Aims. Accurate placement of the acetabular component during total hip arthroplasty (THA) is an important factor in the success of the procedure. However, the reported accuracy varies greatly and is dependent upon whether free hand or navigated techniques are used. The aim of this study was to assess the accuracy of an instrument system that incorporates 3D printed, patient-specific guides designed to optimise the placement of the acetabular component. Patients and Methods. A total of 100 consecutive patients were prospectively enrolled and the accuracy of placement of the acetabular component was measured using post-operative CT scans. Results. The mean absolute deviation from the planned inclination and anteversion was 3.9° (0.0° to 13.6°) and 3.6° (0.0° to 12.9°), respectively. In 91% of cases the planned target of +/-10° was achieved for both inclination and anteversion. Conclusion. Accurate placement of the acetabular component can be achieved using patient-specific guides and is superior to free hand techniques and comparable to navigated and robotic techniques. Cite this article: Bone Joint J 2016;98-B:1342–6

Aims. Abnormal femoral torsion (FT) is increasingly recognized as an additional cause for femoroacetabular impingement (FAI). It is unknown if in-toeing of the foot is a specific diagnostic sign for increased FT in patients with symptomatic FAI. The aims of this study were to determine: 1) the prevalence and diagnostic accuracy of in-toeing to detect increased FT; 2) if foot progression angle (FPA) and tibial torsion (TT) are different among patients with abnormal FT; and 3) if FPA correlates with FT. Patients and Methods. A retrospective, institutional review board (IRB)-approved, controlled study of 85 symptomatic patients (148 hips) with FAI or hip dysplasia was performed in the gait laboratory. All patients had a measurement of FT (pelvic CT scan), TT (CT scan), and FPA (optical motion capture system). We allocated all patients to three groups with decreased FT (< 10°, 37 hips), increased FT (> 25°, 61 hips), and normal FT (10° to 25°, 50 hips). Cluster analysis was performed. Results. We found a specificity of 99%, positive predictive value (PPV) of 93%, and sensitivity of 23% for in-toeing (FPA < 0°) to detect increased FT > 25°. Most of the hips with normal or decreased FT had no in-toeing (false-positive rate of 1%). Patients with increased FT had significantly (p < 0.001) more in-toeing than patients with decreased FT. The majority of the patients (77%) with increased FT walk with a normal foot position. The correlation between FPA and FT was significant (r = 0.404, p < 0.001). Five cluster groups were identified. Conclusion. In-toeing has a high specificity and high PPV to detect increased FT, but increased FT can be missed because of the low sensitivity and high false-negative rate. These results can be used for diagnosis of abnormal FT in patients with FAI or hip dysplasia undergoing hip arthroscopy or femoral derotation osteotomy. However, most of the patients with increased FT walk with a normal foot position. This can lead to underestimation or misdiagnosis of abnormal FT. We recommend measuring FT with CT/MRI scans in all patients with FAI. Cite this article: Bone Joint J 2019;101-B:1218–1229

Pre-operative computerised three-dimensional planning was carried out in 223 patients undergoing total hip replacement with a cementless acetabular component and a cementless modular-neck femoral stem. Components were chosen which best restored leg length and femoral offset. The post-operative restoration of the anatomy was assessed by CT and compared with the pre-operative plan. The component implanted was the same as that planned in 86% of the hips for the acetabular implant, 94% for the stem, and 93% for the neck-shaft angle. The rotational centre of the hip was restored with a mean accuracy of 0.73 mm (. sd. 3.5) craniocaudally and 1.2 mm (. sd. 2) laterally. Limb length was restored with a mean accuracy of 0.3 mm (. sd. 3.3) and femoral offset with a mean accuracy of 0.8 mm (. sd. 3.1). This method appears to offer high accuracy in hip reconstruction as the difficulties likely to be encountered when restoring the anatomy can be anticipated and solved pre-operatively by optimising the selection of implants. Modularity of the femoral neck helped to restore the femoral offset and limb length

