Please note that:

- all the reports can be exported to a comma separated format (CSV). Please click on "Export"to do so.
- all the reports can be seen visually as well. In order to plot a report, please click on chart, select axis and the types of plot.

Number of papers vs. Train-Test split method

Different studies use different train/test splitting techniques due to the constraints and requirements of the work. This report shows the splitting methods and the number of papers that used each technique. As readily seen, 10-fold cross validation is the most favourite technique. The reason could be related to the small sample size in collected datasets.


Important features in each disease

This report lists the set of features that are reported to be important for each heart disease. First, a disease needs to be selected from the drop-down menu. The resulting table will show the feature name, the number of papers that reported the feature to be important for the selected disease, and the mean of the reported ranks for that feature. The smaller the rank, the more important the feature is.


Summary of review papers

This report summarizes the papers that have reviewed the field. It consists of the paper title, publication year, the time span it has covered, and the number of citations by the end of September 2018.


Summary of papers about stenosis of LAD, LCX, and RCA

Since the diagnosis of LAD, LCX, and RCA stenosis is challenging and important, this report summarizes the papers that have studied this subject. It reports the paper title, disease name, the dataset which is used, the method and the achieved accuracy. Please note that very few datasets related to the stenosis of LAD, LCX, and RCA have been collected. Therefore, one can see this report as a list of LAD, LCX, and RCA datasets as well.


Best performance achieved for each feature category per year

Feature categories represent the set of features that are obtained from the same resources. For example, ECG category represents the set of features that are obtained from electrocardiography. This report shows the maximum performance achieved in each year for each category.


Number of papers vs. feature selection methods

This report shows different feature selection methods reported in the literature and their popularity.


Datasets

This report gives details of the collected datasets in this field. It shows the country where the dataset is collected, number of samples, number of features, and the number of papers that have used the dataset.


Number of datasets collected in each country

This report shows how many datasets are collected in each country.


Number of papers vs. feature category

Feature categories represent the set of features that are obtained from the same resources. For example, ECG category represents the set of features that are obtained from electrocardiography. The report shows how many papers used each feature category. As the table shows, demographic features are the most common set of features in the literature.


Number of papers vs. publisher

This table reports the number of studies published by each publication house.


Authors and their number of papers and citations in this field

This table reports on the researchers who have published in this field, the number of their publications which are related to the subject, and the sum of the citations which those papers have received by the end of September 2018.


Number of papers vs. performance metrics

Different studies use different metrics to report the performance of their model. This table reports on the popularity of these metrics.


Papers that investigated the role of sex in CAD

The relation between sex and CAD is one of the most important questions for which researchers have tried to find an answer. In this table, we give details of those works that have investigated this problem. The report consists of the paper title, the dataset it has used, number of features, and the rank which is given to sex feature.


Papers that investigated the role of age in CAD

The relation between age and CAD is one of the most important questions for which researchers have tried to find an answer. In this table, we give details of those works that have investigated this problem. The report consists of the paper title, the dataset it has used, number of features, and the rank which is given to age feature.


Important features reported for a specific disease in a specific country

This table gives a detailed list of what features are collected in each country for each disease. Moreover, one can see the number of papers that have emphasised on the importance of each feature, as well as the mean of ranks given to that feature as a proxy of feature importance in that country.


Rank of sex feature in research on each dataset

The relation between sex and CAD is one of the most important questions for which researchers have tried to find an answer. In this table, we give details of each dataset (sample size, and the number of features), and the average rank that is given to sex feature by all the studies that have used that dataset.


Rank of age feature in research on each dataset

The relation between age and CAD is one of the most important questions for which researchers have tried to find an answer. In this table, we give details of each dataset (sample size, and the number of features), and the average rank that is given to age feature by all the studies that have used that dataset.


Machine learning techniques vs. Datasets

This table reports on the number of published papers using a specific machine learning technique on a dataset.


Frequency of winning machine learning methods

This report shows how popular/successful a machine learning technique is. For each machine learning technique, it reports on the total number of papers that have used it in their analysis, and how many times it outperformed the other techniques.


Papers vs. Specific feature category

Feature categories represent the set of features that are obtained from the same resources. For example, ECG category represents the set of features that are obtained from electrocardiography. For each feature category, this table reports the paper titles and the accuracy they have achieved.


Most cited papers

This table reports on the most cited papers in this field up to the end of September 2018. The report consists of the paper title, year, first author name, publisher, journal/conference name, and the number of citations it has received up to the end of September 2018.


Papers related to classification

This report covers all the papers that have approached the problem from a classification point of view. It covers the paper title, publication year, accuracy, and the method with which that accuracy is achieved.


Papers related to rule-based systems

This report covers all the papers that have approached the problem from a rule-based point of view. It covers the paper title, publication year, accuracy, and the method with which that accuracy is achieved.


Papers related to clustering

This report covers all the papers that have approached the problem from a clustering point of view. It covers the paper title, publication year, and the accuracy it has achieved.


Comparison of machine learning methods in each dataset

Usually, each paper reports the results of applying multiple machine learning methods on a dataset. This table, allows us to compare how these algorithms perform on a dataset. It reports the paper title, the dataset which it has used, and the difference between the accuracy of two selected methods.


Number of papers using a specific algorithm by year

For a given machine learning method, this table reports the number of papers using that method per year, the title of publication with the best performance and the highest accuracy achieved.


Maximum accuracy achieved for a specific feature category by year

Feature categories represent the set of features that are obtained from the same resources. For example, ECG category represents the set of features that are obtained from electrocardiography. For each feature category, this table reports the number of publications per year and the paper that achieved the best performance.


Number of papers and maximum accuracy obtained in each dataset for a specific feature category by year

Feature categories represent the set of features that are obtained from the same resources. For example, ECG category represents the set of features that are obtained from electrocardiography. For each feature category and dataset, this table reports the number of publications per year and the paper that has achieved the best performance.

Number of papers and maximum accuracy for a specific dataset by year

This table reports on the number of publications for a specific dataset by year. Moreover, one can see the title of the paper with the best performance for each dataset/year.


Number of papers in each year

This table reports the number of publications in the field per year.


Number of review papers in each year

This table reports the number of review papers published in the field per year.


Number of published papers in conferences/journals

This table reports the number of papers published in each conference/journal.


Dataset properties

This table reports the properties of collected datasets in the field. The report consists of dataset name, sample size, the country in which the data is collected, number of features, and the number of papers which have used that dataset.


Summary of results achieved on each dataset

This table reports the maximum performance achieved for each dataset/year.


Important features of papers in specific disease

This table reports how papers rank the features of the dataset they have used.


Features of each dataset

This table reports the features collected for each dataset.