Objective: The rapid expansion of digital healthcare has heightened the volume of patient communication, thereby increasing the workload for healthcare professionals. Large Language Models (LLMs) hold promises for offering automated responses to patient questions relayed through eHealth platforms, yet concerns persist regarding their effectiveness, accuracy, and limitations in healthcare settings. This study aims to evaluate the current evidence on the performance and perceived suitability of LLMs in healthcare, focusing on their role in supporting clinical decision-making and patient communication. Materials and methods: A systematic search in PubMed and Embase up to June 11, 2025 identified 330 studies, of which 20 met the inclusion criteria for comparing the accuracy and adequacy of medical information provided by LLMs versus healthcare professionals and guidelines. The search strategy combined terms related to LLMs, healthcare professionals, and patient questions. The ROBINS-I tool assessed the risk of bias. Results: A total of nineteen studies focused on medical specialties and one on the primary care setting. Twelve studies favored the responses generated by LLMs, six reported mixed results, and two favored the healthcare professionals’ response. Bias components generally scored moderate to low, indicating a low risk of bias. Discussion and conclusions: The review summarizes current evidence on the accuracy and adequacy of medical information provided by LLMs in response to patient questions, compared to healthcare professionals and clinical guidelines. While LLMs show potential as supportive tools in healthcare, their integration should be approached cautiously due to inconsistent performance and possible risks. Further research is essential before widespread adoption.

Background and purpose — Treatment-related shared decision-making (SDM) in older adults with hip fractures is complex due to the need to balance patient-specific factors such as life goals, frailty, and surgical risks. It includes considerations such as prognosis and decisions concerning whether to operate or not on frail, life-limited patients. We aimed to develop machine learning (ML)-driven prediction models for short-and long-term mortality in a large cohort of patients with hip fractures. Methods — In this national registry-based retrospective cohort study, patients aged ≥ 70 years registered in the nationwide Dutch Hip Fracture Audit from 2018–2023 were included. Predictive variables were selected based on the literature and/or clinical relevance. 6 ML algorithms, including logistic regression, were trained with internal cross-validation and evaluated on discrimination (c-statistic), sensitivity, specificity, calibration, and interpretability. Results — 74,396 patients (median age 84, IQR 78–89; 68% female) were analyzed. Most patients lived at home (69%) and high malnutrition risk was seen in 10%. 18% had dementia. Mortality rates were 9.1% (30-day), 15% (90-day), and 26% (1-year). Logistic regression performed comparably to other algorithms, but was chosen as the preferred algorithm due to its superior interpretability (c-statistic: 30-day 0.82, 90-day 0.81, 1-year 0.80). Conclusion — We developed and validated ML algorithms, including logistic regression, for mortality prediction in older hip fracture patients with adequate performance. This information may inform SDM.

Machine learning algorithms show promise in assisting clinical decision-making; however, only a few have been successfully implemented in practice. To bridge this gap, it is essential to analyse the clinicians’ perspective on the compatibility of Artificial Intelligence-based clinical decision support systems (AI-CDSSs) with their clinical tasks. We therefore conducted a literature review of 21 empirical qualitative studies that examined the interaction between health professionals and AI-CDSSs. We synthesised the research through the lens of the Task-Technology Fit (TTF) model, analysing task, technology and individual characteristics of AI-CDSS applications, to identify design elements that are (mis)aligned with clinicians’ needs. Three key findings emerged from our analysis. First, clinicians often expressed scepticism about the clinical judgements of AI-CDSSs, particularly questioning the system’s ability to compete with clinical expertise in the absence of contextual information. Users valued AI primarily for specific strengths, such as identifying trends in patient trajectories, consolidating large datasets and pattern recognition, and comparing similar patient cases, but were hesitant to rely on it for clinical decisions. Second, actionability emerged as a desired characteristic of AI-CDSSs. For instance, clinicians particularly appreciated features of AI-CDSSs that enabled them to explore how different clinical actions might influence outcomes, as well as Explainable AI for identifying modifiable variables that impacted prediction scores, allowing them to take informed action. Third, we identified various ways AI-CDSSs could be used in clinical practice, including for patient prioritisation, patient monitoring, care acceleration, risk communication and workflow efficiency. In essence, AI-CDSSs functioned either as an alert system, preventing oversights, or as a tool for more informed decision making. Our analysis challenges the assumption that AI-CDSSs add little value when clinicians disregard its predictions, as it frequently prompts them to critically reassess their judgments through additional testing, consultation with colleagues, and other actions. Overall, our findings underscore the importance of an in-depth understanding of how AI-CDSSs are used in clinical practice. To optimise for effectiveness, the design of AI-CDSSs should prioritise supporting clinicians’ cognitive processes and information needs. This approach ensures that we move beyond the hype, focusing on the responsible integration of AI-CDSSs, and ultimately enhancing patient care.

