We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Prediksi Hipertensi Menggunakan Decision Tree, Naïve Bayes dan Artificial Neural Network pada Software KNIME.
- Authors
Santoni, Mayanda Mega; Chamidah, Nurul; Matondang, Nurhafifah
- Abstract
Hypertension is a non-communicable disease that can cause death because it increases the risk of various diseases such as kidney failure, heart failure, and even stroke. The risk of hypertension is caused by several. Artificial intelligence technology is utilized in the health sector, especially hypertension prediction. In this research, three machine learning algorithms are implemented such as decision tree, naïve bayes and artificial neural network (ANN). The data used in this study were 274 data obtained from questionnaire results with 26 questions, consisting of 25 questions were risk factor variables and one question was a class that stated the respondent had a history of hypertension or not. The data is processed using a data analysis platform KNIME. Before the data is processed to build classification models using decision trees, naïve bayes and neural networks, the data is preprocessed by imputing missing values, oversampling and data normalization. Furthermore, we split data for training and testing using 5-fold cross validation. Evaluation classification model using accuracy, recall and precision. The evaluation results of the experiments carried out showed that the ANN algorithm has a better level of performance than the Decision Tree and Naïve Bayes with 94.7% accuracy, 91.5% recall, and 97.7% precision.
- Subjects
NON-communicable diseases; ARTIFICIAL neural networks; DECISION trees; ALGORITHMS; MACHINE learning; NAIVE Bayes classification; CANDIDATUS diseases
- Publication
Techno.com, 2020, Vol 19, Issue 4, p353
- ISSN
1412-2693
- Publication type
Article
- DOI
10.33633/tc.v19i4.3872