Model Prognosis Masa Pengobatan Pasien Tuberkulosis Dengan Metode C4.5

Penulis

  • Rusdah Rusdah Universitas Budi Luhur, Jakarta Selatan
  • Brian Agni Bregastantyo Universitas Budi Luhur, Jakarta Selatan

DOI:

https://doi.org/10.25126/jtiik.1067393

Abstrak

Pasien Tuberkulosis mempunyai jangka waktu pengobatan yang relatif beragam karena tingkat kepatuhan tiap pasien untuk meminum obat sampai dengan habis dan jangka waktu yang sudah ditentukan oleh Dokter Spesialis Paru. Apabila salah diagnosa terkait dosis obat maka akan meningkatkan faktor resiko kesehatan yaitu dimana proses pengobatan akan lebih memakan waktu dan lebih lama karena adanya kondisi Multi-Drug Resistant. Hal ini yang harus menjadi perhatian semua pihak agat tingkat kegagalan atas proses pengobatan pasien Tuberkulosis harus ditekan se minimal mungkin. Faktor  kebiasaan pasien dan waktu minum obat pasien harus dijaga ketat agar masa pengobatan dapat lebih dipersingkat. Dokter Spesialis Paru berupaya untuk menekan tingkat Drop Out pasien Tuberkulosis dengan cara mengawasi jadwal mereka dengan pengelolaan yang baik. Oleh karena itu, dibutuhkan sistem untuk membantu proses prediksi masa pengobatan pasien dengan menerapkan Cross-Industry Standard Process for Data Mining (CRISP-DM) dan menggunakan pendekatan data mining dengan mengimplementasikan algoritma C4.5 setelah dilakukan eksplorasi data menggunakan beberapa algoritma untuk klasifikasi dengan tujuan untuk hasil akurasi performa model untuk prognosis masa pengobatan pasien tuberkulosis. Melalui tahap Data Understanding dan Data Preprocessing menghasilkan atribut baru yaitu Lama Pengobatan. Dengan menggunakan 596 record mendapatkan hasil akurasi sebesar 74.33%.

 

Abstract

Tuberculosis patients have a relatively diverse treatment period because of the level of compliance of each patient to take the drug until it runs out and the time period has been determined by the Pulmonary Specialist. If a wrong diagnosis is related to drug dosage, it will increase health risk factors, namely where the treatment process will take more time and longer due to the Multi-Drug Resistant condition. This should be the concern of all parties so that the failure rate of the treatment process for tuberculosis patients must be kept to a minimum. The patient's habit factor and the patient's time to take medication must be closely monitored so that the treatment period can be shortened. Pulmonary Specialists try to reduce the Drop Out rate of Tuberculosis patients by monitoring their schedule with good management. Therefore, a system is needed to help predict the patient's treatment period by applying the Cross-Industry Standard Process for Data Mining (CRISP-DM) and using a data mining approach by implementing the C4.5 algorithm after exploring the data using several algorithms for classification with the aim of for the results of model performance accuracy for the prognosis of the treatment period of tuberculosis patients. Through the Data Understanding and Data Preprocessing stages, a new attribute is produced, namely the Length of Treatment. By using 596 records to get an accuracy of 74.33%.

Downloads

Download data is not yet available.

Referensi

AMRAN, R., ABDULKADIR, W. AND MADANIA, M., 2021. ‘Tingkat Kepatuhan Penggunaan Obat Anti Tuberkulosis Pada Pasien Di Puskesmas Tombulilato Kabupaten Bone Bolango’, Indonesian Journal of Pharmaceutical Education, 1(1), pp. 57–66. doi: 10.37311/ijpe.v1i1.10123.

AYAZ, M., SHAUKAT, F. AND RAJA, G., 2021. ‘Ensemble learning based automatic detection of tuberculosis in chest X-ray images using hybrid feature descriptors’, Physical and Engineering Sciences in Medicine, 44(1), pp. 183–194. doi: 10.1007/s13246-020-00966-0.

