Advertisement for orthosearch.org.uk
Results 1 - 20 of 90
Results per page:
The Bone & Joint Journal
Vol. 104-B, Issue 8 | Pages 929 - 937
1 Aug 2022
Gurung B Liu P Harris PDR Sagi A Field RE Sochart DH Tucker K Asopa V

Aims. Total hip arthroplasty (THA) and total knee arthroplasty (TKA) are common orthopaedic procedures requiring postoperative radiographs to confirm implant positioning and identify complications. Artificial intelligence (AI)-based image analysis has the potential to automate this postoperative surveillance. The aim of this study was to prepare a scoping review to investigate how AI is being used in the analysis of radiographs following THA and TKA, and how accurate these tools are. Methods. The Embase, MEDLINE, and PubMed libraries were systematically searched to identify relevant articles. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for scoping reviews and Arksey and O’Malley framework were followed. Study quality was assessed using a modified Methodological Index for Non-Randomized Studies tool. AI performance was reported using either the area under the curve (AUC) or accuracy. Results. Of the 455 studies identified, only 12 were suitable for inclusion. Nine reported implant identification and three described predicting risk of implant failure. Of the 12, three studies compared AI performance with orthopaedic surgeons. AI-based implant identification achieved AUC 0.992 to 1, and most algorithms reported an accuracy > 90%, using 550 to 320,000 training radiographs. AI prediction of dislocation risk post-THA, determined after five-year follow-up, was satisfactory (AUC 76.67; 8,500 training radiographs). Diagnosis of hip implant loosening was good (accuracy 88.3%; 420 training radiographs) and measurement of postoperative acetabular angles was comparable to humans (mean absolute difference 1.35° to 1.39°). However, 11 of the 12 studies had several methodological limitations introducing a high risk of bias. None of the studies were externally validated. Conclusion. These studies show that AI is promising. While it already has the ability to analyze images with significant precision, there is currently insufficient high-level evidence to support its widespread clinical use. Further research to design robust studies that follow standard reporting guidelines should be encouraged to develop AI models that could be easily translated into real-world conditions. Cite this article: Bone Joint J 2022;104-B(8):929–937


The Bone & Joint Journal
Vol. 104-B, Issue 8 | Pages 911 - 914
1 Aug 2022
Prijs J Liao Z Ashkani-Esfahani S Olczak J Gordon M Jayakumar P Jutte PC Jaarsma RL IJpma FFA Doornberg JN

Artificial intelligence (AI) is, in essence, the concept of ‘computer thinking’, encompassing methods that train computers to perform and learn from executing certain tasks, called machine learning, and methods to build intricate computer models that both learn and adapt, called complex neural networks. Computer vision is a function of AI by which machine learning and complex neural networks can be applied to enable computers to capture, analyze, and interpret information from clinical images and visual inputs. This annotation summarizes key considerations and future perspectives concerning computer vision, questioning the need for this technology (the ‘why’), the current applications (the ‘what’), and the approach to unlocking its full potential (the ‘how’). Cite this article: Bone Joint J 2022;104-B(8):911–914


The Bone & Joint Journal
Vol. 106-B, Issue 7 | Pages 688 - 695
1 Jul 2024
Farrow L Zhong M Anderson L

Aims

To examine whether natural language processing (NLP) using a clinically based large language model (LLM) could be used to predict patient selection for total hip or total knee arthroplasty (THA/TKA) from routinely available free-text radiology reports.

Methods

Data pre-processing and analyses were conducted according to the Artificial intelligence to Revolutionize the patient Care pathway in Hip and knEe aRthroplastY (ARCHERY) project protocol. This included use of de-identified Scottish regional clinical data of patients referred for consideration of THA/TKA, held in a secure data environment designed for artificial intelligence (AI) inference. Only preoperative radiology reports were included. NLP algorithms were based on the freely available GatorTron model, a LLM trained on over 82 billion words of de-identified clinical text. Two inference tasks were performed: assessment after model-fine tuning (50 Epochs and three cycles of k-fold cross validation), and external validation.


