Spatio-temporal risk prediction of leptospirosis: A machine-learning-based approach
PLOS Neglected Tropical Diseases·
- DOI
- 10.1371/journal.pntd.0012755
- PMID
- 39820517
- PMCID
- PMC11737754
- OpenAlex
- W4406457893
- Study type
- Journal article
- Publisher
- Public Library of Science (PLoS)
- Article type
- journal-article
- Integrity
- current
Why this research matters now
Recognizing climatic and geographical correlates of disease distribution supports strategic policy formulation and resource deployment in vulnerable tropical communities.
Structured evidence summary
Research question
How can computational modeling integrate environmental and demographic variables to generate accurate spatio-temporal risk maps for leptospirosis?
Study design
An observational modeling study applying machine learning algorithms to historical incidence data combined with meteorological, topographic, and socio-demographic covariates across an eleven-year timeframe.
Population and setting
A national-scale analysis covering tropical and subtropical zones, with sub-city spatial resolution and monthly temporal granularity, emphasizing Pacific island contexts.
Main findings
The predictive algorithm demonstrated high concordance and sensitivity in forecasting contamination risk. Results linked El Niño Southern Oscillation cycles to seasonal variations, while delayed precipitation and moisture levels correlated with elevated risk. Organic-dense soil compositions appeared associated with reduced bacterial survival.
Public-health relevance
Recognizing climatic and geographical correlates of disease distribution supports strategic policy formulation and resource deployment in vulnerable tropical communities.
Important limitations
This summary depends entirely on the provided abstract and bibliographic metadata, requiring access to the complete manuscript for comprehensive methodological appraisal and decision-grade interpretation.
GIDS interpretation
The publication offers contextual insights into environmental predictors and computational forecasting methods relevant to leptospirosis tracking frameworks. It does not reflect ongoing monitoring operations or validate current outbreak metrics.
Related GIDS surveillance
Literature context does not validate, explain, or change a surveillance signal. Exact and contextual relationships are shown separately.
Evidence relationships
This article has 8 auditable classifier relationships to diseases, places, topics, and study design.