ARTIFICIAL INTELLIGENCE IN MEDICINE: A PRESENT FUTURE (Atena Editora)

Abstract

OBJECTIVE: Artificial Intelligence (AI) has attracted attention in the medical field. However, due to the complexity of the system, the variability of its architecture, as well as ethical and regulatory concerns, there is an ongoing need to analyze its application and performance. The objective of this study was to address artificial intelligence in medicine and its respective benefits or harms. METHODOLOGY: This study presents a narrative commentary on the applications of AI and learning algorithms in medical devices, past, current and future application perspectives. A research focus of this study was the identification of problems and issues related to the implementation of AI in the medical field. The commentary is based on scientific articles published in the databases PubMed, Scopus ad ScienceDirect, official publications of international organizations: European Commission (EC), Food and Drug Administration (FDA) and World Health Organization (WHO) published in the period 2015 to 2023. RESULT AND DISCUSSION: AI is revolutionizing healthcare, from medical applications to clinical engineering. The future of AI application can be seen not only in increasing treatment accuracy but also in preventing injuries and deaths caused by medical devices. Because healthcare is generating a lot of data, as in fact all medical devices are generating a lot of data, these big data structures can be used to predict the safety and performance of medical devices. For example, the use of smart infusion pump systems has become the preferred method for ensuring the safety of intravenous medications. Most of these systems are based on specialized AI systems rather than ML, but the durability and reliability of such devices have led to more extensive ML-based applications, such as implantable insulin pumps and emerging closed-loop artificial pancreas devices. CONCLUSION: However, before realizing the full potential, ethical, legal and social concerns need to be resolved and their application needs to be harmonized and regulated with regard to equitable access, privacy, appropriate uses and users, to responsibility, prejudice and inclusion.