Analyzing Satellite Imagery to Target Tuberculosis Control Interventions in Densely Urbanized Areas of Kigali, Rwanda: Cross-Sectional Pilot Study
Bibliographic record
Abstract
Background: Early diagnosis and treatment initiation for tuberculosis (TB) not only improve individual patient outcomes but also reduce circulation within communities. Active case-finding (ACF), a cornerstone of TB control programs, aims to achieve this by targeting symptom screening and laboratory testing for individuals at high risk of infection. However, its efficiency is dependent on the ability to accurately identify such high-risk individuals and communities. The socioeconomic determinants of TB include difficulties in accessing health care and high within-household contact rates. These two determinants are common in the poorest neighborhoods of many sub-Saharan cities, where household crowding and lack of health-care access often coincide with malnutrition and HIV infection, further contributing to the TB burden. Objective: In this study, we propose a new approach to enhance the efficacy of ACF with focused interventions that target subpopulations at high risk. In particular, we focus on densely inhabited urban areas, where the proximity of individuals represents a proxy for poorer neighborhoods with enhanced contact rates. Methods: To this end, we used satellite imagery of the city of Kigali, Rwanda, and computer-vision algorithms to identify areas with a high density of small residential buildings. We subsequently screened 10,423 people living in these areas for TB exposure and symptoms and referred patients with a higher risk score for polymerase chain reaction testing. Results: We found autocorrelation in questionnaire scores for adjacent areas up to 782 meters. We removed the effects of this autocorrelation by aggregating the results based on H3 hexagons with a long diagonal of 1062 meters. Out of 324 people with high questionnaire scores, 202 underwent polymerase chain reaction testing, and 9 people had positive test results. We observed a weak but statistically significant correlation (r=0.28; P=.04) between the mean questionnaire score and the mean urban density of each hexagonal area. Conclusions: Nine previously undiagnosed individuals had positive test results through this screening program. This limited number may be due to low TB incidence in Kigali, Rwanda, during the study period. However, our results suggest that analyzing satellite imagery may allow the identification of urban areas where inhabitants are at higher risk of TB. These findings could be used to efficiently guide targeted ACF interventions.
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 | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".