Gait analysis is an indispensable tool for scientific assessment and treatment of individuals whose ability to walk is impaired. The high cost of installation and operation are a major limitation for wide-spread use in clinical routine. Advances in Artificial Intelligence (AI) could significantly reduce the required instrumentation. A mobile phone could be all equipment necessary for 3D gait analysis. MediaPipe Pose provided by Google Research is such a Machine Learning approach for human body tracking from monocular RGB video frames that is detecting 3D-landmarks of the human body. Aim of this study was to analyze the accuracy of gait phase detection based on the joint landmarks identified by the AI system. Motion data from 10 healthy volunteers walking on a treadmill with a fixed speed of 4.5km/h (Callis, Sprintex, Germany) was sampled with a mobile phone (iPhone SE 2nd Generation, Apple). The video was processed with Mediapipe Pose (Version 0.9.1.0) using custom python software. Gait phases (Initial Contact - IC and Toe Off - TO) were detected from the angular velocities of the lower legs. For the determination of ground truth, the movement was simultaneously recorded with the AS-200 System (LaiTronic GmbH, Innsbruck, Austria). The number of detected strides, the error in IC detection and stance phase duration was calculated. In total, 1692 strides were detected from the reference system during the trials from which the AI-system identified 679 strides. The absolute mean error (AME) in IC detection was 39.3 ± 36.6 ms while the AME for stance duration was 187.6 ± 140 ms. Landmark detection is a challenging task for the AI-system as can clearly be seen be the rate of only 40% detected strides. As mentioned by Fadillioglu et al., error in TO-detection is higher than in IC-detection

To examine whether Natural Language Processing (NLP) using a state-of-the-art clinically based Large Language Model (LLM) could predict patient selection for Total Hip Arthroplasty (THA), across a range of routinely available clinical text sources. Data pre-processing and analyses were conducted according to the Ai to Revolutionise the patient Care pathway in Hip and Knee arthroplasty (ARCHERY) project protocol (. https://www.researchprotocols.org/2022/5/e37092/. ). Three types of deidentified Scottish regional clinical free text data were assessed: Referral letters, radiology reports and clinic letters. NLP algorithms were based on the GatorTron model, a Bidirectional Encoder Representations from Transformers (BERT) based LLM trained on 82 billion words of de-identified clinical text. Three specific inference tasks were performed: assessment of the base GatorTron model, assessment after model-fine tuning, and external validation. There were 3911, 1621 and 1503 patient text documents included from the sources of referral letters, radiology reports and clinic letters respectively. All letter sources displayed significant class imbalance, with only 15.8%, 24.9%, and 5.9% of patients linked to the respective text source documentation having undergone surgery. Untrained model performance was poor, with F1 scores (harmonic mean of precision and recall) of 0.02, 0.38 and 0.09 respectively. This did however improve with model training, with mean scores (range) of 0.39 (0.31–0.47), 0.57 (0.48–0.63) and 0.32 (0.28–0.39) across the 5 folds of cross-validation. Performance deteriorated on external validation across all three groups but remained highest for the radiology report cohort. Even with further training on a large cohort of routinely collected free-text data a clinical LLM fails to adequately perform clinical inference in NLP tasks regarding identification of those selected to undergo THA. This likely relates to the complexity and heterogeneity of free-text information and the way that patients are determined to be surgical candidates

Participation in a physical therapy program is considered one of the greatest predictors for successful conservative management of common shoulder disorders, however, adherence to standard exercise protocols is often poor (around 50%) and typically worse for unsupervised home exercise programs. Currently, there are limited tools available for objective measurement of adherence and performance of shoulder rehabilitation in the home setting. The goal of this study was to develop and evaluate the potential for performing home shoulder physiotherapy monitoring using a commercial smartwatch. We hypothesize that shoulder physiotherapy exercises can be classified by analyzing the temporal sequence of inertial sensor outputs from a smartwatch worn on the extremity performing the exercise.

