Improved arbovirus suspected case analysis via ensemble methods with parameter tuning: Insights from SISA dataset

Abstract

Hospital admission necessity of a patient who is under care for the possibility of arbovirus infection is a critical decision for healthcare practitioners. Medical staff may experience stress when making this decision due to the potential risks it poses to the broader community. Current capacities for diagnosis can be confusing. For this reason, data mining approaches have been proven to be highly effective in the diagnosis of diseases as well as in many other fields. As many research studies suggest, they can also be used to decide whether a patient with arbovirus infection should be hospitalized or not. For this purpose, this study uses Severity Index for Suspected Arbovirus (SISA) dataset and implements various machine learning classification techniques with the aim of binary classification to detect the hospitalization status of a specific patient. Several neural networks, single classifiers, and ensemble supervised learning methods are selected as classifiers during the experiments. The best classification accuracy value is obtained by Random Forest (RF) model with 0.9908. This model has been shown to outperform many data mining techniques previously applied in prominent studies. This improved result leads to additional experiments with a different number of estimators when implementing RF. The outcome also improves the maximum classification performance up to 0.9926 using 25 estimators. The study reveals the effectiveness of ensemble models, especially bagging and boosting approaches, for Arbovirus suspected case analysis.

Keywords

• Machine Learning
• Arboviral Infection
• Random Forest
• Hospitalization

Parametre ayarlaması ile geliştirilmiş topluluk yöntemleri kullanarak arbovirüs şüpheli vaka analizi: SISA veri kümesinden çıkarımlar

Öz

Arbovirüs enfeksiyonu şüphesiyle gözlem altında tutulan bir hastanın hastaneye yatış gerekliliği, sağlık profesyonelleri için kritik bir karardır. Tıbbi personel, bu kararın sağlıklı bireyler üzerindeki potansiyel riskleri nedeniyle baskı altında olabilir. Mevcut teşhis olanakları zaman zaman kafa karıştırıcı olabilir. Bu nedenle, veri madenciliği yaklaşımlarının hastalıkların teşhisinde ve birçok farklı alanda oldukça etkili olduğu kanıtlanmıştır. Yapılan araştırmalar, veri madenciliği yöntemlerinin arbovirüs enfeksiyonu taşıyan bir hastanın hastaneye yatırılıp yatırılmaması kararında da kullanılabileceğini göstermektedir. Bu amaç doğrultusunda, bu çalışma Şüpheli Arbovirüs Vakaları için Şiddet İndeksi (SISA) veri kümesini kullanarak, bir hastanın hastaneye yatış durumunu belirlemek için ikili sınıflandırma gerçekleştiren çeşitli makine öğrenmesi tekniklerini uygulamaktadır. Deneylerde sınıflandırıcı olarak çeşitli yapay sinir ağları, tekil sınıflandırıcılar ve topluluk destekli öğrenme yöntemleri kullanılmıştır. En yüksek sınıflandırma doğruluğu, %99,08 ile Rastgele Orman (Random Forest- RF) modeli tarafından elde edilmiştir. Bu modelin, literatürdeki önemli araştırmalarda uygulanan birçok veri madenciliği tekniğinden daha etkili olduğu kanıtlanmıştır. Bu olumlu sonuçlar, RF modelinin farklı sayıda tahmin edici (estimators) ile ek deneyler yapılmasını teşvik etmiştir. Çalışma sonucunda, en yüksek sınıflandırma performansı 25 tahmin edici kullanılarak %99,26'ya yükseltilmiştir. Elde edilen bulgular, arbovirüs şüpheli vaka analizinde özellikle torbalama (bagging) ve güçlendirme (boosting) yaklaşımlarına dayalı topluluk modellerinin etkinliğini ortaya koymaktadır.

