Uso da tecnologia como ferramenta de apoio na cicatrização de feridas

Abstract

Considered a public health problem, difficult-to-heal wounds affect 5% of the adult population in the Western world and generate high costs for health services as they involve home care, prolonged hospitalizations and complex treatments, in addition to being associated with high recurrence rates. This thesis aims to evaluate the use of technology as a support tool in wound healing, which culminated in two studies. The first, a clinical trial planned with the use of low-intensity laser in diabetic foot ulcers, and, the second, a prototyping-type study for tissue classification in wounds. The planned clinical trial study was developed in a reference wound clinic in the city of Montes Claros, during the years 2021 to 2023. 15 people with diabetic foot ulcers, aged ≥ 18 years, were included, allocated through a draw. in the “experimental” (laser intervention plus conventional treatment) and “control” (conventional treatment) groups. The red laser was used at a wavelength of 630 nm, three times a week, at a dose of 4J/cm2 of damage, for four weeks. Data were collected through a questionnaire with socioeconomic variables; a form with clinical data and lifestyle habits and a protocol for laser use and conventional treatment of injuries. Descriptive analyzes of the variables were performed, using the Wilcoxon test to compare the variables of wound evolution on the first and thirtieth day, and Student's “t” test to compare the means of the lesion area. The study of technological production of the prototyping type was implemented in two phases. In the first, the preparation of images of wound tissues and the training and evaluation of a convolutional neural network were carried out. The images were collected from a database of medical records of people treated at the aforementioned outpatient clinic. In the second phase, an application was developed, responsible for acquiring the image (photo) of the wound through the mobile device's camera, resizing and cropping the image and sending it to the cloud service so that it can predict to the user the classification of the type of wound. tissue present in the wound. Product 1 aimed to analyze the effectiveness of low-intensity laser as an adjuvant in the healing of diabetic foot ulcers. The reduction in the average area of the lesion was significantly greater (p=0.003), as well as the reduction in the amount of exudate (p=0.014) in the experimental group when compared to the control group. Product 2 aimed to develop an application for identifying types of wound tissue, through images, using a convolutional neural network trained with its own photographs. The trained model achieved an accuracy of 76%, considered a good result and the application for classifying the types of tissue in wounds will be available in the Play Store and Apple virtual stores. It is concluded that the laser is an adjuvant therapy that can accelerate the healing process of injuries caused by diabetes mellitus, and these findings may support professionals in the construction of guidelines for the safe use of low-intensity lasers in the treatment of injuries. difficult to heal. The mobility provided by the application will allow healthcare professionals to respond quickly when classifying a wound, as this depends on the indication of appropriate treatment and the direction towards complete resolution of the injury.