COVID-19 in Brazil—Preliminary Analysis of Response Supported by Artificial Intelligence in Municipalities

Abstract

The novel coronavirus disease (COVID-19) forced rapid adaptations in the way healthcare is delivered and coordinated by health systems. Brazil has a universal public health system (Sistema Unico de Saúde—SUS), being the main source of care for 75% of the population. Therefore, a saturation of the system was foreseen with the continuous increase of cases. The use of Artificial Intelligence (AI) to empower telehealth could help to tackle this by increasing a coordinated patient access to the health system. In the present study we describe a descriptive case report analyzing the use of Laura Digital Emergency Room—an AI-powered telehealth platform—in three different cities. It was computed around 130,000 interactions made by the chatbot and 24,162 patients completed the digital triage. Almost half (44.8%) of the patients were classified as having mild symptoms, 33.6% were classified as moderate and only 14.2% were classified as severe. The implementation of an AI-powered telehealth to increase accessibility while maintaining safety and leveraging value amid the unprecedent impact of the COVID-19 pandemic was feasible in Brazil and may reduce healthcare overload. New efforts to yield sustainability of affordable and scalable solutions are needed to truly leverage value in health care systems, particularly in the context of middle-low-income countries.

Artificial Intelligence Applications in Health Care Practice: Scoping Review

“…The greatest number of AI systems were implemented either in hospital-wide settings (6/45, 13%) [ 50 , 55 , 56 , 65 , 74 , 80 ] or in radiology (6/45, 13%) [ 53 , 56 , 66 , 68 , 73 , 76 ]. Most (27/45, 60%) of the studies were authored by a multidisciplinary team [ 46 , 47 , 50 - 55 , 58 , 59 , 61 , 62 , 64 , 67 , 69 , 70 , 72 , 74 , 75 , 78 - 80 , 82 , 86 - 89 ], with clinical and IT or informatics backgrounds being the most common combination (9/27, 33%) [ 47 , 50 , 55 , 61 , 70 , 74 , 79 , 87 , 89 ]. Among studies with authors from only 1 domain, the most common background was clinical (8/45, 18%) [ 63 , 65 , 66 , 68 , 71 , 73 , 76 , 84 ].…”

“…The most common AI model was a symbolic or knowledge-based model, reported in nearly half (22/45, 49%) of the reviewed studies [ 48 , 52 - 54 , 57 , 59 , 68 - 74 , 77 - 80 , 84 , 85 , 88 ], followed by statistical models (9/45, 20%) [ 45 , 49 - 51 , 58 , 81 , 82 ]. The most commonly performed task was recognition (16/45, 36%) [ 52 , 56 , 61 , 63 - 66 , 72 , 73 , 76 , 78 - 80 , 84 , 85 ], followed by forecasting (9/45, 20%) [ 45 , 46 , 49 - 51 , 53 , 54 , 57 , 71 ]. Other tasks performed were event detection, goal-driven optimization, interaction support, and personalization ( Table 2 , Multimedia Appendices 2 and 3 ).…”

“…Other tasks performed were event detection, goal-driven optimization, interaction support, and personalization ( Table 2 , Multimedia Appendices 2 and 3 ). Although more than half (24/45, 53%) of the AI applications had no action autonomy [ 46 , 48 - 51 , 53 , 54 , 57 , 63 , 66 , 67 , 70 , 73 - 75 , 79 , 81 - 85 , 87 - 89 ], a few reported applications had low (2/21, 10%) [ 55 , 72 ], medium (4/21, 19%) [ 58 , 69 , 71 , 86 ], or high (6/21, 29%) [ 52 , 55 , 60 , 61 , 68 , 76 ] action autonomy ( Table 2 , Multimedia Appendices 2 and 3 ). Nearly three-quarters of all AI systems were intended for clinical care (33/45, 73%) [ 46 , 49 , 51 , 53 - 59 , 61 , 63 - 73 , 78 - 80 , 84 - 89 ], and the majority (18/33, 55%) of these concerned providing support to inform the patient-provider encounter [ 46 , 49 , 51 , 55 , 56 , 61 , 63 , 65 , 67 , 68 , 74 , 78 , …”

“…59,61,62,64,67,69,70,72,74,75,[78][79][80]82,[86][87][88][89], with clinical and IT or informatics backgrounds being the most common combination (9/27, 33%)[47,50,55,61,70,74,79,87,89]. Among studies with authors from only 1 domain, the most common background was clinical (8/45, 18%)[63,65,66,68,71,73,76,84].…”

How Far Can Conversational Agents Contribute to IBD Patient Health Care—A Review of the Literature

“…The application of two filters resulted as follows: first, 22 articles were published in 2020; second, and after selecting health topic as a domain area, 11 articles emerged as a final result. In the end, this material was spread across these different Frontier Journals categories: digital health ( N = 7) ( 20 – 26 ); public health ( N = 2) ( 27 , 28 ); and psychiatry ( N = 2) ( 29 , 30 ). All 11 titles were analyzed through a double review discussion.…”