PREDIKSI RISIKO KEMATIAN PASIEN STROKE PERDARAHAN DENGAN MENGGUNAKAN TEKNIK KLASIFIKASI DATA MINING

Indarto Indarto (Universitas AMIKOM Yogyakarta)
Ema Utami (Universitas AMIKOM Yogyakarta)
Suwanto Raharjo (Universitas AMIKOM Yogyakarta)

Informasi Interaktif
Vol 5, No 2 (2020): Jurnal Informasi Interaktif

Stroke is a major health problem in Indonesia and the world, and the cause of disability and death. Hemorrhagic stroke has higher mortality rate compared to ischemic stroke. The objective of this study is to create a mortality risk prediction model by using Logistic Regression, Support Vector Machine, Random Forest, and Decision Tree C4.5 algorithms based on the data demographics and the clinical data in patients with hemorrhagic stroke. Prediction of outcome of patients of stroke help the physician to determine prognosis, targeted treatments and prepare patients and families. 538 subjects obtained from Hospital Stroke Registry in Yogyakarta. This study uses 10 fold cross validation to evaluate a model. The performance of Decision Tree C4.5 is higher than Logistic Regression, Support Vector Machine, and Random Forest. Prediction accuracy of Decision Tree C4.5 is 90.5%. The use of data mining algorithms able to predict the mortality and functional outcome of patients with hemorrhagic stroke. Keywords: mortality risk prediction, data mining, hemorrhagic stroke.