EP8.83 A Data-Driven Unsupervised Approach to Defining Optimal Outcomes Achievement following Hip Arthroscopy for Femoroacetabular Impingement Syndrome

Clicks: 9
ID: 331180
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
Steady

Ranked #292 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 Evaluation of outcomes following hip arthroscopy for femoroacetabular impingement syndrome (FAIS) involves a combination of patient-reported outcomes (PROs) as well as clinical endpoints such as progression of joint degeneration. However, the concept of the optimal observed outcome among patients undergoing this operation has not yet been clearly defined. Methods Patients undergoing hip arthroscopy for FAIS with minimum 2-year follow-up by a single surgeon were identified. Unsupervised spectral clustering via a random forest-generated distance matrix was utilized to develop and validate patient subgroups based on aggregate postoperative outcomes. Both PROs and reoperations were compared across subgroups to define optimal and suboptimal achievers. A 100-point scoring criterion was established using preoperative risk factors to estimate risk of suboptimal achievement using Shapley variable importance cloud. Results A total of 1,196 patients who underwent primary hip arthroscopy for femoroacetabular impingement syndrome were included. The clustering algorithm arrived at an optimal partition of 2 subgroups, with 578 patients identified as optimal outcomes achievers (421 female [72.8%], age 29.36±12.56, BMI 23.6±4.05) and 602 patients identified as suboptimal outcomes achievers (411 female [68.3%], age 35.8±12.6, BMI 26.5±5.59). Patients in the optimal achievement subgroup demonstrated increased achievement of all MCID (range: 91.2-99.0% vs 76.6-79.1%), SCB (range: 79.6-99.3% vs 9.6-45.3%), and PASS (range: 96.9-100.0% vs 27.9-61.1%) thresholds as well as the rate of revision surgery (0.9% vs 3.7%) and progression to arthroplasty (0.3% vs 3.5%) compared to patients in the suboptimal achievement subgroup (all P<0.001). Based on Shapley variable importance cloud, a 100-point scoring criterion was developed using 13 patient factors, including age, gender, BMI, physical examination (primary site of pain), and radiographic findings (preoperative alpha angle and apical JSW) that can be readily used to predict patients at risk of suboptimal achievement. This was validated on a holdout test set, reaching an overall discriminative AUC of 0.726 (P>0.001). Conclusions Two clinically meaningful hip arthroscopy patient subgroups were identified with differential PRO and clinical outcomes achievement following surgery. A scoring criterion was developed that can be calculated from readily available demographic, physical examination, and radiographic findings to inform preoperative patient counseling on the relative success of arthroscopic surgery.
Reference Key
openalex_W7220411425 Use this key to autocite in the manuscript while using SciMatic Manuscript Manager or Thesis Manager
Authors Yining Lu, Joseph Brinkman, Ty Monty, Jack Yang, Shane Nho
Are you one of these authors? Claim your profile
Journal Journal of hip preservation surgery
Year 2026
DOI
10.1093/jhps/hnag043.462
URL
https://doi.org/10.1093/jhps/hnag043.462
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.