Klasifikasi Penurunan Fungsi Kognitif Pasien Stroke Menggunakan Metode Klasifikasi Random Forest

Muhammad Shidqi Fadlilah (Fakultas Ilmu Komputer, Universitas Brawijaya)
Randy Cahya Wihandika (Fakultas Ilmu Komputer, Universitas Brawijaya)
Bayu Rahayudi (Fakultas Ilmu Komputer, Universitas Brawijaya)

Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Vol 3 No 3 (2019): Maret 2019

Stroke is a disease that attacks all human, regardless of race, gender, and age. One of the effects of stroke is a decreased cognitive function. A human brain has many nerves, one of them is regulating the work of the human's cognitive function. Based on research by Wardhani (2015), factors that decreasing cognitive function consist of thirteen factors. So, a system that can detect a decreased cognitive function on a stroke patient is needed. So in this research, we make a system that could be used to classify the decreasing cognitive function using a random forest method. the random forest was chosen because this method is good for categorical data. Based on the testing result, the best tree that builds in this system was 100 trees. The average result of the accuracy obtained from all experiments were 53.094%. That number means that the system is still far from perfect. One of the factors that caused this system's imperfection was the distribution of training classes were not evenly distributed.