Prediction of hypertention drug therapy response using K-NN imputation and SVM algorithm

Lailil Muflikhah, Nurul Hidayat, Dimas Joko Hariyanto

Abstract


Hypertention is a degenerative disease but its healing takes a long time by consuming hypertension drugs until patient’s lifetime. The research is conducted to predict response of drug therapy using bioinformatics approach which is a blend of biological and informatics engineering methods. It is used medical record data of hypertensive patient in drug therapy which has an impact on genetic characteristics. The data is constructed as modelling for learning process. Then, it is implemented as a prediction whether the blood presure is under control or not. However, the amount data have no values, then they are required to be applied preprocessing data. Therefore, this research is proposed K-Nearest Neighbor (K-NN) Imputation algorithm for refining data. After that, it is implemented using Support Vector Machine (SVM) algorithm for prediction.The experiment result is achieved the highest accuracy rate of 90% at the best parameter value λ = 0.9, Σ = 2, C = 0.1, ε = 0.001 in ten times iterations.


Keywords


hypertention, missing value, prediction, K-NN Imputation, SVM

Full Text:

PDF


DOI: http://doi.org/10.11591/ijeecs.v15.i1.pp460-467

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Indonesian Journal of Electrical Engineering and Computer Science (IJEECS)
p-ISSN: 2502-4752, e-ISSN: 2502-4760
This journal is published by the Institute of Advanced Engineering and Science (IAES) in collaboration with Intelektual Pustaka Media Utama (IPMU).

shopify stats IJEECS visitor statistics