Aims. Precise implant positioning, tailored to individual spinopelvic biomechanics and phenotype, is paramount for stability in total hip arthroplasty (THA). Despite a few studies on instability prediction, there is a notable gap in research utilizing artificial intelligence (AI). The objective of our pilot study was to evaluate the feasibility of developing an AI algorithm tailored to individual spinopelvic mechanics and patient phenotype for predicting impingement. Methods. This international, multicentre prospective cohort study across two centres encompassed 157 adults undergoing primary robotic arm-assisted THA. Impingement during specific flexion and extension stances was identified using the virtual range of motion (ROM) tool of the robotic software. The primary AI model, the Light Gradient-Boosting Machine (LGBM), used tabular data to predict impingement presence, direction (flexion or extension), and type. A secondary model integrating tabular data with plain anteroposterior pelvis radiographs was evaluated to assess for any potential enhancement in prediction accuracy. Results. We identified nine predictors from an analysis of baseline spinopelvic characteristics and surgical planning parameters. Using fivefold cross-validation, the LGBM achieved 70.2% impingement prediction accuracy. With impingement data, the LGBM estimated direction with 85% accuracy, while the support vector machine (SVM) determined impingement type with 72.9% accuracy. After integrating imaging data with a multilayer perceptron (tabular) and a convolutional neural network (radiograph), the LGBM’s prediction was 68.1%. Both combined and LGBM-only had similar impingement direction prediction rates (around 84.5%). Conclusion. This study is a pioneering effort in leveraging AI for impingement prediction in THA, utilizing a comprehensive, real-world clinical dataset. Our machine-learning algorithm demonstrated promising accuracy in predicting impingement, its type, and direction. While the addition of imaging data to our deep-learning algorithm did not boost accuracy, the potential for refined annotations, such as landmark markings, offers avenues for future enhancement. Prior to clinical integration, external validation and larger-scale testing of this algorithm are essential. Cite this article: Bone Jt Open 2024;5(8):671–680

Femoroacetabular Impingement (FAI) syndrome, characterised by abnormal hip contact causing symptoms and osteoarthritis, is measured using the International Hip Outcome Tool (iHOT). This study uses machine learning to predict patient outcomes post-treatment for FAI, focusing on achieving a minimally clinically important difference (MCID) at 52 weeks. A retrospective analysis of 6133 patients from the NAHR who underwent hip arthroscopic treatment for FAI between November 2013 and March 2022 was conducted. MCID was defined as half a standard deviation (13.61) from the mean change in iHOT score at 12 months. SKLearn Maximum Absolute Scaler and Logistic Regression were applied to predict achieving MCID, using baseline and 6-month follow-up data. The model's performance was evaluated by accuracy, area under the curve, and recall, using pre-operative and up to 6-month postoperative variables. A total of 23.1% (1422) of patients completed both baseline and 1-year follow-up iHOT surveys. The best results were obtained using both pre and postoperative variables. The machine learning model achieved 88.1% balanced accuracy, 89.6% recall, and 92.3% AUC. Sensitivity was 83.7% and specificity 93.5%. Key variables determining outcomes included MCID achievement at 6 months, baseline iHOT score, 6-month iHOT scores for pain, and difficulty in walking or using stairs. The study confirmed the utility of machine learning in predicting long-term outcomes following arthroscopic treatment for FAI. MCID, based on the iHOT 12 tools, indicates meaningful clinical changes. Machine learning demonstrated high accuracy and recall in distinguishing between patients achieving MCID and those who did not. This approach could help early identification of patients at risk of not meeting the MCID threshold one year after treatment

