Use of a health worker-targeted smartphone app to support quality malaria RDT implementation in Busia County, Kenya: A feasibility and acceptability study.

Malaria rapid diagnostic tests (mRDTs) are an essential diagnostic tool in low-resource settings; however, administration and interpretation errors reduce their effectiveness. HealthPulse, a smartphone mRDT reader application, was developed by Audere to aid health workers in mRDT administration and interpretation, with an aim to improve the mRDT testing process and facilitate timely decision making through access to digitized results. Audere partnered with PSI and PS Kenya to conduct a pilot study in Busia County, Kenya between March and September 2021 to assess the feasibility and acceptability of HealthPulse to support malaria parasitological diagnosis by community health volunteers (CHVs) and private clinic health workers (private clinic HWs). Metadata was interpreted to assess adherence to correct use protocols and health worker perceptions of the app. Changes to mRDT implementation knowledge were measured through baseline and endline surveys. The baseline survey identified clear mRDT implementation gaps, such as few health workers correctly knowing the number of diluent drops and minimum and maximum wait times for mRDT interpretation, although health worker knowledge improved after using the app. Endline survey results showed that 99.6% of health workers found the app useful and 90.1% found the app easy to use. Process control data showed that most mRDTs (89.2%) were photographed within the recommended 30-minute time frame and that 91.4% of uploaded photos passed the app filter quality check on the first submission. During 154 encounters (3.5% of all encounters) a health worker dispensed an artemisinin-based combination therapy (ACT) to their patient even with a negative mRDT readout. Overall, study results indicated that HealthPulse holds potential as a mobile tool for use in low-resource settings, with future supportive supervision, diagnostic, and surveillance benefits. Follow-up studies will aim to more deeply understand the utility and acceptance of the HealthPulse app.

Measuring the performance of computer vision artificial intelligence to interpret images of HIV self-testing results.

Introduction: HIV self-testing (HIVST) is highly sensitive and specific, addresses known barriers to HIV testing (such as stigma), and is recommended by the World Health Organization as a testing option for the delivery of HIV pre-exposure prophylaxis (PrEP). Nevertheless, HIVST remains underutilized as a diagnostic tool in community-based, differentiated HIV service delivery models, possibly due to concerns about result misinterpretation, which could lead to inadvertent onward transmission of HIV, delays in antiretroviral therapy (ART) initiation, and incorrect initiation on PrEP. Ensuring that HIVST results are accurately interpreted for correct clinical decisions will be critical to maximizing HIVST's potential. Early evidence from a few small pilot studies suggests that artificial intelligence (AI) computer vision and machine learning could potentially assist with this task. As part of a broader study that task-shifted HIV testing to a new setting and cadre of healthcare provider (pharmaceutical technologists at private pharmacies) in Kenya, we sought to understand how well AI technology performed at interpreting HIVST results. Methods: At 20 private pharmacies in Kisumu, Kenya, we offered free blood-based HIVST to clients ≥18 years purchasing products indicative of sexual activity (e.g., condoms). Trained pharmacy providers assisted clients with HIVST (as needed), photographed the completed HIVST, and uploaded the photo to a web-based platform. In real time, each self-test was interpreted independently by the (1) client and (2) pharmacy provider, with the HIVST images subsequently interpreted by (3) an AI algorithm (trained on lab-captured images of HIVST results) and (4) an expert panel of three HIVST readers. Using the expert panel's determination as the ground truth, we calculated the sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) for HIVST result interpretation for the AI algorithm as well as for pharmacy clients and providers, for comparison. Results: From March to June 2022, we screened 1,691 pharmacy clients and enrolled 1,500 in the study. All clients completed HIVST. Among 854 clients whose HIVST images were of sufficient quality to be interpretable by the AI algorithm, 63% (540/854) were female, median age was 26 years (interquartile range: 22-31), and 39% (335/855) reported casual sexual partners. The expert panel identified 94.9% (808/854) of HIVST images as HIV-negative, 5.1% (44/854) as HIV-positive, and 0.2% (2/854) as indeterminant. The AI algorithm demonstrated perfect sensitivity (100%), perfect NPV (100%), and 98.8% specificity, and 81.5% PPV (81.5%) due to seven false-positive results. By comparison, pharmacy clients and providers demonstrated lower sensitivity (93.2% and 97.7% respectively) and NPV (99.6% and 99.9% respectively) but perfect specificity (100%) and perfect PPV (100%). Conclusions: AI computer vision technology shows promise as a tool for providing additional quality assurance of HIV testing, particularly for catching Type II error (false-negative test interpretations) committed by human end-users. We discuss possible use cases for this technology to support differentiated HIV service delivery and identify areas for future research that is needed to assess the potential impacts-both positive and negative-of deploying this technology in real-world HIV service delivery settings.

