.png)
Determining Important Features for Dengue Diagnosis using Feature Selection Methods
Abstract
This research aims to determine the important features including symptoms and risk factors for dengue diagnosis. This study’s dataset was obtained from medical records collected from two hospitals in Indonesia from patients with dengue and nondengue diseases. Four feature selection methods including feature importance, recursive feature elimination, correlation matrix and KBest were leveraged to determine significant features. Feature importance employed a tree-based classifier to derive the importance scores of the features. Recursive feature elimination employed a machine learning classifier to choose the most important features from the given dataset. Correlation matrix was employed to select the best features because it has the ability to use the correlation between each feature with the target. Univariate feature selection – Kbest has the ability to choose the best features based on univariate statistical tests. Important features were also gathered from fifteen Indonesian medical doctors to confirm the results. We used six machine learning techniques for dengue prediction. The random forest classifier yields the highest accuracy for the best combination of features with the accuracy of 0.93 (LR: 0.90 (0.04), KNN: 0.89 (0.04), XGBoost: 0.91 (0.03), RF: 0.93 (0.04), NB: 0.88 (0.09), SVM: 0.89 (0.04)) and precision of 0.90 (LR: 0.86 (0.22), KNN: 0.67 (0.14), XGBoost: 0.77 (0.13), RF: 0.90 (0.13), NB: 0.66 (0.20), SVM: 0.66 (0.18)). This study shows the significant features for dengue diagnosis including fever, fever duration, headache, muscle and joint pain, nausea, vomiting, abdominal pain, shivering, malaise, loss of appetite, shortness of breath, rash, bleeding nose, bitter mouth, temperature and age. This knowledge is pivotal to educate society to seek medical advice when dengue symptoms appear to avoid severe conditions. Arthralgia/joint pain and myalgia/muscle pain are the most significant features for the dengue prediction. This knowledge is important for medical doctors as a starting point for clinical dengue diagnosis.
Keywords
Full Text:
PDFReferences
Ministry of Health of Indonesia, “Information on DHF Cases in 2023 Week 19,” [cited 2023 Aug 19]. Available from: https://p2pm.kemkes.go.id/publikasi/infografis/info-kasus-dbd-2023-minggu-ke-19 (Indonesian)
Y.P. Bria, C.H. Yeh, S. Bedingfield, “Significant symptoms and nonsymptom-related factors for malaria diagnosis in endemic regions of Indonesia,” Int J Infect Dis, vol. 103, pp.194 –200, 2021. https://doi.org/10.1016/j.ijid.2020.11.177
World Health Organization, “Update on the Dengue situation in the Western Pacific Region,” vol. 481, 2015, [cited 2024 March 20]. Availabel from : Dengue-20151229.pdf (who.int)
Ministry of Health of Indonesia, “National Guidelines for Medical Services for the Management of Dengue Infection in Children and Adolescents,” p. 1–67, 2021, [cited 2024 Jan 10]. Available from: https://yankes.kemkes.go.id/unduhan/fileunduhan_1660187378_126303.pdf (Indonesian)
World Health Organization, “Dengue Guidelines for Diagnosis, Treatment, Prevention and Control,” 2009, [cited 2024 Feb 15]. Availabel from : https://iris.who.int/handle/10665/44188
Central Bureau of Statistics East Nusa Tenggara Province, “Number of Disease Cases According to Regency/City and Type of Disease (Inhabitant) in 2022,” 2022, [cited 2024 Jan 10]. Available from: https://ntt.bps.go.id/indicator/30/1485/1/jumlah-kasus-penyakit-menurut-kabupaten-kota-dan-jenis-penyakit.html (Indonesian)
A.N. Rakhmani, L. Zuhriyah, “Knowledge, Attitudes, and Practices Regarding Dengue Prevention Among Health Volunteers in an Urban Area – Malang, Indonesia,” J Prev Med Public Health, vol. 57, pp. 176-184, 2024. https://doi.org/10.3961/jpmph.23.484
Z. Noroozi, A. Orooji, L. Erfannia, “Analyzing the impact of feature selection methods on machine learning algorithms for heart disease prediction,” Sci Rep, vol. 13(1), pp. 1–15, 2023. https://doi.org/10.1038/s41598-023-49962-w
J.D. Álvarez, J.A. Matias-Guiu, M.N. Cabrera-Martín, J.L. Risco-Martín, J.L. Ayala, “An application of machine learning with feature selection to improve diagnosis and classification of neurodegenerative disorders,” BMC Bioinformatics, vol. 20(1), pp. 1–12, 2019. https://doi.org/10.1186/s12859-019-3027-7
J. Song, Z. Li, G. Yao, S. Wei, L. Li, H. Wu, “Framework for feature selection of predicting the diagnosis and prognosis of necrotizing enterocolitis,” PLoS One, vol. 17, August 2022. http://dx.doi.org/10.1371/journal.pone.0273383
V. Ramasamy, S. Vadivel, S. Kothandapani, J. Mahilraj, P. Sivaram, B. Sharma, “An Optimal Feature Selection with Neural Network-Based Classification Model for Dengue Fever Prediction,” 6th Int Conf Inf Syst Comput Networks, pp. 1–5, 2023. https://doi.org/10.1109/ISCON57294.2023.10112011
