APPLICATION OF DATA MINING FOR PREDICTION OF LONG COVID ON COVID-19 SURVIVAL WITH FEATURE SELECTION AND NAÏVE BAYES METHOD

Siti Rokhmah; Nendy Akbar  Rozaq Rais

doi:10.20884/1.jutif.2022.3.5.561

Siti Rokhmah Informatika, Fakultas Teknologi, Institut Teknologi Bisnis AAS Indonesia
Nendy Akbar Rozaq Rais Informatika, Fakultas Teknologi, Institut Teknologi Bisnis AAS Indonesia

DOI: https://doi.org/10.20884/1.jutif.2022.3.5.561

Keywords: Data Clasification, Data mining, Featture Selection, Long covid, naïve bayes

Abstract

Since it was declared a global pandemic in March 2020, Corona Virus Disease (Covid-19) has become the world's attention, a lot of research has focused on all things related to Covid-19. Covid-19 is an infectious disease caused by the acute respiratory syndrome Corona virus 2 (SARS-CoV-2). Several studies have shown that the symptoms of COVID-19 persist for a long period of time even though they have been declared cured of Covid-19, this is known as Long Covid. Complaints that are often experienced by patients who progress to Long Covid are fatigue, headaches, coughs, runny noses, sleep disturbances and even shortness of breath. Several risk factors for the occurrence of Long Covid include age, gender, patient congenital disease, condition during acute infection, ethnicity and the patient's Body Mass Index (BMI). To anticipate the occurrence of long covid, it is necessary to have a risk prediction system for the occurrence of long covid in covid-19 patients, this aims to anticipate and prepare for early handling and prevention efforts for covid-19 patients who are at risk of experiencing long covid. Prediction of the risk of long covid can be done by classifying long covid risk factors by utilizing data mining. The purpose of this study is to classify symptom data and patient history, so that data patterns can be obtained that can be used as predictions to estimate the risk of the occurrence of Long covid-19 in Covid-19 survivors. This study uses the Naïve Bayes classification method by classifying data based on the Long covid risk factor and the feature selection information gain method which is used as a technique in attribute selection to optimize the nave Bayes algorithm. The results of this study have a real contribution to the development of science and technology. The concept of the resulting prediction data pattern can be used as a reference in developing early detection of the risk of the occurrence of Long Covid.

Downloads

Download data is not yet available.

References

N. R. Yunus and A. Rezki, “Kebijakan Pemberlakuan Lock Down Sebagai Antisipasi Penyebaran Corona Virus Covid-19,” SALAM J. Sos. dan Budaya Syar-i, vol. 7, no. 3, 2020, doi: 10.15408/sjsbs.v7i3.15083.

M. Siahaan, “Dampak Pandemi Covid-19 Terhadap Dunia Pendidikan,” vol. 1, no. 1, pp. 1–3, 2020.

A. Crispo et al., “Strategies to evaluate outcomes in long-COVID-19 and post-COVID survivors,” Infect. Agent. Cancer, vol. 16, no. 1, pp. 1–20, 2021, doi: 10.1186/s13027-021-00401-3.

I. Visan, “Long COVID,” Nat. Immunol., vol. 22, no. 8, pp. 934–935, 2021, doi: 10.1038/s41590-021-00992-4.

P. Zimmermann, L. F. Pittet, and N. Curtis, “How Common is Long COVID in Children and Adolescents?,” Pediatr. Infect. Dis. J., vol. 40, no. 12, pp. e482–e487, 2021, doi: 10.1097/INF.0000000000003328.

L. Mertz, “Researchers Seek Answers for Millions with Long COVID-19,” IEEE Pulse, vol. 12, no. 2, pp. 17–21, 2021, doi: 10.1109/MPULS.2021.3066718.

H. Crook, S. Raza, J. Nowell, M. Young, and P. Edison, “Long covid - Mechanisms, risk factors, and management,” BMJ, vol. 374, pp. 1–18, 2021, doi: 10.1136/bmj.n1648.

C. H. Sudre et al., “Attributes and predictors of long COVID,” Nat. Med., vol. 27, no. 4, pp. 626–631, 2021, doi: 10.1038/s41591-021-01292-y.

A. H. Ardiansyah, W. Nugroho, N. H. Alfiyah, R. A. Handoko, and M. A. Bakhtiar, “Penerapan Data Mining Menggunakan Metode Clustering untuk Menentukan Status Provinsi di Indonesia 2020,” Semin. Nas. Inov. Teknol., vol. 4, no. 3, pp. 329–333, 2020.

S. Rizal, P. Studi, T. Informatika, and U. Yudharta, “Penerapan Algoritma Naïve Bayes Untuk Prediksi Penerimaan Siswa Baru Di Smk Al-Amien Wonorejo,” Explor. IT J. Keilmuan dan Apl. Tek. Inform., vol. 10, no. 1, pp. 14–21, 2018, doi: 10.35891/explorit.v10i1.1671.

PDPI, PERKI, PAPDI, PERDATIN, and IDAI, Pedoman tatalaksana COVID-19 Edisi 3 Desember 2020. 2020. [Online]. Available: https://www.papdi.or.id/download/983-pedoman-tatalaksana-covid-19-edisi-3-desember-2020

M. Ridwan, H. Suyono, and M. Sarosa, “Penerapan Data Mining Untuk Evaluasi Kinerja Akademik Mahasiswa Menggunakan Algoritma Naive Bayes Classifier,” J. EECCIS, vol. 7, no. 1, p. pp.59-64, 2013.

Bustami, “Penerapan Algoritma Naive Bayes Untuk Nasabah Asuransi,” J. Inform., vol. 8, no. 1, pp. 884–898, 2014.

S. A. Putri and D. Larasati, “Penerapan Feature Selection Pada Bayesian Network Untuk,” PILAR Nusa Mandiri, vol. 13, no. 2, pp. 275–280, 2017.

I. T. Julianto, D. Kurniadi, M. R. Nashrulloh, and A. Mulyani, “COMPARISON OF CLASSIFICATION ALGORITHM AND FEATURE SELECTION IN PERBANDINGAN ALGORITMA KLASIFIKASI DAN FEATURE SELECTION,” JUTIF, vol. 3, no. 3, pp. 739–744, 2022.

M. R. Hasibuan and Marji, “Pemilihan Fitur dengan Information Gain untuk Klasifikasi Penyakit Gagal Ginjal menggunakan Metode Modified K-Nearest Neighbor ( MKNN ),” vol. 3, no. 11, pp. 10435–10443, 2019.

A. C. Khotimah et al., “COMPARISON NAÏVE BAYES CLASSIFIER , K-NEAREST NEIGHBOR AND SUPPORT VECTOR MACHINE IN THE CLASSIFICATION OF INDIVIDUAL ON PERBANDINGAN ALGORITMA NAÏVE BAYES CLASSIFIER , K-NEAREST NEIGHBOR DAN SUPPORT VECTOR MACHINE DALAM KLASIFIKASI,” vol. 3, no. 3, pp. 673–680, 2022