Several radiological methods of measuring anteversion of the acetabular component after total hip replacement (THR) have been described. These studies used different definitions and reference planes to compare methods, allowing for misinterpretation of the results. We compared the reliability and accuracy of five current methods using plain radiographs (those of Lewinnek, Widmer, Liaw, Pradhan, and Woo and Morrey) with CT measurements, using the same definition and reference plane. We retrospectively studied the plain radiographs and CT scans in 84 hips of 84 patients who underwent primary THR. Intra- and inter-observer reliability were high for the measurement of inclination and anteversion with all methods on plain radiographs and CT scans. The measurements of inclination on plain radiographs were similar to the measurements using CT (p = 0.043). The mean difference between CT measurements was 0.6° (-5.9° to 6.8°). Measurements using Widmer’s method were the most similar to those using CT (p = 0.088), with a mean difference between CT measurements of -0.9° (-10.4° to 9.1°), whereas the other four methods differed significantly from those using CT (p < 0.001). This study has shown that Widmer’s method is the best for evaluating the anteversion of the acetabular component on plain radiographs. Cite this article: Bone Joint J 2014; 96-B:597–603

Aims

Cross-table lateral (CTL) radiographs are commonly used to measure acetabular component anteversion after total hip arthroplasty (THA). The CTL measurements may differ by > 10° from CT scan measurements but the reasons for this discrepancy are poorly understood. Anteversion measurements from CTL radiographs and CT scans are compared to identify spinopelvic parameters predictive of inaccuracy.

In 20 patients undergoing hybrid total hip arthroplasty, the reproducibility and accuracy of templating using digital radiographs were assessed. Digital images were manipulated using either a ten-pence coin as a marker to scale for magnification, or two digital-line methods using computer software. On-screen images were templated with standard acetate templates and compared with templating performed on hard-copy digital prints. The digital-line methods were the least reliable and accuracy of sizing compared with the inserted prostheses varied between −1.6% and +10.2%. The hard-copy radiographs showed better reproducibility than the ten-pence coin method, but were less accurate with 3.7% undersizing. The ten-pence coin method was the most accurate, with no significant differences for offset or acetabulum, and undersizing of only 0.9%. On-screen templating of digital radiographs with standard acetate templates is accurate and reproducible if a radiopaque marker such as a ten-pence coin is included when the original radiograph is taken

Several methods of measuring the migration of the femoral component after total hip replacement have been described, but they use different reference lines, and have differing accuracies, some unproven. Statistical comparison of different studies is rarely possible. We report a study of the EBRA-FCA method (femoral component analysis using Einzel-Bild-Röntgen-Analyse) to determine its accuracy using three independent assessments, including a direct comparison with the results of roentgen stereophotogrammetric analysis (RSA). The accuracy of EBRA-FCA was better than ±1.5 mm (95% percentile) with a Cronbach’s coefficient alpha for interobserver reliability of 0.84; a very good result. The method had a specificity of 100% and a sensitivity of 78% compared with RSA for the detection of migration of over 1 mm. This is accurate enough to assess the stability of a prosthesis within a relatively limited period. The best reference line for downward migration is between the greater trochanter and the shoulder of the stem, as confirmed by two experimental analyses and a computer-assisted design

We evaluated the accuracy with which a custom-made acetabular component could be positioned at revision arthroplasty of the hip in patients with a Paprosky type 3 acetabular defect. A total of 16 patients with a Paprosky type 3 defect underwent revision surgery using a custom-made trabecular titanium implant. There were four men and 12 women with a median age of 67 years (48 to 79). The planned inclination (INCL), anteversion (AV), rotation and centre of rotation (COR) of the implant were compared with the post-operative position using CT scans. A total of seven implants were malpositioned in one or more parameters: one with respect to INCL, three with respect to AV, four with respect to rotation and five with respect to the COR. To the best of our knowledge, this is the first study in which CT data acquired for the pre-operative planning of a custom-made revision acetabular implant have been compared with CT data on the post-operative position. The results are encouraging. Cite this article: Bone Joint J 2015; 97-B:780–5

There is great variability in acetabular component orientation following hip replacement. The aims of this study were to compare the component orientation at impaction with the orientation measured on post-operative radiographs and identify factors that influence the difference between the two. A total of 67 hip replacements (52 total hip replacements and 15 hip resurfacings) were prospectively studied. Intra-operatively, the orientation of the acetabular component after impaction relative to the operating table was measured using a validated stereo-photogrammetry protocol. Post-operatively, the radiographic orientation was measured; the mean inclination/anteversion was 43° (sd 6°)/ 19° (sd 7°). A simulated radiographic orientation was calculated based on how the orientation would have appeared had an on-table radiograph been taken intra-operatively. The mean difference between radiographic and intra-operative inclination/anteversion was 5° (sd 5°)/ -8° (sd 8°). The mean difference between simulated radiographic and intra-operative inclination/anteversion, which quantifies the effect of the different way acetabular orientation is measured, was 3°/-6° (sd 2°). The mean difference between radiographic and simulated radiographic orientation inclination/anteversion, which is a manifestation of the change in pelvic position between component impaction and radiograph, was 1°/-2° (sd 7°).