Twenty healthy adult subjects with no prior shoulder disorders performed seven exercises from a standard evidence-based rotator cuff physiotherapy protocol: pendulum, abduction, forward elevation, internal/external rotation and trapezius extension with a resistance band, and a weighted bent-over row. Each participant performed 20 repetitions of each exercise bilaterally under the supervision of an orthopaedic surgeon, while 6-axis inertial sensor data was collected at 50 Hz from an Apple Watch. Using the scikit-learn and keras platforms, four supervised learning algorithms were trained to classify the exercises: k-nearest neighbour (k-NN), random forest (RF), support vector machine classifier (SVC), and a deep convolutional recurrent neural network (CRNN). Algorithm performance was evaluated using 5-fold cross-validation stratified first temporally and then by subject.

Categorical classification accuracy was above 94% for all algorithms on the temporally stratified cross validation, with the best performance achieved by the CRNN algorithm (99.4± 0.2%). The subject stratified cross validation, which evaluated classifier performance on unseen subjects, yielded lower accuracies scores again with CRNN performing best (88.9 ± 1.6%).

This proof-of concept study demonstrates the feasibility of a smartwatch device and machine learning approach to more easily monitor and assess the at-home adherence of shoulder physiotherapy exercise protocols. Future work will focus on translation of this technology to the clinical setting and evaluating exercise classification in shoulder disorder populations.

Aims. The principles of evidence-based medicine (EBM) are the foundation of modern medical practice. Surgeons are familiar with the commonly used statistical techniques to test hypotheses, summarize findings, and provide answers within a specified range of probability. Based on this knowledge, they are able to critically evaluate research before deciding whether or not to adopt the findings into practice. Recently, there has been an increased use of artificial intelligence (AI) to analyze information and derive findings in orthopaedic research. These techniques use a set of statistical tools that are increasingly complex and may be unfamiliar to the orthopaedic surgeon. It is unclear if this shift towards less familiar techniques is widely accepted in the orthopaedic community. This study aimed to provide an exploration of understanding and acceptance of AI use in research among orthopaedic surgeons. Methods. Semi-structured in-depth interviews were carried out on a sample of 12 orthopaedic surgeons. Inductive thematic analysis was used to identify key themes. Results. The four intersecting themes identified were: 1) validity in traditional research, 2) confusion around the definition of AI, 3) an inability to validate AI research, and 4) cautious optimism about AI research. Underpinning these themes is the notion of a validity heuristic that is strongly rooted in traditional research teaching and embedded in medical and surgical training. Conclusion. Research involving AI sometimes challenges the accepted traditional evidence-based framework. This can give rise to confusion among orthopaedic surgeons, who may be unable to confidently validate findings. In our study, the impact of this was mediated by cautious optimism based on an ingrained validity heuristic that orthopaedic surgeons develop through their medical training. Adding to this, the integration of AI into everyday life works to reduce suspicion and aid acceptance. Cite this article: Bone Jt Open 2023;4(9):696–703

The use of artificial intelligence (AI) is rapidly growing across many domains, of which the medical field is no exception. AI is an umbrella term defining the practical application of algorithms to generate useful output, without the need of human cognition. Owing to the expanding volume of patient information collected, known as ‘big data’, AI is showing promise as a useful tool in healthcare research and across all aspects of patient care pathways. Practical applications in orthopaedic surgery include: diagnostics, such as fracture recognition and tumour detection; predictive models of clinical and patient-reported outcome measures, such as calculating mortality rates and length of hospital stay; and real-time rehabilitation monitoring and surgical training. However, clinicians should remain cognizant of AI’s limitations, as the development of robust reporting and validation frameworks is of paramount importance to prevent avoidable errors and biases. The aim of this review article is to provide a comprehensive understanding of AI and its subfields, as well as to delineate its existing clinical applications in trauma and orthopaedic surgery. Furthermore, this narrative review expands upon the limitations of AI and future direction. Cite this article: Bone Joint Res 2023;12(7):447–454