Background: The number of patients suffering from knee complaints is increasing, leading to increased orthopedic healthcare consumption. Predicting knee diagnoses prior to consultation may be valuable in optimizing the consultation workflow. Therefore, the purpose of this study was to develop and internally validate a machine learning (ML) algorithm for predicting a knee diagnosis group for patients aged 18 years and older, based on computer-assisted history taking. Methods: A prospective cohort study at a single general district hospital was conducted to identify patients referred to an orthopedic surgeon for knee complaints. In total, 1172 patients were included, with an average age of 54 years (interquartile range 36–66), of which the majority were female (n = 594, 50.7%). The most frequent diagnosis group was knee osteoarthritis (n = 775, 66.1%), followed by ligamentous injuries (n = 208, 17.7%) and otherwise classified (n = 189, 16.1%). First, the dataset was randomly split 80:20 into training and test subsets. Then, a random forest algorithm was used to identify the variables predictive of a knee diagnosis group. Five different ML algorithms were developed, internally validated, and assessed by discrimination (area under the receiver operating characteristic curve, AUC), accuracy, precision (positive predictive value), recall (sensitivity), and F1‑score (the harmonic mean of precision and recall). Results: The models included patient characteristics and computer-assisted history taking. The support vector machine algorithm had the best performance for knee diagnosis group prediction, with good discrimination (area under the receiver operating characteristic curve, AUC = 0.92), accuracy (0.84), precision (0.85), recall (0.84) and F1-score (0.82). Conclusions: The developed ML algorithm shows promise in predicting a knee diagnosis group in patients presenting with knee complaints to an orthopedic practice. Integrating this algorithm could streamline the consultation workflow by directing patients predicted to have knee osteoarthritis to orthopedic surgeons specializing in knee osteoarthritis, and those predicted to have ligamentous injuries to orthopedic surgeons specializing in sports and traumatic injuries.

Purpose: The aging population is leading to a rise in the number of patients with multiple chronic conditions (MCC), which is putting pressure on healthcare systems. Artificial Intelligence, including Machine Learning (ML) offers potential to enhance care for patients with MCC. This scoping review summarizes current ML applications, discusses shortcomings and identifies opportunities. Additionally, it aims to identify applications explored in practice. Methods: We searched PubMed, Embase, and Web of Science for studies published between 2015 and January 2025 that used ML techniques and specialist care data, focusing on adults with MCC. Screening was assisted by ASReview. Results: The search identified 13381 articles, of which 454 were reviewed full text, resulting in 21 included articles. ML was mainly used for clustering (n = 14), primarily focusing on cardiovasculair diseases, with eight studies focusing on chronic diseases and six studies on clinical features, like medical specialties involved and symptoms. Stated potential clinical use of the clusters varied, but primarily aimed to promote integrated, personalized care. Predictive modelling was employed to support clinical decision-making and enhance research (n = 7). No applications were clinically evaluated. Conclusion: Current research on ML for patients with MCC primarily focuses on cluster analysis and predictive modelling, mainly aiming to enable holistic care. Future efforts should explore clinical evaluation and implementation, Natural Language Processing and Large Language Models. These technologies could significantly enhance care by extracting valuable insights from the data-rich electronic patient records of MCC patients, potentially leading to more effective decision-making and tailored interventions.