This study demonstrated that in order to achieve a specific radiographic orientation target, surgeons should implant the acetabular component 5° less inclined and 8° more anteverted than their target. Great variability (2 sd about ± 15°) in the post-operative radiographic cup orientation was seen. The two equally contributing causes for this are variability in the orientation at which the cup is implanted, and the change in pelvic position between impaction and post-operative radiograph.

Cite this article: Bone Joint J 2014;96-B:1290–7

There is no single standardised method of measuring the orientation of the acetabular component on plain radiographs after total hip arthroplasty. We assessed the reliability and accuracy of three methods of assessing anteversion of the acetabular component for 551 THAs using the PolyWare software and the methods of Liaw et al, and of Woo and Morrey. All measurements of the three methods had excellent intra- and inter-observer reliability. The values of the PolyWare software, which determines version of the acetabular component by edge detection were regarded as the reference standard. Although the PolyWare software and the method of Liaw et al were similarly precise, the method of Woo and Morrey was significantly less accurate (p < 0.001). The method of Liaw et al seemed to be more accurate than that of Woo and Morrey when compared with the measurements using the PolyWare software. If the qualified lateral radiograph was selected, anteversion measured using the method of Woo and Morrey was considered to be relatively reliable.

Cite this article: Bone Joint J 2015; 97-B:611–16.

In this meta-analysis we included 32 English-language articles published between January 1975 and June 2004 on the diagnostic performance of plain radiography, subtraction arthrography, nuclear arthrography and bone scintigraphy in detecting aseptic loosening of the femoral component, using criteria based on the Cochrane systematic review of screening and diagnostic tests.

The mean sensitivity and specificity were, respectively, 82% (95% confidence interval (CI) 76 to 87) and 81% (95% CI 73 to 87) for plain radiography and 85% (95% CI 75 to 91) and 83% (95% CI 75 to 89) for nuclear arthrography. Pooled sensitivity and specificity were, respectively, 86% (95% CI 74 to 93) and 85% (95% CI 77 to 91) for subtraction arthrography and 85% (95% CI 79 to 89) and 72% (95% CI 64 to 79) for bone scintigraphy. Although the diagnostic performance of the imaging techniques was not significantly different, plain radiography and bone scintigraphy are preferred for the assessment of a femoral component because of their efficacy and lower risk of patient morbidity.

Aims. Achieving accurate implant positioning and restoring native hip biomechanics are key surgeon-controlled technical objectives in total hip arthroplasty (THA). The primary objective of this study was to compare the reproducibility of the planned preoperative centre of hip rotation (COR) in patients undergoing robotic arm-assisted THA versus conventional THA. Methods. This prospective randomized controlled trial (RCT) included 60 patients with symptomatic hip osteoarthritis undergoing conventional THA (CO THA) versus robotic arm-assisted THA (RO THA). Patients in both arms underwent pre- and postoperative CT scans, and a patient-specific plan was created using the robotic software. The COR, combined offset, acetabular orientation, and leg length discrepancy were measured on the pre- and postoperative CT scanogram at six weeks following surgery. Results. There were no significant differences for any of the baseline characteristics including spinopelvic mobility. The absolute error for achieving the planned horizontal COR was median 1.4 mm (interquartile range (IQR) 0.87 to 3.42) in RO THA versus 4.3 mm (IQR 3 to 6.8; p < 0.001); vertical COR mean 0.91 mm (SD 0.73) in RO THA versus 2.3 mm (SD 1.3; p < 0.001); and combined offset median 2 mm (IQR 0.97 to 5.45) in RO THA versus 3.9 mm (IQR 2 to 7.9; p = 0.019). Improved accuracy was observed with RO THA in achieving the desired acetabular component positioning (root mean square error for anteversion and inclination was 2.6 and 1.3 vs 8.9 and 5.3, repectively) and leg length (mean 0.6 mm vs 1.4 mm; p < 0.001). Patient-reported outcome measures were comparable between the two groups at baseline and one year. Participants in the RO THA group needed fewer physiotherapy sessions postoperatively (median six (IQR 4.5 to 8) vs eight (IQR 6 to 11; p = 0.005). Conclusion. This RCT suggested that robotic-arm assistance in THA was associated with improved accuracy in restoring the native COR, better preservation of the combined offset, leg length correction, and superior accuracy in achieving the desired acetabular component positioning. Further evaluation through long-term and registry data is necessary to assess whether these findings translate into improved implant survival and functional outcomes. Cite this article: Bone Joint J 2024;106-B(4):324–335