Aims. Femoroacetabular Junction Impingement (FAI) describes abnormalities in the shape of the femoral head–neck junction, or abnormalities in the orientation of the acetabulum. In the short term, FAI can give rise to pain and disability, and in the long-term it significantly increases the risk of developing osteoarthritis. The Femoroacetabular Impingement Trial (FAIT) aims to determine whether operative or non-operative intervention is more effective at improving symptoms and preventing the development and progression of osteoarthritis. . Methods. FAIT is a multicentre superiority parallel two-arm randomised controlled trial comparing physiotherapy and activity modification with arthroscopic surgery for the treatment of symptomatic FAI. Patients aged 18 to 60 with clinical and radiological evidence of FAI are eligible. Principal exclusion criteria include previous surgery to the index hip, established osteoarthritis (Kellgren–Lawrence ≥ 2), hip dysplasia (centre-edge angle < 20°), and completion of a physiotherapy programme targeting FAI within the previous 12 months. Recruitment will take place over 24 months and 120 patients will be randomised in a 1:1 ratio and followed up for three years. The two primary outcome measures are change in hip outcome score eight months post-randomisation (approximately six-months post-intervention initiation) and change in radiographic minimum joint space width 38 months post-randomisation. ClinicalTrials.gov: NCT01893034. Cite this article: Bone Joint Res 2014;3:321–7

The primary treatment goal for patients with femoroacetabular impingement syndrome, a common hip condition in athletes, is to improve pain and function. In selected patients, in the short term following intervention, arthroscopic hip surgery is superior to a pragmatic NHS- type physiotherapy programme. Here, we report the three-year follow-up results from the FemoroAcetabular Impingement Trial (FAIT), comparing arthroscopic hip surgery with physiotherapy in the management of patients with femoroacetabular impingement (FAI) syndrome. Two-group parallel, assessor-blinded, pragmatic randomised controlled study across seven NHS England sites. 222 participants aged 18 to 60 years with FAI syndrome confirmed clinically and radiologically were randomised (1:1) to receive arthroscopic hip surgery (n = 112) or physiotherapy and activity modification (n = 110). We previously reported on the hip outcome score at eight months. The primary outcome measure of this study was minimum Joint Space Width (mJSW) on Anteroposterior Radiograph at 38 months post randomisation. Secondary outcome measures included the Hip Outcome Score and Scoring Hip Osteoarthritis with MRI (SHOMRI) score. Minimum Joint Space Width data were available for 101 participants (45%) at 38 months post randomisation. Hip outcome score and MRI data were available for 77% and 62% of participants respectively. mJSW was higher in the arthroscopy group (mean (SD) 3.34mm (1.01)) compared to the physiotherapy group (2.99mm (1.33)) at 38 months, p=0.017, however this did not exceed the minimally clinically important difference of 0.48mm. SHOMRI score was significantly lower in the arthroscopy group (mean (SD) 9.22 (11.43)) compared to the physiotherapy group (22.76 (15.26)), p-value <0.001. Hip outcome score was higher in the arthroscopy group (mean (SD) 84.2 (17.4)) compared with the physiotherapy group (74.2 (21.9)), p-value < 0.001). Patients with FAI syndrome treated surgically may experience slowing of osteoarthritisprogression and superior pain and function compared with patients treated non- operatively

Impingement of total hip replacements (THRs) can cause rim damage of polyethylene liners, and lead to dislocation and/or mechanical failure of liner locking mechanisms[1]. Previous work has focussed on the influence of femoral neck profile on impingement without consideration of neck-shaft angle. This study assessed the occurrence of impingement with two different stem designs (Corail standard [135°] and coxa vara [125°]) under different activities with varying acetabular cup orientation (30° to 70° inclination; 0° to 50° anteversion) using a geometric modelling tool. The tool was created in a computer aided design software programme, and incorporated an individual's hemi-pelvis and femur geometry[3] with a THR (DePuy Synthes Pinnacle. ®. shell and neutral liner; size 12 Corail. ®. standard or coxa vara and 32mm head). Kinematic data of activities associated with dislocation[2], such as stooping to pick an object from the floor was applied and incidences of impingement were recorded. Predicted implant impingement was influenced by stem design. The coxa vara stem was predicted to cause implant impingement less frequently across the range of activities and cup orientations investigated, compared to the standard stem [Fig. 1]. The cup orientations predicted to cause impingement the least frequently were at lower inclination and anteversion angles, relative to the standard stem [Fig. 1]. The coxa vara stem included a collar, while the standard stem was collarless; additional analysis indicated that differences were due to neck angle and not the presence of a collar. This study demonstrated that stem neck-shaft angle is an important variable in prosthetic impingement in THR and surgeons should be aware of this when choosing implants. Future work will consider further implant design and bone geometry variables. This tool has the potential for use in optimising stem design and position and could assist with patient specific stem selection based on an individual's activity profile. For any figures or tables, please contact the authors directly

Aims

Computer-assisted 3D preoperative planning software has the potential to improve postoperative stability in total hip arthroplasty (THA). Commonly, preoperative protocols simulate two functional positions (standing and relaxed sitting) but do not consider other common positions that may increase postoperative impingement and possible dislocation. This study investigates the feasibility of simulating commonly encountered positions, and positions with an increased risk of impingement, to lower postoperative impingement risk in a CT-based 3D model.