Aims Machine-learning (ML) prediction models in orthopaedic trauma hold great promise in assisting clinicians in various tasks, such as personalized risk stratification. However, an overview of current applications and critical appraisal to peer-reviewed guidelines is lacking. The objectives of this study are to 1) provide an overview of current ML prediction models in orthopaedic trauma; 2) evaluate the completeness of reporting following the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement; and 3) assess the risk of bias following the Prediction model Risk Of Bias Assessment Tool (PROBAST) tool. Methods A systematic search screening 3,252 studies identified 45 ML-based prediction models in orthopaedic trauma up to January 2023. The TRIPOD statement assessed transparent reporting and the PROBAST tool the risk of bias. Results A total of 40 studies reported on training and internal validation; four studies performed both development and external validation, and one study performed only external validation. The most commonly reported outcomes were mortality (33%, 15/45) and length of hospital stay (9%, 4/45), and the majority of prediction models were developed in the hip fracture population (60%, 27/45). The overall median completeness for the TRIPOD statement was 62% (interquartile range 30 to 81%). The overall risk of bias in the PROBAST tool was low in 24% (11/45), high in 69% (31/45), and unclear in 7% (3/45) of the studies. High risk of bias was mainly due to analysis domain concerns including small datasets with low number of outcomes, complete-case analysis in case of missing data, and no reporting of performance measures. Conclusion The results of this study showed that despite a myriad of potential clinically useful applications, a substantial part of ML studies in orthopaedic trauma lack transparent reporting, and are at high risk of bias. These problems must be resolved by following established guidelines to instil confidence in ML models among patients and clinicians. Otherwise, there will remain a sizeable gap between the development of ML prediction models and their clinical application in our day-to-day orthopaedic trauma practice.

AI holds the potential to transform healthcare, promising improvements in patient care. Yet, realizing this potential is hampered by over-reliance on limited datasets and a lack of transparency in validation processes. To overcome these obstacles, we advocate the creation of a detailed registry for AI algorithms. This registry would document the development, training, and validation of AI models, ensuring scientific integrity and transparency. Additionally, it would serve as a platform for peer review and ethical oversight. By bridging the gap between scientific validation and regulatory approval, such as by the FDA, we aim to enhance the integrity and trustworthiness of AI applications in healthcare.

Despite artificial intelligence (AI) technology progresses at unprecedented rate, our ability to translate these advancements into clinical value and adoption at the bedside remains comparatively limited. This paper reviews the current use of implementation outcomes in randomized controlled trials evaluating AI-based clinical decision support and found limited adoption. To advance trust and clinical adoption of AI, there is a need to bridge the gap between traditional quantitative metrics and implementation outcomes to better grasp the reasons behind the success or failure of AI systems and improve their translation into clinical value.

Purpose: The aim of this study was to develop and train a machine learning (ML) algorithm to create a clinical decision support tool (i.e., ML-driven probability calculator) to be used in clinical practice to estimate recurrence rates following an arthroscopic Bankart repair (ABR). Methods: Data from 14 previously published studies were collected. Inclusion criteria were (1) patients treated with ABR without remplissage for traumatic anterior shoulder instability and (2) a minimum of 2 years follow-up. Risk factors associated with recurrence were identified using bivariate logistic regression analysis. Subsequently, four ML algorithms were developed and internally validated. The predictive performance was assessed using discrimination, calibration and the Brier score. Results: In total, 5591 patients underwent ABR with a recurrence rate of 15.4% (n = 862). Age <35 years, participation in contact and collision sports, bony Bankart lesions and full-thickness rotator cuff tears increased the risk of recurrence (all p < 0.05). A single shoulder dislocation (compared to multiple dislocations) lowered the risk of recurrence (p < 0.05). Due to the unavailability of certain variables in some patients, a portion of the patient data had to be excluded before pooling the data set to create the algorithm. A total of 797 patients were included providing information on risk factors associated with recurrence. The discrimination (area under the receiver operating curve) ranged between 0.54 and 0.57 for prediction of recurrence. Conclusion: ML was not able to predict the recurrence following ABR with the current available predictors. Despite a global coordinated effort, the heterogeneity of clinical data limited the predictive capabilities of the algorithm, emphasizing the need for standardized data collection methods in future studies. Level of Evidence: Level IV, retrospective cohort study.

