Keyword: Clinical Decision Support

ABSTRACT: Artificial intelligence (AI) is transforming the practice of surgery through the support of clinical decision-making, improved accuracy and efficiency, and better patient outcomes across the perioperative period. This review evaluates and critically analyzes current, technological and evidence-based applications of AI in surgery. Machine learning, deep learning, computer vision and natural language processing are some of the core AI technologies that are enabling developments in all phases of surgery. Some of these applications include, improved preoperative diagnosis, intraoperative real-time imaging, workflow analysis, robotic surgery assistance and intraoperative clinical decision support. Postoperatively, the potential of AI is also vast. Through the use of predictive models for surveillance and early complications detection, as well as remote management of patients, AI is optimizing postoperative care. 
 Although the findings suggest promise for the future, the clinical adoption of AI in surgery is limited by a number of issues, including data quality and heterogeneity, lack of validation in large prospective studies, potential for bias, ethical concerns and high costs of implementation. Other factors including clinician acceptance, data privacy, regulatory approval and medico-legal implications need to be addressed before any new technology is widely adopted.
 Future directions of AI in surgery includes progression to semi-autonomous systems that augments the efforts of the surgeon, integration with emerging technologies such as genomics and digital twins, and increased use in low resource settings to help address existing global inequities in surgical care. For successful AI adoption in surgery, AI systems will need to undergo robust validation, require interdisciplinary approaches, and all systems must be developed in a manner that is not only transparent but also clinically appropriate for surgeons, so that it can maximise the benefits of human talent in the operating room while maintaining patient safety.
 

ABSTRACT: The rapid application of artificial intelligence (AI) in diagnostic disciplines such as radiology, pathology, microbiology, and genomics has revolutionized the way in which doctors and laboratory workers provide patient care. AI has enhanced the efficacy, accuracy, and cost-effectiveness of laboratory operations, clinical decision support systems, and image interpretation. However, these advantages are accompanied by a severe behavioral issue: an excessive reliance on automation could result in a generation of professionals who lack the reasoning abilities necessary to independently assess or contextualize machine outputs. The dual effects of AI integration are the focus of this paper, which highlights its beneficial aspects—including decreased cognitive load, increased confidence, and educational reinforcement—as well as its adverse effects, which include skill degradation, diagnostic deskilling among trainees, complacency, and reduced situational awareness. The research emphasizes the potential for unregulated dependence on AI to progressively alter professional conduct and expertise by utilizing case examples from radiology, pathology, laboratory medicine, and clinical decision support, as well as parallels from automation in aviation. In order to address these concerns, a conceptual framework is proposed that integrates AI into a "human-in-the-loop" approach, thereby preserving the significance of human judgment while leveraging machine accuracy. In order to achieve equilibrium, strategies include curriculum reform to integrate AI with hands-on experience, regular retraining, the implementation of explainable AI to promote active thinking, and institutional measures similar to recurrent training in high-stakes sectors. Ultimately, AI should complement the existing infrastructure rather than supplant it. In order to guarantee this, we must establish strategic educational, organizational, and regulatory safeguards to preserve diagnostic expertise, ensure accountability, and maintain the resilience of healthcare systems as they become increasingly dependent on intelligent technologies.