Use of artificial intelligence in medicine, surgery, dentistry, and oncology
Svintsitskyi A.V., Klymova V.V., Sendetskyi S.S.
Summary. Introduction. In recent years, there has been a significant increase in interest in artificial intelligence technologies and their application in medical practice. AI algorithms, namely machine and deep learning, as well as convolutional neural networks, have great prospects in the field of medical imaging, from image recognition, processing, and reconstruction to automated analysis and classification. In particular, they make a significant contribution to disciplines that heavily rely on imaging. The purpose of the study was a systematical review of the current literature on the use of artificial intelligence in surgery, dentistry, and oncology. Materials and methods. The study used data from the MEDLINE medical database using search criteria that included the words «artificial intelligence», «surgery», «dentistry», and «oncology». Results. Surgical Data Science (SDS) aims to improve the quality and value of interventional medical care by collecting, organizing, processing, and modeling data. Recent studies have been able to demonstrate the possibility and reliability of machine learning algorithms for early prediction of intraoperative complications. Regarding the application of artificial intelligence in dentistry, it has been determined that it can automatically detect and classify dental restorations on panoramic X-rays, as well as help in the detection of dental and maxillofacial pathologies, such as periodontitis, root caries, bone tissue lesions, facial defects, etc. In oncology, artificial intelligence models, if validated in prospective studies, could play an important role in early cancer detection and classification, especially since their effectiveness is comparable to, if not better, than that of experts in this field. Conclusion. Artificial intelligence is expanding its presence in clinical systems, ranging from databases to intraoperative video analysis. Current studies on the use of artificial intelligence in the medical field have shown that neural networks perform as well as expert specialists, but with greater accuracy and precision. In some studies, artificial intelligence models have even outperformed human experts. Thus, modern artificial intelligence is excellent at using structured knowledge and extracting insights from vast amounts of data. However, it is not capable of making associations like the human brain does, and is only partially capable of making complex decisions in a clinical situation.
Leave a comment