Research into the treatment of Femoro-Acetabular Impingement (FAI) has focussed on surgical correction of structural abnormalities and tended to overlook the dynamic process of impingement. The role of Physiotherapy in addressing abnormal hip movement and any resulting effect on the symptoms of FAI remains untested. A pilot study was therefore instigated to evaluate the effect of physiotherapy on pain and function in patients with FAI. 30 adults aged between 18 and 50 years with a diagnosis of symptomatic FAI were recruited. 23 (77%) completed the study. Intervention was 3 months of specialist physiotherapy focused on improving pelvic and proximal femoral control. The control group received routine care. All functional outcomes improved in the Physiotherapy group and this included improvement beyond minimal clinically important difference and measurement error on the Hip Outcome Score. There was marginal improvement in pain in both groups. Results suggest that physiotherapy treatment can improve function in adults with symptomatic FAI. Larger studies are needed to evaluate the role of conservative management in FAI

Hip precautions following total hip arthroplasty (THA) limits flexion, adduction and internal rotation, yet these precautions cause unnecessary psychological stress. This study aims to assess bony and implant impingement using virtual models from actual patient's bony morphology and spinopelvic parameters to deduce whether hip precautions are necessary with precise implant positioning in the Asian population.

Individualized sitting and standing sacral slope data of robotic THAs performed at two tertiary referral centers in Hong Kong was inputted into the simulation system based on patients’ pre-operative sitting and standing lumbar spine X-rays. Three-dimensional dynamic models were reconstructed using the Stryker Mako THA 4.0 software to assess bony and implant impingement both anteriorly and posteriorly, with default cup placement at 40° inclination and 20° anteversion. Femoral anteversion followed individual patient's native version. A 36mm hip ball was chosen for all cups equal or above 48mm and 32mm for those below. Anterior impingement was assessed by hip flexion and posterior impingement was assessed by hip extension.

113 patients were included. At neutral rotation and adduction, no patients had anterior implant impingement at hip flexion of 100°. 1.7% had impingement at 110°, 3.5% had impingement at 120°, 9.7% had impingement at 130°. With 20° of internal rotation and adduction, 0.8% had anterior implant impingement at hip flexion of 90°, 7.1% had impingement at 100° and 18.5% had impingement at 110°. With the hip externally rotated by 20°, 0.8% of patients had posterior implant impingement, and 8.8% bony impingement at 0° extension.

With enabling technology allowing accurate component positioning, hip precautions without limiting forward flexion in neutral position is safe given precise implant positioning and adequate osteophyte removal. Patients should only be cautioned about combined internal rotation, adduction with flexion.

Most patients presenting with loss of hip motion secondary to FAI have a combination of cam and pincer morphology. In this study, we present a composite index for predicting joint ROM based on anatomic parameters derived from both the femur and acetabulaum using a single reformatted CT slice. Computer models of the hip joint were reconstructed from CT scans of 31 patients with mixed-type FAI (Average alpha angle: 73.6±11.1°, average LCE: 38.9±7.2°). The internal rotation of the hip at impingement was measured at 90° flexion using custom software. With the joint in neutral, a single slice perpendicular to the acetabular rim was taken at the 2 o'clock position. A set of 11 femoral and acetabular parameters measured from this slice were correlated with hip ROM using stepwise logistic regression. Three anatomic parameters provided significant discrimination of cases impinging at <15 and >15 degrees IR: femoral anteversion (28%, p=0.026), the arc of anterior femoral head sphericity (10%, p=0.040), and the LCE in the 2 o'clock plane (10%, p=0.048). This led to the following definition of the Impingement Index: 0.16*(fem version) +0.11*(ant arc)−0.17*(LCE) which correctly classified 82% of cases investigated. None of the traditional parameters (e.g. alpha angle) were significantly correlated with ROM. Our study has identified alternative morphologic parameters that could act as strong predictors of FAI in preoperative assessments. Using this information, each patient's individual risk of impingement may be estimated, regardless of the relative contributions of deformities of the femur and the acetabulum

