Loading
Data Driven Disease Surveillance · Journal article
Journal of Applied Data Sciences · August 28, 2026
Early or partial results. Treat as a signal, not a conclusion.
This is a retrospective machine-learning study applying Bi-LSTM with GIS to forecast monthly malaria incidence across Indonesian provinces using 2014–2025 data. The model achieved high numerical performance (RMSE 0.0522, sMAPE 18.39%, R² 0.9553) in cross-validation, but lacks prospective validation, clinical outcome measurement, or demonstration that forecasts improve public health action. The work is methodologically sound as a prediction framework proof-of-concept but does not yet constitute evidence that the system changes malaria control practice or outcomes.
Retrospective observational prediction modelling study. 12 endemic provinces in eastern Indonesia; monthly malaria incidence data integrated with climate variables, population, and spatial data; no individual patient enrollment.. Intervention: Bi-LSTM model for spatiotemporal malaria incidence forecasting, integrated with GIS mapping and SHAP explainability.. Compared with: Naive Forecasting, SARIMA, and Simple LSTM baseline models.. 12 endemic provinces in Indonesia, including Papua and West Papua..
Bi-LSTM model RMSE of 0.0522, sMAPE of 18.39%, and R² of 0.9553 on global performance assessment. Performance declined in West Nusa Tenggara due to near-zero incidence rates, indicating regional variability. SHAP analysis identified historical malaria incidence as the primary predictor and rainfall as the most significant climatic variable.
No measurement of clinical outcomes, intervention uptake, or actual reduction in malaria cases or mortality.
This model may support province-level epidemiological forecasting and resource allocation, but prospective validation against actual malaria cases and demonstration that forecasts guide and improve intervention decisions are needed before adoption in clinical or public health practice.
A machine-learning forecasting model study with no clinical validation, prospective outcome data, or comparison to actual public health decision-making; presents a methodological proof-of-concept for malaria prediction in Indonesia.
As stated by the source record.
Quoted from the source exactly as published.
This model may support province-level epidemiological forecasting and resource allocation, but prospective validation against actual malaria cases and demonstration that forecasts guide and improve intervention decisions are needed before adoption in clinical or public health practice.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
Malaria continues to be a major public health challenge in Indonesia, particularly in eastern provinces where transmission patterns are influenced by climatic variability, geographical heterogeneity, and historical incidence trends. This study proposes an integrated spatio-temporal malaria forecasting and early warning framework by combining Bidirectional Long Short-Term Memory (Bi-LSTM), Geographic Information Systems (GIS), and SHapley Additive exPlanations (SHAP). Monthly malaria incidence, climate variables, population data, and provincial spatial data from 12 endemic provinces in Indonesia during 2014–2025 were used. The data were preprocessed through incidence-rate conversion, outlier handling, log transformation, Min-Max normalization, and six-month sliding window segmentation. The proposed Bi-LSTM model was assesed using RMSE, sMAPE, and R², and compared againts Naive Forecasting, SARIMA, and Simple LSTM baselines. The model attained optimol global performance, with an RMSE of 0.0522, sMAPE of 18.39%, and R² of 0.9553. The provincial analysis shows good performance throughout most regions, including high-burden areas like Papua and West Papua, however a decline in relative accuracy was observed in West Nusa Tenggara due to near-zero incidence rates. SHAP analysis revealed that historical malaria incidence was the primary predictor, whereas rainfall emerged as the most significant climatic variable. GIS-based forecasting showed spatial patterns aligned with malaria epidemiology in Indonesia, with Papua exhibiting the gratest predicted incidence in December 2025. These findings demonstrate that the Bi-LSTM–GIS–SHAP framework can support malaria endemicity mapping, interpretable forecasting, and province-level early warning for targeted public health interventions.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.