Application of computational intelligence models in IoMT big data for heart disease diagnosis in personalized health care

Bajeh A. O., Abikoye O. C., Mojeed H. A., Salihu S. A., Oladipo I. D., Abdulraheem M., ...Daha Fazla

Intelligent IoT Systems in Personalized Health Care, Elsevier, ss.177-206, 2020

  • Yayın Türü: Kitapta Bölüm / Araştırma Kitabı
  • Basım Tarihi: 2020
  • Doi Numarası: 10.1016/b978-0-12-821187-8.00007-1
  • Yayınevi: Elsevier
  • Sayfa Sayıları: ss.177-206
  • Anahtar Kelimeler: Big data, Computational intelligence, Heart disease diagnosis, Internet of things, Machine learning
  • Recep Tayyip Erdoğan Üniversitesi Adresli: Evet

Özet

Computational intelligence is increasingly being applied to solve problems in the health-care domain due to its evolutionary and processing capabilities for dynamic and voluminous data. With the application of Internet of medical things (IoMT) to health care, computational intelligence has been used rigorously to derive knowledge from medical data. As health care moves toward data-driven personalized health-care approaches via the Internet of things technologies, it is imperative to develop more sophisticated computational intelligence techniques and frameworks to derive knowledge from collected data for quality health-care delivery. This study examined recent applications of computational intelligence in the form of machine learning techniques, optimization, and fuzzy algorithms. In addition, the application of big data analytics in the prediction of heart diseases based on IoMT is reviewed. As a case study, rule-based classification models and tree-based homogeneous ensemble algorithms are applied to predict heart diseases on a new cardiovascular dataset. Preliminary experimental results indicated that rule-based models (PART and JRIP) are effective in diagnosing heart diseases with a predictive accuracy of 73% and area under the curve (AUC) of 0.78. A framework based on Big Data analytics and heterogeneous ensemble techniques is proposed for the diagnosis of heart diseases. The framework can facilitate real-time monitoring and personalized health care in the diagnosis of heart disease such as CVD.