Deep learning of HIV field-based rapid tests

• Published in: Nature medicine Vol. 27; no. 7; pp. 1165 - 1170
• Main Authors: Turbé, Valérian, Herbst, Carina, Mngomezulu, Thobeka, Meshkinfamfard, Sepehr, Dlamini, Nondumiso, Mhlongo, Thembani, Smit, Theresa, Cherepanova, Valeriia, Shimada, Koki, Budd, Jobie, Arsenov, Nestor, Gray, Steven, Pillay, Deenan, Herbst, Kobus, Shahmanesh, Maryam, McKendry, Rachel A.
• Format: Journal Article
• Language: English
• Published: New York Nature Publishing Group US 01.07.2021; Nature Publishing Group
• Subjects: 692/699/255/1901; 706/134; AIDS Serodiagnosis - methods; Algorithms; Applications programs; Biomedical and Life Sciences; Biomedicine; Cancer Research; Deep Learning; Diagnosis; Disease control; Field study; HIV; HIV infection; HIV Infections - diagnosis; Human immunodeficiency virus; Humans; Image acquisition; Image classification; Income; Infectious Diseases; Learning algorithms; Letter; Low income groups; Machine learning; Medical imaging; Medical personnel; Medical tests; Metabolic Diseases; Mobile computing; Molecular Medicine; Neurosciences; Quality assurance; Rural Health Services - organization & administration; Sensitivity and Specificity; South Africa; Technology application; Time and Motion Studies; South Africa; United Kingdom
• ISSN: 1078-8956; 1546-170X
• DOI: 10.1038/s41591-021-01384-9

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 humans—experienced 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. In a pilot field study conducted in rural South Africa, deep learning algorithms can accurately classify rapid HIV tests as positive or negative, highlighting the potential of deep learning–enabled diagnostics for use in low- and middle-income countries.