AZIZAH, I., 2019. ‘Determinan Lama Waktu Kesembuhan Pada Kategori I Di Rsud Ungaran Kabupaten Semarang’, p. 167.

ISWANTO, PERMANASARI M. H. NUGROHO A.E., GRAFIKA H. A., 2015 ‘Pemanfaatan Teknik Data Mining Untuk Diagnosis Tuberculosis (TBC)’, Seminar Nasional Teknologi Informasi dan Multimedia (STMIK AMIKOM), Yogyakarta, pp. 121–126.

LAKSHMI, K. R., 2013. ‘Utilization of Data Techniques for Prediction and Diagnosis of Tuberculosis Disease Survivability’. International Journal of Modern Education and Computer Science, 5(8), pp. 8–17. doi: 10.5815/ijmecs.2013.08.02.

LINO FERREIRA DA SILVA BARROS, M. H., SOUZA G. O., ROCHA L., LYNN J. F., SAMPAIO T., ENDO V., VANDERSON., 2021. ‘Benchmarking machine learning models to assist in the prognosis of Informatics, 8(2), pp. 1–17: 10.3390/informatics8020027.

NESREDIN, A., 2012. Mining Patients’ Data for Effective Tuberculosis Diagnosis:Case of Menelik II Hospital. Addis Ababa University. doi: 10.1002/ana.23645.

PDPI, 2002. Tuberkulosis Pedoman Diagnosis dan Penatalaksanaan di Indonesia.

RUSDAH, WINARKO, E. AND WARDOYO, R., 2017. ‘Predicting The Suspect of New Pulmonary Tuberculosis Case using SVM, C5.0 and Modified Moran’s I’, International Journal of Computer Science and Network Security, 17(12), pp.164–171.

SRIRAM, A., MUCKLEY A., SINHA M., SHAMOUT K., PINEOU F., AZOUR K. J., YAKUBOVA V., MOORE N., 2021. ‘COVID-19 Deterioration Prediction via Self-Supervised Representation Learning and Multi-Image Prediction.’, ArXiv, pp.–17.

TRAN, KONDRASHOVA K. A., WILLIAMS A., PEARSON E. D., WADELL J. V., NICOLA., 2021. ‘Deep learning in cancer diagnosis, prognosis and treatment selection’, Genome Medicine, 13(1), pp. 1–17. doi:.1186/s13073-021-00968-x.Tuberculosis Coalition for Technical Assistance (2006) International Standards for Tuberculosis Care (ISTC). San Francisco, Canada.

TUFAIL, A., KAABAR Y. K., MARTINEZ M. K., JUNEJO F., KHAN I., RAHIM., 2021. ‘Deep Learning in Cancer Diagnosis and Prediction: A Minireview on Challenges, Recent Trends, and Future Directions’, Computational and Mathematical Methods in Medicine. doi: 10.1155/2021/9025470.

VALVERDE-ALBACETE, F. J. AND PELÁEZ-MORENO, C., 2010. ‘Two information-theoretic tools to assess the performance of multi-class classifiers’, Pattern Recognition Letters, 31(12), pp. 1665–1671. doi: 10.1016/j.patrec.2010.05.017.

WARJIMAN, W., BERNIATI, B. AND ER UNJA, E., 2022. ‘Hubungan Dukungan Keluarga Terhadap Kepatuhan Minum Obat Pasien Paru Di Puskesmas Bilu’, Jurnal Keperawatan Suaka Insan (Jksi), 7(2), pp. 163–168. doi: 10.51143/jksi.v7i2.366.

WHO, 2011. Global Tuberculosis Control: WHO Report 2011.

WHO, 2022. Global Tuberculosis Control : WHO Report 2022.

Diterbitkan

30-12-2023

Terbitan

Bagian

Ilmu Komputer

Cara Mengutip

Model Prognosis Masa Pengobatan Pasien Tuberkulosis Dengan Metode C4.5. (2023). Jurnal Teknologi Informasi Dan Ilmu Komputer, 10(6), 1197-1204. https://doi.org/10.25126/jtiik.1067393