SMS-based smartphone application for disease surveillance has doubled completeness and timeliness in a limited-resource setting – evaluation of a 15-week pilot program in Central African Republic (CAR)
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
It is a challenge in low-resource settings to ensure the availability of complete, timely disease surveillance information. Smartphone applications (apps) have the potential to enhance surveillance data transmission. The Central African Republic (CAR) Ministry of Health and Médecins Sans Frontières (MSF) conducted a 15-week pilot project to test a disease surveillance app, Argus, for 20 conditions in 21 health centers in Mambéré Kadéi district (MK 2016). Results were compared to the usual paper-based surveillance in MK the year prior (MK 2015) and simultaneously in an adjacent health district, Nana-Mambére (NM 2016). Wilcoxon rank sum and Kaplan-Meier analyses compared report completeness and timeliness; the cost of the app, and users’ perceptions of its usability were assessed. Two hundred seventy-one weekly reports sent by app identified 3403 cases and 63 deaths; 15 alerts identified 28 cases and 4 deaths. Median completeness (IQR) for MK 2016, 81% (81–86%), was significantly higher than in MK 2015 (31% (24–36%)), and NM 2016 (52% (48–57)) (p < 0.01). Median timeliness (IQR) for MK 2016, 50% (39–57%) was also higher than in MK 2015, 19% (19–24%), and NM 2016 29% (24–36%) (p < 0.01). Kaplan-Meier Survival Analysis showed a significant progressive reduction in the time taken to transmit reports over the 15-week period (p < 0.01). Users ranked the app’s usability as greater than 4/5 on all dimensions. The total cost of the 15-week pilot project was US$40,575. It is estimated that to maintain the app in the 21 health facilities of MK will cost approximately US$18,800 in communication fees per year. The app-based data transmission system more than doubled the completeness and timeliness of disease surveillance reports. This simple, low-cost intervention may permit the early detection of disease outbreaks in similar low-resource settings elsewhere.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it