The Bone & Joint Journal
Vol. 104-B, Issue 12 | Pages 1292 - 1303
1 Dec 2022
Polisetty TS Jain S Pang M Karnuta JM Vigdorchik JM Nawabi DH Wyles CC Ramkumar PN

Literature surrounding artificial intelligence (AI)-related applications for hip and knee arthroplasty has proliferated. However, meaningful advances that fundamentally transform the practice and delivery of joint arthroplasty are yet to be realized, despite the broad range of applications as we continue to search for meaningful and appropriate use of AI. AI literature in hip and knee arthroplasty between 2018 and 2021 regarding image-based analyses, value-based care, remote patient monitoring, and augmented reality was reviewed. Concerns surrounding meaningful use and appropriate methodological approaches of AI in joint arthroplasty research are summarized. Of the 233 AI-related orthopaedics articles published, 178 (76%) constituted original research, while the rest consisted of editorials or reviews. A total of 52% of original AI-related research concerns hip and knee arthroplasty (n = 92), and a narrative review is described. Three studies were externally validated. Pitfalls surrounding present-day research include conflating vernacular (“AI/machine learning”), repackaging limited registry data, prematurely releasing internally validated prediction models, appraising model architecture instead of inputted data, withholding code, and evaluating studies using antiquated regression-based guidelines. While AI has been applied to a variety of hip and knee arthroplasty applications with limited clinical impact, the future remains promising if the question is meaningful, the methodology is rigorous and transparent, the data are rich, and the model is externally validated. Simple checkpoints for meaningful AI adoption include ensuring applications focus on: administrative support over clinical evaluation and management; necessity of the advanced model; and the novelty of the question being answered. Cite this article: Bone Joint J 2022;104-B(12):1292–1303


The Bone & Joint Journal
Vol. 105-B, Issue 12 | Pages 1327 - 1332
1 Dec 2023
Morris WZ Kak A Mayfield LM Kang MS Jo C Kim HKW

Aims. Abduction bracing is commonly used to treat developmental dysplasia of the hip (DDH) following closed reduction and spica casting, with little evidence to support or refute this practice. The purpose of this study was to determine the efficacy of abduction bracing after closed reduction in improving acetabular index (AI) and reducing secondary surgery for residual hip dysplasia. Methods. We performed a retrospective review of patients treated with closed reduction for DDH at a single tertiary referral centre. Demographic data were obtained including severity of dislocation based on the International Hip Dysplasia Institute (IHDI) classification, age at reduction, and casting duration. Patients were prescribed no abduction bracing, part-time, or full-time wear post-reduction and casting. AI measurements were obtained immediately upon cast removal and from two- and four-year follow-up radiographs. Results. A total of 243 hips underwent closed reduction and 82% (199/243) were treated with abduction bracing. There was no difference between those treated with or without bracing with regard to sex, age at reduction, severity of dislocation, spica duration, or immediate post-casting AI (all p > 0.05). There was no difference in hips treated with or without abduction brace with regard to AI at two years post-reduction (32.4° (SD 5.3°) vs 30.9° (SD 4.6°), respectively; p = 0.099) or at four years post-reduction (26.4° (SD 5.2°) vs 25.4° (SD 5.1°), respectively; p = 0.231). Multivariate analysis revealed only IHDI grade predicted AI at two years post-reduction (p = 0.004). There was no difference in overall rate of secondary surgery for residual dysplasia between hips treated with or without bracing (32% vs 39%, respectively; p = 0.372). However, there was an increased risk of early secondary surgery (< two years post-reduction) in the non-braced group (11.4% vs 2.5%; p = 0.019). Conclusion. Abduction bracing following closed reduction for DDH treatment is not associated with decreased residual dysplasia at two or four years post-reduction but may reduce rates of early secondary surgery. A prospective study is indicated to provide more definitive recommendations. Cite this article: Bone Joint J 2023;105-B(12):1327–1332


