Pharmacognosy

Background: Musculoskeletal disorders (MSDs), such as osteoarthritis, fractures, ligament injuries, and chronic back pain, affect over 1.3 billion people worldwide, posing significant clinical and economic burdens. Conventional orthopedic physiotherapy is essential for restoring mobility and reducing disability but is limited by subjectivity, variability in treatment outcomes, and challenges in personalization. Artificial intelligence (AI) and machine learning (ML)have emerged as transformative tools to overcome these gaps. Methodology: This mini-review synthesizes recent advances in AI/ML applications across diagnostic imaging, gait and posture analysis, wearable sensor technologies, predictive analytics, rehabilitation robotics, and tele-physiotherapy. Clinical applications, case studies, and technological innovations are evaluated to highlight their impact on patient assessment, treatment planning, and rehabilitation. Challenges such as data privacy, limited datasets, integration into clinical workflows, and algorithmic bias are also discussed. Results: AI enhances diagnostic precision through automated medical imaging analysis and computer vision–based gait assessment. Wearable sensors combined with ML enable continuous monitoring and adaptive therapy adjustments, while predictive models improve early detection of injury risks and disease progression. AI-assisted rehabilitation tools—including robotic systems, VR/AR platforms, and gamified therapy—enhance patient engagement, adherence, and recovery outcomes. Clinical applications demonstrate improvements in post-operative rehabilitation, chronic back pain management, arthritis grading, sports injury recovery, and remote physiotherapy delivery. Despite barriers, federated learning, IoT integration, multimodal AI, and fully autonomous physiotherapy assistants are emerging as future solutions. Conclusion: AI and ML are revolutionizing orthopedic physiotherapy by enabling precision diagnosis, personalized treatment, and adaptive rehabilitation strategies. While challenges in privacy, clinical adoption, and algorithmic robustness remain, ongoing innovations promise to establish AI as a cornerstone of musculoskeletal care. These technologies are poised to enhance patient-centered rehabilitation, improve global accessibility, and shape the future of physiotherapy practice.

The aim of the current research is to prepare and test sustained-release (SR) tablets of Metformin hydrochloride using hydrophilic polymers such as Hydroxypropyl Methylcellulose (HPMC), Xanthan gum and Eudragit RSPO so as to attain sustained glycemic control in diabetic animal models. The wet granulation method is used to prepare tablets and the physicochemical properties such as weight variation, hardness, friability, thickness and uniformity of drug content are determined and all are found to be within acceptable limits. In vitro drug release showed a release of Metformin is controlled over 12 hours with release kinetics consistent with the Korsmeyer-Peppas model, reflecting diffusion and erosion. Sustained drug absorption is observed in streptozotocin-induced diabetic Wistar rats in which in vivo pharmacokinetic analysis of the SR formulations demonstrated a long Tmax and half-life (t1/2) and higher area under the plasma concentration-time curve (AUC) than immediate-release Metformin. One-way ANOVA and Tukey post-hoc statistical analysis showed that there are significant differences between formulations (p