Open AccessApplying PC Algorithm and GES to Three Clinical Data Sets: Heart Disease, Diabetes, and Hepatitis
Author(s) -
Nurdi Afrianto,
Yopi Azzani,
Yuan Sa'adati,
Nurhaeka Tou,
Putri Mentari Endraswari,
Yohani Setiya Rafika Nur,
Nur Annisa,
Rifai Nur Widyanara,
Ridho Rahmadi
Publication year - 2021
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/1077/1/012067
Subject(s) - machine learning , computer science , artificial intelligence , domain (mathematical analysis) , generative grammar , causal model , focus (optics) , deep learning , algorithm , mathematics , mathematical analysis , statistics , physics , optics
The goal of many sciences, including those related to the clinical domain, is to discover the generative model, that is, to understand how variables in the data take on their values. This goal cannot be addressed directly using approaches such as machine learning and deep learning, as such methods focus more on the association between input and output variables. In this paper, we aim to show to the readers an alternative approach, which can be a more appropriate method to target such aforesaid research goal. This approach is called causal modeling. We will first begin with some application examples of machine learning and deep learning on clinical data, and then show our applications of causal modeling to three clinical real-world data sets. This paper is projected to be a concise guideline for researchers to causal modeling, as well as to choose suitable approaches for problems of interest.