The Bone & Joint Journal
Vol. 105-B, Issue 6 | Pages 587 - 589
1 Jun 2023
Kunze KN Jang SJ Fullerton MA Vigdorchik JM Haddad FS

The OpenAI chatbot ChatGPT is an artificial intelligence (AI) application that uses state-of-the-art language processing AI. It can perform a vast number of tasks, from writing poetry and explaining complex quantum mechanics, to translating language and writing research articles with a human-like understanding and legitimacy. Since its initial release to the public in November 2022, ChatGPT has garnered considerable attention due to its ability to mimic the patterns of human language, and it has attracted billion-dollar investments from Microsoft and PricewaterhouseCoopers. The scope of ChatGPT and other large language models appears infinite, but there are several important limitations. This editorial provides an introduction to the basic functionality of ChatGPT and other large language models, their current applications and limitations, and the associated implications for clinical practice and research. Cite this article: Bone Joint J 2023;105-B(6):587–589


The Bone & Joint Journal
Vol. 105-B, Issue 7 | Pages 735 - 742
1 Jul 2023
Andronic O Germann C Jud L Zingg PO

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


The Bone & Joint Journal
Vol. 105-B, Issue 2 | Pages 99 - 100
1 Feb 2023
Birch NC Tsirikos AI


The Bone & Joint Journal
Vol. 103-B, Issue 11 | Pages 1662 - 1668
1 Nov 2021
Bhanushali A Chimutengwende-Gordon M Beck M Callary SA Costi K Howie DW Solomon LB

Aims. The aims of this study were to compare clinically relevant measurements of hip dysplasia on radiographs taken in the supine and standing position, and to compare Hip2Norm software and Picture Archiving and Communication System (PACS)-derived digital radiological measurements. Methods. Preoperative supine and standing radiographs of 36 consecutive patients (43 hips) who underwent periacetabular osteotomy surgery were retrospectively analyzed from a single-centre, two-surgeon cohort. Anterior coverage (AC), posterior coverage (PC), lateral centre-edge angle (LCEA), acetabular inclination (AI), sharp angle (SA), pelvic tilt (PT), retroversion index (RI), femoroepiphyseal acetabular roof (FEAR) index, femoroepiphyseal horizontal angle (FEHA), leg length discrepancy (LLD), and pelvic obliquity (PO) were analyzed using both Hip2Norm software and PACS-derived measurements where applicable. Results. Analysis of supine and standing radiographs resulted in significant variation for measurements of PT (p < 0.001) and AC (p = 0.005). The variation in PT correlated with the variation in AC in a limited number of patients (R. 2. = 0.378; p = 0.012). Conclusion. The significant variation in PT and AC between supine and standing radiographs suggests that it may benefit surgeons to have both radiographs when planning surgical correction of hip dysplasia. We also recommend using PACS-derived measurements of AI and SA due to the poor interobserver error on Hip2Norm. Cite this article: Bone Joint J 2021;103-B(11):1662–1668


The Bone & Joint Journal
Vol. 102-B, Issue 9 | Pages 1242 - 1247
3 Sep 2020
Hsu P Wu K Lee C Lin S Kuo KN Wang T

