Recently introduced image processing capabilities of AI models, which are accessible to a broad audience, may contribute to progress in medical research. Inspection and physical examination are important components of hand injury assessment, but they have inherent limitations in accuracy. The purpose of this study was to compare the structures identified as damaged during physical examination with those predicted by an AI model, utilizing its image processing capability. We hypothesized that the AI tool would demonstrate a level of accuracy comparable to that of physical examination in predicting injured structures.

We retrospectively reviewed the files of patients with hand and forearm injuries related to the volar aspect from January 2024 to July 2024. After exclusions, a total of 30 patients were included in the final analyses. Structures suspected to be damaged based on the initial evaluation and those identified as injured during surgery were documented through chart review. For the same patients, the AI tool (ChatGPT-4.0) was utilized to predict injured structures from clinical photos obtained during the initial examination. We examined the correlation and overlap between the structures identified as injured during the initial clinical examination and those predicted by the AI tool, as well as the correlation and overlap between the structures predicted by the AI tool and those confirmed as injured during surgical procedures.

The sensitivity of the physical examination was found to be 66.0 % (95 % CI: 57.5 %-73.7 %), while the specificity was 98,7 % (95 % CI: 97,6 % to 99,4 %). The sensitivity of the AI tool was found to be 61.7 % (95 % CI: 53.1 %-69.8 %), while the specificity was 82.4 % (95 % CI: 79.4 %-85.2 %).

In its current form, AI demonstrates limited yet promising potential as an adjunctive tool in the clinical evaluation of flexor-side injuries of the hand and forearm.

III, Diagnostic study.

Digital twin (DT) systems, which involve creating virtual replicas of physical objects or systems, have the potential to transform healthcare by offering personalised and predictive models that grant deeper insight into a patient's condition. This review explores current concepts in DT systems for musculoskeletal (MSK) applications through an overview of the key components, technologies, clinical uses, challenges, and future directions that define this rapidly growing field. DT systems leverage computational models such as multibody dynamics and finite element analysis to simulate the mechanical behaviour of MSK structures, while integration with wearable technologies allows real-time monitoring and feedback, facilitating preventive measures, and adaptive care strategies. Early applications of DT systems to MSK include optimising the monitoring of exercise and rehabilitation, analysing joint mechanics for personalised surgical techniques, and predicting post-operative outcomes. While still under development, these advancements promise to revolutionise MSK care by improving surgical planning, reducing complications, and personalising patient rehabilitation strategies. Integrating advanced machine learning algorithms can enhance the predictive abilities of DTs and provide a better understanding of disease processes through explainable artificial intelligence (AI). Despite their potential, DT systems face significant challenges. These include integrating multi-modal data, modelling ageing and damage, efficiently using computational resources and developing clinically accurate and impactful models. Addressing these challenges will require multidisciplinary collaboration. Furthermore, guaranteeing patient privacy and protection against bias is extremely important, as is navigating regulatory requirements for clinical adoption. DT systems present a significant opportunity to improve patient care, made possible by recent technological advancements in several fields, including wearable sensors, computational modelling of biological structures, and AI. As these technologies continue to mature and their integration is streamlined, DT systems may fast-track medical innovation, ushering in a new era of rapid improvement of treatment outcomes and broadening the scope of preventive medicine. Level of Evidence: Level V.

Patients in intensive care units (ICUs) require rapid critical decision making. Modern ICUs are data rich, where information streams from diverse sources. Machine learning (ML) and neural networks (NN) can leverage the rich data for prognostication and clinical care. They can handle complex nonlinear relationships in medical data and have advantages over traditional predictive methods. A number of models are used: (1) Feedforward networks; and (2) Recurrent NN and convolutional NN to predict key outcomes such as mortality, length of stay in the ICU and the likelihood of complications. Current NN models exist in silos; their integration into clinical workflow requires greater transparency on data that are analyzed. Most models that are accurate enough for use in clinical care operate as 'black-boxes' in which the logic behind their decision making is opaque. Advances have occurred to see through the opacity and peer into the processing of the black-box. In the near future ML is positioned to help in clinical decision making far beyond what is currently possible. Transparency is the first step toward validation which is followed by clinical trust and adoption. In summary, NNs have the transformative ability to enhance predictive accuracy and improve patient management in ICUs. The concept should soon be turning into reality.

This study aims to evaluate the effectiveness of advanced deep learning models, specifically YOLOv8 and EfficientNetV2, in detecting meniscal tears on magnetic resonance imaging (MRI) using a relatively small data set.

Our data set consisted of MRI studies from 642 knees-two orthopaedic surgeons labelled and annotated the MR images. The training pipeline included MRI scans of these knees. It was divided into two stages: initially, a deep learning algorithm called YOLO was employed to identify the meniscus location, and subsequently, the EfficientNetV2 deep learning architecture was utilized to detect meniscal tears. A concise report indicating the location and detection of a torn meniscus is provided at the end.

The YOLOv8 model achieved mean average precision at 50% threshold (mAP@50) scores of 0.98 in the sagittal view and 0.985 in the coronal view. Similarly, the EfficientNetV2 model obtained area under the curve scores of 0.97 and 0.98 in the sagittal and coronal views, respectively. These outstanding results demonstrate exceptional performance in meniscus localization and tear detection.

