Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal RESOLUSI : REKAYASA TEKNIK INFORMATIKA DAN INFORMASI
Jimmy
Universitas Nusa Mandiri, Jakarta
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Penerapan Machine Learning Dalam Analisis Stadium Penyakit Hati Untuk Proses Diagnosis dan Perawatan Jimmy; Lili Dwi Yulianto; Eni Heni Hermaliani; Laela Kurniawati
Resolusi : Rekayasa Teknik Informatika dan Informasi Vol. 3 No. 4 (2023): RESOLUSI Maret 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/resolusi.v3i4.709

Abstract

Liver disease is a disease that has existed for a long time and is quite common in society. This disease occurs because the liver cannot work optimally due to inflammation or viruses. Therefore, one of the ways used to determine liver disease is to do a blood test in the laboratory so as to obtain information in the form of enzyme levels, but blood tests in the laboratory require a fairly expensive so that predictions using machine learning is needed for this case, because the symptoms of liver disease need to be handled quickly. Medical record Data and laboratory results produce many features while too many features can reduce the value of accuracy in machine learning, so the features selection model is needed to determine the most influential features in machine learning. in this research that using three models of features selection, namely Random Forest Importance, Chi Square Test and Recursive Features Elimination and managed to get the two highest features, namely SGOT (Serum Glutamic Oxaloacetic Transaminase) and SGPT (Serum Glutamic Pyruvic Transaminase). Accuracy results will be compared between two features with eleven features using K-fold Cross Validation, and perform comparison using Features Extraction model using Principal Component Analysis (PCA). Accuracy calculation is done using Random Forest algorithm, Decision Tree, Naive Bayes, Logistic Regression, Support Vector Machine, KNN, Gradient Boosting and Artificial Neural Network, the calculation accuracy using Random Forest algorithm with PCA between Eleven and two features decreased by 0.6%, while using features selection increased by 0.7%, found the highest accuracy using Random Forest algorithm with 2 features of 72.2%.
Co-Authors Eni Heni Hermaliani Laela Kurniawati Lili Dwi Yulianto