Clinical informatics, decision support for health professionals, electronic health records, and ehealth infrastructures.

Background: No treatment for COVID-19 is yet available; therefore, providing access to information about SARS-CoV-2, the transmission route of the virus, and ways to prevent the spread of infection is a critical sanitary measure worldwide. Serious games have advantages in the dissemination of reliable information during the pandemic; they can provide qualified content while offering interactivity to the user, and they have great reach over the internet. Objective: This study aimed to develop a serious game with the purpose of providing science-based information on the prevention of COVID-19 and personal care during the pandemic while assessing players’ knowledge about COVID-19–related topics. Methods: The study was conducted with the interdisciplinary collaboration of specialists in health sciences, computing, and design at the Federal University of Minas Gerais, Brazil. The health recommendations were grouped into six thematic blocks, presented in a quiz format. The software languages were based on the progressive web app development methodology with the Ionic framework, JavaScript, HTML5, cascading style sheets, and TypeScript (Angular). Open data reports of how users interact with the serious game were obtained using the Google Analytics application programming interface. The visual identity, logo, infographics, and icons were carefully developed by considering a selection of colors, typography, sounds, and images that are suitable for young audiences. Cards with cartoon characters were introduced at the end of each thematic topic to interact with the player, reinforcing their correct answers or alerting them to the need to learn more about the disease. The players’ performance was assessed by the rate of incorrect and correct answers and analyzed by linear correlation coefficient over 7 weeks. The agile SCRUM development methodology enabled quick and daily interactions of developers through a webchat and sequential team meetings. Results: The game “COVID-19–Did You Know?” was made available for free on a public university website on April 1, 2020. The game had been accessed 17,571 times as of September 2020. Dissemination actions such as reports on social media and television showed a temporal correspondence with the access number. The players’ error rate in the topic “Mask” showed a negative trend (r=–.83; P=.01) over the weeks of follow-up. The other topics showed no significant trend over the weeks. Conclusions: The gamification strategy for health education content on the theme of COVID-19 reached a young audience, which is considered to be a priority in the strategy of orientation toward social distancing. Specific educational reinforcement measures were proposed and implemented based on the players’ performance. The improvement in the users’ performance on the topic about the use of masks may reflect an increase in information about or adherence to mask use over time.

Objective: Medication adherence involves patients correctly taking medications as prescribed. This review evaluates whether artificial intelligence (AI) based tools contribute to adherence-related insights or avoid medication intake errors.Methods: We assessed studies employing AI tools to directly benefit patient medication use, promoting adherence or avoiding self-administration error outcomes. The search strategy was conducted on six databases in August 2024. ROB2 and ROBINS1 assessed the risk of bias.Results: The review gathered seven eligible studies, including patients from three clinical trials and one prospective cohort. The overall risk of bias was moderate to high. Three reports drew on conceptual frameworks with simulated testing. The evidence identified was scarce considering measurable outcomes. However, based on randomized clinical trials, AI-based tools improved medication adherence ranging from 6.7% to 32.7% compared to any intervention controls and current practices, respectively. Digital intervention using video and voice interaction providing real-time monitoring pointed to AI's potential to alert to self-medication errors. Based on conceptual framework reports, we highlight the potential of cognitive behavioral approaches tailored to engage patients in their treatment.Conclusion: Even though the present evidence is weak, smart systems using AI tools are promising in helping patients use prescribed medications. The review offers insights for future research.Systematic review registration: https://www.crd.york.ac.uk/PROSPERO/view/CRD42024571504, identifier: CRD42024571504.

Background: The potential of chatbots for screening and monitoring COVID-19 was envisioned since the outbreak of the disease. Chatbots can help disseminate up-to-date and trustworthy information, promote healthy social behavior, and support the provision of health care services safely and at scale. In this scenario and in view of its far-reaching postpandemic impact, it is important to evaluate user experience with this kind of application. Objective: We aimed to evaluate the quality of user experience with a COVID-19 chatbot designed by a large telehealth service in Brazil, focusing on the usability of real users and the exploration of strengths and shortcomings of the chatbot, as revealed in reports by participants in simulated scenarios. Methods: We examined a chatbot developed by a multidisciplinary team and used it as a component within the workflow of a local public health care service. The chatbot had 2 core functionalities: assisting web-based screening of COVID-19 symptom severity and providing evidence-based information to the population. From October 2020 to January 2021, we conducted a mixed methods approach and performed a 2-fold evaluation of user experience with our chatbot by following 2 methods: a posttask usability Likert-scale survey presented to all users after concluding their interaction with the bot and an interview with volunteer participants who engaged in a simulated interaction with the bot guided by the interviewer. Results: Usability assessment with 63 users revealed very good scores for chatbot usefulness (4.57), likelihood of being recommended (4.48), ease of use (4.44), and user satisfaction (4.38). Interviews with 15 volunteers provided insights into the strengths and shortcomings of our bot. Comments on the positive aspects and problems reported by users were analyzed in terms of recurrent themes. We identified 6 positive aspects and 15 issues organized in 2 categories: usability of the chatbot and health support offered by it, the former referring to usability of the chatbot and how users can interact with it and the latter referring to the chatbot’s goal in supporting people during the pandemic through the screening process and education to users through informative content. We found 6 themes accounting for what people liked most about our chatbot and why they found it useful—3 themes pertaining to the usability domain and 3 themes regarding health support. Our findings also identified 15 types of problems producing a negative impact on users—10 of them related to the usability of the chatbot and 5 related to the health support it provides. Conclusions: Our results indicate that users had an overall positive experience with the chatbot and found the health support relevant. Nonetheless, qualitative evaluation of the chatbot indicated challenges and directions to be pursued in improving not only our COVID-19 chatbot but also health chatbots in general.

Neurological findings in preeclampsia fulfill diagnostic criteria of posterior reversible encephalopathy syndrome (PRES), which is related to cerebral autoregulation impairment associated with high blood pressure. In preeclampsia, PRES may occur without a significant increase in blood pressure. Our aim was to investigate the association between ophthalmic artery resistive index (OARI) and clinical evidence of PRES, defined as the presence of headache and blurred vision, in patients with severe preeclampsia. OARI and main clinical and laboratory parameters were obtained in 112 patients with severe preeclampsia. Differences in these parameters were analyzed in the function of clinical evidence of PRES with a 2-sample t test. The area under receiver operating characteristic curve for each of these parameters in the function of clinical evidence of PRES was obtained. Logistic regression models were established with parameters categorized by cutoff points obtained in receiver operating characteristic curves. Among 112 patients with severe preeclampsia, 46 (41%) presented clinical evidence of PRES. These patients presented lower OARI ( P <0.0001), higher mean blood pressure at admission ( P <0.0001), higher mean blood pressure elevation after the first trimester ( P <0.0001), and higher lactate dehydrogenase ( P <0.0001) than those without clinical evidence of PRES. OARI presented an area under receiver operating characteristic curve of 0.810±0.039 (95% CI: 0.742 to 0.895; P <0.0001). OARI <0.56 was associated with clinical evidence of PRES, with an odds ratio of 12.67 (95% CI: 4.08 to 39.39; P <0.0001). Data suggest that OARI is a relevant biomarker of PRES in severe preeclampsia.