Although deep learning algorithms show increasing promise for disease diagnosis, their use with rapid diagnostic tests performed in the field has not been extensively tested. Here we use deep learning to classify images of rapid human immunodeficiency virus (HIV) tests acquired in rural South Africa. Using newly developed image capture protocols with the Samsung SM-P585 tablet, 60 fieldworkers routinely collected images of HIV lateral flow tests. From a library of 11,374 images, deep learning algorithms were trained to classify tests as positive or negative. A pilot field study of the algorithms deployed as a mobile application demonstrated high levels of sensitivity (97.8%) and specificity (100%) compared with traditional visual interpretation by humansexperienced nurses and newly trained community health worker staff-and reduced the number of false positives and false negatives. Our findings lay the foundations for a new paradigm of deep learning-enabled diagnostics in low-and middle-income countries, termed REASSURED diagnostics 1 , an acronym for real-time connectivity, ease of specimen collection, affordable, sensitive, specific, user-friendly, rapid, equipment-free and deliverable. Such diagnostics have the potential to provide a platform for workforce training, quality assurance, decision support and mobile connectivity to inform disease control strategies, strengthen healthcare system efficiency and improve patient outcomes and outbreak management in emerging infections.Rapid diagnostic tests (RDTs) save lives by informing case management, treatment, screening, disease control and elimination programs 1 . Lateral flow tests are among the most common RDTs, and hundreds of millions of these tests are performed worldwide each year. They have the potential to support near-person testing and decentralized management of a range of clinically important diseases (including malaria, HIV, syphilis, tuberculosis, influenza and noncommunicable diseases 2 ), making it convenient for the end user and more affordable for health systems 3 . However, RDTs also present some issues, namely: errors in performing the test and interpreting the result 4,5 , quality control and lack of electronic data capture records of the test and results within health systems and surveillance. Many of these would be overcome with the real-time connectivity associated with REASSURED-the new criterion for an ideal test to reflect the importance of digital connectivity, coined by Peeling and coworkers 1 . Real-time connectivity involves the use of mobile-phone-connected RDTs. To date there have been few peer-reviewed studies or evaluations of the effectiveness of connected lateral flow tests at scale in populations in low-and middle-income countries.
Uptake of HIV testing remains low among men in South Africa. As part of a trial, we assessed the acceptability of a theoretically derived and adapted tablet-based-application (EPIC-HIV1) in rural South Africa. We conducted 20 in-depth interviews with men aged ≥18 years and offered a tablet-based survey to all men aged ≥15 years who received EPIC-HIV1 (Sep-Dec 2018). We conducted a descriptive analysis of the survey and used Self-Determination Theory (SDT) to guide our thematic analysis. A total of 232/307 (75%) completed the survey, 55% of whom were aged 15-24 years. 96%[ CI: 92.8-98.2%; n = 223] found EPIC-HIV1 acceptable and 77% [95% CI: 71.8-82.6%; n = 179] found it user-friendly. 222 [96%] reported that EPIC-HIV1 motivated them to test; 83% (192/232) tested for HIV, of which 33% (64/192) were first time testers. Those who did not consent (n = 40) were more likely to have had an HIV-positive test result. Participants reported that the app boosted their confidence to test. However, they were unsure that the app would help them overcome barriers to test in local clinics. Given reach and usability, an adapted SDT male-tailored app was found to be acceptable and could encourage positive health-seeking behavioural change among men.
ObjectivePeer-to-peer (PTP) HIV self-testing (HIVST) distribution models can increase uptake of HIV testing and potentially create demand for HIV treatment and pre-exposure prophylaxis (PrEP). We describe the acceptability and experiences of young women and men participating in a cluster randomised trial of PTP HIVST distribution and antiretroviral/PrEP promotion in rural KwaZulu-Natal.MethodsBetween March and September 2019, 24 pairs of trained peer navigators were randomised to two approaches to distribute HIVST packs (kits+HIV prevention information): incentivised-peer-networks where peer-age friends distributed packs within their social network for a small incentive, or direct distribution where peer navigators distributed HIVST packs directly. Standard-of-care peer navigators distributed information without HIVST kits. For the process evaluation, we conducted semi-structured interviews with purposively sampled young women (n=30) and men (n=15) aged 18–29 years from all arms. Qualitative data were transcribed, translated, coded manually and thematically analysed using an interpretivist approach.ResultsOverall, PTP approaches were acceptable and valued by young people. Participants were comfortable sharing sexual health issues they would not share with adults. Coupled with HIVST, peer (friends) support facilitated HIV testing and solidarity for HIV status disclosure and treatment. However, some young people showed limited interest in other sexual health information provided. Some young people were wary of receiving health information from friends perceived as non-professionals while others avoided sharing personal issues with peer navigators from their community. Referral slips and youth-friendly clinics were facilitators to PrEP uptake. Family disapproval, limited information, daily pills and perceived risks were major barriers to PrEP uptake.ConclusionBoth professional (peer navigators) and social network (friends) approaches were acceptable methods to receive HIVST and sexual health information. Doubts about the professionalism of friends and overly exclusive focus on HIVST information materials may in part explain why HIVST kits, without peer navigators support, did not create demand for PrEP.
who were tested for GC/CT but not empirically treated. Either GC or CT was positive at 90 (14.7%) visits. Median age and race/ethnicity did not differ between the groups. Mean and median time to treatment for GC/CT decreased from 6 and 4 days prior to implementing GeneXpert™, to 1.7 and 0 days for those tested with the POC test (p<0.001). Conclusion Prevalence of GC and CT was high among asymptomatic patients on PrEP. The introduction of POC testing decreases time to treatment, reducing duration of infectivity and potentially preventing ongoing transmissions. Disclosure No significant relationships.
No abstract
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.