Specialized AI Models for Predicting Dengue Disease

[Short version]

Raphael Saldanha et al.

Inria & LNCC

Context

  • Raphael SALDANHA: Degrees on Geography, Statistics, Public Health and Health Information
  • Postdoc call from International Relations Department of Inria. Duration of 24 months (2023-2024)
  • Supervisors: Prof. Reza Akbarinia (Inria) and Prof. Fabio Porto (LNCC)

Arboviruses

  • Dengue, Zika, Chikungunya, and other arboviruses imposes a significant burden over populations health
  • Endemic vector borne disease (Aedes mosquitoes)
  • Impacts all geographic regions in Brazil, with its continental extension
  • Follow spatial and seasonal trends

Modeling dengue outbreaks

  • Dengue cases as target variable
  • Predictors
    • Temperature, droughts, rainfall, floods, land use, deforestation
    • Living conditions, urban environment
    • Water supply, water rationing
    • Mosquito infestation? Only few and localized data available.

Territory diversity

  • On rainy season, water accumulates on cans, pots and litter present at backyards, junkyards and on the streets.

Harvard-Brazil Collaborative Public Health Field Course Fortaleza, jan. 2016.

Fortaleza, jan. 2016.

Territory diversity

  • On dry season or droughts, water is stored on open drums.
  • The same predictor (ie. rain) may have different signal, in respect to other conditions.

Modeling considerations

  • General models tend to ignore the diversity of the territory
  • Local models are basically restricted, not useful for different regions and dengue transmission regimes
  • A single machine-learning model is not a good option due the Brazilian diversity

Global and subsets models

Consider each square as a municipality

Subsets approach

  • Model 1: global model, with all municipalities data
  • Model 2: subset models
    • Group Brazilian municipalities into clusters
    • Train several ML models for each cluster
    • Compare the accuracy with the global model
  • Predict cases using the model with best accuracy

Workflow

Abbreviated version

flowchart LR
A[All data] --> G[Global Model]
A --> C(Clustering)
C --> K1[Model Cluster 1]
C --> K2[Model Cluster 1]
C --> Kn[Model Cluster n]
G --> P1[Predictions]
K1 --> P2[Predictions]
K2 --> P2
Kn --> P2
P1 --> AC[Accuracy comparison]
P2 --> AC

Key decisions

  • How to cluster municipalities based on time series data?

    • Outcome (dengue cases)

    • Predictors

  • What are the best predictors for forecast?

    • Choice of lags and rolling windows

  • What are the best ML algorithms to forecast dengue cases?

Expected results

  • More precise predictions for regions
  • Less dependency on specific data availability for each municipality
  • Provide health managers with tools, predictions and scenarios adequate to different scales of health surveillance, preparedness and field action
  • Contribute to public health policies formulation and implementation