Flu@home: the Comparative Accuracy of an At-Home Influenza Rapid Diagnostic Test Using a Prepositioned Test Kit, Mobile App, Mail-in Reference Sample, and Symptom-Based Testing Trigger.

At-home testing with rapid diagnostic tests (RDTs) for respiratory viruses could facilitate early diagnosis, guide patient care, and prevent transmission. Such RDTs are best used near the onset of illness when viral load is highest and clinical action will be most impactful, which may be achieved by at-home testing. We evaluated the diagnostic accuracy of the QuickVue Influenza A+B RDT in an at-home setting. A convenience sample of 5,229 individuals who were engaged with an on-line health research platform were prospectively recruited throughout the United States. "Flu@home" test kits containing a QuickVue RDT and reference sample collection and shipping materials were prepositioned with participants at the beginning of the study. Participants responded to daily symptom surveys. If they reported experiencing cough along with aches, fever, chills, and/or sweats, they used their flu@home kit following instructions on a mobile app and indicated what lines they saw on the RDT. Of the 976 participants who met criteria to use their self-collection kit and completed study procedures, 202 (20.7%) were positive for influenza by qPCR. The RDT had a sensitivity of 28% (95% CI = 21 to 36) and specificity of 99% (98 to 99) for influenza A, and 32% (95% CI = 20 to 46) and 99% (95% CI = 98 to 99), for influenza B. Our results support the concept of app-supported, prepositioned at-home RDT kits using symptom-based triggers, although it cannot be recommended with the RDT used in this study. Further research is needed to determine ways to improve the accuracy and utility of home-based testing for influenza.

Evaluating an app-guided self-test for influenza: lessons learned for improving the feasibility of study designs to evaluate self-tests for respiratory viruses.

BACKGROUND: Seasonal influenza leads to significant morbidity and mortality. Rapid self-tests could improve access to influenza testing in community settings. We aimed to evaluate the diagnostic accuracy of a mobile app-guided influenza rapid self-test for adults with influenza like illness (ILI), and identify optimal methods for conducting accuracy studies for home-based assays for influenza and other respiratory viruses. METHODS: This cross-sectional study recruited adults who self-reported ILI online. Participants downloaded a mobile app, which guided them through two low nasal swab self-samples. Participants tested the index swab using a lateral flow assay. Test accuracy results were compared to the reference swab tested in a research laboratory for influenza A/B using a molecular assay. RESULTS: Analysis included 739 participants, 80% were 25-64 years of age, 79% female, and 73% white. Influenza positivity was 5.9% based on the laboratory reference test. Of those who started their test, 92% reported a self-test result. The sensitivity and specificity of participants' interpretation of the test result compared to the laboratory reference standard were 14% (95%CI 5-28%) and 90% (95%CI 87-92%), respectively. CONCLUSIONS: A mobile app facilitated study procedures to determine the accuracy of a home based test for influenza, however, test sensitivity was low. Recruiting individuals outside clinical settings who self-report ILI symptoms may lead to lower rates of influenza and/or less severe disease. Earlier identification of study subjects within 48 h of symptom onset through inclusion criteria and rapid shipping of tests or pre-positioning tests is needed to allow self-testing earlier in the course of illness, when viral load is higher.