Malaria, as one of the most serious infectious diseases causing public health problems in the world, affects about two-thirds of the world population, with estimated resultant deaths close to a million annually. The effects of this disease are much more profound in third world countries, which have very limited medical resources. When an intense outbreak occurs, most of these countries cannot cope with the high number of patients due to the lack of medicine, equipment and hospital facilities. The prevention or reduction of the risk factor of this disease is very challenging, especially in third world countries, due to poverty and economic insatiability. Technology can offer alternative solutions by providing early detection mechanisms that help to control the spread of the disease and allow the management of treatment facilities in advance to ensure a more timely health service, which can save thousands of lives. In this study, we have deployed an intelligent malaria outbreak early warning system, which is a mobile application that predicts malaria outbreak based on climatic factors using machine learning algorithms. The system will help hospitals, healthcare providers, and health organizations take precautions in time and utilize their resources in case of emergency. To our best knowledge, the system developed in this paper is the first publicly available application. Since confounding effects of climatic factors have a greater influence on the incidence of malaria, we have also conducted extensive research on exploring a new ecosystem model for the assessment of hidden ecological factors and identified three confounding factors that significantly influence the malaria incidence. Additionally, we deploy a smart healthcare application; this paper also makes a significant contribution by identifying hidden ecological factors of malaria.

Despite global efforts to eradicate malaria, it remains a major health threat to nearly half of the world’s population. Recent statistics show that globally, there are over 200 million malaria cases, and estimated deaths are close to half a million. Africa alone accounts for almost 90% of these cases. Numerous studies have been conducted to understand the transmission dynamics of malaria. Mathematical methods have been widely used to model and understand disease dynamics and outbreak patterns. Although mathematical methods have provided good results for homogeneous populations, they impose significant limitations for investigating certain heterogeneities in a population, such as age and vaccine status. This paper proposes an agent-based modeling approach that permits the capture of heterogeneous mixing and agent interactions, thus enabling a better understanding of malaria dynamics and outbreak patterns. Our approach is illustrated in a case study using climate and demographic data of the cities of Tripura, Limpopo, and Benin. Our agent-based simulation was validated against the reported cases of malaria collected in these cities. Furthermore, the efficiency of the proposed model was compared with the mathematical models used as a benchmark. A statistical test confirmed that the agent-based model is robust and has the potential to accurately predict the peak seasons of malaria. These results can help healthcare providers and policymakers have intervention mechanisms in place in advance, which can potentially help reduce the malaria transmission rate.

Confounding effects of climatic factors temporally contribute to the prevalence of malaria. In this study, we explore a new framework for assessment and identification of hidden ecological factors to the incidence of malaria. A statistical technique, partial least squares path modeling and exploratory factor analysis, is employed to identify hidden ecological factors. Three hidden factors are identified: Factor I is related to minimum temperature and relative humidity, Factor II is related to maximum temperature and solar radiation and Factor III is related to precipitation and wind speed, respectively. Factor I is identified as the most influential hidden ecological factor of malaria incidence in the study area, as evaluated by communality and Dillon-Goldstein’s indices.

Recent statistics of malaria shows that over 200 million cases and estimated deaths of nearly half a million occur globally. Africa alone accounts for almost 90% of the cases. Several studies have been conducted to understand the disease transmission dynamics. In particular, mathematical methods have been frequently used to model and understand the disease dynamics and outbreak patterns. Although, mathematical methods have provided good results for homogeneous populations, these methods impose significant limitations for studying malaria dynamics in heterogeneous populations, a result of various factors, e.g. spatial and temporal fluctuations, social networks, human movements pattern etc. This paper proposes an agent-based modelling approach that permits modelling and analysing malaria dynamics for heterogenous populations. Our approach is illustrated using the climate and demographic data for the Tripura, Limpopo and Benin cities. Our agent-based simulation has been validated against the reported cases of malaria collected in the cities mentioned. Furthermore, the efficiency of the proposed model has been compared with the mathematical model used as benchmark. A statistical test confirms the proposed model is robust and has potential for predicting the peak seasons of malaria. This potentially makes our methods a useful tool as an intervention mechanism, which will have impact on hospitals, healthcare providers, health organisations.

Public awareness of non-clinical COVID-19 preventive measures is critical for effective health communication, strategic planning, and evidence-based decision-making. This study analyzes trends in public interest using Google Trends data on preventive measures such as face mask usage, hand sanitizer use, social distancing, and lockdowns, in relation to COVID-19 case trends. Statistical diagnostics, including correlation matrices, Variance Inflation Factor (VIF), and eigenvalue analysis, were employed to assess multicollinearity. At the same time, Breusch–Pagan, White, and Breusch–Godfrey tests were applied to detect and address heteroscedasticity. The results reveal significant positive associations between COVID-19 case trends and both face mask usage and lockdown measures, whereas hand sanitizer and social distancing trends exhibited negligible correlations. No evidence of multicollinearity was found, as all condition indices were below 10, indicating stable model estimates. These findings provide valuable insights into temporal changes in public behavior and awareness of preventive measures, informing policymakers and public health authorities in the design of targeted interventions to mitigate the spread of COVID-19.