Aims. Guided growth has been used to treat coxa valga for cerebral palsy (CP) children. However, there has been no study on the optimal position of screw application. In this paper we have investigated the influence of screw position on the outcomes of guided growth. Methods. We retrospectively analyzed 61 hips in 32 CP children who underwent proximal femoral hemi epiphysiodesis between July 2012 and September 2017. The hips were divided into two groups according to the transphyseal position of the screw in the coronal plane: across medial quarter (Group 1) or middle quarter (Group 2) of the medial half of the physis. We compared pre- and postoperative radiographs in head-shaft angle (HSA), Reimer’s migration percentage (MP), acetabular index (AI), and femoral anteversion angle (FAVA), as well as incidences of the physis growing-off the screw within two years. Linear and Cox regression analysis were conducted to identify factors related to HSA correction and risk of the physis growing-off the screw. Results. A total of 37 hips in Group 1 and 24 hips in Group 2 were compared. Group 1 showed a more substantial decrease in the HSA (p = 0.003) and the MP (p = 0.032). Both groups had significant and similar improvements in the AI (p = 0.809) and the FAVA (p = 0.304). Group 1 presented a higher incidence of the physis growing-off the screw (p = 0.038). Results of the regression analysis indicated that the eccentricity of screw position correlated with HSA correction and increases the risk of the physis growing-off the screw. Conclusion. Guided growth is effective in improving coxa valga and excessive femoral anteversion in CP children. For younger children, despite compromised efficacy of varus correction, we recommend a more centered screw position, at least across the middle quarter of the medial physis, to avoid early revision. Cite this article: Bone Joint J 2020;102-B(9):1242–1247


The Bone & Joint Journal
Vol. 103-B, Issue 6 | Pages 1133 - 1141
1 Jun 2021
Tsirikos AI Wordie SJ

Aims

To report the outcome of spinal deformity correction through anterior spinal fusion in wheelchair-bound patients with myelomeningocele.

Methods

We reviewed 12 consecutive patients (7M:5F; mean age 12.4 years (9.2 to 16.8)) including demographic details, spinopelvic parameters, surgical correction, and perioperative data. We assessed the impact of surgery on patient outcomes using the Spina Bifida Spine Questionnaire and a qualitative questionnaire.


The Bone & Joint Journal
Vol. 104-B, Issue 8 | Pages 915 - 921
1 Aug 2022
Marya S Tambe AD Millner PA Tsirikos AI

Adolescent idiopathic scoliosis (AIS), defined by an age at presentation of 11 to 18 years, has a prevalence of 0.47% and accounts for approximately 90% of all cases of idiopathic scoliosis. Despite decades of research, the exact aetiology of AIS remains unknown. It is becoming evident that it is the result of a complex interplay of genetic, internal, and environmental factors. It has been hypothesized that genetic variants act as the initial trigger that allow epigenetic factors to propagate AIS, which could also explain the wide phenotypic variation in the presentation of the disorder. A better understanding of the underlying aetiological mechanisms could help to establish the diagnosis earlier and allow a more accurate prediction of deformity progression. This, in turn, would prompt imaging and therapeutic intervention at the appropriate time, thereby achieving the best clinical outcome for this group of patients.

Cite this article: Bone Joint J 2022;104-B(8):915–921.


The Bone & Joint Journal
Vol. 103-B, Issue 4 | Pages 804 - 804
1 Apr 2021
Tsirikos AI Carter TH


The Bone & Joint Journal
Vol. 103-B, Issue 1 | Pages 148 - 156
1 Jan 2021
Tsirikos AI Carter TH

Aims

To report the surgical outcome of patients with severe Scheuermann’s kyphosis treated using a consistent technique and perioperative management.

Methods

We reviewed 88 consecutive patients with a severe Scheuermann's kyphosis who had undergone posterior spinal fusion with closing wedge osteotomies and hybrid instrumentation. There were 55 males and 33 females with a mean age of 15.9 years (12.0 to 24.7) at the time of surgery. We recorded their demographics, spinopelvic parameters, surgical correction, and perioperative data, and assessed the impact of surgical complications on outcome using the Scoliosis Research Society (SRS)-22 questionnaire.


The Bone & Joint Journal
Vol. 106-B, Issue 2 | Pages 174 - 181
1 Feb 2024
Mandalia KP Brodeur PG Li LT Ives K Cruz Jr. AI Shah SS

Aims

The aim of this study was to characterize the influence of social deprivation on the rate of complications, readmissions, and revisions following primary total shoulder arthroplasty (TSA), using the Social Deprivation Index (SDI). The SDI is a composite measurement, in percentages, of seven demographic characteristics: living in poverty, with < 12 years of education, single-parent households, living in rented or overcrowded housing, households without a car, and unemployed adults aged < 65 years.

