The utility of the Risk Assessment and Prediction Tool in predicting discharge disposition, length of stay, and readmissions in patients undergoing transforaminal lumbar interbody fusion.
Aug 2026· Journal of Neurosurgery : Spine· pp.
1-7
· 0 citations· 19 references
Medicine
Abstract
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.
BACKGROUND
Frailty assessment has become increasingly important in predicting surgical outcomes, particularly in complex revision procedures. Among patients undergoing revision total hip arthroplasty (rTHA) for mechanical prosthetic complications, optimal frailty stratification remains poorly defined. This study compared the Risk Analysis Index (RAI) and the modified 5-item frailty index (mFI-5) in predicting postoperative outcomes within this high-risk population.
METHODS
We conducted a retrospective cohort study of 5631 adult patients undergoing rTHA for mechanical prosthetic complications using data from the 2015-2021 American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP). Frailty was assessed using RAI and mFI-5, calculated via published algorithms. Primary outcomes were 30-day all-cause mortality and non-home discharge. Secondary outcomes included major complications, minor complications, unplanned readmission, reoperation, and extended length of stay (LOS >4 days). Discriminative performance was evaluated using receiver operating characteristic curves and area under the curve (AUC) analysis, with bootstrap resampling (100 iterations) for internal validation.
RESULTS
Mean patient age was 66.80 ± 11.57 years with 57.61% female. Overall, 30-day mortality was 0.4% with major complications occurring in 2.4%. RAI demonstrated superior discrimination for mortality (AUC 0.822) compared to mFI-5 (0.688, p < 0.001). For non-home discharge, RAI achieved AUC 0.735 versus mFI-5 0.607 (p < 0.001). RAI showed strong performance for extended length of stay (AUC 0.624) and minor complications (AUC 0.652), significantly outperforming mFI-5 across multiple outcome measures.
CONCLUSION
The Risk Analysis Index significantly outperforms the mFI-5 across key outcomes following revision total hip arthroplasty for mechanical prosthetic complications. Its multidomain structure, which captures age, functional dependence, comorbidities, and acute physiological stress, makes it a superior tool for surgical risk stratification, discharge planning, and identifying high-risk patients who may benefit from targeted perioperative optimisation.
C. Sabet, Bhav Jain, Jad J. Lawand et al.· HIP International· 0 citations
BACKGROUND
Patient-reported outcome measures and healthcare utilization metrics are increasingly used to evaluate the success of total knee arthroplasty (TKA). Predictive models may improve preoperative planning, patient counseling, and resource allocation. 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.
METHODS
A prospective cohort of 14,900 patients who underwent primary unilateral TKA at a large tertiary academic center from 2016 to 2022 was analyzed. Patients undergoing bilateral TKA or missing baseline patient-reported outcome measures were excluded. Random Forest and XGBoost models were developed using baseline demographic, clinical, socioeconomic, and surgical variables. Outcomes included postoperative Knee injury and Osteoarthritis Outcome Score (KOOS) Pain, Physical Function, Joint Replacement, and Quality of Life subscales; Patient Acceptable Symptom State; length of stay; discharge disposition; 90-day readmission; 1-year mortality; and return to work. Model performance was evaluated using root mean square error for continuous outcomes and accuracy for categorical outcomes.
RESULTS
Predictive performance was moderate to strong across outcomes. For KOOS outcomes, root mean square error ranged from 15.13 to 23.49. Accuracy for healthcare utilization outcomes ranged from 55 to 71%. Accuracy reached 73% for 1-year mortality and 78% for return to work. Important predictors across models included baseline KOOS Joint Replacement score, patient-reported outcome phenotype, age, body mass index, Area Deprivation Index, race, and surgery start time. The Charlson Comorbidity Index also contributed to the prediction of select clinical outcomes.
CONCLUSION
Machine learning models demonstrated moderate to strong performance for predicting patient-reported outcomes, satisfaction, healthcare utilization, mortality, and return to work after TKA. Integration of these tools may allow population-level variable parsing - identifying distinct socioeconomic, functional, and operational signals within an optimized cohort. External validation is needed before widespread clinical implementation.
Shujaa T Khan, Anukriti Sharma, Shlok V Patel et al.· Journal of Arthroplasty· 0 citations
INTRODUCTION
Same-day discharge (SDD) following primary total hip arthroplasty (THA) is increasingly utilized and has been shown to be safe in appropriately selected patients. However, limited data compare whether specific patient risk factors for postoperative readmission exert different magnitudes of influence in the SDD versus in the non-same-day discharge (NSDD) cohorts. Identifying risk factors that disproportionately affect SDD patients may refine SDD selection criteria and improve postoperative safety.: METHODS: This retrospective cohort study evaluated 11,245 patients who underwent primary elective THA at a single institution between 2017 and 2024. Patients were grouped by discharge timing into SDD (n = 2,318) and NSDD (n = 8,927). The primary outcome was orthopaedic-related hospital readmission within 90 days. Multivariable logistic regression models were constructed separately for SDD and NSDD cohorts to identify independent predictors of readmission. Adjusted odds ratios were compared between cohorts using z-tests to assess differences in effect magnitude. A sub-analysis was performed among cases by high-volume surgeons (≥ 100 THAs/year).
RESULTS
The SDD patients had a significantly lower 90-day readmission rate compared with NSDD patients (0.8 versus 2.1%, P < 0.001). In SDD patients, smoking (odds ratio (OR) 13.98, P < 0.01) and older age (OR 1.13, P < 0.01) were strongly associated with readmission, while women were protected. In NSDD patients, higher body mass index and American Society of Anesthesiologists score ≥ III increased readmission risk, whereas partner status, higher hemoglobin, and non-White race were protective. Effect-size comparisons demonstrated that smoking (z = 4.34, P < 0.001) and age (z = 3.65, P < 0.001) had stronger associations with readmission in SDD patients than in NSDD patients. Readmission etiologies were similar between groups. Findings were consistent in the high-volume surgeon sub-analysis.
