Generative artificial intelligence use in medical research: A medical student vs. physician survey from Saudi Arabia.

Plato's cave and the neurobiology of reality construction.

To evaluate the efficacy of active pedagogical strategies for teaching the nursing process compared to traditional teaching methods. Systematic review with meta-analyses performed according to the recommendations of Cochrane Handbook and reported according to Preferred Reporting Items for Systematic Reviews and Metanalyses (PRISMA) Statement. Searches were carried out in February 2024 and updated in October 2025 in the databases Cumulative Index to Nursing and Allied Health Literature, Latin American and Caribbean Literature on Health Sciences, Excerpta Medica Database, Medical Literature Analysis and Retrieval System Online, Scopus and Web of Science. Free searches and searches in gray literature were performed in Google Scholar. The selection of studies and data extraction was performed independently by two reviewers. Data synthesis was performed through narrative synthesis and meta-analytic methods. Meta-analyses were conducted for knowledge, clinical reasoning, critical thinking and attitudinal skills. Thirty-four studies involving undergraduate and graduate nursing students were included to evaluate the effectiveness of active teaching strategies in developing nursing process related competencies. The meta-analyses demonstrated that active learning strategies significantly improved knowledge (SMD=0.95; p<0.001; I2=80%), clinical reasoning (SMD=0.48; p<0.001; I2=43%), and attitudinal skills (SMD=0.39; p=0.004; I2=81%) when compared to traditional methods. There was no difference in critical thinking (SMD=0.92; p=0.074; I2=95%). Subgroup analyses showed that among the strategies evaluated, simulation consistently showed favorable results for knowledge, clinical reasoning, and attitudinal skills. This study supports the effectiveness of active teaching strategies - particularly simulation - in enhancing learning outcomes associated with the nursing process. The findings emphasize the value of integrating structured, student-centered pedagogies in nursing curricula to foster core competencies.

Olfaction in Surgical Education: An Overlooked Dimension of Clinical Reasoning.

This commentary on Steir's 2026 article asks the question: What is the role of clinical reasoning in an age of advanced diagnostic tools and technological advances? We use the case study presented as a starting point to explore what clinical reasoning might look like in the future and how the skills highlighted in this case may be applicable for future generations of neuropsychologists. (PsycInfo Database Record (c) 2026 APA, all rights reserved).

Undergraduate nursing students' perceptions of using holopatient in learning and clinical training: An exploratory-descriptive qualitative study.

BACKGROUND: Hip dysplasia is a common cause of hip-related pain in young adults. Hip dysplasia is frequently overlooked by clinicians, leading to delayed diagnosis and subsequent adverse outcomes, including debilitating pain, functional impairments, and poor quality of life. Diagnosing hip dysplasia is often challenging due to its variable clinical presentation, its overlap with other conditions, and the absence of standard diagnostic criteria. Despite these challenges, an emerging body of research provides valuable insight into the management of hip dysplasia. CLINICAL QUESTION: How can new and existing evidence on hip dysplasia be synthesized to support clinicians in understanding its etiopathogenesis and diagnostic approaches-including both imaging and clinical evaluation-and in improving management strategies to enable timely diagnosis and treatment of this common condition? KEY FINDINGS: Hip dysplasia presents with variable symptoms and commonly coexists with other musculoskeletal conditions. Clinical examinations should include assessment of generalized joint hypermobility, hip range of motion, symptom-reproducing tests, and extra-articular structures. Imaging remains essential but must be interpreted in the clinical context. Evidence for non-surgical management, including exercise and education, is emerging but remains limited. CLINICAL APPLICATION: Clinicians should adopt a comprehensive and structured assessment approach that integrates patient history, physical examination, and imaging findings. Awareness of coexisting conditions and alternative pain sources is critical. Early recognition may facilitate timely referral and appropriate management. In the absence of strong condition-specific evidence, clinicians should combine available research with clinical reasoning and consider outcomes beyond pain, including quality of life, physical function, and participation. J Orthop Sports Phys Ther 2026;56(7):382-398. Epub 9 April 2026. doi:10.2519/jospt.2026.13860.

Towards interpretable AI in personalized medicine through a radiological-biological radiomics dictionary linking semantic Lung-RADS and imaging radiomics features.

