IO, Malang – Basic Health Research Data (Riskesdas) 2018 points to heart disease as still the most common cause of death in Indonesia. Aldi Dwi Putra, Andro Syahreza, and Ervan Andi Wijaya, three students of the Faculty of Mathematics and Natural Sciences, Brawijaya University, Malang, East Java, have invented a digital tensiometer tool model for early diagnosis of heart disease.
The three designed an Artificial Intelligence-based Diagnosis (AID) to diagnose heart disease, based on heart rate, blood pressure, and age, as well as qualitative parameters consisting of gender and symptoms of angina during activity. Aldi explained that the artificial intelligence method used is an Artificial Neural Network (ANN).
AID’s artificial intelligence is trained using UCI Machine Learning Repository data, which contains the relationship between heart disease symptoms and a diagnosis, as quoted by Prasetya.ub.ac.id, Sunday (10/4/2020). Once the training process was carried out, the accuracy is quite good, namely, 83.6 percent.
The results of the diagnosis will be displayed as a percentage of potential heart disease. If the percentage of output is higher, the potential for suffering from heart disease will also be higher, and vice versa.
If the result of an early diagnosis from artificial intelligence is ≥50 percent, users are strongly advised to immediately carry out further checks, using more sophisticated tools at the hospital. If a figure of ≤49 percent is obtained, users are advised to stay healthy, get enough rest, and engage in regular exercise. However, if the symptoms of chest pain appear or get worse, a check-up with a doctor is recommended immediately.
Aldi hopes that the design of the tool made by his team can help reduce the death rate, often due to a lack of awareness of heart disease. “AID was made as a solution to equal distribution of health facilities throughout Indonesia and to reduce the number of deaths caused by heart disease, by making an early diagnosis,” he said. (est)