Background
Estimating the risk of revision after arthroplasty could inform patient and surgeon decision-making. However, there is a lack of well-performing prediction models assisting in this task, which may be due to current conventional modeling approaches such as traditional survivorship estimators (such as Kaplan-Meier) or competing risk estimators. Recent advances in machine learning survival analysis might improve decision support tools in this setting. Therefore, this study aimed to assess the performance of machine learning compared with that of conventional modeling to predict revision after arthroplasty.

Question/purpose
Does machine learning perform better than traditional regression models for estimating the risk of revision for patients undergoing hip or knee arthroplasty?

Methods
Eleven datasets from published studies from the Dutch Arthroplasty Register reporting on factors associated with revision or survival after partial or total knee and hip arthroplasty between 2018 and 2022 were included in our study. The 11 datasets were observational registry studies, with a sample size ranging from 3038 to 218,214 procedures. We developed a set of time-to-event models for each dataset, leading to 11 comparisons. A set of predictors (factors associated with revision surgery) was identified based on the variables that were selected in the included studies. We assessed the predictive performance of two state-of-the-art statistical time-to-event models for 1-, 2-, and 3-year follow-up: a Fine and Gray model (which models the cumulative incidence of revision) and a cause-specific Cox model (which models the hazard of revision). These were compared with a machine-learning approach (a random survival forest model, which is a decision tree–based machine-learning algorithm for time-to-event analysis). Performance was assessed according to discriminative ability (time-dependent area under the receiver operating curve), calibration (slope and intercept), and overall prediction error (scaled Brier score). Discrimination, known as the area under the receiver operating characteristic curve, measures the model’s ability to distinguish patients who achieved the outcomes from those who did not and ranges from 0.5 to 1.0, with 1.0 indicating the highest discrimination score and 0.50 the lowest. Calibration plots the predicted versus the observed probabilities; a perfect plot has an intercept of 0 and a slope of 1. The Brier score calculates a composite of discrimination and calibration, with 0 indicating perfect prediction and 1 the poorest. A scaled version of the Brier score, 1 – (model Brier score/null model Brier score), can be interpreted as the amount of overall prediction error.

Results
Using machine learning survivorship analysis, we found no differences between the competing risks estimator and traditional regression models for patients undergoing arthroplasty in terms of discriminative ability (patients who received a revision compared with those who did not). We found no consistent differences between the validated performance (time-dependent area under the receiver operating characteristic curve) of different modeling approaches because these values ranged between -0.04 and 0.03 across the 11 datasets (the time-dependent area under the receiver operating characteristic curve of the models across 11 datasets ranged between 0.52 to 0.68). In addition, the calibration metrics and scaled Brier scores produced comparable estimates, showing no advantage of machine learning over traditional regression models.

Conclusion
Machine learning did not outperform traditional regression models.

Clinical Relevance
Neither machine learning modeling nor traditional regression methods were sufficiently accurate in order to offer prognostic information when predicting revision arthroplasty. The benefit of these modeling approaches may be limited in this context.