This study aimed to clarify the structure of the individual matching support process within Team Orange, a community-based dementia support initiative in Japan. Using reflexive thematic analysis, we qualitatively examined semi-structured interviews with seven coordinators who facilitate matching between people living with dementia and community supporters. We also analysed 14 implementation reports documenting actual support cases from community comprehensive support centres in Sapporo, Hokkaido. Analysis identified seven themes constituting a cyclical support process: 'diverse triggers for initiating matching', 'assessing needs and evaluating support potential', 'safe and sustainable support coordination', 'building trust relationships to facilitate matching', 'reaching consensus among people living with dementia, families and supporters', 'implementing individual matching support' and 'reviewing and readjusting toward sustainable support'. These findings suggest that individual matching is not simply a combination of volunteer activities, but rather a support process in which the coordinator's clinical reasoning and relational coordination cyclically support the agency of people living with dementia, family members and supporters. This practice has the potential to serve as an implementation model that flexibly connects informal community resources with individuals whose needs fall outside the scope of formal care services.

Wilms tumour (WT) has excellent event-free and overall survival (OS). However, small differences exist between countries participating in the same international study. This led us to examine variation in adherence to protocol recommendations as a potential contributing factor. Retrospective analysis of risk-stratified chemotherapy and radiotherapy regimens given to children with unilateral WT treated with pre-operative chemotherapy in the SIOPWT2001 (2002-2011) and Improving Population Outcomes for Renal Tumours of Childhood (IMPORT) (2012-2018) studies in the United Kingdom and Ireland. Pre- and post-operative treatments were classified as per protocol (PP), deviation (PDEV)-variation for specified clinical reasons, violation (PVIOL)-not treated PP. A total of 1256 children with WT were registered by 20 centres. A total of 1052 (84%) had unilateral WT treated with pre-operative chemotherapy. All had centrally reviewed pathology. Case report forms allowing categorisation of the whole treatment pathway were available for 756 (72%) patients. Treatment was classified as PP in 452 (60%), PDEV in 175 (23%) and PVIOL in 129 (17%). Stage III/IV tumours had higher proportion PVIOL (21% and 35%, respectively) compared to Stage I/II tumours (8%-10%). Two-thirds of patients were treated in 'high-volume' centres (≥5 new WTs/year). Protocol adherence rates were similar between high- and low-volume centres. Protocol adherence category had no impact on event-free or OS. Protocol guidelines are followed closely for lower stage tumours, but there is greater variation in advanced disease. Centre size showed no association with survival, emphasising the effectiveness of using a national treatment protocol, supported by central pathology review.

A hierarchical prompt and prototype learning framework for brain disorder classification.

Diagnostic reasoning in musculoskeletal healthcare: a scoping review.

As AI integration in medicine becomes critical, this study evaluated medical students' attitudes and knowledge regarding AI and determined its impact on career specialization choices. This cross-sectional study used a voluntary, web-based convenience sample of 274 first- to fifth-year students at Gazi University Faculty of Medicine in Ankara, Türkiye (October-November 2025). Data were collected with a structured questionnaire incorporating the validated Perceptions on Artificial Intelligence in Medicine (PAIM) scale. Although 74.5% reported no formal AI training, 52.6% expected AI to influence their specialization choice. Students who expected AI to shape their careers reported higher "Knowledge and Trust" (p = 0.018); the "Disadvantages and Risks" subscale did not differ significantly between career-impact expectation groups (p = 0.131). Among the three PAIM dimensions, only "Informed Self-Control" differed significantly by training phase, with clinical-phase students scoring lower than pre-clinical peers (p = 0.027). In multivariable regression, expecting AI to influence specialization was the only positive predictor of "Knowledge and Trust" (B = 0.16, p = 0.018), and formal training predicted higher "Informed Self-Control" (B = 0.28, p = 0.015), while older age predicted lower scores (B = - 0.05, p = 0.015). Both models were statistically significant but explained only a small share of variance (adjusted R2 = 0.02 and 0.04). Overall, 94.2% supported integrating AI into the medical curriculum. The findings highlight a marked gap between students' strong demand for AI training and the limited formal instruction currently provided. Cross-sectional differences across training phases may reflect a shift from early optimism toward a more cautious stance, although the design cannot establish such a developmental trajectory. Because more than half of students expected AI to affect their specialty choice, curricula should move beyond technical instruction to integrate ethical and clinical reasoning alongside AI literacy. These associations are exploratory and require confirmation in larger, longitudinal studies. This study did not involve a clinical trial and therefore was not registered in a clinical trials registry.

