SICOMBO: sistema universal de IoT com computação de borda para seguro monitoramento clínico

• Ano de defesa: 2020
• Autor(a) principal: Silva, Rafael Marinho e
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de Uberlândia; Brasil; Programa de Pós-graduação em Ciência da Computação
• Palavras-chave em Português: Acessibilidade de pacientes; Computação de borda; Dispositivos de IoT; Monitoramento remoto de pacientes; Segurança de pacientes; Sistema de baixo custo; Patient affordability; Edge computing; IoT devices; Patient remote monitoring; Patient safety; Low cost system; Computação; CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::SISTEMAS DE COMPUTACAO::ARQUITETURA DE SISTEMAS DE COMPUTACAO; CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::SISTEMAS DE COMPUTACAO::SOFTWARE BASICO; CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::SISTEMAS DE COMPUTACAO::HARDWARE; Internet das coisas; Integração de dados (Computação); Linguagem de programação de domínio específico (Computadores); ODS::ODS 3. Saúde e bem-estar - Assegurar uma vida saudável e promover o bem-estar para todos, em todas as idades.
• Link de acesso: https://repositorio.ufu.br/handle/123456789/41643; http://doi.org/10.14393/ufu.di.2021.9

Traditionally, the comprehensive monitoring of patients' clinical conditions occurs in hospital environments with specialized equipment and professionals, requiring high financial investments. This limits the access of low-income individuals to basic treatments in SUS hospitals in Brazil. However, advances in the Internet of Things (IoT) have propelled innovations in the healthcare sector, including remote patient monitoring. In this context, this work proposes a low-cost system utilizing edge computing and IoT devices to remotely monitor specific vital patient data and precisely control medication administration. Two architectures were created during the development of the system; the first one has ESP32 microcontrollers connected to the Internet for collecting and managing vital data such as heart rate, blood oxygen peripheral saturation, a patient's body temperature, and the temperature of his or her environment. It also has the feature of identifying the professional who performs the medication procedure on the patient. The second architecture, on the other hand, was developed to improve the first, adding the following features: precise control of prescription and administration of medications, to reduce the risks to the patient's health due to errors in these processes; locally store the data collected by the sensors and processed by the ESP32 microcontrollers on microSD cards (datalogger); send this data through a protocol (MQTT) to a minicomputer (Raspberry Pi) that is managed by the system developed in Node-RED, which in turn stores it (via protocol (HTTP) all information generated in a spreadsheet on Google Drive. The experimental results, from the simulations of the two architectures with a volunteer, were duly validated (benchmarking) compared to devices used in hospital environments. Also, data were collected, transmitted and stored by the respective modules of the developed system, as expected in the experiments. One can conclude that the developed system, aiming for accessibility (low cost) for all patients, achieved the proposed objectives and fulfilled the hypotheses regarding remote monitoring of patients' clinical conditions and safety in precise prescription and administration of medications.