Aims. The aim of this study was to examine the implant accuracy of custom-made partial pelvis replacements (PPRs) in revision total hip arthroplasty (rTHA). Custom-made implants offer an option to achieve a reconstruction in cases with severe acetabular bone loss. By analyzing implant deviation in CT and radiograph imaging and correlating early clinical complications, we aimed to optimize the usage of custom-made implants. Methods. A consecutive series of 45 (2014 to 2019) PPRs for Paprosky III defects at rTHA were analyzed comparing the preoperative planning CT scans used to manufacture the implants with postoperative CT scans and radiographs. The anteversion (AV), inclination (IC), deviation from the preoperatively planned implant position, and deviation of the centre of rotation (COR) were explored. Early postoperative complications were recorded, and factors for malpositioning were sought. The mean follow-up was 30 months (SD 19; 6 to 74), with four patients lost to follow-up. Results. Mean CT defined discrepancy (Δ) between planned and achieved AV and IC was 4.5° (SD 3°; 0° to 12°) and 4° (SD 3.5°; 1° to 12°), respectively. Malpositioning (Δ > 10°) occurred in five hips (10.6%). Native COR reconstruction was planned in 42 cases (93%), and the mean 3D deviation vector was 15.5 mm (SD 8.5; 4 to 35). There was no significant influence in malpositioning found for femoral stem retention, surgical approach, or fixation method. Conclusion. At short-term follow-up, we found that PPR offers a viable solution for rTHA in cases with massive acetabular bone loss, as highly accurate positioning can be accomplished with meticulous planning, achieving anatomical reconstruction. Accuracy of achieved placement contributed to reduced complications with no injury to vital structures by screw fixation. Cite this article: Bone Joint J 2022;104-B(10):1110–1117

Aims. Although CT is considered the benchmark to measure femoral version, 3D biplanar radiography (hipEOS) has recently emerged as a possible alternative with reduced exposure to ionizing radiation and shorter examination time. The aim of our study was to evaluate femoral stem version in postoperative total hip arthroplasty (THA) patients and compare the accuracy of hipEOS to CT. We hypothesize that there will be no significant difference in calculated femoral stem version measurements between the two imaging methods. Methods. In this study, 45 patients who underwent THA between February 2016 and February 2020 and had both a postoperative CT and EOS scan were included for evaluation. A fellowship-trained musculoskeletal radiologist and radiological technician measured femoral version for CT and 3D EOS, respectively. Comparison of values for each imaging modality were assessed for statistical significance. Results. Comparison of the mean postoperative femoral stem version measurements between CT and 3D hipEOS showed no significant difference (p = 0.862). In addition, the two version measurements were strongly correlated (r = 0.95; p < 0.001), and the mean paired difference in postoperative femoral version for CT scan and 3D biplanar radiography was -0.09° (95% confidence interval -1.09 to 0.91). Only three stem measurements (6.7%) were considered outliers with a > 5° difference. Conclusion. Our study supports the use of low-dose biplanar radiography for the postoperative assessment of femoral stem version after THA, demonstrating high correlation with CT. We found no significant difference for postoperative femoral version when comparing CT to 3D EOS. We believe 3D EOS is a reliable option to measure postoperative femoral version given its advantages of lower radiation dosage and shorter examination time. Cite this article: Bone Joint J 2022;104-B(11):1196–1201