Operation selection in metabolic surgery is a complex decision making process led by a multidisciplinary team that integrates multiple anatomical, clinical, metabolic and psychosocial aspects. The ability of large language models (LLMs) has been proposed to provide capability to act as decision support tools, but their performance in replicating MDT level decision making in metabolic surgery remains uncertain. A retrospective pilot study was performed using anonymised data from 100 patients at a single high-volume UK NHS bariatric centre who underwent surgery up to August 2025. Preoperative demographic, anthropometric, clinical and psychosocial variables were extracted from electronic records. These were provided to ChatGPT-4 Auto using a single standardised prompt instructing the model to act collectively on behalf of the whole bariatric MDT and recommend the most appropriate metabolic operation. These recommendations were compared with formal MDT decisions and with the operation ultimately performed. Concordance was assessed using raw percentage agreement, Cohen's kappa and Stuart-Maxwell tests. ChatGPT demonstrated 70% concordance with MDT recommendations. Concordance between MDT and operation performed was 83%, while concordance between ChatGPT and operation performed was 63%. Agreement beyond chance between ChatGPT and MDT recommendations was low (Cohen's kappa 0.036) reflecting class imbalance. Stuart-Maxwell test showed no significant difference in marginal distribution between ChatGPT and MDT recommendations. Both ChatGPT and MDT recommended bypass procedures more frequently than ultimately performed. ChatGPT overall demonstrated moderate crude agreement with bariatric MDT decision making in a real world UK NHS cohort of patients. However, limited agreement beyond chance and influence of unmeasured human factors may preclude its use in an autonomous fashion. This study establishes the requirement for larger scale evaluation of LLM clinical reasoning and supports the future exploration of them as adjunctive rather than autonomous decision support tools in metabolic surgery.

Mistletoe extract is a widespread complementary therapy mainly used for quality-of-life improvement in cancer patients. Advanced pancreatic cancer is associated with poor quality of life and better therapies for symptomatic relief are highly needed. MISTRAL aimed to assess the impact of mistletoe extract on quality of life, body weight, observed costs and blood biomarkers in patients with advanced pancreatic cancer. MISTRAL was an investigator-initiated, phase III, randomized, double-blind, placebo-controlled, parallel-group, superiority, multicenter, clinical trial with a nested biomarker study. Registration EudraCT 2014-004552-64, NCT02948309. At 9 oncology centers, 290 participants were randomized to standard treatment (palliative chemotherapy or best supportive care) plus subcutaneous mistletoe extract or placebo. Main inclusion criteria were advanced pancreatic cancer, performance status 0-2, main exclusion criteria neuroendocrine pancreatic tumor. EORTC-QLQ-C30, EORTC-QLQ-PAN26, body weight, cost parameters and biomarkers were assessed from baseline up until 9 months. No statistically significant differences for quality of life and weight were evident between treatment arms. Parameters for observed costs for supportive and inpatient care (days at hospital, parenteral nutrition infusions, nutritional supplement drinks, number of visits of palliative home care teams, symptom-relieving medication) were similar in both arms. Thus, calculation of costs was not performed. No effect on explored biomarkers (differential blood count, lymphocyte subpopulations, C-reactive protein, albumin and Ca19-9) was found except for a statistically significant increase of eosinophils in the mistletoe arm without association to clinical effect. Since no benefit was observed, there is no clinical reason to recommend mistletoe extract in patients with advanced pancreatic cancer.

Contemporary biomimetic and bioactive materials in paediatric dentistry: a narrative review.

Subspecialty recognition and certification in Pediatric Nephrology remain heterogeneous across Europe and globally, resulting in variations in training standards and professional mobility. To address this gap, the European Society for Paediatric Nephrology (ESPN) launched the European Board Certification in 2020 as a pan-European and curriculum-based assessment of knowledge and clinical reasoning in Pediatric Nephrology. We performed a descriptive and analytical evaluation of candidates who applied for the ESPN Board Certification in Pediatric Nephrology between 2020 and 2025. Candidate characteristics, examination performance, and factors associated with success were analyzed. The exam consisted of 100 case-based multiple-choice questions developed according to a predefined blueprint. Multivariable logistic regression was used to identify factors independently associated with passing. Additionally, a cross-sectional survey assessed candidates' perceptions of the examination and its professional impact. A total of 349 pediatric nephrologists from 52 countries and four continents completed the examination. Median age was 38.2years (IQR 34.7-43.5), and 59.9% were female. The overall pass rate was 54.7%, with significant variation by continent (p = 0.014). Attendance at the International Pediatric Nephrology Association (IPNA)-ESPN Junior Master Class was associated with higher odds of success (OR 3.76, 95% CI 1.65-5.87, p < 0.001), whereas increasing age was associated with lower odds of success (OR 0.66 per additional year, 95% CI 0.55-0.78, p = 0.002). Among 74 survey respondents, perceptions regarding the examination were highly positive: 93.2% considered the content clinically relevant, 89.2% reported increased self-confidence, and 75.6% perceived a positive professional impact. Since its launch, the ESPN Board Examination has emerged as an internationally acknowledged benchmark of key knowledge and clinical reasoning in Pediatric Nephrology. Structured preparatory education enhances examination success, and certification is widely perceived as professionally meaningful. The examination plays a vital role in standardizing subspecialty criteria and reinforcing the professional identity within Pediatric Nephrology.