Purpose: Mortality prediction in elderly femoral neck fracture patients is valuable in treatment decision-making. A previously developed and internally validated clinical prediction model shows promise in identifying patients at risk of 90-day and 2-year mortality. Validation in an independent cohort is required to assess the generalizability; especially in geographically distinct regions. Therefore we questioned, is the SORG Orthopaedic Research Group (SORG) femoral neck fracture mortality algorithm externally valid in an Israeli cohort to predict 90-day and 2-year mortality? Methods: We previously developed a prediction model in 2022 for estimating the risk of mortality in femoral neck fracture patients using a multicenter institutional cohort of 2,478 patients from the USA. The model included the following input variables that are available on clinical admission: age, male gender, creatinine level, absolute neutrophil, hemoglobin level, international normalized ratio (INR), congestive heart failure (CHF), displaced fracture, hemiplegia, chronic obstructive pulmonary disease (COPD), history of cerebrovascular accident (CVA) and beta-blocker use. To assess the generalizability, we used an intercontinental institutional cohort from the Sheba Medical Center in Israel (level I trauma center), queried between June 2008 and February 2022. Generalizability of the model was assessed using discrimination, calibration, Brier score, and decision curve analysis. Results: The validation cohort included 2,033 patients, aged 65 years or above, that underwent femoral neck fracture surgery. Most patients were female 64.8% (n = 1317), the median age was 81 years (interquartile range = 75–86), and 80.4% (n = 1635) patients sustained a displaced fracture (Garden III/IV). The 90-day mortality was 9.4% (n = 190) and 2-year mortality was 30.0% (n = 610). Despite numerous baseline differences, the model performed acceptably to the validation cohort on discrimination (c-statistic 0.67 for 90-day, 0.67 for 2-year), calibration, Brier score, and decision curve analysis. Conclusions: The previously developed SORG femoral neck fracture mortality algorithm demonstrated good performance in an independent intercontinental population. Current iteration should not be relied on for patient care, though suggesting potential utility in assessing patients at low risk for 90-day or 2-year mortality. Further studies should evaluate this tool in a prospective setting and evaluate its feasibility and efficacy in clinical practice. The algorithm can be freely accessed: https://sorg-apps.shinyapps.io/hipfracturemortality/. Level of evidence: Level III, Prognostic study.

Objectives:With more than 300,000 patients per year in the United States alone, hip fractures are one of the most common injuries occurring in the elderly. The incidence is predicted to rise to 6 million cases per annum worldwide by 2050. Many fracture registries have been established, serving as tools for quality surveillance and evaluating patient outcomes. Most registries are based on billing and procedural codes, prone to under-reporting of cases. Deep learning (DL) is able to interpret radiographic images and assist in fracture detection; we propose to conduct a DL-based approach intended to autocreate a fracture registry, specifically for the hip fracture population.Methods:Conventional radiographs (n = 18,834) from 2919 patients from Massachusetts General Brigham hospitals were extracted (images designated as hip radiographs within the medical record). We designed a cascade model consisting of 3 submodules for image view classification (MI), postoperative implant detection (MII), and proximal femoral fracture detection (MIII), including data augmentation and scaling, and convolutional neural networks for model development. An ensemble model of 10 models (based on ResNet, VGG, DenseNet, and EfficientNet architectures) was created to detect the presence of a fracture.Results:The accuracy of the developed submodules reached 92%-100%; visual explanations of model predictions were generated through gradient-based methods. Time for the automated model-based fracture-labeling was 0.03 seconds/image, compared with an average of 12 seconds/image for human annotation as calculated in our preprocessing stages.Conclusion:This semisupervised DL approach labeled hip fractures with high accuracy. This mitigates the burden of annotations in a large data set, which is time-consuming and prone to under-reporting. The DL approach may prove beneficial for future efforts to autocreate construct registries that outperform current diagnosis and procedural codes. Clinicians and researchers can use the developed DL approach for quality improvement, diagnostic and prognostic research purposes, and building clinical decision support tools.