Aims. Hip dysplasia (HD) leads to premature osteoarthritis. Timely detection and correction of HD has been shown to improve pain, functional status, and hip longevity. Several time-consuming radiological measurements are currently used to confirm HD. An artificial intelligence (AI) software named HIPPO automatically locates anatomical landmarks on anteroposterior pelvis radiographs and performs the needed measurements. The primary aim of this study was to assess the reliability of this tool as compared to multi-reader evaluation in clinically proven cases of adult HD. The secondary aims were to assess the time savings achieved and evaluate inter-reader assessment. Methods. A consecutive preoperative sample of 130 HD patients (256 hips) was used. This cohort included 82.3% females (n = 107) and 17.7% males (n = 23) with median patient age of 28.6 years (interquartile range (IQR) 22.5 to 37.2). Three trained readers’ measurements were compared to AI outputs of lateral centre-edge angle (LCEA), caput-collum-diaphyseal (CCD) angle, pelvic obliquity, Tönnis angle, Sharp’s angle, and femoral head coverage. Intraclass correlation coefficients (ICC) and Bland-Altman analyses were obtained. Results. Among 256 hips with AI outputs, all six hip AI measurements were successfully obtained. The AI-reader correlations were generally good (ICC 0.60 to 0.74) to excellent (ICC > 0.75). There was lower agreement for CCD angle measurement. Most widely used measurements for HD diagnosis (LCEA and Tönnis angle) demonstrated good to excellent inter-method reliability (ICC 0.71 to 0.86 and 0.82 to 0.90, respectively). The median reading time for the three readers and AI was 212 (IQR 197 to 230), 131 (IQR 126 to 147), 734 (IQR 690 to 786), and 41 (IQR 38 to 44) seconds, respectively. Conclusion. This study showed that AI-based software demonstrated reliable radiological assessment of patients with HD with significant interpretation-related time savings. Cite this article: Bone Jt Open 2022;3(11):877–884

Aims. The aim of this study was to create artificial intelligence (AI) software with the purpose of providing a second opinion to physicians to support distal radius fracture (DRF) detection, and to compare the accuracy of fracture detection of physicians with and without software support. Methods. The dataset consisted of 26,121 anonymized anterior-posterior (AP) and lateral standard view radiographs of the wrist, with and without DRF. The convolutional neural network (CNN) model was trained to detect the presence of a DRF by comparing the radiographs containing a fracture to the inconspicuous ones. A total of 11 physicians (six surgeons in training and five hand surgeons) assessed 200 pairs of randomly selected digital radiographs of the wrist (AP and lateral) for the presence of a DRF. The same images were first evaluated without, and then with, the support of the CNN model, and the diagnostic accuracy of the two methods was compared. Results. At the time of the study, the CNN model showed an area under the receiver operating curve of 0.97. AI assistance improved the physician’s sensitivity (correct fracture detection) from 80% to 87%, and the specificity (correct fracture exclusion) from 91% to 95%. The overall error rate (combined false positive and false negative) was reduced from 14% without AI to 9% with AI. Conclusion. The use of a CNN model as a second opinion can improve the diagnostic accuracy of DRF detection in the study setting. Cite this article: Bone Joint Res 2024;13(10):588–595

Aims. The lateral centre-edge angle (LCEA) is a plain radiological measure of superolateral cover of the femoral head. This study aims to establish the correlation between 2D radiological and 3D CT measurements of acetabular morphology, and to describe the relationship between LCEA and femoral head cover (FHC). Methods. This retrospective study included 353 periacetabular osteotomies (PAOs) performed between January 2014 and December 2017. Overall, 97 hips in 75 patients had 3D analysis by Clinical Graphics, giving measurements for LCEA, acetabular index (AI), and FHC. Roentgenographical LCEA, AI, posterior wall index (PWI), and anterior wall index (AWI) were measured from supine AP pelvis radiographs. The correlation between CT and roentgenographical measurements was calculated. Sequential multiple linear regression was performed to determine the relationship between roentgenographical measurements and CT FHC. Results. CT-measured LCEA and AI correlated strongly with roentgenographical LCEA (r = 0.92; p < 0.001) and AI (r = 0.83; p < 0.001). Radiological LCEA correlated very strongly with CT FHC (r = 0.92; p < 0.001). The sum of AWI and PWI also correlated strongly with CTFHC (r = 0.73; p < 0.001). CT measurements of LCEA and AI were 3.4° less and 2.3° greater than radiological LCEA and AI measures. There was a linear relation between radiological LCEA and CT FHC. The linear regression model statistically significantly predicted FHC from LCEA, F(1,96) = 545.1 (p < 0.001), adjusted R. 2. = 85.0%, with the prediction equation: CT FHC(%) = 42.1 + 0.77(XRLCEA). Conclusion. CT and roentgenographical measurement of acetabular parameters are comparable. Currently, a radiological LCEA greater than 25° is considered normal. This study demonstrates that those with hip pain and normal radiological acetabular parameters may still have deficiencies in FHC. More sophisticated imaging techniques such as 3D CT should be considered for those with hip pain to identify deficiencies in FHC. Cite this article: Bone Jt Open 2022;3(1):12–19