There is little known about how patient socioeconomic status impacts clinical outcomes in hip preservation surgery. The aim of this study was to evaluate the relationship between indices of multiple deprivation, funding provider (NHS Funded or Private Funded) and clinical outcomes following surgery for femoroacetabular impingement (FAI)

The study analysed the data of 5590 patients recorded in the NAHR who underwent primary hip arthroscopic treatment for FAI between November 2013 and July 2023. Records were matched to the UK National index of multiple deprivation using the lower layer super output area. Using iHOT12 score, patient reported outcome measures were analysed at base line and 1 year following surgery.

2358 records were matched to LLSOA deciles. Between the lowest (most deprived) 3 deciles and the highest (least deprived) the average baseline iHOT12 score was 28.98 (n=366) and 35.33 (n=821). The proportion of patients receiving treatment through NHS funding compared to independent funding for the most deprived, 292 (90%) 37 (10%) respectively compared to the least deprived 515 (70%) and 244 (30%) respectively. At 1year, iHOT12 scores for each group were 51.64 (29.1 SD) compared to 61.5 (28.06 SD) respectively.

The study demonstrates that patients from lower socioeconomic backgrounds had poorer baseline and one-year post-surgery iHOT12 scores compared to those from higher socioeconomic strata. Furthermore, a higher reliance on NHS funding was observed among the most deprived, while more affluent patients predominantly opted for private funding. These findings underscore the significant influence of socioeconomic status on both the quality of healthcare received and recovery outcomes in hip preservation surgery, calling attention to the need for more equitable healthcare solutions.

There is a limited literature available describing the various diagnostic modalities and treatment options for the management of subspine impingement (SSI). We developed a study to evaluate the clinical improvement at 1 year and 5 years, with iHOT 33 and HOS hip scores.

(1) Do patients with subspine compression improve with arthroscopic treatment clinically at short term follow-up (1 year)? (2) Is the improvement maintained in the mid-term (5 years)?

43 young patients with subspine compression (prominent anterior inferior iliac spine) treated arthroscopically between January 2010 and December 2021 were included. Patients completed the iHOT33, HOS-SPORT and HOS-ADL questionnaires before surgery, 1 year and 5 years follow up. We evaluated pre and postoperative differences at one year and at 5 years. Minimum Clinically Significant Difference (MCID) and the Substantial Clinical Benefit (SCB) were used to stablish clinical improvement.

Mean age was 37.38 years and 66% were males. Almost 75% and 70% of our patients exceed the MCID and the SCB respectively in all the questionnaires after 1 year-follow up. However, at 5 years-follow up, nearly 70% and 65% of the patients exceeded MCID and SCB respectively.

We demonstrate that arthroscopic treatment of subspine impingement as an effective treatment for Subspine impingement. However, it is necessary larger sample size and longer follow up period to analyze the long-term results to demonstrate this treatment as the “gold standard”.

Dual Mobility (DM) Total Hip Replacements (THRs), are becoming widely used but function in-vivo is not fully understood.

The aim of this study was to compare the incidence of impingement of a modular dual mobility with that of a standard cup.

A geometrical model of one subject's bony anatomy \[1\] was developed, a THR was implanted with the cup at a range of inclination and anteversion positions (Corail® stem, Pinnacle® cup (DePuy Synthes)). Two DM variants and one STD acetabular cup were modelled. Joint motions were taken from kinematic data of activities of daily living associated with dislocation \[2\] and walking. The occurrence of impingement was assessed for each component combination, orientation and activity. Implant-implant impingement can occur between the femoral neck and the metal or PE liner (DM or STD constructs respectively) or neck-PE mobile liner (DM only).

The results comprise a colour coded matrix which sums the number of impingement events for each cup position and activity and for each implant variant.

Neck-PE mobile liner impingement, occurred for both DM sizes, for all activities, and most cup placement positions indicating that the PE mobile liner is likely to move at the start of all activities including walking.

