Accuracy of Computer-Aided Detection of Occupational Lung Disease: Silicosis and Pulmonary Tuberculosis in Ex-Miners from the South African Gold Mines.

BACKGROUND: Computer-aided detection (CAD) of pulmonary tuberculosis (TB) and silicosis among ex-miners from the South African gold mines has the potential to ease the backlog of lung examinations in clinical screening and medical adjudication for miners' compensation. This study aimed to determine whether CAD systems developed to date primarily for TB were able to identify TB (without distinction between prior and active disease) and silicosis (or "other abnormality") in this population. METHODS: A total of 501 chest X-rays (CXRs) from a screening programme were submitted to two commercial CAD systems for detection of "any abnormality", TB (any) and silicosis. The outcomes were tested against the readings of occupational medicine specialists with experience in reading miners' CXRs. Accuracy of CAD against the readers was calculated as the area under the curve (AUC) of the receiver operating characteristic (ROC) curve. Sensitivity and specificity were derived using a threshold requiring at least 90% sensitivity. RESULTS: One system was able to detect silicosis and/or TB with high AUCs (>0.85) against both readers, and specificity > 70% in most of the comparisons. The other system was able to detect "any abnormality" and TB with high AUCs, but with specificity < 70%. CONCLUSION: CAD systems have the potential to come close to expert readers in the identification of TB and silicosis in this population. The findings underscore the need for CAD systems to be developed and validated in specific use-case settings.

CareConekta: study protocol for a randomized controlled trial of a mobile health intervention to improve engagement in postpartum HIV care in South Africa.

BACKGROUND: South Africa is home to the world's largest antiretroviral therapy program but sustaining engagement along the HIV care continuum has proven challenging in the country and throughout the wider region. Population mobility is common in South Africa, but there are important research gaps in describing this mobility and its impact on engagement in HIV care. Postpartum women and their infants in South Africa are known to be at high risk of dropping out of HIV care after delivery and are frequently mobile. METHODS: In 2017, we developed a beta version of a smartphone application (app) - CareConekta - that detects a user's smartphone location to allow for prospective characterization of mobility. Now we will adapt and test CareConekta to conduct essential formative work on mobility and evaluate an intervention - the CareConekta app plus text notifications and phone calls and/or WhatsApp messages - to facilitate engagement in HIV care during times of mobility. During the 3-year project period, our first objective is to evaluate the feasibility, acceptability, and initial efficacy of using CareConekta as an intervention to improve engagement in HIV care. Our second objective is to characterize mobility among South African women during the peripartum period and its impact on engagement in HIV care. We will enroll 200 eligible pregnant women living with HIV and receiving care at the Gugulethu Midwife Obstetric Unit in Cape Town, South Africa. DISCUSSION: This work will provide critical information about mobility during the peripartum period and the impact on engagement in HIV care. Simultaneously, we will pilot test an intervention to improve engagement with rigorously assessed outcomes. If successful, CareConekta offers tremendous potential as a research and service tool that can be adapted and evaluated in multiple geographic regions, study contexts, and patient populations. TRIAL REGISTRATION: ClinicalTrials.gov: NCT03836625. Registered on 8 February 2019.