The Implementation of a GPS-Based Location-Tracking Smartphone App in South Africa to Improve Engagement in HIV Care: Randomized Controlled Trial
Bibliographic record
Abstract
BACKGROUND: Mobile health interventions are common in public health settings in Africa, and our preliminary work showed that smartphones are increasing in South Africa. We developed a novel smartphone app-CareConekta-that used GPS location data to characterize personal mobility to improve engagement in HIV care among pregnant and postpartum women living with HIV in South Africa. The app also used the user's location to map nearby clinics. OBJECTIVE: We aimed to describe the feasibility, acceptability, and initial efficacy of using the app in a real-world setting. METHODS: We conducted a prospective randomized controlled trial at a public sector clinic near Cape Town, South Africa. We enrolled 200 pregnant (third trimester) women living with HIV who owned a smartphone that met the required specifications. All participants installed the app, designed to collect 2 GPS heartbeats per day to geolocate the participant within a random 1-km fuzzy radius (for privacy). We randomized (1:1) participants to a control arm to receive the app with no additional support or an intervention arm to receive supportive phone calls, WhatsApp (Meta Platforms, Inc) messages, or both from the study team when traveling >50 km from the study area for >7 days. In addition to mobility data collected daily through the phone, participants completed questionnaires at enrollment and follow-up (approximately 6 months post partum). RESULTS: A total of 7 participants were withdrawn at enrollment or shortly after because of app installation failure (6/200, 3%) or changing to an unsuitable phone (1/200, 0.50%). During the study period, no participant's smartphone recorded at least 1 heartbeat per day, which was our primary feasibility measure. Of the 171 participants who completed follow-up, only half (91/171, 53.2%) reported using the same phone as that used at enrollment, with the CareConekta app still installed on the phone and GPS usually enabled. The top reasons reported for the lack of heartbeat data were not having mobile data, uninstalling the app, and no longer having a smartphone. Acceptability measures were positive, but participants at follow-up demonstrated a lack of understanding of the app's purpose and function. The clinic finder was a popular feature. Owing to the lack of consistent GPS heartbeats throughout the study, we were unable to assess the efficacy of the intervention. CONCLUSIONS: Several key challenges impeded our study feasibility. Although the app was designed to reverse bill participants for any data use, the lack of mobile data was a substantial barrier to our study success. Participants reported purchasing WhatsApp data, which could not support the app. Problems with the web-based dashboard meant that we could not consistently monitor mobility. Our study provides important lessons about implementing an ambitious GPS-based study under real-world conditions in a limited-resource setting. TRIAL REGISTRATION: ClinicalTrials.gov NCT03836625; https://clinicaltrials.gov/ct2/show/NCT03836625. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.1186/s13063-020-4190-x.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.007 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.004 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.012 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".