CONCLUSIONS
While SDD after primary THA is associated with low overall readmission rates, smoking and advanced age confer disproportionately greater readmission risk when same-day discharge is pursued. These findings suggest that smoking status and age may warrant additional attention during preoperative counseling and individualized same-day discharge decision-making, while recognizing that absolute readmission rates remain low.
Braden V. Saba, Michael D. Montague, Moses I Markowitz et al.· Journal of Arthroplasty· 0 citations
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.
Dan-dan Lin, Yu-Cai Jiang, Lin-Lin Zheng et al.· Frontiers in Medicine· 0 citations
BACKGROUND
This study aims to elucidate the demographic characteristics, incidence, causes, and risk factors of unplanned reoperations post-spinal surgery (URPS) within 30 days, and to develop and validate a nomogram-based prediction model.
METHODS
We retrospectively analysed data from patients who underwent spinal surgery at three tertiary hospitals between January 2013 and January 2023, with a particular focus on those requiring unplanned reoperation within 30 days postoperatively. Demographic characteristics, incidence rates, and temporal patterns of URPS were assessed. A detailed review of causes and presenting symptoms across different postoperative intervals was also performed. Furthermore, we investigated risk factors for URPS and constructed a predictive nomogram.
RESULTS
Among 77,026 individuals included, 476 cases of URPS within 30 days were identified, comprising 258 males (54.2%) and 218 females (45.8%). Patient ages ranged from 4 to 84 years, with a mean of 48.98 ± 14.75 years. The overall incidence of URPS was 0.62%, showing a gradual annual increase. The leading causes were surgical site infection (SSI) and symptomatic epidural haematoma (SEH), which predominantly manifested as signs of surgical infection, radicular pain, and motor paralysis. The acute phase (postoperative days 2-10) represented the most critical period for symptom presentation, whereas SEH occurred mainly during the hyper-acute phase (days 0-1). Independent risk factors for URPS included drinking (p = 0.027, OR: 1.36, 95% CI: 1.040-1.790), diabetes mellitus (DM) (p < 0.001, OR: 2.056, 95% CI: 1.580-2.676), length of hospital stay (LOS) ≥ 7 days (p < 0.001, OR: 2.269, 95% CI: 1.566-3.288), first operation time (FOT) ≥ 3 h (p = 0.008, OR: 1.396, 95% CI: 1.093-1.783), drainage volume (DV) ≥ 300 ml (p < 0.001, OR: 5.156, 95% CI: 3.854-6.899), and disease type (DT) (p < 0.001, OR: 1.571, 95% CI: 1.382-1.787). The predictive nomogram demonstrated good discriminative ability, with an area under the receiver operating characteristic curve (AUC) of 0.752 (95% CI: 0.726-0.778). Calibration curves showed excellent agreement between predicted and observed probabilities (Hosmer-Lemeshow test, p = 0.892, Brier score = 0.185, R2 = 0.232), and decision curve analysis (DCA) confirmed net clinical benefit across a wide range of threshold probabilities. Patients who experienced URPS had significantly higher nomogram scores than those who did not (p < 0.001), validating the model's risk-stratification capacity.
CONCLUSIONS
This study delineates the incidence, causes, and independent risk factors for URPS within 30 days. The newly developed nomogram exhibits good discrimination, favourable calibration, and superior net clinical benefit, enabling accurate individualized prediction of short-term unplanned reoperation. This predictive tool can assist clinicians in preoperative risk stratification, identification of high-risk patients, and design of tailored intervention strategies, thereby potentially reducing the incidence of unplanned reoperations and improving postoperative outcomes.
Jiao Dai, W. Dong, Shuo Wang et al.· BMC Surgery· 0 citations
Purpose To identify independent risk factors for recovery room delirium (RRD) in patients undergoing transurethral resection of the prostate (TURP) and to develop a predictive model for early identification of high-risk patients. Patients and Methods We retrospectively reviewed 1166 adult patients who underwent TURP under general anesthesia between January 2020 and December 2024. RRD was assessed using the 3-minute Diagnostic Interview for CAM-defined Delirium (3D-CAM). Patients were randomly assigned to the training set (n = 816) and the validation set (n = 350). Independent risk factors were identified by multivariate logistic regression, and a nomogram was constructed. Model performance was evaluated by the area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis (DCA). Results The incidence of RRD was 19.5% in the training set and 20% in the validation set. Multivariable logistic regression identified older age, higher ASA physical status classification, preoperative hypoalbuminemia, intraoperative hypothermia, and intraoperative hypotension as independent predictors associated with an increased risk of RRD. Based on these predictors, a nomogram was established. The model demonstrated good discrimination, with an AUC of 0.841 (95% CI, 0.806–0.876) in the training cohort and 0.858 (95% CI, 0.810–0.906) in the validation cohort. Calibration analysis showed good agreement between the predicted and observed probabilities, and decision curve analysis demonstrated favorable clinical utility across a wide range of threshold probabilities. Conclusion The RRD prediction model incorporating age, ASA classification, preoperative hypoalbuminemia, intraoperative hypothermia, and hypotension demonstrated promising discriminatory ability and calibration in this single-center cohort. However, prospective external validation is required before widespread clinical implementation.
Zhen-Xiang Jiang, Hongrui Zhu, Ting Wang et al.· Clinical Interventions in Ag...· 0 citations