A.L. Ramadona, Y. Tozan, J. Wallin, L. Lazuardi, A. Utarini, J. Rocklöv, “Predicting the dengue cluster outbreak dynamics in Yogyakarta, Indonesia: a modelling study,” Lancet Reg Heal - Southeast Asia, vol. 15:100209, 2023. https://doi.org/10.1016/j.lansea.2023.100209
I.N. Tanawi, V. Vito, D. Sarwinda, H. Tasman, G.F. Hertono, “Support Vector Regression for Predicting the Number of Dengue Incidents in DKI Jakarta,” Procedia Comput Sci, vol. 179, pp. 747–53, 2021. https://doi.org/10.1016/j.procs.2021.01.063
N.A. Lestari, R. Tyasnurita, R.A. Vinarti, W. Anggraeni, “Long Short-Term Memory forecasting model for dengue fever cases in Malang regency, Indonesia,” Procedia Comput Sci, vol. 197, pp 180–188, 2022. https://doi.org/10.1016/j.procs.2021.12.131
S.A. Thamrin, Aswi, Ansariadi, A.K. Jaya, K. Mengersen, “Bayesian spatial survival modelling for dengue fever in Makassar, Indonesia,” Gac Sanit, vol. 35, pp. S59–S63, 2021. https://doi.org/10.1016/j.gaceta.2020.12.017
A. Joshi, C. Miller, “Review of machine learning techniques for mosquito control in urban environments,” Ecol Inform, vol. 61:101241, 2021. https://doi.org/10.1016/j.ecoinf.2021.101241
W. Hoyos, J. Aguilar, M. Toro, “Dengue models based on machine learning techniques: A systematic literature review,” Artif Intell Med, vol. 119:102157, August 2021. https://doi.org/10.1016/j.artmed.2021.102157
M.S.G. Shaikh, D.B. SureshKumar, D.G. Narang, “Development of optimized ensemble classifier for dengue fever prediction and recommendation system,” Biomed Signal Process Control, vol. 85:104809, March 2023. https://doi.org/10.1016/j.bspc.2023.104809
Y.P. Bria, C.H. Yeh, S. Bedingfield, “Machine Learning Classifiers for Symptom-Based Malaria Prediction,” Proc Int Jt Conf Neural Networks, July 2022. 10.1109/IJCNN55064.2022.9891945
P. Qiu, Z. Niu, “TCIC_FS: Total correlation information coefficient-based feature selection method for high-dimensional data,” Knowledge-Based Syst, vol. 231:107418, 2021. https://doi.org/10.1016/j.knosys.2021.107418
E.M. Senan, I. Abunadi, M.E. Jadhav, S.M. Fati, “Score and Correlation Coefficient-Based Feature Selection for Predicting Heart Failure Diagnosis by Using Machine Learning Algorithms,” Comput Math Methods Med, 2021. https://doi.org/10.1155/2021/8500314
R.C. Chen, C. Dewi, S.W. Huang, R.E. Caraka, “Selecting critical features for data classification based on machine learning methods,” J Big Data, vol. 7(1), 2020. https://doi.org/10.1186/s40537-020-00327-4
T.E. Mathew, “A Logistic Regression with Recursive Feature Elimination Model for Breast Cancer Diagnosis,” Int J Emerging Technol, vol. 10(3):55–63, 2019.
G. Gupta, S. Khan, V. Guleria, A. Almjally, B.I. Alabduallah, T. Siddiqui, et al., “DDPM: A Dengue Disease Prediction and Diagnosis Model Using Sentiment Analysis and Machine Learning Algorithms,” Diagnostics, vol. 13:6, 2023. https://doi.org/10.3390/diagnostics13061093
World Health Organization, “Dengue and severe dengue [Internet]”, 2023 [cited 2023 Aug 6]. Available from: https://www.who.int/news-room/fact-sheets/detail/dengue-and-severe-dengue#:~:text=The incidence of dengue has, dengue cases are under-reported.
S.N.N. Tatura, D. Denis, M.S. Santoso, R.F. Hayati, B.J. Kepel, B. Yohan, et al., “Outbreak of severe dengue associated with DENV-3 in the city of Manado, North Sulawesi, Indonesia,” Int J Infect Dis, vol. 106, pp. 185–96, 2021. https://doi.org/10.1016/j.ijid.2021.03.065
M.S. Santoso, B. Yohan, D. Denis, R.F. Hayati, S. Haryanto, L. Trianty, et al., “Diagnostic accuracy of 5 different brands of dengue virus non-structural protein 1 (NS1) antigen rapid diagnostic tests (RDT) in Indonesia,” Diagn Microbiol Infect Dis, vol. 98(2):115116, 2020. https://doi.org/10.1016/j.diagmicrobio.2020.115116
Ministry of Health of Indonesia. Dengue Hemorrhagic Fever [Internet]. 2022 [cited 2024 Feb 5]. Available from: https://ayosehat.kemkes.go.id/topik/demam-berdarah-dengue (Indonesian)
E. Nwokolo, C. Ujuju, J. Anyanti, C. Isiguzo, I. Udoye, E. Bongos-Ikwue, et al., “Misuse of artemisinin combination therapies by clients of medicine retailers suspected to have malaria without prior parasitological confirmation in Nigeria,” Int J Heal Policy Manag, vol. 7:6, pp. 542–548, 2018. https://doi.org/10.15171/ijhpm.2017.122
N.S. Romero-Castro, I. Colín-Hernández, M.E. Godoy-Reyes, M. Hernández-Hernández, A. García-Verónica, S. Paredes-Solis, et al., “Clinical Signs and Symptoms Associated with COVID-19: A Cross Sectional Study,” Int J Odontostomatol, vol. 16:1, pp. 112–119, 2022. http://dx.doi.org/10.4067/S0718-381X2022000100112
DOI: https://doi.org/10.47738/jads.v6i1.445
Refbacks
- There are currently no refbacks.
Journal of Applied Data Sciences
| ISSN | : | 2723-6471 (Online) |
| Publisher | : | Bright Publisher |
| Website | : | http://bright-journal.org/JADS |
| : | taqwa@amikompurwokerto.ac.id (principal contact) | |
| support@bright-journal.org (technical issues) |
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0