The management of non-communicable diseases increasingly demands reasoning that integrates multiple mechanisms, disciplinary perspectives, and contextual constraints. Although graduate training in the health sciences is highly effective in helping learners apply stabilized evidence through Evidence-Based Practice (EBP), clinical guidelines, and decision pathways, it often gives less explicit attention to how learners should reason when evidence is incomplete, conflicting, or poorly aligned with the problem at hand. These tools compress scientific knowledge into clinical schemas that, through repeated use, support heuristic decision-making in routine contexts. The challenge emerges when evidence is sparse, conflicting, or misaligned with the clinical problem. At that point, schema-based strategies become insufficient, and uncertainty becomes a structural feature of decision-making rather than a temporary lack of data. This Hypothesis and Theory article proposes a pedagogical framework for training cross-silo integrative reasoning under uncertainty in graduate health education. The framework distinguishes three layers of clinical reasoning and operationalizes the third (i.e., the Uncertainty Layer) through five adaptive simulators that can train both horizontal and vertical integration, in which large language models function as constrained epistemic adversaries. A non-normative rubric, intended for developmental monitoring rather than summative judgment of correctness, assesses how learners deal with uncertainty across simulator sessions. The framework does not replace EBP, clinical expertise, or mentorship; it formalizes the reasoning processes required when stabilized evidence reaches its limits, making expert judgment under uncertainty explicit, inspectable, and teachable within graduate health-sciences education.

Artificial intelligence (AI) in dermatology has moved beyond the early paradigm of single-image classification. Dermatological diagnosis is achieved based on morphology, distribution, symptoms, tactile findings, temporal evolution, patient history, histopathology, and treatment response. Clinically important differentials, such as eczema versus psoriasis, cutaneous T-cell lymphoma versus chronic dermatitis, drug eruption versus viral exanthem, lupus erythematosus versus dermatomyositis, and melanoma versus atypical nevus, are rarely resolved with one photograph alone. This review therefore frames AI-assisted dermatology around a central argument: the field must progress from lesion recognition to dermatology-specific multimodal clinical reasoning. We summarize major advances in convolutional neural networks, dermoscopic benchmarks, clinical-image datasets, large language models, vision-language systems, and dermatology foundation models. We also analyze challenges that are particularly relevant to dermatology, including morphologic overlap, skin-tone bias, reduced erythema visibility on darker skin, dataset imbalance, variable smartphone imaging, imperfect reference standards, and the gap between benchmark performance and clinical deployment. Special attention is given to fairness, regulatory oversight, software as a medical device, human-AI collaboration, prognosis prediction, biologic-response modeling, longitudinal monitoring, and treatment optimization. Finally, we discuss future directions, including skin-tone-aware foundation models, lesion-level and body-site grounding, pathology-genomics integration, dermatology copilots, post-marketing surveillance, and prospective clinical trials. By prioritizing dermatological reasoning rather than generic AI architecture, this review outlines a clinically grounded pathway for building safe, interpretable, equitable, and useful AI systems for skin disease management.

Acute uncomplicated diverticulitis is commonly managed in hospital in Australia. Virtual care may offer reassurance to clinicians and enable out-of-hospital management by providing remote monitoring. This study evaluated the feasibility, safety and acceptability of a virtual care pathway for acute diverticulitis (iCAD). This Phase I/II trial comprised a single-centre pilot of patients managed via the iCAD pathway, followed by a multicentre randomised trial comparing iCAD with conventional inpatient care. The iCAD model involved initial in-person assessment and intravenous antibiotics, followed by daily medical/nursing videoconferencing, supported by wearable devices and a mobile app for vital signs monitoring. Outcomes included treatment retention (defined as the proportion of patients who remained on the iCAD pathway without crossover to inpatient care), rate of major complications and patient-reported acceptability. In Phase I, 10 participants were treated on the iCAD pathway with no withdrawals, crossovers or major complications. In Phase II, 40 patients were randomised and no major complications occurred in either group. Two iCAD patients crossed over to inpatient care for clinical reasons. The treatment retention rate for the virtual care group across both phases of the trial was 93%. Patient-reported experiences favoured the iCAD group, with more participants rating their care as 'excellent' (88% vs. 40%, p = 0.03) and felt their healthcare needs were 'always' met (88% vs. 47%, p = 0.02). Virtual care for acute uncomplicated diverticulitis appears feasible, safe and acceptable, with potential advantages over inpatient care, including superior patient-reported experience.