Environmental and Disease Vulnerability Prediction Using a Random Forest-Based Multi output Classifier

Abstract

Climate Change and Environment Affect the Incidence of Many Diseases Around The Globe. Understanding How Climate and Environmental Change Increases Vulnerability to Disease Is CriticaltoAdvancing Public HealthKnowledgeand DiseaseRiskAssessment.ThisPaperDescribesA Machine Learning Framework CreatedToPredict Climate-Sensitive Disease Risk Levels By Integrating ManyEnvironmentalVariables SuchAs Temperature,Precipitation,Humidity,WindSpeed, Atmospheric Pressure, And Climate Zone Classifications To Predict Climate-Sensitive Diseases Through The Development Of Relationships Between Climate Conditions And The Rates Of Disease Across Multiple Countries ThroughoutTheWorld.InConstructing,Training, And Validating This Framework, The Authors Utilized A Dataset That Combined Disease Incidence Data And Typical Meteorological Data For A Variety Of Countries. A structured framework, using a multi-country dataset, will provide an equal representation of many different countries that are in differing climatic conditions. To predict multiple common climate-sensitive diseases,multiplediseasepredictionsweretrained through environmental indicators using Random Forest Model as Multioutput Classifier. The structured frameworkresultswillassist researchers inunderstandinghowclimatecanleadtoincreased susceptibility to disease.

Introduction

Traditional studies often analyze climate data and health data separately, limiting the ability to understand their complex relationships. To address this gap, the text emphasizes the need for an integrated, machine learning–based framework that combines environmental and health data to better predict disease risks and outbreaks.

Machine learning techniques such as Random Forest, Gradient Boosting, and neural networks are shown to be effective in identifying hidden patterns in large datasets and improving prediction accuracy for disease outbreaks. However, existing research is often limited to specific diseases, regions, or datasets, and lacks a unified global framework.

The literature review shows that:

• Machine learning is widely used for infectious disease prediction and diagnosis.
• Climate and pollution data can help predict respiratory and vector-borne diseases.
• Some studies also explore healthcare cost prediction using ML models.
• Despite progress, most models are narrow in scope and lack generalization.

Conclusion

The purpose of this research is to develop an innovativemethodofpredictingillnessesbytaking into accountthedifferent kindsofweatherthatexist, and how each type may influence human health. This paper will highlight the relationship between various forms of climate and the number of individualsatriskofdevelopingillnessesaswellas their chances of developing illness due to the atmosphere they live in. Therefore by including thesevariablesintopredictivemodelingtechniques the system will be able to recognize patterns associated with increased risks of developing a particular disease as one moves from one type of weather condition to another. Recent studies indicate that the application of Machine Learning and merging Environmental Data can create a higher level of analytic and interpreting ability when assessing the risk of varioustypesofdiseases.TheusefulnessofFeature Importance Analysis to explain how different environmental factors may contribute to the occurrenceofdiseasewillresultinvaluabledatain ordertotrackPublicHealth,aswellasformulatean early warning System. The methodology used to combineData-DrivenModels(DDMs)fordecision makingwillassistwithplanningforHealthServices and the assessment of climate-related healthrisks. Future Research will explore the use of real-time EnvironmentalData,expandthedatasetto include countries outside of the current dataset and co-frequency with socio-economic and demographic variabls,toprovidemoreaccuratepredictive analysis. The suggested framework for predicting the risks of disease based on Environmental Conditions is scalable and interpretable, and will thuscontributetoPublicHealtheffortsworldwide.

