Future Access Enablers for Ubiquitous and Intelligent Infrastructures. Third International Conference, FABULOUS 2017, Bucharest, Romania, October 12-14, 2017, Proceedings

Research Article

Prediction of Coronary Plaque Progression Using Data Driven Approach

  • @INPROCEEDINGS{10.1007/978-3-319-92213-3_33,
        author={Bojana Cirkovic and Velibor Isailovic and Dalibor Nikolic and Igor Saveljic and Oberdan Parodi and Nenad Filipovic},
        title={Prediction of Coronary Plaque Progression Using Data Driven Approach},
        proceedings={Future Access Enablers for Ubiquitous and Intelligent Infrastructures. Third International Conference, FABULOUS 2017, Bucharest, Romania, October 12-14, 2017, Proceedings},
        proceedings_a={FABULOUS},
        year={2018},
        month={7},
        keywords={Coronary artery disease Atherosclerosis progression Machine learning Feature selection},
        doi={10.1007/978-3-319-92213-3_33}
    }
    
  • Bojana Cirkovic
    Velibor Isailovic
    Dalibor Nikolic
    Igor Saveljic
    Oberdan Parodi
    Nenad Filipovic
    Year: 2018
    Prediction of Coronary Plaque Progression Using Data Driven Approach
    FABULOUS
    Springer
    DOI: 10.1007/978-3-319-92213-3_33
Bojana Cirkovic,*, Velibor Isailovic,*, Dalibor Nikolic1,*, Igor Saveljic,*, Oberdan Parodi2,*, Nenad Filipovic,*
  • 1: Research and Development Center for Bioengineering “BioIRC”
  • 2: CNR Clinical Physiology Institute
*Contact email: abojana@kg.ac.rs, velibor@kg.ac.rs, markovac85@kg.ac.rs, isaveljic@kg.ac.rs, oberpar@tin.it, fica@kg.ac.rs

Abstract

Coronary artery disease or coronary atherosclerosis (CATS) is the most common type of cardiovascular disease and the number one cause of death worldwide. Early identification of patients who will develop progression of disease is beneficial for treatment planning and adopting the strategy for reduction of risk factors that could cause future cardiac events. In this paper, we propose the data mining model for prediction of CATS progression. We exploit patient’s health record by using various machine learning methods. Predictor variables, including heterogenious data from cellular to the whole organism level, are initially preprocessed by feature selection approaches to select only the most informative features as inputs to machine learning algorithms. Results obtained and features selected within this study indicate the high potential of machine learning to be used in clinical practice as well as that specific monocytes are important markers impacting the plaque progression.