Methods

Patients aged ≥ 40 years, who underwent primary TSA between 2011 and 2017, were identified using International Classification of Diseases (ICD)-9 Clinical Modification and ICD-10 procedure codes for TSA in the New York Statewide Planning and Research Cooperative System database. Readmission, reoperation, and other complications were analyzed using multivariable Cox proportional hazards regression controlling for SDI, age, ethnicity, insurance status, and Charlson Comorbidity Index.


The Bone & Joint Journal
Vol. 101-B, Issue 8 | Pages 902 - 909
1 Aug 2019
Innmann MM Merle C Gotterbarm T Ewerbeck V Beaulé PE Grammatopoulos G

Aims. This study of patients with osteoarthritis (OA) of the hip aimed to: 1) characterize the contribution of the hip, spinopelvic complex, and lumbar spine when moving from the standing to the sitting position; 2) assess whether abnormal spinopelvic mobility is associated with worse symptoms; and 3) identify whether spinopelvic mobility can be predicted from static anatomical radiological parameters. Patients and Methods. A total of 122 patients with end-stage OA of the hip awaiting total hip arthroplasty (THA) were prospectively studied. Patient-reported outcome measures (PROMs; Oxford Hip Score, Oswestry Disability Index, and Veterans RAND 12-Item Health Survey Score) and clinical data were collected. Sagittal spinopelvic mobility was calculated as the change from the standing to sitting position using the lumbar lordosis angle (LL), sacral slope (SS), pelvic tilt (PT), pelvic-femoral angle (PFA), and acetabular anteinclination (AI) from lateral radiographs. The interaction of the different parameters was assessed. PROMs were compared between patients with normal spinopelvic mobility (10° ≤ ∆PT ≤ 30°) or abnormal spinopelvic mobility (stiff: ∆PT < ± 10°; hypermobile: ∆PT > ± 30°). Multiple regression and receiver operating characteristic (ROC) curve analyses were used to test for possible predictors of spinopelvic mobility. Results. Standing to sitting, the hip flexed by a mean of 57° (. sd. 17°), the pelvis tilted backwards by a mean of 20° (. sd. 12°), and the lumbar spine flexed by a mean of 20° (. sd. 14°); strong correlations were detected. There was no difference in PROMs between patients in the different spinopelvic mobility groups. Maximum hip flexion, standing PT, and standing AI were independent predictors of spinopelvic mobility (R. 2. = 0.42). The combined thresholds for standing was PT ≥ 13° and hip flexion ≥ 88° in the clinical examination, and had 90% sensitivity and 63% specificity of predicting spinopelvic stiffness, while SS ≥ 42° had 84% sensitivity and 67% specificity of predicting spinopelvic hypermobility. Conclusion. The hip, on average, accounts for three-quarters of the standing-to-sitting movement, but there is great variation. Abnormal spinopelvic mobility cannot be screened with PROMs. However, clinical and standing radiological features can predict spinopelvic mobility with good enough accuracy, allowing them to be used as reliable screening tools. Cite this article: Bone Joint J 2019;101-B:902–909


The Bone & Joint Journal
Vol. 101-B, Issue 6_Supple_B | Pages 45 - 50
1 Jun 2019
Schloemann DT Edelstein AI Barrack RL

Aims

The aims of this study were to determine the change in pelvic sagittal alignment before, during, and after total hip arthroplasty (THA) undertaken with the patient in the lateral decubitus position, and to determine the impact of these changes on acetabular component position.

