Association Between Preoperative Patient Factors and Clinically Meaningful Outcomes After Hip Arthroscopy for Femoroacetabular Impingement Syndrome: A Machine Learning Analysis

Kunze, Kyle N.; Polce, Evan M.; Clapp, Ian M.; Alter, Thomas D.; Nho, Shane J.

doi:10.1177/03635465211067546

Cited by 21 publications

(11 citation statements)

References 51 publications

(64 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Within the field of hip arthroscopy several studies have now been performed that seek to predict patient-specific outcome following the procedure. Most have focused on patient reported outcome, with Kunze et al analysing single-surgeon data to predict multiple post-operative endpoints based on different outcome measuring tools [19][20][21][22]. The prediction of subsequent surgery following hip arthroscopy has also been performed by Haeberle et al based on another single-surgeon database of over 3000 patients [11].…”

Section: Discussionmentioning

confidence: 99%

Limited clinical utility of a machine learning revision prediction model based on a national hip arthroscopy registry

Martin

Wastvedt

Lange

et al. 2022

Knee Surg Sports Traumatol Arthrosc

View full text Add to dashboard Cite

Purpose Accurate prediction of outcome following hip arthroscopy is challenging and machine learning has the potential to improve our predictive capability. The purpose of this study was to determine if machine learning analysis of the Danish Hip Arthroscopy Registry (DHAR) can develop a clinically meaningful calculator for predicting the probability of a patient undergoing subsequent revision surgery following primary hip arthroscopy. Methods Machine learning analysis was performed on the DHAR. The primary outcome for the models was probability of revision hip arthroscopy within 1, 2, and/or 5 years after primary hip arthroscopy. Data were split randomly into training (75%) and test (25%) sets. Four models intended for these types of data were tested: Cox elastic net, random survival forest, gradient boosted regression (GBM), and super learner. These four models represent a range of approaches to statistical details like variable selection and model complexity. Model performance was assessed by calculating calibration and area under the curve (AUC). Analysis was performed using only variables available in the pre-operative clinical setting and then repeated to compare model performance using all variables available in the registry. Results In total, 5581 patients were included for analysis. Average follow-up time or time-to-revision was 4.25 years (± 2.51) years and overall revision rate was 11%. All four models were generally well calibrated and demonstrated concordance in the moderate range when restricted to only pre-operative variables (0.62–0.67), and when considering all variables available in the registry (0.63–0.66). The 95% confidence intervals for model concordance were wide for both analyses, ranging from a low of 0.53 to a high of 0.75, indicating uncertainty about the true accuracy of the models. Conclusion The association between pre-surgical factors and outcome following hip arthroscopy is complex. Machine learning analysis of the DHAR produced a model capable of predicting revision surgery risk following primary hip arthroscopy that demonstrated moderate accuracy but likely limited clinical usefulness. Prediction accuracy would benefit from enhanced data quality within the registry and this preliminary study holds promise for future model generation as the DHAR matures. Ongoing collection of high-quality data by the DHAR should enable improved patient-specific outcome prediction that is generalisable across the population. Level of evidence Level III.

show abstract

Section: Discussionmentioning

confidence: 99%

Limited clinical utility of a machine learning revision prediction model based on a national hip arthroscopy registry

Martin

Wastvedt

Lange

et al. 2022

Knee Surg Sports Traumatol Arthrosc

View full text Add to dashboard Cite

show abstract

“…In regards to age specifically, patients as young as 40 years old have been associated with worse outcomes in several studies. [21][22][23] In contrast, Griffin et al conducted a systematic review that found that 7 of 8 included studies reported good PROs for patients aged 40 or older. 45 Regarding isolated acetabuloplasty and short-term outcomes, Tjong et al found that there was no correlation between age and legacy scale PROs.…”

Section: Discussionmentioning

confidence: 99%

“…40, grade 0-I vs. grade II-IV). [21][22][23]26,27 Because age and OA are often interrelated, we attempted to evaluate the independent effect of each variable by subdividing the patients into four subgroups: (1) aged less than 40 and grade 0 to I, (2) aged 40 or greater and grade 0 to I, (3) aged less than 40 and grade II to IV, and (4) aged 40 or greater and grade II to IV. We also compared these two variables between patients that achieved favorable outcomes versus those that did not.…”

Section: Methodsmentioning

confidence: 99%

“…Age and degree of osteoarthritis (OA) are two of the most widely studied factors that can influence hip arthroscopy outcomes. There is a consensus that increasing age 14,[21][22][23] and OA severity 14,15,21,22,[24][25][26][27] are negative prognostic factors for hip arthroscopy outcomes. More specifically, patients aged 40 or older [21][22][23] as well as patients with Outerbridge intraoperative arthritis grade of II or higher [26][27][28] have been found to achieve lower patient-reported outcome (PRO) scores and more likely convert to total hip arthroplasty (THA) than their younger, less arthritic counterparts.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Determining Clinically Meaningful Outcomes after Isolated Acetabuloplasty in the Context of Age and Arthritic Severity: A Retrospective Review of Prospectively Collected Data

