Key result
Logistic regression using administrative data poorly predicts 30-day readmission after total knee arthroplasty.
Why the study?
Thirty-day readmission is an increasingly important problem for total knee arthroplasty patients, prompting the development of a risk prediction model using machine learning and clinical insight.
Does a machine learning model accurately predict 30-day readmission in primary TKA patients?
Observational (n=3,685)
No
Does a machine learning model accurately predict 30-day readmission in primary TKA patients?
Effect estimate: AUC-ROC 0.589 (95% CI 0.506-0.673)
Machine learning and logistic regression models for predicting 30-day readmission after TKA showed poor discriminative performance but adequate calibration, suggesting utility for patient-specific probability estimation rather than binary classification.
May support calibrated probability estimates over binary classification for TKA readmission risk; leaves open higher-performing models in prospective cohorts.
BACKGROUND: Thirty-day readmission is an increasingly important problem for total knee arthroplasty (TKA) patients. The aim of this study was to develop a risk prediction model using machine learning and clinical insight for 30-day readmission in primary TKA patients. METHOD: Data used to train and internally validate a multivariable predictive model were obtained from a single tertiary referral centre for TKA located in Victoria, Australia. Hospital administrative data and clinical registry data were utilised, and predictors were selected through systematic review and subsequent consultation with clinicians caring for TKA patients. Logistic regression and random forest models were compared to one another. Calibration was evaluated by visual inspection of calibration curves and calculation of the integrated calibration index (ICI). Discriminative performance was evaluated using the area under the receiver operating characteristic curve (AUC-ROC). RESULTS: The models developed in this study demonstrated adequate calibration for use in the clinical setting, despite having poor discriminative performance. The best-calibrated readmission prediction model was a logistic regression model trained on administrative data using risk factors identified from systematic review and meta-analysis, which are available at the initial consultation (ICI = 0.012, AUC-ROC = 0.589). Models developed to predict complications associated with readmission also had reasonable calibration (ICI = 0.012, AUC-ROC = 0.658). CONCLUSION: Discriminative performance of the prediction models was poor, although machine learning provided a slight improvement. The models were reasonably well calibrated, meaning they provide accurate patient-specific probabilities of these outcomes. This information can be used in shared clinical decision-making for discharge planning and post-discharge follow up.
No takes yet. Share an insight, caveat, or question.
Gould et al. (2023) conducted an observational in Primary total knee arthroplasty (TKA) (n=3,685). Risk prediction models (logistic regression and random forest) was evaluated on 30-day unplanned hospital readmission (AUC-ROC 0.589, 95% CI 0.506-0.673). A logistic regression model using administrative data and systematic review predictors demonstrated poor discriminative performance (AUC-ROC 0.589) but adequate calibration (ICI 0.012) for predicting 30-day readmission following total knee arthroplasty.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: