Medical imaging utilisation continues to increase globally, raising concerns regarding sustainability, workforce capacity, patient safety and environmental impact. Electronic Clinical Decision Support (eCDS) systems have been proposed as a strategy to improve imaging appropriateness; however, international experience suggests that technology alone is insufficient for successful adoption. This study describes an organisational implementation strategy for an eCDS programme for imaging referrals and examines early changes in imaging utilisation associated with clinician engagement and education strategies preceding system go-live. An eCDS system was implemented within the electronic medical record at a quaternary referral centre in Melbourne, Australia. The initiative included governance structures, clinician engagement and targeted education to support integration into clinical workflows. Imaging utilisation data, including computed tomography (CT) examinations per emergency department (ED) presentation, were obtained from hospital activity records and analysed descriptively across engagement and deployment phases. Prior to eCDS go-live, CT utilisation increased from 32 to 44 examinations per 100 ED presentations. During the engagement phase preceding system deployment, CT ordering declined by 9.1%, coinciding with clinician engagement and education activities. Following eCDS deployment, imaging utilisation trends stabilised. Successful implementation of eCDS requires more than technological deployment. Governance, clinician engagement and sustained education appear important for supporting adoption of decision support systems and may facilitate early cultural change in imaging utilisation.

Shared decision-making (SDM) and the use of patient decision aids (PtDAs) can enhance patient involvement in treatment decisions, yet sustainable implementation in clinical practice remains challenging. This study explores the sustained use of a paperbased PtDA, the DECISION HELPER™, in adjuvant chemotherapy consultations for patients with early-stage colorectal cancer at a Danish hospital. The colorectal cancer team expressed reluctance to discontinue using the tool during the testing of a digital pre-consult version. Using a hermeneutic phenomenological approach, two focus group interviews were conducted with seven physicians and four nurses from the Department of Oncology at Vejle Hospital, Denmark. All participants had intensive experience using the DECISION HELPER™ in consultations. Data were thematically analysed through inductive coding to identify factors supporting long-term integration of the tool. Two main themes were identified across both professional groups: (A) the DECISION HELPER™ functions as a pedagogical tool that facilitates patient involvement, and (B) it enhances patients' understanding of their own life situation. Clinicians emphasized the tool's role in visualizing complex choices, supporting structured communication, and enabling patients to regulate the amount of information received. Importantly, no significant differences were found between nurses' and physicians' perspectives, and the tool was experienced as enhancing professional practice and consistency in patient care. From the clinicians' perspective, the DECISION HELPER™ supported meaningful SDM. Its visual presentation of treatment options and structured consultation format helped make complex treatment choices tangible for patients and supported its sustained use in practice. The findings suggest that successful and sustainable use of patient decision aids may depend on tools that integrate naturally into clinical workflows while structuring the consultation process. Visualizing treatment options and outcomes and supporting conversations about patient values may help clinicians facilitate meaningful SDM and promote consistent patient-centered dialog in oncology care.

Artificial intelligence and computerized decision support in adult intensive care: A systematic review of randomized controlled trials.

Hybrid learning/numerical framework for fast and robust electric field simulation in irreversible electroporation.

To evaluate whether GPT-4-turbo can generate accurate, patient-centered prostate cancer pathology reports at or below a 6th-grade reading level using a validated reporting template. We retrieved 44 prostate cancer pathology reports from The Cancer Genome Atlas database. We used twenty reports to iteratively refine our prompt refinement and tested the final prompts on 24 unseen reports. GPT-4-turbo generated two patient-centered versions for each report, one below and one above the 6th-grade reading level. We assessed readability using the TextEvaluator tool, which measures eight educational text-complexity dimensions aligned with Common Core standards. We performed paired t-tests to compare the original reports to both simplified versions. GPT-4 significantly reduced the overall text complexity of the pathology reports (p < 0.001). The below 6th-grade versions showed the most improvement. These versions reduced academic vocabulary (mean 68.47-23.16), simplified syntactic structures (p = 0.0018), and used more concrete language (36.65-44.12). Our iterative prompt engineering eliminated hallucinations and ensured clinical accuracy. GPT-4-turbo, when guided by a well-designed prompt and validated template, can produce accurate, patient-accessible prostate cancer pathology summaries. This approach could improve health communication, particularly for patients with limited health literacy, and offers a low-cost, scalable solution for integrating PCPRs into clinical workflows with minimal burden on clinicians. This workflow may improve patient comprehension of cancer diagnoses, enhance shared decision-making, and promote more equitable access to understandable medical information without substantial additional resource demands.

From decision support to clinical integration: A scoping review of artificial intelligence in prehospital airway management.

How I Do It: "And That's a BINGO!" Using a Self-Directed, Gamified Instrument to Structure Learning on the Obstetrics Clerkship.

Beyond literacy to clinical competency: A framework for integrating generative AI into nursing education.

Sports-related knee injuries are common and debilitating, often leading to chronic pain, early osteoarthritis, and reduced performance. Artificial Intelligence (AI) has emerged as a promising tool to improve their prevention, diagnosis, prognosis, and rehabilitation. This review summarises current evidence on the clinical applications, limitations, and future directions of AI and machine learning in sports-related knee injuries. A narrative review of PubMed, Embase, Medline and Web of Science was conducted, examining recent literature on AI-based models in musculoskeletal and sports medicine. The review was categorised into key domains: injury prediction and prevention, diagnostic imaging performance, AI-enabled clinical workflows, alongside postoperative and rehabilitation outcome modelling. AI algorithms demonstrate strong potential across the sports knee injury continuum. Predictive models analysing biomechanical and physiological data have achieved high area under the curve (AUC) values, in some cases above 0.90, in experimental and pilot setting when identifying athletes at risk of ACL rupture or overuse injuries, while machine learning approaches have been used to predict graft failure, revision surgery, and return-to-sport. However, most remain investigational rather than clinically deployable, with limited explainability, insufficient external validation, and training datasets that are often narrow or unrepresentative of broader athletic populations. AI has the potential to transform the management of sports-related knee injuries through more predictive, personalised, and precise care. However, wider clinical adoption will require multicentre validation, improved interpretability, and robust ethical and regulatory oversight. With further development, AI may enhance injury prevention, recovery, and improve long-term joint health outcomes in athletes.

BackgroundThe clinical heterogeneity of systemic lupus erythematosus exceeds the resolution of conventional disease activity instruments. Artificial intelligence offers the analytical infrastructure to engage with this complexity, yet the translation of AI models into clinical practice remains limited.MethodsThis review critically appraises the current evidence for AI applications across the SLE clinical workflow, including computational phenotyping, diagnosis, disease activity monitoring, organ-specific predictive modelling, and treatment personalization. Studies were evaluated for external validation, prospective testing, algorithmic fairness, explainability, and regulatory status.FindingsAI applications across the SLE clinical workflow show uneven methodological maturity. Diagnostic and monitoring tools include the SLERPI index, with multinational external validation, and an LSTM flare-prediction model (C-index 0.897). Treatment personalization is anchored by serum IgA2 anti-dsDNA, the only SLE response biomarker validated across independent trials, and by multi-stain deep learning on renal biopsies (AUC 0.84, three external centers). Predictive modelling for organ-specific manifestations has progressed unevenly: cardiovascular risk stratification (SLECRISK) and a multicenter thrombocytopenia model are the most mature, while neuropsychiatric, gastrointestinal, and ocular applications remain single-center proofs of concept. External validation is the exception across SLE prediction models, no AI tool has received regulatory clearance, and populations most affected by SLE remain underrepresented in training data.ConclusionsAI demonstrates genuine analytical capability in SLE but the translation gap is defined by insufficient validation, limited explainability, and absent equity evidence. Closing it will require fewer published models and more validated tools, optimization for clinical impact rather than discrimination alone, and demonstration of performance equity across the demographic spectrum of the disease.

Epilepsy-IEDs: An automated machine learning model for detecting interictal epileptiform discharges from scalp electroencephalograms.

Deep learning-based Wilms tumor segmentation to create 3D models for surgical planning: Implementation in the clinical workflow.

Lung cancer remains the leading cause of cancer mortality, yet blood-based biomarkers are not routinely used in diagnosis. This study evaluated four commercial blood protein assays, originally validated for other indications, in indeterminate pulmonary nodules (IPN). Using a prospective specimen collection, retrospective blinded evaluation design, samples were collected from patients with screening-detected, incidental, or symptomatic IPNs. Cytokeratin 19 fragment (CYFRA 21-1), carcinoembryonic antigen (CEA), cancer antigen 125 (CA-125), and human epididymis protein 4 (HE-4) concentrations were quantified on commercial immunoassays. Logistic regression models were developed using internal training (Train), external testing (Test), and combined reestimation (Train + Test) cohorts and externally validated in an outcome-blinded multicenter cohort (Lung Team Project-2, LTP-2). This study included 816 patients: 371 in Train, 166 in Test, and 279 in LTP-2. Malignancy rates were 54%, 44%, and 64%, respectively. In Train + Test, the area under the receiver operating curve (AUC) for lung cancer was 0.60 (95% confidence interval, 0.56-0.65) for CYFRA 21-1, 0.62 (0.58-0.67) for CEA, 0.60 (0.55-0.65) for CA-125, and 0.65 (0.60-0.70) for HE-4. In LTP-2, AUCs were 0.63 (0.56-0.70), 0.64 (0.57-0.70), 0.48 (0.40-0.55), and 0.61 (0.54-0.68), respectively. Combining all four biomarkers yielded an AUC of 0.70 (0.65-0.74) in Train + Test and 0.61 (0.54-0.68) in LTP-2. In the first biomarker study reporting external validation in LTP-2, CYFRA 21-1, CEA, CA-125, and HE-4 demonstrated diagnostic value in IPNs. By leveraging commercial assays, this study highlights opportunities to enhance lung cancer risk stratification using widely available diagnostics that could be rapidly integrated into clinical workflows.

AI-assisted protocol information extraction for improved accuracy and efficiency in clinical trial workflows.

Architectural and translational perspectives on clinical decision support systems for rare disease diagnosis: a scoping review.

Comparative accuracy of molecular assays for detecting methicillin-resistant Staphylococcus aureus: Evidence from 32 studies.

MADCrowner: Margin Aware Dental Crown design with template deformation and refinement.

Socio-technical risks of clinical speech-to-text systems: Transparency, privacy, and reliability challenges in AI-driven documentation.

To develop and retrospectively validate an artificial intelligence-based decision support system (AI-DSS) for optimising prostate biopsy decisions and improving benefit-to-harm ratios. This retrospective, multicentre, multiscanner study used data from 1022 patients. An AI-DSS integrating PI-RADS scores, automated prostate-specific antigen density (PSAd), and deep-learning imaging risk scores was developed on 770 cases and validated on an independent cohort of 252 men from six UK centres. The AI-DSS performance was benchmarked against the real-world clinical decisions (reference standard) using grade selectivity, biopsy efficiency, and selective biopsy avoidance as outcome measures. Biopsy-proven detection of grade group (GG) ≥ 2 disease was the reference standard. In the validation cohort of 252 patients (mean age, 67.3 years), 137 underwent biopsy and 79 (31%) harboured ≥ GG2 disease. Compared to the reference standard, the AI-DSS at the 31% cancer detection rate (CDR) would have avoided 28 biopsies while missing one ≥ GG2 cancer. This corresponded to a 70% increase in grade selectivity (from 4.6 to 7.8), 79% increase in biopsy efficiency (from 1.4 to 2.5), and a 143% increase in selective biopsy avoidance (from 2.8 to 6.8). At the reduced CDR of 30%, grade selectivity, biopsy efficiency, and selective biopsy avoidance increased by 172%, 236%, and 475%, with four ≥ GG2 cancers missed. An AI-DSS that integrates clinical and advanced imaging data improves the benefit-to-harm ratio of prostate biopsy decisions in a retrospective setting. Future prospective validation as part of real-world clinical workflow is required to enable clinical implementation. Question Current prostate cancer diagnostic pathways result in fewer unnecessary biopsies. Can an AI decision support system (AI-DSS) further improve biopsy efficiency for detecting significant cancer? Findings An AI-DSS avoided 28 biopsies in a 252-patient cohort, increasing grade selectivity, biopsy efficiency, and selective biopsy avoidance by 70%, 79%, and 143%, respectively. Clinical relevance Integrating an AI-DSS into clinical workflows may further reduce unnecessary prostate biopsies and overdiagnosis of indolent disease, thus potentially improving the efficiency of the prostate cancer diagnostic pathway.

Comparing large language models and human experts in interpreting MRI reports for personalized patient education.