Lower baseline scores best predict achievement of the minimal clinically important difference after hip arthroscopy: A machine learning analysis from the Femoroacetabular Impingement RandomiSed Controlled Trial and embedded prospective cohort
Bibliographic record
Abstract
PURPOSE: This analysis evaluated whether logistic regression and machine learning models could predict achievement of the minimal clinically important difference (MCID) for the International Hip Outcome Tool (iHOT-12) and Hip Outcome Score (HOS) at 6 and 12 months following hip arthroscopy. METHODS: Data from the multicenter Femoroacetabular Impingement RandomiSed controlled Trial and its embedded prospective cohort were used. A total of 309 patients (mean ± SD age 34.0 ± 8.7 years, 37.7% female) were included. The MCID thresholds for iHOT-12 and HOS were calculated using a distribution-based method and were 9.0 and 13.0, respectively. Predictive models were trained with demographic, radiographic, and intraoperative variables using a 70:30 training-to-test data split. MCID achievement was defined as a change from preoperative to postoperative scores that surpassed the calculated threshold. Model discrimination was assessed using the area under the curve (AUC), and calibration was evaluated via slope, intercept, and Brier scores. RESULTS: Achievement rates were 83.3% at 6 months and 81.1% at 12 months for iHOT-12, and 64.3% at 6 months and 75% at 12 months for HOS. Logistic regression performed best at 12 months (AUC = 0.724) for iHOT-12 with poor calibration (slope = 2.19). AUCs for HOS ranged between 0.672-0.715 at 6 months and 0.665-0.699 at 12 months. Best calibration was achieved by Least Absolute Shrinkage and Selection Operator (slope = 1.270, intercept = -0.177) at 6 months and by logistic regression at 12 months (slope = 1.093, intercept = -0.079). Lower baseline patient-reported outcome measures (PROMs) were associated with MCID achievement in most models. CONCLUSION: The most robust predictor of MCID achievement for both PROMs were lower baseline scores, and can be used as a prognostic variable for preoperative counselling. Model performance for predicting MCID was superior for HOS relative to iHOT-12. Machine learning models generally had comparable discrimination and calibration scores to traditional logistic regression models. LEVEL OF EVIDENCE: Level III.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.023 | 0.035 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.003 | 0.005 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 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 source (direct Gemma or distilled Codex), 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".