CIARS Project – Artificial Intelligence applied to Health

Abstract: With the growing volume of data, the use of data mining algorithms and techniques has become essential for the extraction of knowledge from data in the field of Data Science. In this context, it is noteworthy that, for decades, the area of ​​Artificial Intelligence (AI) and Machine Learning (ML) techniques has been contributing with algorithms, techniques and methods to make different classes of systems able to improve on the basis of data. Today, AI and ML play an essential role in Data Science. One of the areas in which these techniques have and can contribute even more with solutions is the Health area. In the broad context of the so-called digital transformation of healthcare, technologies such as AI, big data, the Internet of Things (IoT), blockchain, smart wearable devices, tools that allow remote capture, exchange and data storage and sharing of relevant information across the healthcare ecosystem have proven potential to improve health outcomes by aiding medical diagnosis, facilitating and qualifying data-driven treatment decisions, providing digital therapy alternatives, supporting clinical trials, enabling self-management of person-centered care and care. In general terms, the digital healthcare transformation supported by data science and artificial intelligence generates more knowledge evidence-based, expanding the skills and competencies of health professionals. This evidence, pointed out in a recent document by the World Health Organization (WHO), has already been observed through growing innovation in medical products and platforms aimed at real-time care, involving AI, in addition to other areas of Computing. Such solutions cover several aspects of the ecosystem of Health. Given this scenario, the present proposal is centered on the observed need for a set of solutions computational tools to provide significant advances in several processes in the health area, namely: (1) Aid to medical diagnosis based on the location and prediction of clinical findings in the different modalities of available data: clinical data, multimodality imaging, genomic, behavioral, between others; (2) Prediction of higher risk situations in advance, both at an individual, community or population level, in order to guide proactive health management and control actions; (3) Assistance in classifying patients according to the degree of complexity and urgency of the treatment for better allocation according to available resources; (4) Managing the flow of patients and optimizing the distribution of hospital resources according to the clinical condition of patients and the availability of these resources; (5) Facilitation of patient access to the health system suited to their needs in urgent and emergency cases, through the management of patient flow between public and private systems; and (6) Providing managers with accurate information that can be used in the decision-making process for incorporating technologies and managing health resources.

Ano Inicio: 2022

Ano Fim: 2026

Coordenador Local: Jéferson Campos Nobre

Agência de Fomento: FAPERGS