Huyke-Hernández

Samagh

Hassan

et al. 2022

The Journal of Hip Surgery

View full text Add to dashboard Cite

Outcomes after isolated acetabuloplasty in mixed-type femoroacetabular impingement (FAI) patients can be favorable but are relatively unknown in the context of clinically important outcome variables (CIOVs) such as minimum clinically important difference and patient acceptable symptomatic state (PASS). Prognostic roles of age and osteoarthritis (OA) in hip arthroscopy are still unclear. We aimed to evaluate isolated acetabuloplasty outcomes including CIOVs while controlling for age and arthritis.This was a retrospective review of prospectively collected data. We analyzed patients with available 1-year follow-up for Patient-Reported Outcome Measurement Information System (PROMIS) scales for Physical Function (PF) and Pain Interference (PI). Patients were divided into two age groups (< 40 years old vs. ≥ 40 years old) and two Outerbridge arthritis grade groups (grade 0–I vs. grade II–IV). Demographic, radiographic, and surgical characteristics as well as revision surgeries and complications were extracted. Our outcome was the proportion of patients that achieved values over literature-reported CIOV thresholds for PROMIS-PF and PROMIS-PI.A total of 63 patients of 96 eligible (65.6%) had minimum 1-year data. Characteristics were comparable between patients aged younger than 40 and 40 and over as well as between grade 0 to I and grade II to IV patients. Overall, average PROMIS-PF and PROMIS-PI scores improved. Approximately 81.0% of patients reached values over CIOV threshold (71.4% for PROMIS-PF, 54.0% for PROMIS-PI), with 44.4% reporting these outcomes for both PROMIS-PF and PROMIS-PI. Approximately 30.2% of patients reported values over PASS threshold for both PROMIS-PF and PROMIS-PI, with 25.4% of patients achieving values above all CIOV thresholds. Only one patient required revision surgery. When evaluating the effect of age while controlling for OA severity and vice versa, there were no significant outcome differences (p > 0.615). When comparing patients reporting values above CIOV threshold versus those that did not, there were no differences in age (41.2 ± 13.0 [37.7, 44.8] vs. 45.9 ± 13.2 [38.4, 53.4], p = 0.265) or Outerbridge grade distribution (p = 0.177).This study uses CIOVs to describe clinically meaningful isolated acetabuloplasty outcomes for mixed-type FAI. Most patients over a wide spectrum of age and OA achieved favorable clinically meaningful outcomes following surgery. Isolated acetabuloplasty can alleviate symptomatology in mixed-type FAI patients on a case-by-case basis.

show abstract

“… 30 Despite consistent improvements in PROs after hip arthroscopic surgery, meaningful improvements are negatively influenced by a greater BMI. 15 Furthermore, BMI has been established as a positive predictor of conversion to total hip arthroplasty (THA) after hip arthroscopic surgery. 10 This is a finding that has been consistently reported in the current literature.…”

mentioning

confidence: 99%

Survivorship, Outcomes, and Risk Factors for Conversion to Total Hip Arthroplasty After Revision Hip Arthroscopic Surgery in Obese Patients: Results at a Minimum 5-Year Follow-up

Maldonado

Lee

Kyin

et al. 2023

Orthopaedic Journal of Sports Medicine

View full text Add to dashboard Cite

Background: There is a paucity of literature reporting outcomes after revision hip arthroscopic surgery in obese patients. Purpose: To report the minimum 5-year survivorship, patient-reported outcomes (PROs), clinical benefit, and risk factors for conversion to total hip arthroplasty (THA) in obese patients after revision hip arthroscopic surgery. Study Design: Case series; Level of evidence, 4. Methods: Data were prospectively collected and retrospectively reviewed for patients who underwent revision hip arthroscopic surgery by a single surgeon between April 2010 and August 2016. Inclusion criteria were a body mass index ≥30 and baseline and minimum 5-year postoperative values for the modified Harris Hip Score (mHHS), Nonarthritic Hip Score (NAHS), Hip Outcome Score–Sport-Specific Subscale (HOS-SSS), and visual analog scale (VAS) for pain. Exclusion criteria were Tönnis grade >1 and hip dysplasia. Survivorship was defined as no conversion to THA. Clinical benefit was measured using the minimal clinically important difference (MCID). Survivors and nonsurvivors underwent further bivariate and regression analyses to determine the predictors of conversion to THA. Results: Included were 24 hips in 24 patients. The mean patient age was 39.3 ± 12.7 years, and the mean follow-up was 83.9 ± 26.5 months. The survivorship rate was 75.0%, and patients demonstrated a significant improvement in all PROs ( P < .01). At 5-year follow-up, the MCID for the mHHS, NAHS, HOS-SSS, and VAS was achieved by 70.6%, 94.1%, 92.9%, and 64.7%, respectively, of the patients. Older age, higher grade ligamentum teres tears, and acetabuloplasty were significant on bivariate analysis for conversion to THA, and increased age was identified as a significant variable for conversion to THA on regression analysis (odds ratio, 1.297 [95% CI, 1.045-1.609]; P = .018), with a 29.7% greater risk for every additional year of age at the time of revision. Conclusion: In this study, 25.0% of obese patients who underwent revision hip arthroscopic surgery required conversion to THA. The study patients who did not need conversion to THA had a significant improvement in all PROs, with >90% achieving MCID for one or more outcome measures. Older age was identified as a significant predictor of conversion to THA.

show abstract

Association Between Preoperative Patient Factors and Clinically Meaningful Outcomes After Hip Arthroscopy for Femoroacetabular Impingement Syndrome: A Machine Learning Analysis

Cited by 21 publications

References 51 publications

Limited clinical utility of a machine learning revision prediction model based on a national hip arthroscopy registry

Limited clinical utility of a machine learning revision prediction model based on a national hip arthroscopy registry

Determining Clinically Meaningful Outcomes after Isolated Acetabuloplasty in the Context of Age and Arthritic Severity: A Retrospective Review of Prospectively Collected Data

Survivorship, Outcomes, and Risk Factors for Conversion to Total Hip Arthroplasty After Revision Hip Arthroscopic Surgery in Obese Patients: Results at a Minimum 5-Year Follow-up

Contact Info

Product

Resources

About