Costa, Isabelle Katherinne FernandesMesquita, Simone Karine da Costa2023-01-182023-01-182022-08-26MESQUITA, Simone Karine da Costa. Redes neurais artificiais para auxílio aos enfermeiros na tomada de decisão sobre coberturas para lesões venosas. Orientador: Isabelle Katherinne Fernandes Costa. 2022. 168f. Tese (Doutorado em Enfermagem na Atenção à Saúde) - Centro de Ciências da Saúde, Universidade Federal do Rio Grande do Norte, Natal, 2022.https://repositorio.ufrn.br/handle/123456789/50983Venous ulcers are considered a public health problem due to the socioeconomic impact caused by the costs of treatment, high incidence and recurrence, as well as the gaps in health services, in particular, the difficulty of professionals in clinical judgment during treatment. choice of coverage for the injury. In this way, a computer system can help nurses to minimize these difficulties related to the treatment of venous ulcers, through artificial intelligence. Among the intelligent technologies, the Deep Artificial Neural Networks have stood out for their high power to solve complex problems, which makes it possible to maximize the quality of care offered to patients and contributes to the decision-making of professionals during clinical practice. Given the context, the study aims to develop computational aid to nurses in decision making about dressings for venous ulcers. This is a methodological research that was divided into four phases, according to the Unified Process methodological model. Phase 1 refers to the design and requirements gathering; phase 2 comprises the elaboration of the structure of neural networks; phase 3 refers to the development of networks, carrying out the tests, building the VenoTEC application and evaluating the usability; and phase 4 refers to the finalization of the software, ready to be used. Data were analyzed according to a calculation guided by the System Usability Scale, as well as exported to the Statistical Package for Social Science 20.0 program, where they were analyzed using relative and absolute frequency statistics. The deep neural network focused on tissue classification obtained an accuracy of 70%, while the neural network focused on coverage classification obtained an accuracy of 100%. In this way, the networks proved to be effective for the application. The requirements regarding coverage were obtained through an integrative review of the literature, protocols and suggestions from specialists in dermatological nursing or stomatherapy. The results focused on usability evaluation obtained a score of 88.07 points, which characterizes very good usability. The participating nurses, when using the software, felt satisfied and indicated the ease of using the system efficiently, easy to remember and few inconsistencies. With the research, it was possible to develop two deep artificial neural networks aimed at offering computational support to nurses during the treatment of venous ulcers and may bring contributions as a work tool based on scientific evidence and protocols, in order to standardize the conduct of professionals in the health services, which may expand the care provided in the assistance. The contributions of a technology aimed at artificial intelligence at this level make it possible to acquire a high amount of information in real time, which favors the expansion of human intelligence of the various actors involved in the process of caring for the person with venous ulcers. In this way, it makes it possible to make decisions quickly and to reduce errors. For the patient, it may favor the reduction of treatment time and, consequently, the costs involved in the treatment. The benefits can also be extended to health services and society, as the technology can contribute to reducing the financial impact that venous ulcers have on health systems.Acesso AbertoEnfermagemÚlcera varicosaTecnologiadoctoralThesisCNPQ::CIENCIAS DA SAUDE::ENFERMAGEM