The approach with the Prevalence Project is to encourage collaboration and not restrict ideas, technologies, or approaches. We want to develop an infrastructure that can be used to improve the way that prevalence is reported and used. The infrastructure is an open accessible repository where prevalence information can be accessed through a variety of technologies.
Potential collaborative research projects:
Quality Assessment
- Validation of automated methods for extracting information from the literature
- Validation of automated methods for automatically deriving prevalence information
Economics
- Economic evaluation of what academic prevalence reporting is costing
- How is prevalence information actually used by healthcare organizations, non government organizations and government institutions.
- How much prevalence information is not reported
- How up to date is prevalence information
Natural Language Processing
- Section boundary of abstracts (background vs results)
- Sentence extraction of prevalence information
- Sentiment analysis
Information Management and Information Technology
- Data storage and formatting of information (Relational Database, Graph Database)
- Technologies for information exchange (XML, JSON, CSV)
- Data Linkage with World Bank API, WHO Global Health Observatory
Ontologies
- Determine a multi-level disease ontology that all prevalence information could fit into
Visualization
- Geographical reporting of prevalence information using touch interfaces
- Display Multi-level geographical data (city-level, province-level)
- Display temporal information
Simulation
- Simulation models for using this prevalence information for population modeling
How to cite the Prevalence Project:
[to be determined]