Improved Prediction of Postoperative Knee Function Using Preoperative Patient Factors and Intraoperative Measures of Bony Resection, Ligament Release, and Implant Alignment in Total Knee Arthroplasty: A Database Analysis of 363 Cases
Bibliographic record
Abstract
Total knee arthroplasty (TKA) is a common approach to treating end-stage osteoarthritis of the knee while relieving pain and restoring joint function. However, the procedure has produced variations in postoperative outcomes, with up to 20% of patients left dissatisfied. Therefore, it is important to understand the preoperative and intraoperative factors that drive knee function post-TKA. Using intraoperative data acquired from a surgical navigation system and matched with patient pre- and postoperative data, this study aimed to identify preoperative and intraoperative predictors of PROMs measured using the Oxford Knee Score (OKS) at 1-year follow-up. We analysed 363 cases of navigated TKA at our institution and matched them to preoperative and postoperative patient clinical records including age at index surgery, BMI, sex, presence of co-morbidities, EQ5D anxiety/depression score, and preoperative and postoperative OKS. Starting with a base model of 26 predictor variables, a linear regression model with backward elimination was used to identify predictors of postoperative OKS on a training set of 290 patients. 73 patients (20%) were randomly set aside to use as validation. We then used the remaining predictor variables to train two additional regression models: a Support Vector Machine (SVM) and a Boosted Decision Tree then calculated the coefficient of determination (R2) and percent of patients that where the postoperative OKS was correctly identified within the minimally important clinical difference of 4.9 when the models were applied to the validation set. Of the 26 predictor variables, 10 predictors remained in the final model following backwards elimination, including four that were directly under the control of the surgeon. The R2 of the linear regression, SVM, and XGBoost models were 0.37, 0.30, and 0.29 respectively within the validation set. Percentages of patients with correctly predicted OKS within the MICD ranged from 52% to 57% (linear regression to SVM). In this study, we identified sets of preoperative and intraoperative factors which are partially predictive of postoperative OKS at 1-year follow-up. Post-operative prediction models such as the models presented here will help to guide continued research into which intraoperative variables, including bony resection depths, implant alignment, and whether to do ligament releases in surgery, most affect implant function post-TKA and to inform patients and clinicians of possible clinical outcomes.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".