics including AUC, PR-AUC, sensitivity, specificity, calibration, and decision curve analysis (DCA). The SHAP method was used to explain the prediction mechanism of the XGBoost model. Results Elastic Net identified eight key predictors: length of hospital stay, postoperative kinesiophobia, monthly household income, educational level, preoperative kinesiophobia, age, and occupation. The XGBoost model performed the best, with an AUC of 0.833 (95% CI: 0.811–0.855) and a PR-AUC of 0.750 (95% CI: 0.708–0.790), significantly outperforming the logistic regression model (DeLong test p = 0.0035). The calibration curve showed good consistency, and DCA confirmed that it had the highest clinical net benefit within the threshold probability range of 5–40%. SHAP analysis indicated that the shortest length of hospital stay, high preoperative kinesiophobia level, and low household income were the three core risk drivers. Conclusion This study successfully developed a high-precision and interpretable machine learning prediction tool that can effectively identify high-risk patients with poor discharge readiness. The model highlights the critical impact of shortening hospital stay, preoperative psychological state, and socioeconomic status on rehabilitation outcomes, providing a scientific basis for implementing early and personalized interventions.
OBJECTIVE
The Risk Assessment and Prediction Tool (RAPT) has been utilized to anticipate discharge needs after procedures such as total joint arthroplasty. Its usefulness for spine patients, particularly those undergoing transforaminal lumbar interbody fusion (TLIF), has not been clearly established. This study evaluated the relationship between the preoperative RAPT score and 3 postoperative outcomes: discharge destination, hospital length of stay (LOS), and 30-day readmission.
METHODS
A retrospective cohort study was conducted of adults who underwent elective TLIF with a recorded preoperative RAPT score. RAPT was analyzed as a continuous variable. Home discharge and 30-day readmission were modeled with logistic regression, and LOS with linear regression. Multivariable models adjusted for age, sex, Charlson Comorbidity Index (CCI), and insurance type. Discrimination for facility discharge was assessed by receiver operating characteristic (ROC) analysis at literature-aligned thresholds (RAPT scores 9.5 and 8.5: balanced and conservative, respectively).
RESULTS
Among 116 patients, the mean age was 62.2 years and 50.9% of patients were female; the mean BMI was 29.9, and the mean CCI was 5.64. The mean RAPT score was 9.65, and the mean LOS was 3.14 days. Discharge to a skilled nursing or rehabilitation facility occurred in 6.9% of patients, and 30-day readmission occurred in 6.0%. Each 1-point increase in the RAPT score was associated with higher odds of home discharge (univariate: OR 1.74, 95% CI 1.11-2.73, p = 0.016; multivariable: OR 2.17, 95% CI 1.24-3.80, p = 0.007) and a shorter LOS (β = -0.38 days, 95% CI -0.71 to -0.05, p = 0.025; adjusted β = -0.39, bootstrap 95% CI -0.76 to -0.10, p = 0.038). The RAPT score was not associated with 30-day readmission (adjusted OR 0.93, 95% CI 0.52-1.65; p = 0.798). ROC analysis for predicting facility discharge showed moderate discrimination with an area under the curve of 0.709 (95% CI 0.543-0.876, p = 0.049), with sensitivity 63% and specificity 62% at 9.5, and sensitivity 38% and specificity 82% at 8.5. Youden's index revealed an optimal cutoff of 10.5, with sensitivity 100% and specificity 29.6%.
CONCLUSIONS
In patients undergoing TLIF, higher preoperative RAPT scores were associated with greater odds of home discharge and shorter LOS. RAPT may serve as a practical preoperative tool to support discharge planning and resource allocation in spine surgery.
Gabriel A. Gonzalez, Caden R. Moenning, Aaron Davidson et al.· Journal of Neurosurgery : Sp...· 0 citations
BACKGROUND
With major lower limb orthopaedic surgery performed in increasingly older and comorbid patients, accurate risk prediction is essential to guide perioperative management and shared decision-making.
AIMS
To compare the Clinical Frailty Scale (CFS), Charlson Comorbidity Index (CCI) and the American College of Surgeons National Surgical Quality Improvement Program Surgical Risk Calculator (ACS NSQIP Calculator) in predicting complications following major lower limb orthopaedic surgery.
METHODS
We conducted an audit assessing the clinical utility of the CFS, CCI and ACS NSQIP Calculator at an Australian tertiary hospital (2023-2024). Scores were calculated retrospectively using admission documentation, and complications were identified prospectively.