Anahtar Kelimeler

• Makine öğrenimi
• Arbovirüs Enfeksiyonu
• Rastgele Orman
• Hastane yatış durumu

Kaynakça

1. [1] Görür K, Çetin O, Özer Z, Temurtaş F. “Hospitalization status and gender recognition over the arboviral medical records using shallow and RNN-based deep models.” Results in Engineering, 18, 101109, 2023.
2. [2] Sippy R, Farrell DF, Lichtenstein DA, Nightingale R, Harris MA, Toth J, Hantztidiamantis P, Usher N, Cueva Aponte C, Barzallo Aguilar J, Puthumana A, Lupone CD, Endy T, Ryan SJ, Stewart Ibarra AM. “Severity Index for Suspected Arbovirus (SISA): Machine learning for accurate prediction of hospitalization in subjects suspected of arboviral infection.” PLoS Neglected Tropical Diseases, 14(2), e0007969, 2020.
3. [3] Fite J, Baldet T, Ludwig A, et al. “A one health approach for integrated vector management monitoring and evaluation.” One Health, 20, 100954, 2025.
4. [4] Gutiérrez-López R, Ruiz-López MJ, Ledesma J, et al. “First isolation of the Sindbis virus in mosquitoes from southwestern Spain reveals a new recent introduction from Africa.” One Health, 20, 100947, 2025.
5. [5] Nenaah GE, Mahfouz ME, Almadiy AA, et al. “Fabrication, characterization, and mosquitocidal activity of CuO nanoparticles against Aedes aegypti L. (Diptera: Culicidae), the main vector of dengue arbovirus, with environmental risk assessment.” BioNanoScience, 15(1), 93–106, 2025.
6. [6] Panmei K, Syed AH, Okafor O, et al. “Performance evaluation of TaqMan™ Arbovirus Triplex Kit (ZIKV/DENV/CHIKV) for detection and differentiation of dengue and chikungunya viral RNA in serum samples of symptomatic patients.” Journal of Virological Methods, 332, 115072, 2025.
7. [7] Xiao P, Hao Y, Yuan Y, et al. “Emerging West African genotype chikungunya virus in mosquito virome.” Virulence, 16(1), 2444686, 2025.
8. [8] Saihar A, Yaseen AR, Suleman M, et al. “From bytes to bites: In-silico creation of a novel multi-epitope vaccine against Murray Valley Encephalitis Virus.” Microbial Pathogenesis, 198, 107171, 2025.

