2023· International Journal of Applied Data Science & Modern Computing· 0 citations
TL;DR
A comprehensive review of CI models for outbreak prediction, comparing supervised and unsupervised methods such as Support Vector Machines (SVM), Random Forest (RF), Artificial Neural Networks (ANN), Long Short-Term Memory (LSTM), and hybrid models.
Abstract
Disease outbreak prediction has become increasingly important due to the rise of emerging and re-emerging infectious diseases such as COVID-19, Ebola, Zika, Dengue, and Influenza. Traditional epidemiological surveillance systems rely on historical case reports and laboratory confirmations, often resulting in delayed reporting and limited spatial resolution, which hinder timely intervention and preparedness. Computational Intelligence Systems (CIS), including machine learning (ML), deep learning (DL), evolutionary computing, and fuzzy systems, offer improved prediction by identifying complex nonlinear patterns from heterogeneous data sources such as epidemiological, environmental, mobility, and social media data. This paper presents a comprehensive review of CI models for outbreak prediction, comparing supervised and unsupervised methods such as Support Vector Machines (SVM), Random Forest (RF), Artificial Neural Networks (ANN), Long Short-Term Memory (LSTM), and hybrid models. A multi-layered predictive framework is proposed, incorporating data preprocessing, feature engineering, dimensionality reduction, ensemble learning, and performance evaluation. A hybrid LSTM–CNN model is introduced to capture temporal and spatial dependencies in outbreak data. Experimental results demonstrate that CI models outperform traditional statistical approaches like ARIMA and regression models in short- and medium-term forecasting. Evaluation metrics including RMSE, MAPE, Precision, Recall, and F1-score confirm the superior predictive performance and robustness of hybrid models. The study highlights the importance of integrating heterogeneous data and intelligent modeling for smart disease surveillance and supports future research in explainable AI, federated learning, and real-time adaptive prediction systems.
The development and assessment of a machine learning-driven early warning system for infectious disease prediction using geospatial big data from South-Western Nigeria, at the level of Local Government Area outperform conventional surveillance systems in developing countries.
I. Adewumi, N. Bakare, W. Ajayi et al.· London Journal of Physics· 0 citations
While LSTM networks demonstrate promising performance in modeling nonlinear temporal dynamics, the ARIMA model provided the most accurate predictions for the studied dengue dataset, suggesting that while deep learning models are capable of capturing complex temporal patterns, their advantage over well-tuned statistical models is not guaranteed for this dataset.
Tahmid Nowsher, Shaiful Islam Arafat, Md. Kamrujjaman· Discover Public Health· 0 citations
A machine learning-based model for predicting outbreaks, explainability, and spatial risk propagation, validated through a multiyear data set of an epidemiological nature from 12 cities in the Eastern Province of Saudi Arabia (2021–2025).
N. F. Saleem ALAnsary, Mahmood Berekaa, Raghad Alhotheyfa et al.· Frontiers in Public Health· 0 citations
Background: Evaluating outbreak detection models is a key component of syndromic surveillance. However, balancing timeliness, predictive performance, and local surveillance constraints remains a major challenge. We developed and assessed whether stacking ensemble approaches, which integrate multiple outbreak detection methods, can improve the timeliness and predictive performance of influenza-like illness (ILI) surge detection. Methods: We developed a two-stage stacking ensemble framework to detect early warning of ILI surges in city-level Primary Health Care encounter time series from Brazil (2022 to 2025). Epidemic thresholds were defined using the Moving Epidemic Method (MEM). In the first stage, multiple outbreak detection models (ODMs) generated warnings of unusual ILI activity. In the second, these warnings were then used as inputs to three supervised meta-classifiers: Logistic Regression, Extreme Gradient Boosting (XGB), and a Multi-layer Perceptron (MLP). For comparison, a Majority Voting (MV) aggregation is also examined. Timeliness, sensitivity, specificity, positive and negative predictive values are evaluated to measure each model's ability to anticipate epidemic periods of varying intensity in 2025. Robustness was further assessed using simulated outbreak scenarios with varying magnitudes and durations. Findings: We identified 5,765 ILI surge onsets across 5,365 Brazilian municipalities in 2025. Compared with individual ODMs and MV, stacking ensemble meta-classifiers anticipated up to 33% of surge onsets three weeks in advance (an average improvement of 15 percentage points) while reducing missed detections to <10%. They achieved sensitivity >90%, while maintaining balanced specificity >80%, PPV >65%, and NPV >99%. Improvements were greatest for very high-intensity surges, with missed detections reduced by more than half compared with individual ODMs. In simulated outbreak scenarios, the MLP and XGB classifiers remained robust despite being trained on fewer than half of all simulated surge events, consistently outperforming individual detection methods and simpler integration approaches. Interpretation: We provide a practical framework for integrating complementary ODMs into a single, robust early warning decision. By improving both timeliness and predictive performance without requiring additional surveillance data or resources, this approach offers a scalable methodological upgrade for syndromic surveillance systems and supports more reliable public health decision-making. Funding: The Rockefeller Foundation (award 2023 PPI 007 to MB-N); Brazilian National Research Council - CNPq (408775/2024-6); MB-N, PIPR, RFSA are CNPq fellows.
J. F. Oliveira, A. L. Alencar, E. R. Coutinho et al.· medRxiv· 0 citations
Prediction of diseases at the right time and accurately is crucial for improving patients' health conditions and reducing costs of healthcare services. Therefore, machine learning approaches have recently become very popular in predicting diseases in patients. Dengue fever, which is a highly spreading mosquito-born disease caused by the virus, still poses a significant threat to human health in the world. In this paper, a novel dengue prediction approach using the novel Light Gradient Boosting Machine (LightGBM), which is a high-performing decision tree-based ensemble learning method, is introduced. Clinical symptoms, lab tests, and demographic information are considered as features to predict whether a patient has been infected with dengue fever. Experimental results prove that proposed LightGBM model yields better accuracy, precision, recall, and F1-score than traditional machine learning algorithms.
Susmitha A., Rakesh Kumar Pattanaik, S. K. Mohapatra et al.· 2026 International Conferenc...· 0 citations
Infectious disease surveillance is a critical component of global public health systems, enabling the detection, monitoring, and prevention of disease outbreaks. Traditional surveillance methods often rely on manual reporting and laboratory confirmation, which can lead to delays, incomplete data, and limited real-time analysis. In recent years, artificial intelligence (AI) has emerged as a transformative approach to overcoming these limitations by enabling faster, more accurate, and data-driven surveillance systems. This article explores the role of AI in infectious disease surveillance, highlighting its applications in early outbreak detection, real-time monitoring, predictive modeling, genomic surveillance, and digital data analysis. AI technologies such as machine learning, deep learning, and natural language processing allow the analysis of large and diverse datasets from sources including electronic health records, social media, mobile data, and global health databases. These systems have been effectively used in identifying early signals of outbreaks such as COVID-19, tracking disease spread during Ebola, and predicting seasonal influenza trends. Despite these advantages, challenges such as data privacy concerns, algorithmic bias, data quality issues, and infrastructure limitations in developing regions remain significant barriers. Overall, AI holds great potential to enhance global disease surveillance by improving early detection, increasing accuracy, and enabling real-time insights. With proper ethical frameworks and global collaboration, AI can play a vital role in strengthening future public health preparedness and response systems.
Muhammad Naveed Aslam, Hussna Khan· Electronic Journal of Medica...· 0 citations