RESULTS
We recruited 302 patients with a mean age of 75.1 ± 12.7 years. Patients underwent surgery for hip fracture (n = 100), elective total knee (n = 103) and hip (n = 69) arthroplasty and other indications (n = 30). During index hospitalisation, 27.5% (n = 83) experienced a serious complication (Clavien-Dindo Grade ≥ II). All tools demonstrated moderate discrimination for serious in-hospital complications; the CFS, CCI and ACS NSQIP Calculator had area under the receiver operating characteristic curves of 0.77 (95% confidence interval (CI) 0.71-0.83), 0.71 (95% CI 0.64-0.77) and 0.76 (95% CI 0.70-0.82) respectively. The CFS was the fastest tool to administer, and the ACS NSQIP Calculator was the most time-consuming (median time 9.5 s (interquartile range (IQR) 7-13) vs 98.5 s (IQR 73-165), P < 0.001).
CONCLUSION
The CFS and ACS NSQIP Calculator demonstrated similar predictive performance in this cohort. Given its faster administration, the CFS may represent a practical tool for routine perioperative risk stratification, though prospective validation is required to confirm performance in real-time clinical workflows.
Alexa Yao, Emily Schembri, Ejoy Zhang et al.· Internal medicine journal (P...· 0 citations
This study developed and validated machine learning models to predict postoperative patient-reported outcomes, satisfaction, healthcare utilization, mortality, and return to work after primary TKA.
Shujaa T Khan, Anukriti Sharma, Shlok V Patel et al.· Journal of Arthroplasty· 0 citations
BACKGROUND
Older adults requiring emergency surgery for acute tibial fractures are vulnerable to hospital-associated complications (HACs), but admission-time risk stratification tools are lacking. We aimed to characterize HACs and develop both an ensemble prediction model and a simplified bedside risk score.
METHODS
This retrospective cohort study used the Japanese Diagnosis Procedure Combination database provided by JMDC Inc. Patients aged ≥ 65 years emergently admitted for tibial fracture (ICD-10: S82, 2014-2025) who underwent surgery within 5 days, with stay > 5 days, were included. The primary outcome was composite HACs during index hospitalization. Missing data were handled with multiple imputation. A Super Learner ensemble was developed and evaluated on held-out test data, and a simplified scorecard was derived using analysis of variance (ANOVA)-based feature selection and Weight-of-Evidence transformation.
RESULTS
Among 53,186 admissions, 5,193 met eligibility criteria. HACs occurred in 851 patients (16.4%), most commonly delirium (7.5%) and falls/trauma (5.7%). The Super Learner achieved a test-set area under the receiver operating characteristic curve (AUC) of 0.740 (95% CI 0.707-0.772), higher than conventional linear logistic regression (0.724). The most influential predictors were Hospital Frailty Risk Score, dementia, Barthel Index, comorbidity burden, and days to surgery. The simplified 7-variable scorecard achieved a test-set AUC of 0.736 (95% CI 0.703-0.769), stratifying patients into five risk groups (HAC rate: 3.45%-38.64%).
CONCLUSIONS
HAC risk after emergency tibial fracture surgery in older adults was driven primarily by geriatric vulnerability rather than fracture-specific factors. A simplified admission-time score may support targeted prevention, pending external validation.
Akio Shimizu, Ryota Sakamoto, H. Nagayama et al.· Aging Clinical and Experimen...· 0 citations
Background Post-operative delirium (POD) is a common complication in older adults undergoing total knee arthroplasty (TKA). Procedure-specific predictive models remain limited. This study aimed to develop a preliminary, internally validated, machine-learning-assisted logistic regression model using routinely available perioperative variables. Methods We retrospectively included 451 patients aged ≥60 years undergoing TKA. The cohort was randomly split into a training set (70%) and a validation set (30%). A two-stage selection was applied: Random Forest ranked candidate predictors, and LASSO regression reduced dimensionality. Selected variables were entered into a multivariable logistic regression model to estimate odds ratios (OR) and 95% confidence intervals (CI). Model performance was assessed in the validation set using the area under the receiver operating characteristic curve (AUC). Results POD occurred in 137 patients (30.4%). Six variables were selected using Random Forest and LASSO. Logistic regression showed intraoperative hypoxia as the strongest predictor (OR 6.69, 95% CI 2.90–16.6), followed by history of surgery (OR 2.55, 95% CI 1.22–5.32) and higher ASA class (ASA 2: OR 2.31, 95% CI 1.20–4.54; ASA 3: OR 2.01, 95% CI 0.99–4.15). Creatinine (per umol/L) and airway management type also showed smaller associations, while time from admission to surgery was not statistically significant. The model achieved an AUC of 0.704 in the validation set, indicating moderate discrimination. Conclusion In older adults undergoing TKA, intraoperative hypoxia, prior surgery, and higher ASA class were associated with POD risk. This preliminary machine-learning-assisted logistic regression model showed moderate discrimination in internal validation and should be externally validated before routine clinical implementation.
Huajuan Wang, Jie Yu, Li-hua Zheng et al.· Frontiers in Neurology· 0 citations