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

Introduction:. Most of the published papers on AI based diagnosis have focused on the algorithm's diagnostic performance in a ‘binary’ setting (i.e. disease vs no disease). However, no study evaluated the actual value for the clinicians of an AI based approach in diagnostic. Detection of Traumatic thoracolumbar (TL) fractures is challenging on planar radiographs, resulting in significant rates of missed diagnoses (30-60%), thus constituting a field in which a performance improvement is needed. Aim of this study is therefore to evaluate the value provided by AI generated saliency maps (SM), i.e. the maps that highlight the AI identified region of interests. Methods:. An AI model aimed at identifying TL fractures on plain radiographs was trained and tested on 567 single vertebrae images. Three expert spine surgeons established the Ground Truth (GT) using CT and MRI to confirm the presence of the fracture. From the test set, 12 cases (6 with a GT of fracture and 6 with a GT of no fracture, associated with varying levels of algorithm confidence) were selected and the corresponding SMs were generated and shown to 7 independent evaluators with different grade of experience; the evaluators were requested to: (1) identify the presence or absence of a fracture before and after the saliency map was shown; (2) grade, with a score from 1 (low) to 6 (high) the pertinency (correlation between the map and the human diagnosis), and the utility (the perceived utility in confirming or not the initial diagnosis) of the SM. Furthermore, the usefulness of the SM was evaluated through the rate of correct change in diagnosis after the maps had been shown. Finally, the obtained scores were correlated with the algorithm confidence for the specific case. Results:. Of the selected maps, 8 had an agreement between the AI diagnosis and the GT, while in 4 the diagnosis was discordant (67% accuracy). The pertinency of the map was found higher when the AI diagnosis was the same as the GT and the human diagnosis (respectively p-value = .021 and <.000). A positive and significant correlation between the AI confidence score and the perceived utility (Spearman: 27%, p-value=.0-27) was found. Furthermore, evaluator with experience < 5 year found the maps more useful than the experts (z-score=2.004; p-value=.0455). Among the 84 evaluation we found 12 diagnostic errors in respect to the GT, 6 (50%) of which were reverted after the saliency map evaluation (z statistic = 1.25 and p-value = .21). Discussion:. The perceived utility of AI generated SM correlate with the model confidence in the diagnosis. This highlights the fact that to be considered helpful, the AI must provide not only the diagnosis but also the case specific confidence. Furthermore, the perceived utility was higher among less experienced users, but overall, the SM were useful in improving the human diagnostic accuracy. Therefore, in this setting, the AI enhanced approach provides value in improving the human performance

Despite the vast quantities of published artificial intelligence (AI) algorithms that target trauma and orthopaedic applications, very few progress to inform clinical practice. One key reason for this is the lack of a clear pathway from development to deployment. In order to assist with this process, we have developed the Clinical Practice Integration of Artificial Intelligence (CPI-AI) framework – a five-stage approach to the clinical practice adoption of AI in the setting of trauma and orthopaedics, based on the IDEAL principles (. https://www.ideal-collaboration.net/. ). Adherence to the framework would provide a robust evidence-based mechanism for developing trust in AI applications, where the underlying algorithms are unlikely to be fully understood by clinical teams. Cite this article: Bone Joint Res 2024;13(9):507–512

