Forecasting Schistosoma haematobium Infections in Mali
Author Information
Author(s): Medina Daniel C., Findley Sally E., Doumbia Seydou
Primary Institution: Columbia University
Hypothesis
Can a state-space forecasting model accurately predict the incidence of Schistosoma haematobium in Niono, Mali?
Conclusion
The state-space forecasting model provided reasonably accurate predictions for Schistosoma haematobium infections in Niono, Mali.
Supporting Evidence
- Schistosoma haematobium is endemic in the Sahel region, affecting over 200 million people.
- The forecasting model achieved a mean absolute percentage error of approximately 25%.
- Inter-annual fluctuations in disease incidence were captured effectively by the model.
Takeaway
This study shows how scientists can use past data to predict future cases of a disease, helping doctors and health workers prepare better.
Methodology
The study used a longitudinal retrospective analysis of Schistosoma haematobium consultation rates from 1996 to 2004, applying exponential smoothing methods within a state-space framework.
Potential Biases
Potential bias from missing consultation records, although the distribution of missing data was random.
Limitations
The study faced limitations due to missing data and the complexity of environmental factors affecting disease transmission.
Participant Demographics
The study included a projected population of 278,741 individuals in the district of Niono, Mali.
Statistical Information
P-Value
0.05
Confidence Interval
95%
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website