Bone defects caused by trauma, infection, tumour resection and impaired healing remain difficult to reconstruct because successful repair requires coordinated mechanical stability, vascularisation, immune regulation and osteogenesis. Natural-based hydrogels provide hydrated, extracellular-matrix-mimicking platforms that can conform to irregular defects and integrate local delivery of bioactive factors, cells, extracellular vesicles and mineral phases. This critical narrative review examines natural-based hydrogels for bone regeneration from a biomaterials-to-clinic perspective, focusing on material design, cell–material interactions, vascularisation, osteoimmunomodulation, controlled therapeutic delivery, injectable and stimuli-responsive systems, composite reinforcement and 3D bioprinting. Human evidence exists for selected gelatin- and hyaluronan-based systems and for clinically adjacent applications such as growth-factor-assisted fracture healing and antibacterial implant coatings; however, most multifunctional regenerative systems remain preclinical. We therefore emphasise translational maturity rather than technological novelty alone. Key barriers include insufficient load-bearing mechanics, variable in vivo degradation, vascularisation at clinically relevant scale, manufacturing and sterilisation constraints, regulatory complexity and limited comparative clinical evidence. The most credible path to clinical adoption is likely to involve indication-specific systems that provide a reproducible biological advantage while remaining surgically compatible, scalable and practically manufacturable.

Aims: Diabetes mellitus is a global health challenge requiring innovative solutions for early diagnosis, personalized treatment, and ongoing management. This review aims to examine the impact of artificial intelligence (AI) on diabetes care, focusing on precision diagnosis, tailored therapies, and real-time monitoring, while addressing challenges related to model transparency and equitable access to healthcare. Methods: We conducted a comprehensive review of AI applications in diabetes management. Studies utilizing supervised and unsupervised learning, deep learning, federated learning, and reinforcement learning were analyzed for predictive accuracy, clinical impact, and integration. Comparisons with conventional methods were also included. Results: Machine learning models show strong predictive performance for diabetes risk assessment, with random forest algorithms reporting accuracy up to 97% in hospital-based datasets. Deep learning models applied to clinical cohorts have achieved approximately 94.6% accuracy in predicting adverse events in patients with type 2 diabetes. Reinforcement learning approaches for automated insulin delivery have maintained glucose within the normoglycemic range for up to 95.66% of simulated time in artificial pancreas studies. Federated learning enables privacy-preserving collaborative model development with performance comparable to centralized models. AI-driven decision-support systems and wearable technologies further support improved glycemic monitoring and patient self-management. However, model performance varies depending on dataset characteristics, patient populations, and evaluation protocols. Conclusions: AI has reshaped diabetes care by enabling precise diagnosis, individualized treatments, and adaptive disease management. Responsible implementation is essential to address ethical concerns and ensure equitable access. Future work should refine AI frameworks for broader clinical adoption, prioritizing patient-centered care and data security.