9. [9] Hefti E, Xie Y, Engelen K. “Machine learning model better identifies patients for pharmacist intervention to reduce hospitalization risk in a large outpatient population.” Journal of Medical Artificial Intelligence, 8, 11, 2025.
10. [10] Rosman L, Lampert R, Wang K, Gehi AK, Dziura J, Salmoirago-Blotcher E, Brandt C, Sears SF, Burg M. “Machine learning-based prediction of death and hospitalization in patients with implantable cardioverter defibrillators.” Journal of the American College of Cardiology, 85(1), 42–55, 2025.
11. [11] Chang CY, Chen CC, Tsai ML, Hsieh MJ, Chen TH, Chen SW, Chang SH, Chu PH, Hsieh IC, Wen MS, Chen DY. “Predicting mortality and hospitalization in heart failure with preserved ejection fraction by using machine learning.” JACC: Asia, 4(12), 956–968, 2024.
12. [12] Larkin JW, Lama S, Chaudhuri S, Willetts J, Winter AC, Jiao Y, Stauss-Grabo M, Usvyat LA, Hymes JL, Maddux FW, Wheeler DC, Stenvinkel P, Floege J, Zimbelman J. “Prediction of gastrointestinal bleeding hospitalization risk in hemodialysis using machine learning.” BMC Nephrology, 25(1), Article no. 366, 2024.
13. [13] Albrecht S, Broderick D, Dost K, Cheung I, Nghiem N, Wu M, Zhu J, Poonawala-Lohani N, Jamison S, Rasanathan D, Huang S, Trenholme A, Stanley A, Lawrence S, Marsh S, Castelino L, Paynter J, Turner N, McIntyre P, Riddle P, Grant C, Dobbie G, Wicker JS. “Forecasting severe respiratory disease hospitalizations using machine learning algorithms.” BMC Medical Informatics and Decision Making, 24(1), Article no. 293, 2024.
14. [14] Fan S, Abulizi A, You Y, Huang C, Yimit Y, Li Q, Zou X, Nijiati M. “Predicting hospitalization costs for pulmonary tuberculosis patients based on machine learning.” BMC Infectious Diseases, 24(1), Article no. 875, 2024.
15. [15] Peacock J, Stanelle EJ, Johnson LC, Hylek EM, Kanwar R, Lakkireddy DR, Mittal S, Passman RS, Russo AM, Soderlund D, Hills MT, Piccini JP. “Using atrial fibrillation burden trends and machine learning to predict near-term risk of cardiovascular hospitalization.” Circulation: Arrhythmia and Electrophysiology, 17(11), e012991, 2024.
16. [16] Wu WT, Kor CT, Chou MC, Hsieh HM, Huang WC, Huang WL, Lin SY, Chen MR, Lin TH. “Prediction model of in-hospital cardiac arrest using machine learning in the early phase of hospitalization.” Kaohsiung Journal of Medical Sciences, 40(11), 1029–1035, 2024.
17. [17] Abdul-Samad K, Ma S, Austin DE, Chong A, Wang CX, Wang X, Austin PC, Ross HJ, Wang B, Lee DS. “Comparison of machine learning and conventional statistical modeling for predicting readmission following acute heart failure hospitalization.” American Heart Journal, 277, 93–103, 2024.
18. [18] Davoudi A, Chae S, Evans L, Sridharan S, Song J, Bowles KH, McDonald MV, Topaz M. “Fairness gaps in machine learning models for hospitalization and emergency department visit risk prediction in home healthcare patients with heart failure.” International Journal of Medical Informatics, 191, Article no. 105534, 2024.
19. [19] Windle N, Alam A, Patel H, Street JM, Lathwood M, Farrington T, Maruthappu M. “Predicting hospitalization risk among home care residents in the United Kingdom: Development and validation of a machine learning-based predictive model.” Home Health Care Management and Practice, 36(4), 253–261, 2024.
20. [20] Lee VJ, Chow A, Zheng X, et al. “Simple clinical and laboratory predictors of chikungunya versus dengue infections in adults.” PLoS Neglected Tropical Diseases, 6, e1786, 2012.
21. [21] Huang SW, Tsai HP, Hung SJ, et al. “Assessing the risk of dengue severity using demographic information and laboratory test results with machine learning.” PLoS Neglected Tropical Diseases, 14, e0008960, 2020.
22. [22] Görür K, Başçıl MS, Bozkurt MR, et al. “Classification of thyroid data using decision trees, kNN, and SVM methods.” In Proceedings of the International Artificial Intelligence and Data Processing Symposium (IDAP’16) (pp. 130–134). Malatya, Turkey, 2016.
23. [23] Fathima SA, Hundewale N. “Comparative analysis of machine learning techniques for classification of arbovirus.” In Proceedings of the 2012 IEEE-EMBS International Conference on Biomedical and Health Informatics (pp. 376–379). IEEE, 2012.
24. [24] Akhtar M, Kraemer MU, Gardner LM. “A dynamic neural network model for predicting risk of Zika in real time.” BMC Medicine, 17, Article no. 171, 2019.
25. [25] Salim NAM, Wah YB, Reeves C, Smith M, Yaacob WFW, Mudin RN, Dapari RNFF, Haque U. “Prediction of dengue outbreak in Selangor, Malaysia using machine learning techniques.” Scientific Reports, 11, Article no. 939,
26. [26] Neto L.M., da Silva Neto S.R., Endo P.T. “A comparative analysis of converters of tabular data into image for the classification of Arboviruses using Convolutional Neural Networks.” PLoS ONE, 18 (12), e0295598, 2023.
27. [27] Neto S.R.D.S., Oliveira T.T., Teixeira I.V., Oliveira S.B.A.D., Sampaio V.S., Lynn T., Endo P.T. “Machine learning and deep learning techniques to support clinical diagnosis of arboviral diseases: A systematic review.” PLoS Neglected Tropical Diseases, 16 (1), e0010061, 2022.
28. [28] Ozer I., Cetin O., Gorur K., Temurtas F. “Improved machine learning performances with transfer learning to predicting need for hospitalization in arboviral infections against the small dataset.” Neural Computing and Applications, 33 (21), 14975–14989, 2021.
29. [29] Sciannameo V., Goffi A., Maffeis G., Gianfreda R., Jahier Pagliari D., Filippini T., Mancuso P., Giorgi-Rossi P., Alberto Dal Zovo L., Corbari A., Vinceti M., Berchialla P. “A deep learning approach for Spatio-Temporal forecasting of new cases and new hospital admissions of COVID-19 spread in Reggio Emilia, Northern Italy.” Journal of Biomedical Informatics, 132, 104132, 2022.