Developmental dysplasia of the hip can cause pain and premature osteoarthritis. However, the risk factors and timing for disease progression in young adults are not fully defined. This study identified the incidence and risk factors for contralateral hip pain and surgery after periacetabular osteotomy (PAO) on an index dysplastic hip. Patients followed for 2+ years after unilateral PAO were grouped by eventual contralateral pain or no-pain, based on modified Harris Hip Score, and surgery or no-surgery. Univariate analysis tested group differences in demographics, radiographic measures, and range-of-motion. Kaplan-Meier survival analysis assessed pain development and contralateral hip surgery over time. Multivariate regression identified pain and surgery risk factors. Pain and surgery predictors were further analyzed in Dysplastic, Borderline, and Non-dysplastic subcategories, and in five-degree increments of lateral center edge angle (LCEA) and acetabular inclination (AI). 184 patients were followed for 4.6±1.6 years, during which 51% (93/184) reported hip pain and 33% (60/184) underwent contralateral surgery. Kaplan-Meier analysis predicted 5-year survivorship of 49% for pain development and 66% for contralateral surgery. Painful hips exhibited more severe dysplasia than no-pain hips (LCEA 16.5º vs 20.3º, p<0.001; AI 13.2º vs 10.0º p<0.001). AI was the sole predictor of pain, with every 1° AI increase raising the risk by 11%. Surgical hips also had more severe dysplasia (LCEA 14.9º vs 20.0º, p<0.001; AI 14.7º vs 10.2º p<0.001) and were younger (21.6 vs 24.1 years, p=0.022). AI and a maximum alpha angle ≥55° predicted contralateral surgery. 5 years after index hip PAO, 51% of contralateral hips experience pain and 34% percent are expected to need surgery. More severe dysplasia, based on LCEA and AI, increases the risk of contralateral hip pain and surgery, with AI being a predictor of both outcomes. Knowing these risks can inform patient counseling and treatment planning

The Pavlik harness (PH) is commonly used to treat infantile dislocated hips. Variability exists in the duration of brace treatment after successful reduction of the dislocated hip. In this study we evaluate the effect of prescribed time in brace on acetabular index (AI) at two years of age using a prospective, international, multicenter database. We retrospectively studied prospectively enrolled infants with at least one dislocated hip that were initially treated with a PH and had a recorded AI at two-year follow-up. Subjects were treated at one of two institutions. Institution 1 used the PH until they observed normal radiographic acetabular development. Institution 2 followed a structured 12-week brace treatment protocol. Hip dislocation was defined as less than 30% femoral head coverage at rest on the pre-treatment ultrasound or IHDI grade III or IV on the pre-treatment radiograph. Fifty-three hips met our inclusion criteria. Hips from Institution 1 were treated with a brace 3x longer than hips from institution 2 (adjusted mean 8.9±1.3 months vs 2.6±0.2 months)(p < 0 .001). Institution 1 had an 88% success rate and institution 2 had an 85% success rate at achieving hip reduction (p=0.735). At 2-year follow-up, we observed no significant difference in AI between Institution 1 (adjusted mean 25.6±0.9˚) compared to Institution 2 (adjusted mean 23.5±0.8˚) (p=0.1). However, 19% of patients from Institution 1 and 44% of patients from Institution 2 were at or below the 50th percentile of previously published age- and sex- matched AI normal data (p=0.049). Also, 27% (7/26) of hips from Institution 1 had significant acetabular dysplasia, compared to a 22% (6/27) from Institution 2 (p=0.691). We found no correlation between age at initiation of bracing and AI at 2-year follow-up (p=0.071). Our findings suggest that prolonged brace treatment does not result in improved acetabular index at age two years. Hips treated at Institution 1 had the same AI at age two years as hips treated at Institution 2, while spending about 1/3 the amount of time in a brace. We recommend close follow-up for all children treated for dislocated hips, as ~1/4 of infants had acetabular index measurements at or above the 90th percentile of normal. Continued follow-up of this prospective cohort will be critical to determine how many children require acetabular procedures during childhood. The PH brace can successfully treat dislocated infant hips, however, prolonged brace treatment was not found to result in improved acetabular development at two-year follow-up

