An exploration into the application of large language models in diabetes care as a support tool for clinical decision-making is warranted due to the model’s ability to integrate clinical guidelines, synthesize large volumes of patient data, construct clinical notes, assist in clinical teaching, and provide a rationale for complex management decisions. Diabetes, in particular, presents a complex clinical scenario, as the formulation of management decisions must consider multiple factors, including, but not limited to, multiple targets and risk factors, monitoring data, medication safety, and the patient’s behavioral and psychosocial needs, burdens, and nutritional preferences. This narrative review describes the possibilities of clinician-facing diabetes decision-support systems utilizing large language models and proposes a patient safety architecture and evaluation framework for their clinical assessment. The emphasis is on the safe implementation of these systems, not in an autonomous care setting. Based on the current literature, the systems will most likely assist with preparing clinical visits, reviewing clinical medications, preparing patient summaries for continuous glucose monitoring, planning clinical procedures, and coordinating communication within the clinical team. Despite the above benefits, these systems remain limited, and the constraints of large language models may have serious consequences in the field of diabetes, considering the potential risks of treatment-related adverse events, including hypoglycemia, diabetic ketoacidosis, and other complications based on inequitable provision of care. The safest and most viable near-term solution for large language models in clinical practice is a controlled, evidence-based, and clinician-supervised model that supports the retrieval of clinical guidelines, indicates appropriate levels of uncertainty, identifies gaps in the data, and assumes professional accountability. The focus of future studies should extend beyond validation studies and accuracy benchmarks to evaluating the impact on clinical workflows, equity, patient care and safety, and to monitoring these systems once deployed. Large language models have the potential to support diabetes care; however, they must act to enhance the clinical voice and judgment rather than diminish it.

Purpose: This study aims to critically evaluate dietary and gut-directed strategies for weight management, distinguishing association from causation while integrating fibre structure, biomaterials, precision nutrition, microbial therapeutics and glucagon-like peptide-1 receptor agonist (GLP-1 RA) care. Design/methodology/approach: A targeted narrative synthesis of human interventions, mechanistic studies, consensus statements, systematic reviews and preclinical studies was assessed for design, replication, clinical relevance and causal mediation. Findings: Microbiome changes alone do not establish clinically meaningful mechanisms. Causal support is strongest from transfer experiments, short-term human faecal microbiota transplantation, controlled feeding and targeted metabolite delivery, although effects are often transient. Whole-food diets rich in diverse fibres, resistant starch, minimally processed plants and fermented foods remain the most mature strategy. Prebiotic effects vary with structure, dose, food matrix and host ecology; fibre–clay hybrids remain preclinical. Precision nutrition using multi-omics and machine learning is advancing, but external validation and superior weight-loss outcomes remain limited. Live biotherapeutics, engineered microbes, postbiotics and faecal microbiota transplantation differ in readiness, safety and regulation. Research limitations/implications: Future trials require standardised outcomes, direct metabolomics, shotgun metagenomics, longer follow-up and prespecified mediation analyses. Practical implications: Care should remain food-first, culturally adaptable and integrated with obesity therapies. During GLP-1 RA treatment, gradual fibre titration, hydration, smaller meals and symptom-specific foods may improve tolerability, although direct evidence is limited. Social implications: Public health policy should improve access to minimally processed, fibre-rich foods and avoid deterministic microbiome claims. Originality/value: This review provides an evidence hierarchy linking fibre structure, biomaterials, precision nutrition and microbial therapeutics to clinical weight-management decisions.

Rising recognition of attention deficit hyperactivity disorder (ADHD) in adults and children is reshaping how Australian health systems organise diagnosis, prescribing and long-term management. This has coincided with sharp increases in ADHD medicine dispensing, high private assessment costs and prolonged waiting times for psychiatrists and paediatricians. Australian states and territories have commenced reforms that expand the role of general practitioners (GPs) in ADHD diagnosis, prescribing and long-term management. This commentary assesses whether these reforms can expand timely and equitable access while maintaining diagnostic accuracy, medication safety and specialist referral. It uses the New South Wales (NSW) model as a detailed exemplar because it has developed a staged pathway: trained continuation prescribers support previously diagnosed patients who are stable on psychostimulant treatment, while endorsed prescribers receive further accredited training or recognition of prior learning to assess, diagnose, initiate and adjust psychostimulant treatment. The commentary distinguishes professional specialty status from ADHD-specific competency: specialist registration in general practice establishes the professional status of qualified Australian GPs, whereas safe extension of ADHD diagnosis and psychostimulant prescribing requires condition-specific education, competency assessment, prescribing authority, monitoring and defined referral pathways. It reviews Australian reforms, explains the NSW training and governance pathway, compares overseas approaches, and identifies safeguards needed to avoid diagnostic compression, overdiagnosis, stimulant diversion and widening inequity. The central argument is that GP involvement should be framed as trained, governed primary-care capacity. If adequately funded, audited and linked to specialist escalation pathways, the model may reduce access barriers while preserving diagnostic rigour.

Background/Objectives: Pediatric acute-onset neuropsychiatric syndrome (PANS) describes the rapid onset of obsessive–compulsive symptoms or severe food restriction, accompanied by neuropsychiatric or somatic features that are not better explained by another disorder. PANDAS (Pediatric Autoimmune Neuropsychiatric Disorders Associated with Streptococcal infections) is a related, more narrowly defined construct in which symptoms are temporally associated with group A Streptococcus infection. This review examines clinical symptoms, infectious associations, proposed immune mechanisms, biomarker limitations, and treatment strategies for infection-associated PANS/PANDAS. Methods: A structured narrative search of PubMed/MEDLINE, Embase, the Cochrane Library, Google Scholar/publisher-indexed literature, ClinicalTrials.gov, and reference lists was performed up to 16 June 2026. Original cohorts, case series, systematic reviews, narrative reviews, consensus guidance, mechanistic studies, and registered prospective studies were prioritized. The review was not designed as a PRISMA-ScR scoping review; however, the methods were expanded to improve transparency and align with SANRA principles. Results: Group A Streptococcus remains the best characterized infectious association, although prospective studies have not uniformly demonstrated a consistent temporal relationship between streptococcal infection and neuropsychiatric exacerbations. Parent-reported surveys and case-based literature also describe temporal associations with Mycoplasma pneumoniae, influenza-like illnesses, upper respiratory infections, Borrelia burgdorferi, Epstein–Barr virus, and SARS-CoV-2. Proposed mechanisms include molecular mimicry, anti-D1R and anti-D2R antibodies, other antineuronal antibodies, calcium/calmodulin-dependent protein kinase II signaling, blood–brain barrier vulnerability, cytokine and Th17 effects, neuroinflammatory amplification, basal ganglia/CSTC circuit dysfunction, and gut–oral–brain immune interactions. None currently provides a definitive diagnostic biomarker. Conclusions: Infection-associated PANS is best approached as a clinically defined, heterogeneous neuroimmune presentation that requires rigorous differential diagnosis, multidisciplinary care, cautious treatment escalation, prospective biomarker validation, and large, multicenter treatment trials.