سامانه همایش های دانشگاه آزاد اسلامی واحد نجف آباد

صفحه اصلی / اولین همایش بین المللی تحول خدمات سلامت: تلفیق مراقبت، درمان، بازتوانی و امیدبخشی

Artificial Intelligence in Disease Diagnosis and Treatment: Current Applications, Challenges, and Future Perspectives

نویسندگان :

Mina Allami¹ Hamed Moeini² Ala Jomehri³ Mina Jouzi⁴

1- دانشگاه ازاد نجف اباد 2- دانشگاه ازاد نجف اباد 3- دانشگاه ازاد نجف اباد 4- دانشگاه ازاد نجف اباد

کلمات کلیدی :

Artificial Intelligence،Machine Learning،Deep Learning،Clinical Decision Support،Personalized Medicine،Medical Diagnosis

چکیده :

Abstract: Background: Artificial intelligence (AI) refers to computational technologies capable of analyzing complex data, identifying patterns, and supporting decision-making in healthcare. AI is increasingly being incorporated into healthcare for disease detection, risk prediction, treatment selection, remote monitoring, and clinical decision support. This narrative review aimed to summarize current applications of AI in disease diagnosis and treatment and critically examine the clinical, ethical, organizational, and humanistic challenges associated with its implementation. Method: Relevant literature was searched in PubMed, Scopus, Web of Science, and Google Scholar using combinations of terms including “Artificial Intelligence,” “Machine Learning,” “Deep Learning,” “Disease Diagnosis,” “Disease Treatment,” “Personalized Medicine,” and “Clinical Decision Support.” Recent clinical trials, cohort studies, validation studies, systematic reviews, and relevant nursing and healthcare literature were qualitatively reviewed and synthesized. Finding: AI demonstrates substantial potential in medical imaging, cancer screening, cardiovascular risk stratification, electronic health record analysis, personalized treatment, rehabilitation, and clinical decision support. Clinical evidence included prospective diagnostic evaluation, AI-guided personalized treatment, and multimodal clinical decision support. In a randomized controlled trial of persistent atrial fibrillation, an AI-guided treatment strategy achieved higher freedom from documented atrial fibrillation at 12 months than conventional treatment (88% vs. 70%), although it required longer procedural and ablation time. Generative AI and multimodal clinical agents further extend these capabilities by integrating heterogeneous clinical information. However, algorithmic performance alone doesnot ensure clinical benefit. Data quality, bias, generalizability, explainability, privacy, regulation, infrastructure, workforce readiness, patient health literacy, and human oversight remain critical determinants of successful implementation. Conclusion: AI should be considered an augmentative component of healthcare rather than a replacement for clinicians. Future AI systems should be integrated with established continuous-care models and designed around patient engagement, clinical expertise, communication, safety, and humanistic care. Keywords: Artificial Intelligence; Machine Learning; Deep Learning; Clinical Decision Support; Personalized Medicine; Medical Diagnosis