Heart disease diagnosis is a challenging task which can offer automated prediction about the heart disease of patient so that further treatment can be made easy. Due to this fact, heart disease diagnosis has received immense interest globally among medical community. Here, artificial intelligence played an important role in diagnosis of heart disease with improved effectiveness. Based on this perspective,several researches have been conducted in the literature recently. So, analyzing those diagnosis techniques can lead to new development in this area. Accordingly, we present a detailed survey of 47 articles published in the standard journals from the year 2005 to 2013. The survey of the papers related to heart disease and also the survey of many categories of heart disease such as coronary heart disease, coronary artery disease, heart failure, ischemic heart disease, cardiovascular disease, congenital heart disease, valvular heart disease and hypoplastic left heart syndrome are presented in this paper. From the survey the finding is that neural network based techniques contribute more effectiveness and some techniques have obtained more than 90% accuracy. Finally, some of the research issue is also addressed to precede the further research on the same direction.