Patients and Methods

We retrospectively compared the radiological pelvic ratio among 91 patients undergoing THA. In total, 41 patients (46%) were female. The mean age was 61.6 years (sd 10.7) and the mean body mass index (BMI) was 20.0 kg/m2 (sd 5.5). Anteroposterior radiographs were obtained: in the standing position preoperatively and at six weeks postoperatively; in the lateral decubitus position after trial reduction intraoperatively; and in the supine position in the post-anaesthesia care unit. Pelvic ratio was defined as the ratio between the vertical distance from the inferior aspect of the sacroiliac (SI) joints to the superior pubic symphysis and the horizontal distance between the inferior aspect of the SI joints. Changes in the apparent component position based on changes in pelvic ratio were determined, with a change of > 5° considered clinically significant. Analyses were performed using Wilcoxon’s signed-rank test, with p < 0.05 considered significant.


The Bone & Joint Journal
Vol. 96-B, Issue 3 | Pages 406 - 413
1 Mar 2014
Tarassoli P Gargan MF Atherton WG Thomas SRYW

The medial approach for the treatment of children with developmental dysplasia of the hip (DDH) in whom closed reduction has failed requires minimal access with negligible blood loss. In the United Kingdom, there is a preference for these children to be treated using an anterolateral approach after the appearance of the ossific nucleus. In this study we compared these two protocols, primarily for the risk of osteonecrosis. Data were gathered prospectively for protocols involving the medial approach (26 hips in 22 children) and the anterolateral approach (22 hips in 21 children) in children aged <  24 months at the time of surgery. Osteonecrosis of the femoral head was assessed with validated scores. The acetabular index (AI) and centre–edge angle (CEA) were also measured. . The mean age of the children at the time of surgery was 11 months (3 to 24) for the medial approach group and 18 months (12 to 24) for the anterolateral group, and the combined mean follow-up was 70 months (26 to 228). Osteonecrosis of the femoral head was evident or asphericity predicted in three of 26 hips (12%) in the medial approach group and four of 22 (18%) in the anterolateral group (p = 0.52). The mean improvement in AI was 8.8° (4° to 12°) and 7.9° (6° to 10°), respectively, at two years post-operatively (p = 0.18). There was no significant difference in CEA values of affected hips between the two groups. Children treated using an early medial approach did not have a higher risk of developing osteonecrosis at early to mid-term follow-up than those treated using a delayed anterolateral approach. The rates of acetabular remodelling were similar for both protocols. Cite this article: Bone Joint J 2014;96-B:406–13


The Journal of Bone & Joint Surgery British Volume
Vol. 50-B, Issue 2 | Pages 447 - 449
1 May 1968
Manzoni AI


The Bone & Joint Journal
Vol. 106-B, Issue 5 Supple B | Pages 17 - 24
1 May 2024
Anderson LA Wylie JD Kapron C Blackburn BE Erickson JA Peters CL

Aims

Periacetabular osteotomy (PAO) is the preferred treatment for symptomatic acetabular dysplasia in adolescents and young adults. There remains a lack of consensus regarding whether intra-articular procedures such as labral repair or improvement of femoral offset should be performed at the time of PAO or addressed subsequent to PAO if symptoms warrant. The purpose was to determine the rate of subsequent hip arthroscopy (HA) in a contemporary cohort of patients, who underwent PAO in isolation without any intra-articular procedures.

Methods

From June 2012 to March 2022, 349 rectus-sparing PAOs were performed and followed for a minimum of one year (mean 6.2 years (1 to 11)). The mean age was 24 years (14 to 46) and 88.8% were female (n = 310). Patients were evaluated at final follow-up for patient-reported outcome measures (PROMs). Clinical records were reviewed for complications or subsequent surgery. Radiographs were reviewed for the following acetabular parameters: lateral centre-edge angle, anterior centre-edge angle, acetabular index, and the alpha-angle (AA). Patients were cross-referenced from the two largest hospital systems in our area to determine if subsequent HA was performed. Descriptive statistics were used to analyze risk factors for HA.