Introduction. The functional ante-inclination (AI) of the cup after total hip arthroplasty (THA) is a key component in the combined sagittal index (CSI) to predict joint stability after THA. To accurately predict AI, we deducted a mathematic algorithm between the radiographic anteversion (RA), radiographic inclincation (RI), pelvic tilting (PT), and AI. The current study aims (1) to validate the mathematic algorithm; (2) to convert the AI limits in the CSI index (standing AI ≤ 45°, sitting AI ≥ 41°) into coronal functional safe zone (CFSZ) and explore the influences of the stand-to-sit pelvic motion (PM) and pelvic incidence (PI) on CFSZ; (3) to locate a universal cup orientation that always fulfill the AI criteria of CSI safe zone for all patients or subgroups of PM(PM ≤ 10°, 10° < PM ≤ 30°, and PM > 30°) and PI (PI≤ 41°, 41°< PI ≤ 62°, and PI >62°), respectively. Methods. A 3D printed phantom pelvic model was designed to simulate changing PT values. An acetabular cup was implanted with different RA, RI, and PT settings using robot assisted technique. We enrolled 100 consecutive patients who underwent robot assisted THA from April, 2019 to June, 2019 in our hospital. EOS images before THA and at 6-month follow-up were collected. AI angles were measured on the lateral view radiographs as the reference method. Mean absolute error (MAE), Bland-Altman analysis and linear regression were conducted to assess the accuracy of the AI algorithm for both the phantom and patient radiographic studies. The 100 patients were classified into three subgroups by PM and PI, respectively. Linear regression and ANOVA analysis were conducted to explore the relationship between the size of CFSZ, and PM and PI, respectively. Intersection of the CFSZ was conducted to identify if any universal cup orientation (RA, RI) existed for the CSI index. Results. The mathematic algorithm for calculating AI based on RI, RA, and PT is highly accurate according to the phantom and patient radiographic study. CFSZ size corresponds linearly with PM (R² = 0.638) and PI (R² = 0.129), respectively. There are significant differences in the size of CFSZ, as well as in the intersection of CFSZ and LSZ, between the subgroups of PM and PI, respectively (P<0.017). There is no universal cup orientations could be identified to fulfill the AI limits of the CSI index for all the 100 patients or any of the three subgroups, according to either PM or PI. Conclusions. The cup target orientation should be individualized. The validated algorithm between AI and RA, RI, and PT parameters can serve as the quantitative tool for patient-specific optimization of functional cup AI in different postures

Acetabular morphology and orientation differs from ethnic group to another. Thus, investigating the normal range of the parameters that are used to assess both was a matter of essence. Nevertheless, the main aim of this study was clarification the relationship between acetabular inclination (AI) and acetabular and femoral head arcs’ radii (AAR and FHAR). A cross-sectional retrospective study that had been done in a tertiary center where Computed tomography abdomen scouts’ radiographs of non-orthopedics patients were included. They had no history of pelvic or hips’ related symptoms or fractures in femur or pelvis. A total of 84 patients was included with 52% of them were females. The mean of age was 30.38± 5.48. Also, Means of AI were 38.02±3.89 and 40.15±4.40 (P 0.02, significant gender difference) for males and females, respectively. Nonetheless, Head neck shaft angle (HNSA) means were 129.90±5.55 and 130.72±6.62 for males and females, respectively. However, AAR and FHAR means for males and females were 21.3±3.1mm, 19.9±3.1mm, P 0.04 and 19.7±3.1mm, 18.1±2.7mm, P 0.019, respectively. In addition, negative significant correlations were detected between AI against AAR, FHAR, HNSA and body mass index (BMI) (r 0.529, P ≤0.0001, r 0.445, P ≤0.0001, r 0.238, P 0.029, r 0.329, P ≤0.007, respectively). On the other hand, high BMI was associated with AAR and FHAR (r 0.577, P 0.0001 and r 0.266, p 0.031, respectively). This study shows that high AI is correlated with lower AAR, FHAR. Each ethnic group has its own normal values that must be studied to tailor the path for future implications in clinical setting

As patient data continues to grow, the importance of efficient and precise analysis cannot be overstated. The employment of Generative Artificial Intelligence (AI), specifically Chat GPT-4, in the realm of medical data interpretation has been on the rise. However, its effectiveness in comparison to manual data analysis has been insufficiently investigated. This quality improvement project aimed to evaluate the accuracy and time-efficiency of Generative AI (GPT-4) against manual data interpretation within extensive datasets pertaining to patients with orthopaedic injuries. A dataset, containing details of 6,562 orthopaedic trauma patients admitted to a district general hospital over a span of two years, was reviewed. Two researchers operated independently: one utilised GPT-4 for insights via prompts, while the other manually examined the identical dataset employing Microsoft Excel and IBM® SPSS® software. Both were blinded on each other's procedures and outcomes. Each researcher answered 20 questions based on the dataset including injury details, age groups, injury specifics, activity trends and the duration taken to assess the data. Upon comparison, both GPT-4 and the manual researcher achieved consistent results for 19 out of the 20 questions (95% accuracy). After a subsequent review and refined prompts (prompt engineering) to GPT-4, the answer to the final question aligned with the manual researcher's findings. GPT-4 required just 30 minutes, a stark contrast to the manual researcher's 9-hour analytical duration. This quality improvement project emphasises the transformative potential of Generative AI in the domain of medical data analysis. GPT-4 not only paralleled the accuracy of manual analysis but also achieved this in significantly less time. For optimal accurate results, data analysis by AI can be enhanced through human oversight. Adopting AI-driven approaches, particularly in orthopaedic data interpretation, can enhance efficiency and ultimately improve patient care. We recommend future investigations on large and more varied datasets to reaffirm these outcomes