Aims. This study reports mid-term outcomes after periacetabular osteotomy (PAO) exclusively in a borderline hip dysplasia (BHD) population to provide a contrast to published outcomes for arthroscopic surgery of the hip in BHD. Methods. We identified 42 hips in 40 patients treated between January 2009 and January 2016 with BHD defined as a lateral centre-edge angle (LCEA) of ≥ 18° but < 25°. A minimum five-year follow-up was available. Patient-reported outcomes (PROMs) including Tegner score, subjective hip value (SHV), modified Harris Hip Score (mHHS), and Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) were assessed. The following morphological parameters were evaluated: LCEA, acetabular index (AI), α angle, Tönnis staging, acetabular retroversion, femoral version, femoroepiphyseal acetabular roof index (FEAR), iliocapsularis to rectus femoris ratio (IC/RF), and labral and ligamentum teres (LT) pathology. Results. The mean follow-up was 96 months (67 to 139). The SHV, mHHS, WOMAC, and Tegner scores significantly improved (p < 0.001) at last follow-up. According to SHV and mHHS, there were three hips (7%) with poor results (SHV < 70), three (7%) with a fair score (70 to 79), eight (19%) with good results (80 to 89), and 28 (67%) who scored excellent (> 90) at the last follow-up. There were 11 subsequent operations: nine implant removals due to local irritation, one resection of postoperative heterotopic ossification, and one hip arthroscopy for intra-articular adhesions. No hips were converted to total hip arthroplasty at last follow-up. The presence of preoperative labral lesions or LT lesions did not influence any PROMs at last follow-up. From the three hips that had poor PROMs, two have developed severe osteoarthritis (> Tönnis II), presumably due to surgical overcorrection (postoperative AI < -10°). Conclusion. PAO is reliable in treating BHD with favourable mid-term outcomes. Concomitant LT and labral lesions did not negatively influence outcomes in our cohort. Technical accuracy with avoidance of overcorrection is essential in achieving successful outcomes. Cite this article: Bone Joint J 2023;105-B(7):735–742

Aims. Periacetabular osteotomy (PAO) is widely recognized as a demanding surgical procedure for acetabular reorientation. Reports about the learning curve have primarily focused on complication rates during the initial learning phase. Therefore, our aim was to assess the PAO learning curve from an analytical perspective by determining the number of PAOs required for the duration of surgery to plateau and the accuracy to improve. Methods. The study included 118 consecutive PAOs in 106 patients. Of these, 28 were male (23.7%) and 90 were female (76.3%). The primary endpoint was surgical time. Secondary outcome measures included radiological parameters. Cumulative summation analysis was used to determine changes in surgical duration. A multivariate linear regression model was used to identify independent factors influencing surgical time. Results. The learning curve in this series was 26 PAOs in a period of six months. After 26 PAO procedures, a significant drop in surgical time was observed and a plateau was also achieved. The mean duration of surgery during the learning curve was 103.8 minutes (SD 33.2), and 69.7 minutes (SD 18.6) thereafter (p < 0.001). Radiological correction of acetabular retroversion showed a significant improvement after having performed a total of 93 PAOs, including anteverting PAOs on 35 hips with a retroverted acetabular morphology (p = 0.005). Several factors were identified as independent variables influencing duration of surgery, including patient weight (β = 0.5 (95% confidence interval (CI) 0.2 to 0.7); p < 0.001), learning curve procedure phase of 26 procedures (β = 34.0 (95% CI 24.3 to 43.8); p < 0.001), and the degree of lateral correction expressed as the change in the lateral centre-edge angle (β = 0.7 (95% CI 0.001 to 1.3); p = 0.048). Conclusion. The learning curve for PAO surgery requires extensive surgical training at a high-volume centre, with a minimum of 50 PAOs per surgeon per year. This study defined a cut-off value of 26 PAO procedures, after which a significant drop in surgical duration occurred. Furthermore, it was observed that a retroverted morphology of the acetabulum required a greater number of procedures to acquire proficiency in consistently eliminating the crossover sign. These findings are relevant for fellows and fellowship programme directors in establishing the extent of training required to impart competence in PAO. Cite this article: Bone Joint J 2024;106-B(4):336–343

Aims. Natural Language Processing (NLP) offers an automated method to extract data from unstructured free text fields for arthroplasty registry participation. Our objective was to investigate how accurately NLP can be used to extract structured clinical data from unstructured clinical notes when compared with manual data extraction. Methods. A group of 1,000 randomly selected clinical and hospital notes from eight different surgeons were collected for patients undergoing primary arthroplasty between 2012 and 2018. In all, 19 preoperative, 17 operative, and two postoperative variables of interest were manually extracted from these notes. A NLP algorithm was created to automatically extract these variables from a training sample of these notes, and the algorithm was tested on a random test sample of notes. Performance of the NLP algorithm was measured in Statistical Analysis System (SAS) by calculating the accuracy of the variables collected, the ability of the algorithm to collect the correct information when it was indeed in the note (sensitivity), and the ability of the algorithm to not collect a certain data element when it was not in the note (specificity). Results. The NLP algorithm performed well at extracting variables from unstructured data in our random test dataset (accuracy = 96.3%, sensitivity = 95.2%, and specificity = 97.4%). It performed better at extracting data that were in a structured, templated format such as range of movement (ROM) (accuracy = 98%) and implant brand (accuracy = 98%) than data that were entered with variation depending on the author of the note such as the presence of deep-vein thrombosis (DVT) (accuracy = 90%). Conclusion. The NLP algorithm used in this study was able to identify a subset of variables from randomly selected unstructured notes in arthroplasty with an accuracy above 90%. For some variables, such as objective exam data, the accuracy was very high. Our findings suggest that automated algorithms using NLP can help orthopaedic practices retrospectively collect information for registries and quality improvement (QI) efforts. Cite this article: Bone Joint J 2020;102-B(7 Supple B):99–104

