Article Preview
Top1. Introduction
Heart plays an important role in pumping blood to the rest of the organs; thus, any functional problem in the heart has a direct effect on other parts of the body such as lungs, liver, and kidney, etc. Heart disease diagnosis depends on vague, imprecise, ambiguity and inconsistent combination of clinical and pathological data. Because of this complexity, sometimes heart disease diagnosis is hard for experts. Disease prognosis through various factors is a debatable problem, even that could lead to a false assumption. Multi-criteria decision making cannot handle uncertainty, whereas fuzzy logic presents a poor representation of uncertain data as it expresses the true membership degree in a value between 0 and 1. This problem demands new approaches based on many-valued logic models that deal with uncertainty (Paul et al., 2018) (Santhanam & Ephzibah, 2015).
Heart disease is one of the important causes of death among Egyptians as there are five hundred deaths per one hundred thousand occur annually in Egypt (Abdel-Basset et al., 2019). Heart disease is related to many symptoms and many pathologic features such as blood pressure, cholesterol, smoking, physically inactive, obesity and diabetes. The diagnosis of heart disease remains a great problem for less experienced doctors which give uncertain information to the medical experts for heart disease diagnosis (Srivastava & Sharma, 2019). Doctors’ decision is based on the examining results of a patient and by comparing the prior decisions made on other patients that depend on the doctor’s knowledge and his experience. Considering the number of factors to be evaluated, this job cannot get easily done (Kalantari et al., 2018). It is widely recognized that the information available to the medical practitioners about patients, in general, is vague, imprecise, ambiguity, or inconsistent (Shahzadi et al., 2018).
Data sets of the same medical problems like heart disease show various results when the same machine learning technique is applied. The Integration of the machine learning analysis was applied to different data sets targeting heart disease to avoid the missing, incorrect, and inconsistent data problems that may appear in the data collection. The results show that there are a complexity inaccuracy result as heart disease diagnosis depends on vague, imprecise, ambiguity and inconsistent combination of clinical and pathological data (El-Bialy et al., 2015).
Experts take medical diagnosis decisions depends on their experiences, but this may not contribute towards the effective diagnosis of a disease. A genetic algorithm-based fuzzy decision support system is implemented for predicting the risk level of heart disease. The results depict that when the number of diagnostic tests decreases better accuracy occurs. By selecting the optimal attribute’s set and predicting heart disease at an early stage of the disease is achieved. But vague, imprecise, ambiguity and inconsistent data are major barriers to provide the best decision (Paul et al., 2016).
Alqudah presented a fuzzy system to diagnose the severity of the heart disease of a patient. The results showed that the system can be used for diagnosing heart disease based on the medical records, but the problem of the system cannot handle inaccuracy in data (Alqudah, 2017). An adaptive fuzzy system appraised with quantitative, qualitative and comparative analysis on the publicly available different real-life data sets can manage the vagueness and imprecise knowledge but cannot handle ambiguity and inconsistent which is needed for better accuracy (Paul et al., 2018).
Fuzzy logic, type 2 fuzzy logic or intuitionistic fuzzy logic is suggested to handle uncertainty data in heart disease by Ion Iancu. The fuzzy logic can only describe vagueness when information is naturally graded, type-2 fuzzy logic and intuitionistic fuzzy logic which is presented by Attanssov as an extension of the standard fuzzy sets can describe vagueness and imprecision by a range of membership values (Atanassov, 1986)(Iancu, 2018).