References

[1] O. E. Santangelo, V. Gentile, S. Pizzo, D. Giordano,andF.Cedrone,“MachineLearningand Prediction of Infectious Diseases: A Systematic Review,” Machine Learning and Knowledge Extraction, vol. 5, no. 1, pp. 175–198, 2023. [2] K. Attai, Y. Amannejad, M. Vahdat Pour, O. Obot, and F.-M. Uzoka, “A Systematic Review of Applications of Machine Learning and Other Soft Computing Techniques for the Diagnosis of Tropical Diseases,” Tropical Medicine and InfectiousDisease,vol.7,no.12,Art.no.398, 2022. [3] Y.Ku,S.B.Kwon,J.H.Yoon,S.G.Moon, and M. Y. Chang, “Machine Learning Models for Predicting the Occurrence ofRespiratoryDiseases Using Climatic and Air-Pollution Factors,” Clinical and Experimental Otorhinolaryngology, vol. 15, no. 2, pp. 168–176, 2022. [4] A. I. Taloba, R. M. Abd El-Aziz, H. M. Alshanbari,andA.-A.H.El-Bagoury,“Estimation andPredictionofHospitalizationandMedicalCare Costs Using Regression in Machine Learning,” JournalofHealthcareEngineering,vol.2022,Art. no. 7969220, 2022. [5] S. Q. Ong, P. Isawasan, A. M. M. Ngesom, H. Shahar, A. M. Lasim, and G. Nair, “Predicting dengue transmission rates by comparing different machine learning models with vector indices and meteorological data,” Scientific Reports, vol. 13, Art. no. 19129, 2023. [6] A.Sebastianelli,D.Spiller,R.Carmo,etal.,“A reproducibleensemble machine learning approach to forecast dengue outbreaks,” Scientific Reports, vol. 14, Art. no. 3807, 2024. [7] M. Al Mobin, “Forecasting dengue in Bangladesh using meteorological variables with a novel feature selection approach,” Scientific Reports, vol. 14, Art. no. 32073, 2024. [8] S. Kumar, A. Srivastava, and R. Maity, “Modelingclimatechangeimpactsonvector-borne diseaseusingmachinelearningmodels:Casestudy of Visceral leishmaniasis (Kala-azar) from Indian state of Bihar,” Expert Systems with Applications, vol. 238, Art. no. 121490, 2024. [9] V. A. Pizzulli, V. Telesca, and G. Covatariu, “Analysis ofCorrelation between Climate Change and Human Health Based on a Machine Learning Approach,”Healthcare,vol.9,no.1,Art.no.86,2021. [10] H.Xu,S.Guo,X.Shi,Y.Wu,J.Pan,H. Gao,Y. Tang, and A. Han, “Machine learning-based analysis and prediction of meteorological factors andurbanheatstrokediseases,”FrontiersinPublic Health, vol. 12, Art. no. 1420608, 2024. [11] J. Boudreault, A. Ruf, C. Campagna, and F. Chebana,“Multi-regionmodelsbuiltwithmachine and deep learning for predicting several heat-related health outcomes,” Sustainable Cities and Society, vol. 115, Art. no. 105785, 2024. [12] Y. Dowlatabadi, S. Abadi, M. Sarkhosh, M. Mohammadi,andS.M.M.Moezzi,“Assessingthe impact of meteorological factors and air pollution on respiratory disease mortality rates: a random forest model analysis (2017–2021),” Scientific Reports, vol. 14, Art. no. 24535, 2024. [13] L. M. Mayer, J. R. Strich, et al., “Machine Learning in Infectious Disease for Risk Factor IdentificationandHypothesisGeneration:Proofof ConceptUsingInvasiveCandidiasis,”OpenForum InfectiousDiseases,vol.9,no.8,Art.no.ofac401, 2022. [14] E. Y. Alqaissi, F. S. Alotaibi, and M. S. Ramzan, “Modern Machine-Learning Predictive Models for Diagnosing Infectious Diseases,” Computational and Mathematical Methods in Medicine, vol. 2022, Art. no. 6902321, 2022. [15] A. Z. Al Meslamani, M. Villar, and J. de la Fuente, “Machine learning in infectious diseases: potential applications and limitations,” Future Microbiology, vol. 19, no. 8, pp. 663–668, 2024. [16] S. Haque, et al., “Towards development of functional climate-driven early warning systems forclimate-sensitiveinfectiousdiseases:Statistical models and recommendations,” Environmental Research, vol. 247, Art. no. 118568, 2024. [17] S.A.Inam,“Areviewofartificialintelligence for predicting climate driven infectious disease outbreaks to enhance global health resilience,” DiscoverPublicHealth,vol.22,Art.no.738,2025. [18] M.A.Morid,K.Kawamoto,T.Ault,J.Dorius, and S. Abdelrahman, “Supervised Learning Methods for Predicting Healthcare Costs: Systematic Literature Review and Empirical Evaluation,” AMIA Annual Symposium Proceedings, vol. 2017, pp. 1312–1321, 2018. [19] M.A.Morid,O.R.L.Sheng,K.Kawamoto, T. Ault, J. Dorius, and S. Abdelrahman, “Healthcarecostprediction:Leveraging fine-grain temporal patterns,” Journal of Biomedical Informatics, vol. 91, Art. no. 103113, 2019. [20] M.A.Morid,O.R.L.Sheng,K.Kawamoto, T.Ault, J.Dorius, andS.Abdelrahman, “Learning hidden patterns from patient multivariate time seriesdatausing convolutionalneuralnetworks:A case study of healthcare cost prediction,” Journal of Biomedical Informatics, vol. 109, Art. no. 103565, 2020.

Copyright

Copyright © 2026 Poojitha Settipally , K. Harshitha, Salman Abdullah , Mrs. Jujuroo Sowmya. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.