Desafios e avanços na personalização diagnóstica e terapêutica na era da inteligência artificial na saúde

• Autor(a) principal: Lobato Coelho, Rebecca
• Data de Publicação: 2024
• Outros Autores: Esteves, Júlia Peres, Aquino Ragognete, Isadora, AMARAL COSTA, AYGHOR, de Miranda Ferreira, Yago, Rossi Camargo, Bruno, Minhoto Pozzobon, Amanda, Santos Malaquias Pereira, Marri, Pimentel Sampaio, Breno, Rodrigues Vasques, Amanda, Damas Meireles, Adriano Junio, Boscarioli Ramenzoni, Francesca Bruna, Benedetti Barbosa, Beatriz, Ferreira Ros, Lucas, Zampronio , Isabella
• Tipo de documento: Artigo
• Idioma: por
• Título da fonte: Brazilian Journal of Implantology and Health Sciences
• Texto Completo: https://bjihs.emnuvens.com.br/bjihs/article/view/1259
• topic: Inteligência Artificial; Aprendizado de Máquina; Diagnóstico Clínico; Machine Learning; Deep Learning

The integration of artificial intelligence (AI) and machine learning (ML) in medicine represents a rapidly growing field, promising significant advances in diagnostic and treatment processes. Given this scenario, this integrative review seeks to consolidate and critically analyze the available scientific evidence on the application of these innovative technologies in medical practice. The methodology adopted for this integrative review involved a comprehensive search of the main databases, such as PubMed, Scielo and ScienceDirect, using the relevant descriptors, such as "Artificial Intelligence", "Machine Learning", "Clinical Diagnosis", "Machine Learning" and "Deep Learning". The careful selection of references included relevant studies that address the application of AI and ML in various domains of medicine, with a special focus on the references indicated in Vancouver in this abstract. The results of this review reveal a wide range of successful applications of AI and AM in medical diagnosis and treatment. Studies such as Wang et al. (2019) highlight the progress and challenges of using deep learning in medicine, while work by Erickson et al. (2017) highlights the effectiveness of ML in medical imaging, contributing to advances in clinical practice. Ethical approaches and future impacts on the actions of healthcare professionals, as discussed by Ahuja (2019) and Farhud and Zokaei (2021), emerge as crucial points in the integration of these technologies. The conclusion of this integrative review reinforces the significant transformation provided by the integration of AI and AM in medicine, offering faster and more accurate diagnoses, as well as outlining intrinsic ethical challenges. Patient privacy and ethical considerations become critical factors in this scenario. This comprehensive analysis highlights the continued need for responsible research and development, promoting advances that optimize clinical efficacy and ensure the trust of healthcare professionals and patients in the face of these transformative innovations.