For all constructs no placement positions avoided neck-metal (DM) or neck-PE liner (STD) impingementevents in all activities. The least number of events occurred at higher inclination and anteversion component positions. In addition to implant-implant impingement, some instances of bone-bone and implant-bone impingement were also observed.

Consistent with DM philosophy, neck-PE mobile liner impingement and liner motion occurred for all activities including walking. Neck-liner impingement frequency was comparable between both DM sizes (metal liner) and a standard cup (PE liner).

This study used a national registry to assess the outcomes of hip arthroscopy (HA) for the treatment femoroacetabular impingement (FAI).

All HAs for FAI recorded in the UK Non-Arthroplasty Hip Registry (NAHR) between January 2012 and September 2023 were identified. Cases were grouped according to the index procedure performed for FAI (cam, pincer, or mixed). Patient outcomes captured included the International Hip Outcome Tool (iHOT)-12.

7,511 HAs were identified; 4,583 cam (61%), 675 pincer (9%), 2,253 mixed (30%). Mean age (34.8) was similar between groups. There was a greater proportion of females in the pincer group (75%) compared to cam (52%) and mixed (50%). A higher proportion of patients had a recorded cartilage injury in association with a cam lesion compared to pincer. The pincer group had poorer mean pre-op iHOT-12 scores (31.6 \[95%CI 29.9 to 33.3\]; n=364) compared to cam (33.7 \[95%CI 32.1 to 34.4\]; n=3,941) and achieved significantly lower scores at 12 months (pincer = 52.6 (50.2 to 55); n=249, cam = 58.3 (57.1 to 59.5); n=1,679).

Overall, significant (p < 0.0001) iHOT-12 and EQ-5D improvement vs baseline pre-operative scores were achieved for all FAI subtypes at 6 months (overall mean iHOT-12 improvement +26.0 \[95%CI 25.0 to 26.9\]; n=2,983) and maintained out to 12 months (+26.2 \[25.1 to 27.2\]; n=2,760) at which point 67% and 48% of patients continued to demonstrate a score improvement greater than or equal to the minimum clinically important difference (>/=13 points) and substantial clinical benefit (>/=28 points) for iHOT-12 respectively.

This study demonstrates excellent early functional outcomes following HA undertaken for FAI in a large national registry.

Femoroacetabular impingement is a prearthritic deformity frequently associated with early chondral damage. Several techniques exist for restoring larger cartilage defects. While AMIC proved to be an effective treatment in knee and ankle, there are only short-term data available in hip. This study aimed to investigate the mid-term clinical outcome of patients with chondral lesions treated by AMIC and evaluate the quality of repair tissue via MRI.

This retrospective, single center study includes 18 patients undergoing surgical hip dislocation for FAI between 2013 and 2016. Inclusion criteria were: cam or pincer-type FAI, femoral or acetabular chondral lesions > 1 cm², (IRCS III-IV). Due to exclusion criteria and loss-to-follow-up 9 patients (10 hips) could be included. Patient reported outcome measures included Oxford Hip Score (OHS) & Core Outcome Measure Index (COMI)). MRIs were evaluated using the Magnetic Resonance Observation of Cartilage Repair Tissue (MOCART) score.

None of the patients underwent revision surgery except screw removals from the greater trochanter. Followup data indicate a satisfactory to good hip function at 5 years: PROMS improved from pre- to postop at 5 years: OHS from 38.1 to 43.4, COMI from to 1.8 and UCLA from 4 to 8.1 respectively. MOCART score was 67.5 postoperatively. Subgrouping showed slightly better results for acetabular defects (Ø 69.4) compared femoral defects (Ø 60).

Based on the reported mid-term results, we consider AMIC as a valuable treatment option for larger chondral defects of the hip.

To evaluate the impact of routine capsular repair on patient-reported outcomes, survivorship and achievability of clinically important improvement, minimum 5-years post-surgery.

Our prospective institutional registry was reviewed for cases undergoing primary HA for FAI, and stratified into two groups depending on whether the capsule was repaired or not. Routine repair was introduced in late 2013. The No Repair group consisted of patients undergoing HA between Jan 2010-June 2013 while the Repair group consisted of patients undergoing HA between Jan 2015-Sept 2018. Exclusion criteria consisted of >50 years, Tonnis>1, dysplasia(LCEA<25), concomitant hip pathologies. PROMs consisted of mHHS, SF36 and UCLA. Metrics of clinically important improvement was evaluated using MCID and SCB. Rates of repeat HA or THA conversion were recorded.