Critical shoulder angle (CSA), lateral acromial angle (LAA), and acromion index (AI) are common radiologic parameters used to distinguish between patients with rotator cuff tears (RCT) and those with an intact rotator cuff. This study aims to assess the predictive power of these parameters in degenerative RCT. This retrospective study included data from 92 patients who were divided into two groups: the RCT group, which included 47 patients with degenerative full-thickness supraspinatus tendon tears, and a control group of 45 subjects without tears. CSA, AI, and LAA measurements from standardized true anteroposterior radiographs were independently derived and analyzed by two orthopedic surgeons. Receiver operating characteristic (ROC) analyses were performed to determine the cutoff values. No significant differences were found between patients in the RCT and control groups in age (p = 0.079), gender (p = 0.804), or injury side (p = 0.552). Excellent inter-observer reliability was seen for CSA, LAA, and AI values. Mean CSA (38.1°) and AI (0.72) values were significantly larger in the RCT group than in the control group (34.56° and 0.67°, respectively, p < 0.001) with no significant difference between groups for LAA (RCT, 77.99° vs. control, 79.82°; p = 0.056). ROC analysis yielded an area under the curve (AUC) of 0.815 for CSA with a cutoff value of 37.95°, and CSA was found to be the strongest predictor of the presence of a RCT, followed by AI with an AUC of 0.783 and a cutoff value of 0.705. We conclude that CSA and AI may be useful predictive factors for degenerative RCT in the Turkish population

Introduction. The recent introduction of Chatbots has provided an interactive medium to answer patient questions. The accuracy of responses with these programs in limb lengthening and reconstruction surgery has not previously been determined. Therefore, the purpose of this study was to assess the accuracy of answers from 3 free AI chatbot platforms to 23 common questions regarding treatment for limb lengthening and reconstruction. Method. We generated a list of 23 common questions asked by parents before their child's limb lengthening and reconstruction surgery. Each question was posed to three different AI chatbots (ChatGPT 3.5 [OpenAI], Google Bard, and Microsoft Copilot [Bing!]) by three different answer retrievers on separate computers between November 17 and November 18, 2023. Responses were only asked one time to each chatbot by each answer retriever. Nine answers (3 answer retrievers × 3 chatbots) were randomized and platform-blinded prior to rating by three orthopedic surgeons. The 4-point rating system reported by Mika et al. was used to grade all responses. Result. ChatGPT had the best response accuracy score (RAS) with a mean score of 1.73 ± 0.88 across all three raters (range of means for all three raters – 1.62 – 1.81) and a median score of 2. The mean response accuracy scores for Google Bard and Microsoft Copilot were 2.32 ± 0.97 and 3.14 ± 0.82, respectively. This ranged from 2.10 – 2.48 and 2.86 – 3.54 for Google Bard and Microsoft Copilot, respectively. The differences between the mean RAS scores were statistically significant (p < 0.0001). The median scores for Google Bard and Microsoft Copilot were 2 and 3, respectively. Conclusion. Using the Response Accuracy Score, the responses from ChatGPT were determined to be satisfactory, requiring minimal clarification, while the responses from Microsoft Copilot were either satisfactory, requiring moderate clarification, or unsatisfactory, requiring substantial clarification