Objectives. The primary objective of this study was to compare accuracy in restoring the native centre of hip rotation in patients undergoing conventional manual total hip arthroplasty (THA) versus robotic-arm assisted THA. Secondary objectives were to determine differences between these treatment techniques for THA in achieving the planned combined offset, component inclination, component version, and leg-length correction. Materials and Methods. This prospective cohort study included 50 patients undergoing conventional manual THA and 25 patients receiving robotic-arm assisted THA. Patients undergoing conventional manual THA and robotic-arm assisted THA were well matched for age (mean age, 69.4 years (. sd. 5.2) vs 67.5 years (. sd. 5.8) (p = 0.25); body mass index (27.4 kg/m. 2. (. sd. 2.1) vs 26.9 kg/m. 2. (. sd. 2.2); p = 0.39); and laterality of surgery (right = 28, left = 22 vs right = 12, left = 13; p = 0.78). All operative procedures were undertaken by a single surgeon using the posterior approach. Two independent blinded observers recorded all radiological outcomes of interest using plain radiographs. Results. The correlation coefficient was 0.92 (95% confidence interval (CI) 0.88 to 0.95) for intraobserver agreement and 0.88 (95% CI 0.82 to 0.94) for interobserver agreement in all study outcomes. Robotic THA was associated with improved accuracy in restoring the native horizontal (p < 0.001) and vertical (p < 0.001) centres of rotation, and improved preservation of the patient’s native combined offset (p < 0.001) compared with conventional THA. Robotic THA improved accuracy in positioning of the acetabular component within the combined safe zones of inclination and anteversion described by Lewinnek et al (p = 0.02) and Callanan et al (p = 0.01) compared with conventional THA. There was no difference between the two treatment groups in achieving the planned leg-length correction (p = 0.10). Conclusion. Robotic-arm assisted THA was associated with improved accuracy in restoring the native centre of rotation, better preservation of the combined offset, and more precise acetabular component positioning within the safe zones of inclination and anteversion compared with conventional manual THA

Aims. Failure of irrigation and debridement (I&D) for prosthetic joint infection (PJI) is influenced by numerous host, surgical, and pathogen-related factors. We aimed to develop and validate a practical, easy-to-use tool based on machine learning that may accurately predict outcome following I&D surgery taking into account the influence of numerous factors. Methods. This was an international, multicentre retrospective study of 1,174 revision total hip (THA) and knee arthroplasties (TKA) undergoing I&D for PJI between January 2005 and December 2017. PJI was defined using the Musculoskeletal Infection Society (MSIS) criteria. A total of 52 variables including demographics, comorbidities, and clinical and laboratory findings were evaluated using random forest machine learning analysis. The algorithm was then verified through cross-validation. Results. Of the 1,174 patients that were included in the study, 405 patients (34.5%) failed treatment. Using random forest analysis, an algorithm that provides the probability for failure for each specific patient was created. By order of importance, the ten most important variables associated with failure of I&D were serum CRP levels, positive blood cultures, indication for index arthroplasty other than osteoarthritis, not exchanging the modular components, use of immunosuppressive medication, late acute (haematogenous) infections, methicillin-resistant Staphylococcus aureus infection, overlying skin infection, polymicrobial infection, and older age. The algorithm had good discriminatory capability (area under the curve = 0.74). Cross-validation showed similar probabilities comparing predicted and observed failures indicating high accuracy of the model. Conclusion. This is the first study in the orthopaedic literature to use machine learning as a tool for predicting outcomes following I&D surgery. The developed algorithm provides the medical profession with a tool that can be employed in clinical decision-making and improve patient care. Future studies should aid in further validating this tool on additional cohorts. Cite this article: Bone Joint J 2020;102-B(7 Supple B):11–19

Aims

The primary objective of this study was to develop a validated classification system for assessing iatrogenic bone trauma and soft-tissue injury during total hip arthroplasty (THA). The secondary objective was to compare macroscopic bone trauma and soft-tissues injury in conventional THA (CO THA) versus robotic arm-assisted THA (RO THA) using this classification system.