985 cases were included (359 No Repair; 626 Repair), 86% male, average age 27.4±6.7years. Significant improvement in all PROMs at minimum 5-years was observed for both groups (p<0.001 for all; large effect sizes for mHHS and SF36, medium effect sizes for UCLA). At 5-years post-op there was no significant difference between groups for mHHS(p=0.078) or UCLA(0.794). SF36 was significantly poorer for those cases undergoing routine repair(p<0.001) however effect size was small (0.20). Thresholds of MCID and SCB were calculated as 69% and 86% for mHHS, 64% and 77% for UCLA, 43% and 60% for SF36. Both groups achieved MCID and SCB at similar rates for mHHS and UCLA. A significantly lower proportion of cases in the repair groups achieved MCID for SF36 (53.6% vs 63.5%, p=0.034) and SCB for SF36 (37.3% vs 52.8%, p<0.001). No significant difference between groups for THA conversion (0.6% No Repair vs 0.5% Repair) or repeat HA (9.7% No Repair vs 8.1% Repair).

Routinely repairing the capsule following HA for FAI demonstrates no clinical benefit over not repairing the capsule 5 years post-surgery

The postoperative pain after hip arthroscopy remains a major challenge in the immediate postoperative period. Adequate postoperative analgesia has been associated with increased patient satisfaction and decreased consumption of opioids. We evaluated the efficacy of pericapsular nerve group block (PENG) versus fascia iliaca block (FIB) in reducing post-operative pain and analgesic consumption within the first 24 hours following arthroscopic management of femoroacetabular impingement (FAI).

Thirty-nine patients (17 females and 25 males, ages 18–42 years, mean ± SD (27.9 ± 6.2), and mean BMI of 25.13±5.08 kg/m2 were scheduled for primary arthroscopic management of FAI. Included patients were randomized into two groups according to the block used in each. Group (A) 19 patients were included and had FIB and group (B) 20 patients were included and received PENG block. The efficacy of both techniques was clinically and statistically valuated using VAS score and quadriceps muscle power.

There was a statically significance difference in the mean at rest between the two groups at all measured time points following surgery (6, 12, 18 and 24 h). Also, in dynamic pain scores (with hip flexion) scores were statistically significant at 24 hours post-operative (P = .001). Total opioid consumption in the first 24 hours postoperative was lower in the PENG group with significant difference of mean 16.5 ±9.9 mg for PENG group versus 27.5±9.6 mg for FIB group (P < .005). Five patients (26.31%) in FIB group had weaker quadriceps muscle power while none in PENG group patients had quadriceps weakness.

PENG block might be considered as an ideal regional anesthesia modality for hip arthroscopy. As an alternative to more conventional regional nerve blocks such as a fascia iliaca block. PENG block is easily performed in the preoperative setting, and appears to spare motor function while providing a prolonged sensory pain relief.

Periacetabular osteotomy (PAO) is an established treatment for developmental hip dysplasia (DDH) in young adults and can also be utilised in the management of femoroacetabular impingement (FAI) with acetabular retroversion. This study used a national registry to assess the outcomes of PAO for DDH and FAI.

PAOs recorded in the UK Non-Arthroplasty Hip Registry between 2012 and November 2022 were identified along with recorded patient and surgical characteristics. Cases were grouped according to the primary pathology (DDH or FAI). Patient reported outcome measures (PROMs) captured included the International Hip Outcome Tool (iHOT)-12 (primary outcome) and the EuroQol-5 Dimensions (EQ-5D) index preoperatively and at 6 months, 1, 2, and 5 years post-operatively.

