SavedAdd your journal

Journals / Academic Platform Journal of Engineering and Smart Systems / 2021 / Cilt: 9 - Sayı: 3

Feature Selection Based Data Mining Approach for Coronary Artery Disease Diagnosis

Kemal AKYOL
Pages
451–459
Publication Date
2021-09-30
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Logistic Regression algorithm outperformed others with %90.88 value of accuracy, 95.18% value of sensitivity, and 81.34% value of specificity.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Cardiovascular diseases responsible for many deaths are very common and important health problems.
📊
Key Findings & Data:According to World Health Organization, each year 17.7 million people die because of them.
💡
Conclusion & Impact:Logistic Regression algorithm outperformed others with %90.88 value of accuracy, 95.18% value of sensitivity, and 81.34% value of specificity.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Medical data · coronary artery disease · attribute selection

Abstract

Cardiovascular diseases responsible for many deaths are very common and important health problems. According to World Health Organization, each year 17.7 million people die because of them. Coronary artery disease is the most important type of cardiovascular diseases that cause serious heart problems in patients, affecting the heart’s function negatively. Being aware of the important attributes for this disease will help field-specialist in the analysis of routine laboratory test results of a patient coming internal medicine or another medicine unit except for the cardiology unit. In this study, it is aimed to determine the significance of attributes for coronary artery disease by utilizing Stability Selection method. In experiments, the attributes; ‘Age’, ‘Atypical’, ‘Blood pressure’, ‘Current smoker’, ‘Diastolic murmur’, ‘Dyslipidemia’, ‘Diabetes mellitus’, ‘Ejection fraction’, ‘Erythrocyte sedimentation rate’, ‘Family history’, ‘Hypertension’, ‘Potassium’, ‘Nonanginal’, ‘Pulse rate’, ‘Q wave’, ‘Regional wall motion abnormality’, ‘Sex’, ‘St Depression’, ‘Triglyceride’, ‘Tinversion’, ‘Typical chest pain’ and ‘Valvular heart disease’ were found important for each sub-dataset. Besides, the performances of four traditional machine learning algorithms were evaluated to detection of this disease. Logistic Regression algorithm outperformed others with %90.88 value of accuracy, 95.18% value of sensitivity, and 81.34% value of specificity.

🔖

Cite This Article

AKYOL, K. (2021). Feature Selection Based Data Mining Approach for Coronary Artery Disease Diagnosis. Academic Platform Journal of Engineering and Smart Systems, Cilt: 9 - Sayı: 3, 451–459. https://ajindex.com/articles/730605

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (12)

  1. Alizadehsani R, Habibi J, Hosseini MJ, et al (2013) A data mining approach for diagnosis of coronary artery disease. Comput Methods Programs Biomed 111:52–61. https://doi.org/10.1016/j.cmpb.2013.03.004
  2. Chagas P, Mazocco L, Piccoli J da CE, et al (2017) Association of alcohol consumption with coronary artery disease severity. Clin Nutr 36:1036–1039. https://doi.org/10.1016/j.clnu.2016.06.017
  3. Roberts R (2015) A genetic basis for coronary artery disease. Trends Cardiovasc. Med. 25:171–178
  4. Yadav C, Lade S, Professor A, Suman MK (2014) Predictive Analysis for the Diagnosis of Coronary Artery Disease using Association Rule Mining Ghadiri Hedeshi N, Saniee Abadeh M (2014) Coronary artery disease detection using a fuzzy-boosting PSO approach. Comput Intell Neurosci 2014:. https://doi.org/10.1155/2014/783734
  5. Alizadehsani R, Hosseini MJ, Boghrati R, et al (2013) Exerting Cost-Sensitive and Feature Creation Algorithms for Coronary Artery Disease Diagnosis. Int J Knowl Discov Bioinforma 3:59–79. https://doi.org/10.4018/jkdb.2012010104
  6. Nithya S, Suresh C, Dhas G (2015) FUZZY LOGIC BASED IMPROVED SUPPORT VECTOR MACHINE (F-ISVM) CLASSIFIERFOR HEART DISEASE CLASSIFICATION. 10: Arabasadi Z, Alizadehsani R, Roshanzamir M, et al (2017) Computer aided decision making for heart disease detection using hybrid neural network-Genetic algorithm. Comput Methods Programs Biomed 141:19–26. https://doi.org/10.1016/j.cmpb.2017.01.004
  7. Alizadehsani R, Hosseini MJ, Sani ZA, et al (2012) Diagnosis of coronary artery disease using cost-sensitive algorithms. In: Proceedings - 12th IEEE International Conference on Data Mining Workshops, ICDMW 2012. pp 9–16
  8. Qin CJ, Guan Q, Wang XP (2017) Application of ensemble algorithm integrating multiple criteria feature selection in coronary heart disease detection. Biomed Eng - Appl Basis Commun 29:. https://doi.org/10.4015/S1016237217500430
  9. Babic F, Olejar J, Vantova Z, Paralic J (2017) Predictive and descriptive analysis for heart disease diagnosis. In: Proceedings of the 2017 Federated Conference on Computer Science and Information Systems, FedCSIS 2017. Institute of Electrical and Electronics Engineers Inc., pp 155–163
  10. Pathak LA, Shirodkar S, Ruparelia R, Rajebahadur J (2017) Coronary artery disease in women. Indian Heart J. 69:532–538
  11. Malakar AK, Choudhury D, Halder B, et al (2019) A review on coronary artery disease, its risk factors, and therapeutics. J Cell Physiol 234:16812–16823. https://doi.org/10.1002/jcp.28350
  12. Effrosynidis D, Arampatzis A (2