Application of Decision Tree Algorithms in Predicting the Risk of Stroke

Bagas Harmadi

Abstract


Health is the most important aspect of human life. Currently, many diseases are caused by germs, viruses, and bacteria, but the main cause is unhealthy habits or lifestyles. Stroke is one of these diseases. Therefore, an analysis of the prediction of a person's susceptibility to disease is needed, such as research related to the prediction of stroke. This study aims to determine the model and results of predicting the risk of stroke in humans using the Decision Tree algorithm. This method has a good level of accuracy and is effective in decision making. From the eight factors that cause a person to suffer from stroke, namely gender, age, hypertension, heart disease, type of residence, glucose levels, body mass index (BMI), and smoking status, the results of stroke risk prediction were obtained from 360 data using the C4 Decision Tree algorithm. 5 and the RapidMiner tool, with an accuracy percentage of 68.89%, precision of 68.68%, recall of 69.4%, and a ROC curve with an AUC of 0.726. These results indicate that the model in the Decision Tree method is classified as fair. Furthermore, using 360 data, a tree model was obtained with 28 decision rules, and the most dominant factor causing stroke was age above 65 years.

Full Text:

PDF (19-32)

References


American Stroke Association. (2020). “About Stroke,.” Stroke.Org. https://www.stroke.org/en/about-stroke

Ceballos, F. (2013). Scikit-Learn Decision Trees Explained. Medium. https://towardsdatascience.com/scikit-learn-decision-trees-explained-803f3812290d

Han, J. (2006). Data Mining:Concepts and Techniques. Diane Cerra.

Hopkins, J. (2020). Risk Factors for Stroke. Hopkinsmedicien.Org. https://www.hopkinsmedicine.org/health/conditions-and-diseases/stroke/risk-factors-for-stroke

Indriani, A. (2014). Klasifikasi Data Forum dengan menggunakan Metode Naïve Bayes Classifier. Seminasi Nasional Aplikasi Teknologi Informasi, 5–10.

Junaedi, H., Budianto, H., Mariati, I., & Melani, Y. (2011). DATA TRANSFORMATION PADA DATA MINING. Inovasi Dalam Desain Dan Teknologi.

Kusrini, E. T., & Luthfi. (2009). Algoritma Datamining,. CV Andi Offset.

Mashlahah, S. (2013). Prediksi kelulusan mahasiswa menggunakan metode decision tree dengan penerapan algoritma C4.5. UIN Maulana Malik Ibrahim Malang.

Rifai, B. (2013). ALGORITMA NEURAL NETWORK UNTUK PREDIKSI PENYAKIT JANTUNG. Jurnal Techno Nusa Mandiri, IX(1).

Rohman, A., & Rufiyanto, A. (2019). PENERAPAN ALGORITMA DECISION TREE ID3 UNTUK PREDIKSI KELULUSAN MAHASISWA JENJANG PENDIDIKAN D3 DI FAKULTAS TEKNIK UNIVERSITAS PANDANARAN. Jurnal Neo Teknika, 5(2).


Refbacks

  • There are currently no refbacks.