Abstract:Günümüzde teknolojinin hızla ilerlemesi ile birlikte yapay zekâ yöntemleri de birçok alanda sıklıkla kullanılmaktadır. Yapay zekanın önemli kullanım alanlarından birisi de sağlık sektörüdür. Sağlık sektöründe erken teşhis, insan kaynaklı hataların minimuma indirilmesi gibi birçok durumda yapay zekâ yöntemleri kullanılmaktadır. Çalışmada açık kaynak erişimli internet sitesinden (kaggle.com) elde edilen 127710 adet EKG sinyallerine ait veri seti kullanılmıştır. Veri seti 100.710 adet eğitim, 1.500 adet veri de t… Show more
According to the World Health Organization (WHO) data, heart diseases are among the diseases with the highest mortality rate. Cardiovascular diseases, known as cardiovascular diseases, are defined as the formation of plaque on the inner wall of the vessel, the hardening of the vessels, the narrowing of the vessel and making the blood flow difficult. The diagnosis of the disease is made by examining various clinical findings. The clinical findings and tests take time, prolonging the diagnostic phase. For this reason, new tools and methods are being researched to facilitate the disease diagnosis process. Materials and Methods: Heart disease dataset from Kaggle, a public sharing site, was used in the study. There are 14 features in the dataset. The features were selected with the Eta correlation coefficient and reduced to 11. Rule-based diagnostic algorithms have been developed with the help of decision tree algorithms. Results: As a result of the study, rule-based algorithms were developed at approximately 5 levels, with an average accuracy rate of 94.15, sensitivity of 0.98, and specificity of 0.91. Conclusion: According to the model performances, it has a high accuracy rate developed with artificial intelligence methods for the diagnosis of CVD, and it is thought that it can be used as a rule-based diagnostic algorithm by the clinician.
According to the World Health Organization (WHO) data, heart diseases are among the diseases with the highest mortality rate. Cardiovascular diseases, known as cardiovascular diseases, are defined as the formation of plaque on the inner wall of the vessel, the hardening of the vessels, the narrowing of the vessel and making the blood flow difficult. The diagnosis of the disease is made by examining various clinical findings. The clinical findings and tests take time, prolonging the diagnostic phase. For this reason, new tools and methods are being researched to facilitate the disease diagnosis process. Materials and Methods: Heart disease dataset from Kaggle, a public sharing site, was used in the study. There are 14 features in the dataset. The features were selected with the Eta correlation coefficient and reduced to 11. Rule-based diagnostic algorithms have been developed with the help of decision tree algorithms. Results: As a result of the study, rule-based algorithms were developed at approximately 5 levels, with an average accuracy rate of 94.15, sensitivity of 0.98, and specificity of 0.91. Conclusion: According to the model performances, it has a high accuracy rate developed with artificial intelligence methods for the diagnosis of CVD, and it is thought that it can be used as a rule-based diagnostic algorithm by the clinician.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.