Introduction. Shoulder arthroplasty (SA) has been performed with different types of implants, each requiring different replacement systems. However, data on previously utilized implant types are not always available before revision surgery, which is paramount to determining the appropriate equipment and procedure. Therefore, this meta-analysis aimed to evaluate the accuracy of the AI models in classifying SA implant types. Methods. This systematic review was conducted in Pubmed, Embase, SCOPUS, and Web of Science from inception to December 2023, according to PRISMA guidelines. Peer-reviewed research evaluating the accuracy of AI-based tools on upper-limb X-rays for recognizing and categorizing SA implants was included. In addition to the overall meta-analysis, subgroup analysis was performed according to the type of AI model applied (CNN (Convolutional neural network), non-CNN, or Combination of both) and the similarity of utilized datasets between studies. Results. 13 articles were eligible for inclusion in this meta-analysis (including 138 different tests assessing models’ efficacy). Our meta-analysis demonstrated an overall sensitivity and specificity of 0.891 (95% CI:0.866-0.912) and 0.549 (95% CI:0.532,0.566) for classifying implants in SA, respectively. The results of our subgroup analyses were as follows: CNN-subgroup: a sensitivity of 0.898 (95% CI:0.873-0.919) and a specificity of 0.554 (95% CI:0.537,0.570), Non-CNN subgroup: a sensitivity of 0.809 (95% CI:0.665-0.900) and specificity of 0.522 (95% CI:0.440,0.603), combined subgroup: a sensitivity of 0.891 (95% CI:0.752-0.957) and a specificity of 0.547 (95% CI:0.463,0.629). Studies using the same dataset demonstrated an overall sensitivity and specificity of 0.881 (95% CI:0.856-0.903) and 0.542 (95% CI:0.53,0.554), respectively. Studies that used other datasets showed an overall sensitivity and specificity of 0.995 (95% CI:969,0.999) and 0.678 (95% CI:0.234, 0.936), respectively. Conclusion. AI-based classification of shoulder implant types can be considered a sensitive method. Our study showed the potential role of using CNN-based models and different datasets to enhance accuracy, which could be investigated in future studies

Purpose. Collagen-rich structures of the knee are prone to damage through acute injury or chronic “wear and tear”. Collagen becomes more disorganised in degenerative tissue e.g. osteoarthritis. An alignment index (AI) used to analyse orientation distribution of collagen-rich structures is presented. Method. A healthy caprine knee was scanned in a Siemens Verio 3T Scanner. The caprine knee was rotated and scanned in nine directions to the main magnetic field B. 0. A 3D PD SPACE sequence with isotropic 1×1×1mm voxels (TR1300ms, TE13ms, FOV256mm,) was optimised to allow for a greater angle-sensitive contrast. For each collagen-rich voxel the orientation vector is computed using Szeverenyi and Bydder's method. Each orientation vector reflects the net effect of all the fibres comprised within a voxel. The assembly of all unit vectors represents the fibre orientation map. Alignment Index (AI) in any direction is defined as a ratio of the fraction of orientations within 20° (solid angle) centred in that direction to the same fraction in a random (flat) case. In addition, AI is normalised in such a way that AI=0 indicates isotropic collagen alignment. Increasing AI values indicate increasingly aligned structures: AI=1 indicates that all collagen fibres are orientated within the cone of 20° centred at the selected direction. AI = (nM - nRnd)/(nTotal - nRnd) if nM >= nRnd. AI = 0 if nM < nRnd. Where:. nM is a number of reconstructed orientations that are within a cone of 20° centred in selected direction. nRnd is a number of random orientations within a cone of 20° around selected direction. nTotal is a number of collagen reach voxels. By computing AI for a regular gridded orientation space we are able to visualise change of AI on a hemisphere facilitating understanding of the collagen fibre orientation distribution. Results. The patella tendon had an AI=0.6453. The Anterior Cruciate Ligament (ACL) had an AI=0.2732. The meniscus had an AI=0.1847. Discussion. The most aligned knee structure is the patella tendon where the collagen fibres align with the skeleton to transmit forces through bones and muscles. This structure had the AI closest to 1. The ACL had the second highest AI and is composed of two fibre bundles aligned diagonally across the knee. The meniscus acts as a shock absorber and is made up of vertical, radial and circumferential fibres which disperse forces more equally. The complexity of the meniscal structure resulted in the lowest AI. To date, this technique has only been performed with healthy tissue; the AI may become closer to zero if there is damage disrupting the collagen fibre alignment. The AI can further our understanding of collagen orientation distribution and could be used as a quantitative, non-invasive measure of structural health