Leveraging Smartphone Mobility Data to Understand HIV Risk Among Rural South African Young Adults: Feasibility Study
Bibliographic record
Abstract
Background: Smartphones provide a precise method to study human mobility at an unprecedented scale, allowing researchers to explore the links between mobility, HIV risk, and treatment outcomes. However, leveraging smartphone technology to study HIV risk in rural settings presents unique challenges and opportunities. Objective: This study assessed the feasibility of using smartphone GPS technology to collect mobility data from young adults in rural KwaZulu Natal, South Africa. We also present key lessons learned during the study. Methods: The study was conducted in 2 phases (June 2021-May 2023) with males and females aged 20-30 years old. In phase I, participants received smartphones with a customized study app (Avicenna research software). In phase II, they used their personal smartphones and installed the study app. The app used Android location services to record the smartphone location every 30 minutes and send it to a secure study server hourly. Participants were followed up for 6 months (26 wk). If location data were missing for 48-72 hours, participants were contacted for troubleshooting. Engagement strategies, including reverse billing and gamification (Wheel of Fortune), were implemented to address internet connection barriers and aid data collection. Results: A total of 207 participants were enrolled (phase I: 163; phase II: 44) with 204 providing mobility data. Participants recorded 27.6 million location points with a median number of 74,865 (IQR 28,471-186,578) per participant. The mean weekly location points recorded was 95.3 out of 336 possible half-hour intervals (28.4%). Phase II saw more stable data collection in the latter half of the study, due to increased user engagement with the app. Challenges included phone-related issues (screen malfunctions, lost and broken phone), app terminations, and limited internet connectivity. Reverse billing and gamification strategies improved location data collection through increased user engagement. Conclusions: This study demonstrates that the use of smartphone-based GPS technology is feasible among young adults in a rural South African setting. Although only 28.4% (95.3/336) of expected weekly location data were collected, the study offers insights into engagement strategies that can be used to enhance location data collection in similar contexts. Continuous troubleshooting identified challenges and informed solutions to data collection gaps. Reverse billing system and gamification resulted in significant increases in location data received. These findings underscore the potential of integrating mobile health tools into health systems to better support high-risk mobile populations.
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 | 0.005 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".