AI app accurately interprets HIV testing in Africa

July 20, 2021 | 2 minutes read

AI app improves HIV test accuracy  in South Africa as scientists suggest that this AI app was successful in identifying 97.8 percent of positive and 100 percent of negative HIV diagnostic test results.

The AI based mobile app was deployed in a pilot field study in KwaZulu-Natal in South Africa. The trained professionals on the other hand predicted 89% of negative tests while 95.6% of positive tests thus showing the superior accuracy of AI technology. The workers working with the AI app  used the mobile app to record their 40 HIV test results and also took the picture of the tests so that it can be read automatically by the machine learning classifier.

Rachel McKendry, the study co-author and a professor of bio medicine and nanotechnology at University College London UK while explaining the efficiency and efficacy of app termed the results as notably more accurate than traditional visual interpretation saying:

“The findings demonstrate the potential of deep learning for accurate classification, whether it’s positive or negative, of rapid diagnostic tests. The overall performance of 98.9 percent accuracy is notably higher than traditional visual interpretation of study participants.”

The study began in 2017 with the sole purpose of developing the low-cost, user-friendly AI fueled  app which can be used as the mobile phone connected diagnostic tool for HIV detection. Another aim was to evaluate the feasibility of introduction of tools to enhance the access to HIV testing and resultant care especially in the resource-limited settings.

The AI app improves HIV test accuracy and is highly beneficial as it can also detect other infectious diseases. As study co-author and director of the Department of Science and Technology-funded South African Population Research Infrastructure Network Kobus Herbst said:

“Although the study focuses on interpretation of HIV tests, this tool could be adapted to interpret results of rapid diagnostic tests for other infectious diseases.”

 

InvoZone
ca flagCanada — Head Office
220 Duncan Mill Road, Toronto, Ontario, Canada M3B 3J5
usa flagUSA
8 The Green Suite # 11684 Dover, DE 19901
my flagMalaysia
Tower A, Level 25, The Vertical, Unit 10, Jalan Kerinchi, Bangsar South, 59200 Kuala Lumpur
pk flagPakistan
605, Block H3, Opposite to Expo Center Gate No 1, Johar Town Lahore