INTRODUCTION: Despite technological advancements in recent years, glenoid component loosening remains a common complication after anatomical total shoulder arthroplasty (ATSA) and is one of the main causes of revision surgery. Increasing emphasis is placed on the prevention of glenoid component failure. Previous studies have successfully predicted range of motion, patient-reported outcomes and short-term complications after ATSA using machine learning methods, but an accurate predictive model for (glenoid component) revision is currently lacking. This study aims to use a large international database to accurately predict aseptic loosening of the glenoid component after ATSA using machine learning algorithms. METHODS AND ANALYSIS: For this multicentre, retrospective study, individual patient data will be compiled from previously published studies reporting revision of ATSA. A systematic literature search will be performed in Medline (PubMed) identifying all studies reporting outcomes of ATSA. Authors will be contacted and invited to participate in the Machine Learning Consortium by sharing their anonymised databases. All databases reporting revisions after ATSA will be included, and individual patients with a follow-up less than 2 years or a fracture as the indication for ATSA will be excluded. First, features (predictive variables) will be identified using a random forest feature selection. The resulting features from the compiled database will be used to train various machine learning algorithms (stochastic gradient boosting, random forest, support vector machine, neural network and elastic-net penalised logistic regression). The developed and validated algorithms will be evaluated across discrimination (c-statistic), calibration, the Brier score and the decision curve analysis. The best-performing algorithm will be used to create an open-access online prediction tool. ETHICS AND DISSEMINATION: Data will be collected adhering to the WHO regulation on data sharing. An Institutional Review Board review is not applicable. The study results will be published in a peer-reviewed journal.

Objective: When correcting for the “class imbalance” problem in medical data, the effects of resampling applied on classifier algorithms remain unclear. We examined the effect on performance over several combinations of classifiers and resampling ratios. Materials and Methods: Multiple classification algorithms were trained on 7 resampled datasets: no correction, random undersampling, 4 ratios of Synthetic Minority Oversampling Technique (SMOTE), and random oversampling with the Adaptive Synthetic algorithm (ADASYN). Performance was evaluated in Area Under the Curve (AUC), precision, recall, Brier score, and calibration metrics. A case study on prediction modeling for 30-day unplanned readmissions in previously admitted Urology patients was presented. Results: For most algorithms, using resampled data showed a significant increase in AUC and precision, ranging from 0.74 (CI: 0.69–0.79) to 0.93 (CI: 0.92–0.94), and 0.35 (CI: 0.12–0.58) to 0.86 (CI: 0.81–0.92) respectively. All classification algorithms showed significant increases in recall, and significant decreases in Brier score with distorted calibration overestimating positives. Discussion: Imbalance correction resulted in an overall improved performance, yet poorly calibrated models. There can still be clinical utility due to a strong discriminating performance, specifically when predicting only low and high risk cases is clinically more relevant. Conclusion: Resampling data resulted in increased performances in classification algorithms, yet produced an overestimation of positive predictions. Based on the findings from our case study, a thoughtful predefinition of the clinical prediction task may guide the use of resampling techniques in future studies aiming to improve clinical decision support tools.

Purpose: Effects of clockwise torque rotation onto proximal femoral fracture fixation have been subject of ongoing debate: fixated right-sided trochanteric fractures seem more rotationally stable than left-sided fractures in the biomechanical setting, but this theoretical advantage has not been demonstrated in the clinical setting to date. The purpose of this study was to identify a difference in early reoperation rate between patients undergoing surgery for left- versus right-sided proximal femur fractures using cephalomedullary nailing (CMN). Materials and methods: The American College of Surgeons National Surgical Quality Improvement Program was queried from 2016-2019 to identify patients aged 50 years and older undergoing CMN for a proximal femoral fracture. The primary outcome was any unplanned reoperation within 30 days following surgery. The difference was calculated using a Chi-square test, and observed power calculated using post-hoc power analysis. Results: In total, of 20,122 patients undergoing CMN for proximal femoral fracture management, 1.8% (n=371) had to undergo an unplanned reoperation within 30 days after surgery. Overall, 208 (2.0%) were left-sided and 163 (1.7%) right-sided fractures (p=0.052, risk ratio [RR] 1.22, 95% confidence interval [CI] 1.00–1.50), odds ratio [OR] 1.23 (95%CI 1.00–1.51), power 49.2% (α=0.05). Conclusion: This study shows a higher risk of reoperation for left-sided compared to right-sided proximal femur fractures after CMN in a large sample size. Although results may be underpowered and statistically insignificant, this finding might substantiate the hypothesis that clockwise rotation during implant insertion and (postoperative) weightbearing may lead to higher reoperation rates. Level of evidence: Therapeutic level II.