Technological solutions for an effective health surveillance system for road traffic crashes in Burkina Faso
Bibliographic record
Abstract
BACKGROUND: In the early 2000s, electronic surveillance systems began to be developed to collect and transmit data on infectious diseases in low-income countries (LICs) in real-time using mobile technologies. Such surveillance systems, however, are still very rare in Africa. Among the non-infectious epidemics to be surveilled are road traffic injuries, which constitute major health events and are the fifth leading cause of mortality in Africa. This situation also prevails in Burkina Faso, whose capital city, Ouagadougou, is much afflicted by this burden. There is no surveillance system, but there have been occasional surveys, and media reports of fatal crashes are numerous and increasing in frequency. OBJECTIVE: The objective of this article is to present the methodology and implementation of, and quality of results produced by, a prototype of a road traffic crash and trauma surveillance system in the city of Ouagadougou. METHODS: A surveillance system was deployed in partnership with the National Police over a six-month period, from February to July 2015, across the entire city of Ouagadougou. Data were collected by all seven units of the city's National Police road crash intervention service. They were equipped with geotracers that geolocalized the crash sites and sent their positions by SMS (short message service) to a surveillance platform developed using the open-source tool Ushahidi. Descriptive statistical analyses and spatial analyses (kernel density) were subsequently performed on the data collected. RESULTS: The process of data collection by police officers functioned well. Researchers were able to validate the data collection on road crashes by comparing the number of entries in the platform against the number of reports completed by the crash intervention teams. In total, 873 crash scenes were recorded over 3 months. The system was accessible on the Internet for open consultation of the map of crash sites. Crash-concentration analyses were produced that identified 'hot spots' in the city. Nearly 80% of crashes involved two-wheeled vehicles. Crashes were more numerous at night and during rush hours. They occurred primarily at intersections with traffic lights. With regard to health impacts, half of the injured were under the age of 29 years, and 6 persons were killed. CONCLUSIONS: This pilot study demonstrated the feasibility of developing simple surveillance systems, based on mHealth, in LICs.
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 | 0.003 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 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".