EP8.91 Trajectories Towards Achieving Clinically Significant Outcomes After Hip Arthroscopy Differ Based on Clinical Phenotype: A Machine Learning Survival Analysis

Clicks: 11
ID: 331031
2026
Free PDF
Article Quality & Performance Metrics
Overall Quality
Not rated
Combines reader engagement with the AI quality analysis. This article has not been analysed, so there is no overall score — reader engagement is measured and shown alongside.
AI Quality Assessment
Not analyzed
Readership in this journal
Popular

Ranked #87 of 444 articles by views in Journal of hip preservation surgery

Most read Least read

Bar heights use a square-root scale. Only the 120 most-read articles are drawn; the journal has 444 in total.

Mint this article as an NFT
Not yet minted

Create a permanent, verifiable on-chain record of this article on the Scimatic Network. The NFT is held in your Journament account, and you can withdraw it to your own wallet at any time.

5 SUSD one-off · no wallet required
Sign in to mint
Abstract
Abstract Background Hip arthroscopy for femoroacetabular impingement syndrome yields favorable outcomes, though recovery trajectories remain heterogeneous. Clinically significant outcomes (CSOs) are increasingly used to assess surgical success; however, accurately predicting both the likelihood and timing of their achievement remains challenging due to variable patient characteristics and recovery patterns. Machine learning methods offer a framework for individualized prediction of outcome achievement over time and for identifying factors associated with delayed or suboptimal recovery. Methods Patients undergoing hip arthroscopy for femoroacetabular impingement syndrome with ≥2-year follow-up were identified. Postoperatively patients completed iHOT-12 and associated anchor questions. Rates and time to achievement of minimal clinically important difference (MCID), substantial clinical benefit (SCB), and patient acceptable symptom state (PASS) were modeled using random survival forest (RSF) algorithms. Model performance was assessed using out-of-bag c-statistics and Brier scores. Global variable importance and partial dependence plots were used to identify predictors of delayed CSO achievement. Results A total of 1,231 patients (age=32.6±12.7 years; 70.3% female) were included. Achievement rates for MCID, SCB, and PASS were 87.0%, 56.3%, and 61.1%, respectively. Mean time to achievement was 105±88 days for MCID, 137±91 days for SCB, and 129±88 days for PASS. RSF models demonstrated excellent predictive performance for MCID (0.82) and acceptable performance for SCB (0.72) and PASS (0.69). Preoperative patient reported outcomes, range of motion (ROM), body mass index (BMI), and age demonstrated nonlinear, parabolic associations with CSO achievement, with higher likelihood at the lowest and highest tertiles of PROs, BMI, and age, but lower likelihood at extreme ROM. Negative predictors included: for MCID, increased alpha angle (AA), extreme preoperative ROM, decreased beta angle, and reduced joint space width (JSW); for SCB, increased AA, acetabular over- or undercoverage, extreme ROM, larger labral tears, coxa profunda, and decreased JSW; for PASS, prior hip injection, increased AA, extreme ROM, coxa profunda, preoperative back pain, and narcotic use. Conclusions RSF-based time-to-event modeling enables individualized predictions for time to CSO achievement following hip arthroscopy. Nonlinear effects were observed among several variables, suggesting multiple recovery trajectories exist and that individual clinical phenotypes must be considered when evaluating propensity for CSO achievement.
Reference Key
openalex_W7220386720 Use this key to autocite in the manuscript while using SciMatic Manuscript Manager or Thesis Manager
Authors Yining Lu, Kyle N. Kunze, Jack Yang, Ty Monty, Shane Nho
Are you one of these authors? Claim your profile
Journal Journal of hip preservation surgery
Year 2026
DOI
10.1093/jhps/hnag043.470
URL
https://doi.org/10.1093/jhps/hnag043.470
Keywords Keywords not found

Citations

No citations found. To add a citation, contact the admin at info@scimatic.org

Comments

No comments yet. Be the first to comment on this article.