1,087 PAOs were identified; 995 for DDH (91%), 98 for FAI (9%). Most patients (91%) were female. The DDH group were significantly older (mean 31.7 years) than the FAI group (25.4 years) but had similar body mass index (mean 25.7kg/m2). Overall, significant (all p<0.0001) iHOT-12 and EQ-5D improvement (delta) vs baseline pre-operative scores were achieved at 6 months (mean iHOT-12 improvement +27.4 (95%CI 25.3 to 29.5); n=515) and maintained out to 5 years (+30.0 (21.4 to 38.6); n=44 [9.8% of those eligible for follow-up at 5 years]), at which point 71% and 55% of patients continued to demonstrate a score improvement greater than or equal to the minimum clinically important difference (≥13 points) and substantial clinical benefit (≥28 points) for iHOT-12 respectively.

This study demonstrates excellent functional outcomes following PAO undertaken for DDH and FAI in the short to medium term in a large national registry.

Mechanical irritation or impingement of the iliopsoas tendon accounts for 2–6% of persistent postoperative pain cases after total hip arthroplasty (THA). The most common trigger is anterior cup overhang. CT-scan can be used to identify and measure this overhang; however, no threshold exists for symptomatic anterior iliopsoas impingement. We conducted a case–control study in which CT-scan was used to define a threshold that differentiates patients with iliopsoas impingement from asymptomatic patients after THA.

We analyzed the CT-scans of 622 patients (758 CT-scans) between 2011 and 2020. Out of this population we identified 136 patients with symptoms suggestive of iliopsoas impingement. Among them, 6 were subsequently excluded: three because the diagnosis was reestablished intra-operatively (one metallosis, two anterior instability related to posterior prosthetic impingement) and three because they had another obvious cause of impingement (one protruding screw, one protruding cement plug, one stem collar), leaving 130 patients in the study (impingement) group. They were matched to a control group of 138 patients who were asymptomatic after THA. The anterior cup overhang (anterior margin of cup not covered by anterior wall) was measured by an observer (without knowledge of the clinical status) on an axial CT slice based on anatomical landmarks (orthogonal to pelvic axis).

The impingement group had a median overhang of 8 mm [IQR: 5 to 11] versus 0 mm [IQR: 0 to 4] for the control group (p<.001). Using ROC curves, an overhang threshold of 4 mm was best correlated with a diagnosis of impingement (sensitivity 79%, specificity 85%, PPV = 75%, NPV = 85%).

Pain after THA related to iliopsoas impingement can be reasonably linked to acetabular overhang if it exceeds 4 mm on a CT scan. Below this threshold, it seems logical to look for another cause of iliopsoas irritation or another reason for the pain after THA before concluding impingement is present.

Identification of patients at risk of not achieving minimally clinically important differences (MCID) in patient reported outcome measures (PROMs) is important to ensure principled and informed pre-operative decision making. Machine learning techniques may enable the generation of a predictive model for attainment of MCID in hip arthroscopy.

Aims: 1) to determine whether machine learning techniques could predict which patients will achieve MCID in the iHOT-12 PROM 6 months after arthroscopic management of femoroacetabular impingement (FAI), 2) to determine which factors contribute to their predictive power.

Data from the UK Non-Arthroplasty Hip Registry database was utilised. We identified 1917 patients who had undergone hip arthroscopy for FAI with both baseline and 6 month follow up iHOT-12 and baseline EQ-5D scores. We trained three established machine learning algorithms on our dataset to predict an outcome of iHOT-12 MCID improvement at 6 months given baseline characteristics including demographic factors, disease characteristics and PROMs. Performance was assessed using area under the receiver operating characteristic (AUROC) statistics with 5-fold cross validation.

The three machine learning algorithms showed quite different performance. The linear logistic regression model achieved AUROC = 0.59, the deep neural network achieved AUROC = 0.82, while a random forest model had the best predictive performance with AUROC 0.87. Of demographic factors, we found that BMI and age were key predictors for this model. We also found that removing all features except baseline responses to the iHOT-12 questionnaire had little effect on performance for the random forest model (AUROC = 0.85). Disease characteristics had little effect on model performance.

Machine learning models are able to predict with good accuracy 6-month post-operative MCID attainment in patients undergoing arthroscopic management for FAI. Baseline scores from the iHOT-12 questionnaire are sufficient to predict with good accuracy whether a patient is likely to reach MCID in post-operative PROMs.

Aims

Our aim was to evaluate the radiographic characteristics of patients undergoing total hip arthroplasty (THA) for the potential of posterior bony impingement using CT simulations.