@article{fdi:010092704,
  title = {{I}ncreasing the resolution of malaria early warning systems for use by local health actors},
  author = {{E}vans, {M}. {V}. and {I}hantamalala, {F}. {A}. and {R}andriamihaja, {M}. and {H}erbreteau, {V}incent and {R}{\'e}villion, {C}. and {C}atry, {T}hibault and {D}ela{\^i}tre, {E}ric and {B}onds, {M}. {H}. and {R}oche, {B}enjamin and {M}itsinjoniala, {E}. and {R}alaivavikoa, {F}. {A}. and {R}azafinjato, {B}. and {R}aobela, {O}. and {G}architorena, {A}ndres},
  editor = {},
  language = {{ENG}},
  abstract = {{B}ackground {T}he increasing availability of electronic health system data and remotely-sensed environmental variables has led to the emergence of statistical models capable of producing malaria forecasts. {M}any of these models have been operationalized into malaria early warning systems ({MEWS}s), which provide predictions of malaria dynamics several months in advance at national and regional levels. {H}owever, {MEWS}s rarely produce predictions at the village-level, the operational scale of community health systems and the first point of contact for the majority of rural populations in malaria-endemic countries. {M}ethods {T}his study developed a hyper-local {MEWS} for use within a health-system strengthening intervention in rural {M}adagascar. {I}t combined bias-corrected, village-level case notification data with remotely sensed environmental variables at spatial scales as fine as a 10 m resolution. {A} spatio-temporal hierarchical generalized linear regression model was trained on monthly malaria case data from 195 communities from 2017 to 2020 and evaluated via cross-validation. {T}he model was then integrated into an automated workflow with environmental data updated monthly to create a continuously updating {MEWS} capable of predicting malaria cases up to three months in advance at the village-level. {P}redictions were transformed into indicators relevant to health system actors by estimating the quantities of medical supplies required at each health clinic and the number of cases remaining untreated at the community level.{R}esults{T}he statistical model was able to accurately reproduce village-level case data, performing nearly five times as well as a null model during cross-validation. {T}he dynamic environmental variables, particularly those associated with standing water and rice field dynamics, were strongly associated with malaria incidence, allowing the model to accurately predict future incidence rates. {T}he {MEWS} represented an improvement of over 50% compared to existing stock order quantification methods when applied retrospectively. {C}onclusion {T}his study demonstrates the feasibility of developing an automatic, hyper-local {MEWS} leveraging remotely-sensed environmental data at fine spatial scales. {A}s health system data become increasingly digitized, this method can be easily applied to other regions and be updated with near real-time health data to further increase performance.},
  keywords = {{M}alaria ; {D}isease forecasting ; {C}limate ; {D}igital health ; {P}recision public ; health ; {MADAGASCAR}},
  booktitle = {},
  journal = {{M}alaria {J}ournal},
  volume = {24},
  numero = {1},
  pages = {30 [18 p.]},
  year = {2025},
  DOI = {10.1186/s12936-025-05266-0},
  URL = {https://www.documentation.ird.fr/hor/fdi:010092704},
}