Despite a relatively small data set, state-of-the-art models like YOLOv8 and EfficientNetV2 yielded promising results. This artificial intelligence system enhances meniscal injury diagnosis by generating instant structured reports, facilitating faster image interpretation and reducing physician workload.

Level III.

While public databases like Transfermarkt provide valuable data for assessing the impact of anterior cruciate ligament (ACL) injuries in professional footballers, they require robust verification methods due to accuracy concerns. We hypothesised that an artificial intelligence (AI)-powered framework could cross-check ACL tear-related information from large publicly available data sets with high specificity.

The AI-powered framework uses Google Programmable Search Engine to search a curated, multilingual list of websites and OpenAI's GPT to translate search queries, appraise search results and analyse injury-related information in search result items (SRIs). Specificity was the chosen performance metric-the AI-powered framework's ability to accurately identify texts that do not mention an athlete suffering an ACL tear-with SRI as the evaluation unit. A database of ACL tears in male professional footballers from first- and second-tier leagues worldwide (1999-2024) was collected from Transfermarkt.com, and players were randomly selected for appraisal until enough SRIs were obtained to validate the framework's specificity. Player age at injury and time until return-to-play (RTP) were recorded and compared with Union of European Football Associations (UEFA) Elite Club Injury Study data.

Verification of 231 athletes yielded 1546 SRIs. Human analysis of the SRIs showed that 335 mentioned an ACL tear, corresponding to 83 athletes with ACL tears. Specificity and sensitivity of GPT in identifying mentions of ACL tears in a player were 99.3% and 88.4%, respectively. Mean age at rupture was 26.6 years (standard deviation: 4.6, 95% confidence interval [CI]: 25.6-27.6). Median RTP time was 225 days (interquartile range: 96, 95% CI: 209-251), which is comparable to reports using data from the UEFA Elite Club Injury Study.

This study shows that an AI-powered framework can achieve high specificity in cross-checking ACL tear reports in male professional football from public databases, markedly reducing manual workload and enhancing the reliability of media-based sports medicine research.

Level III.

Predictive models help determine predictive factors necessary to improve functional outcomes after total knee arthroplasty (TKA). However, no study has assessed predictive models for functional outcomes after TKA based on the new concepts of personalised surgery and new technologies. This study aimed to develop and evaluate predictive modelling approaches to predict the achievement of minimal clinically important difference (MCID) in patient-reported outcome measures (PROMs) 1 year after TKA.

Four hundred thirty robotic-assisted TKAs were analysed in this retrospective study. The mean age was 67.9 ± 7.9 years; the mean body mass index (BMI) was 32.0 ± 6.8 kg/m2. The following PROMs were collected preoperatively and 1-year postoperatively: knee injury and osteoarthritis outcome score for joint replacement, Western Ontario and McMaster Universities osteoarthritis index (WOMAC) Function, WOMAC Pain. Demographic data, preoperative CT scan, implant size, implant position on the robotic system and characteristics of the joint replacement procedure were selected as predictive variables. Four machine learning algorithms were trained to predict the MCID status at 1-year post-TKA for each PROM survey. 'No MCID' was chosen as the target. Models were evaluated by class discrimination (F1-score) and area under the receiver operating characteristic curve (ROC-AUC).

The best-performing model was ridge logistic regression for WOMAC Function (area under the curve [AUC]  = 0.80, F1 = 0.48, sensitivity = 0.79, specificity = 0.62). Variables most strongly contributing to not achieving MCID status were preoperative PROMs, high BMI and femoral resection depth (posterior and distal), supporting functional positioning principles. Conversely, variables contributing to a positive outcome (achieving MCID) were medial/lateral alignment of the tibial component, whether the procedure was an outpatient surgery and whether the patient received managed Medicare insurance.

The most predictive variables included preoperative PROMs, BMI and surgical planning. The surgical predictive variables were valgus femoral alignment and femoral rotation, reflecting the benefits of personalised surgery. Including surgical variables in predictive models for functional outcomes after TKA should guide clinical and surgical decision-making for every patient.

Level III.

Explorative data analysis (EDA) is a critical step in scientific projects, aiming to uncover valuable insights and patterns within data. Traditionally, EDA involves manual inspection, visualization, and various statistical methods. The advent of artificial intelligence (AI) and machine learning (ML) has the potential to improve EDA, offering more sophisticated approaches that enhance its efficacy. This review explores how AI and ML algorithms can improve feature engineering and selection during EDA, leading to more robust predictive models and data-driven decisions. Tree-based models, regularized regression, and clustering algorithms were identified as key techniques. These methods automate feature importance ranking, handle complex interactions, perform feature selection, reveal hidden groupings, and detect anomalies. Real-world applications include risk prediction in total hip arthroplasty and subgroup identification in scoliosis patients. Recent advances in explainable AI and EDA automation show potential for further improvement. The integration of AI and ML into EDA accelerates tasks and uncovers sophisticated insights. However, effective utilization requires a deep understanding of the algorithms, their assumptions, and limitations, along with domain knowledge for proper interpretation. As data continues to grow, AI will play an increasingly pivotal role in EDA when combined with human expertise, driving more informed, data-driven decision-making across various scientific domains. Level of Evidence: Level V - Expert opinion.