gnb  (Biosynth Carbosynth)

Journal: Scientific Reports

Article Title: An extensive experimental analysis for heart disease prediction using artificial intelligence techniques

doi: 10.1038/s41598-025-90530-1

Figure Lengend Snippet: Results of classifiers (in %) without feature selection.

Article Snippet: Models like FCMIM + SVM and GNB also performed well, with FCMIM + SVM on the Cleveland dataset achieving an accuracy of 92.37%, 89% sensitivity, and 98% specificity and with GNB on the Z-Alizadeh Sani, Statlog, and Cardiovascular disease datasets achieving 95.43%, 93.3%, and 73.2% accuracies, 95.84%, 89.2%, and 69.3% sensitivities, 94.44%, 96.7%, and 77% specificities, and 96.77%, 92.1%, and 71.9% F1 scores.

Techniques: Selection

Journal: Scientific Reports

Article Title: An extensive experimental analysis for heart disease prediction using artificial intelligence techniques

doi: 10.1038/s41598-025-90530-1

Figure Lengend Snippet: Results of classifiers (in %) with Information Gain.

Article Snippet: Models like FCMIM + SVM and GNB also performed well, with FCMIM + SVM on the Cleveland dataset achieving an accuracy of 92.37%, 89% sensitivity, and 98% specificity and with GNB on the Z-Alizadeh Sani, Statlog, and Cardiovascular disease datasets achieving 95.43%, 93.3%, and 73.2% accuracies, 95.84%, 89.2%, and 69.3% sensitivities, 94.44%, 96.7%, and 77% specificities, and 96.77%, 92.1%, and 71.9% F1 scores.

Techniques:

Journal: Scientific Reports

Article Title: An extensive experimental analysis for heart disease prediction using artificial intelligence techniques

doi: 10.1038/s41598-025-90530-1

Figure Lengend Snippet: Results of classifiers (in %) with Chi-Square Test.

Article Snippet: Models like FCMIM + SVM and GNB also performed well, with FCMIM + SVM on the Cleveland dataset achieving an accuracy of 92.37%, 89% sensitivity, and 98% specificity and with GNB on the Z-Alizadeh Sani, Statlog, and Cardiovascular disease datasets achieving 95.43%, 93.3%, and 73.2% accuracies, 95.84%, 89.2%, and 69.3% sensitivities, 94.44%, 96.7%, and 77% specificities, and 96.77%, 92.1%, and 71.9% F1 scores.

Techniques:

Journal: Scientific Reports

Article Title: An extensive experimental analysis for heart disease prediction using artificial intelligence techniques

doi: 10.1038/s41598-025-90530-1

Figure Lengend Snippet: Results of classifiers (in %) with FDA.

Article Snippet: Models like FCMIM + SVM and GNB also performed well, with FCMIM + SVM on the Cleveland dataset achieving an accuracy of 92.37%, 89% sensitivity, and 98% specificity and with GNB on the Z-Alizadeh Sani, Statlog, and Cardiovascular disease datasets achieving 95.43%, 93.3%, and 73.2% accuracies, 95.84%, 89.2%, and 69.3% sensitivities, 94.44%, 96.7%, and 77% specificities, and 96.77%, 92.1%, and 71.9% F1 scores.

Techniques:

Journal: Scientific Reports

Article Title: An extensive experimental analysis for heart disease prediction using artificial intelligence techniques

doi: 10.1038/s41598-025-90530-1

Figure Lengend Snippet: Results of classifiers (in %) with Variance Threshold.

Article Snippet: Models like FCMIM + SVM and GNB also performed well, with FCMIM + SVM on the Cleveland dataset achieving an accuracy of 92.37%, 89% sensitivity, and 98% specificity and with GNB on the Z-Alizadeh Sani, Statlog, and Cardiovascular disease datasets achieving 95.43%, 93.3%, and 73.2% accuracies, 95.84%, 89.2%, and 69.3% sensitivities, 94.44%, 96.7%, and 77% specificities, and 96.77%, 92.1%, and 71.9% F1 scores.

Techniques:

Journal: Scientific Reports

Article Title: An extensive experimental analysis for heart disease prediction using artificial intelligence techniques

doi: 10.1038/s41598-025-90530-1

Figure Lengend Snippet: Results of classifiers (in %) with MAD.

Article Snippet: Models like FCMIM + SVM and GNB also performed well, with FCMIM + SVM on the Cleveland dataset achieving an accuracy of 92.37%, 89% sensitivity, and 98% specificity and with GNB on the Z-Alizadeh Sani, Statlog, and Cardiovascular disease datasets achieving 95.43%, 93.3%, and 73.2% accuracies, 95.84%, 89.2%, and 69.3% sensitivities, 94.44%, 96.7%, and 77% specificities, and 96.77%, 92.1%, and 71.9% F1 scores.

Techniques:

Journal: Scientific Reports

Article Title: An extensive experimental analysis for heart disease prediction using artificial intelligence techniques

doi: 10.1038/s41598-025-90530-1

Figure Lengend Snippet: Results of classifiers (in %) with Dispersion Ratio.

Article Snippet: Models like FCMIM + SVM and GNB also performed well, with FCMIM + SVM on the Cleveland dataset achieving an accuracy of 92.37%, 89% sensitivity, and 98% specificity and with GNB on the Z-Alizadeh Sani, Statlog, and Cardiovascular disease datasets achieving 95.43%, 93.3%, and 73.2% accuracies, 95.84%, 89.2%, and 69.3% sensitivities, 94.44%, 96.7%, and 77% specificities, and 96.77%, 92.1%, and 71.9% F1 scores.

Techniques: Dispersion

Journal: Scientific Reports

Article Title: An extensive experimental analysis for heart disease prediction using artificial intelligence techniques

doi: 10.1038/s41598-025-90530-1

Figure Lengend Snippet: Results of classifiers (in %) with Relief.

Article Snippet: Models like FCMIM + SVM and GNB also performed well, with FCMIM + SVM on the Cleveland dataset achieving an accuracy of 92.37%, 89% sensitivity, and 98% specificity and with GNB on the Z-Alizadeh Sani, Statlog, and Cardiovascular disease datasets achieving 95.43%, 93.3%, and 73.2% accuracies, 95.84%, 89.2%, and 69.3% sensitivities, 94.44%, 96.7%, and 77% specificities, and 96.77%, 92.1%, and 71.9% F1 scores.

Techniques:

Journal: Scientific Reports

Article Title: An extensive experimental analysis for heart disease prediction using artificial intelligence techniques

doi: 10.1038/s41598-025-90530-1

Figure Lengend Snippet: Results of classifiers (in %) with Lasso.

Article Snippet: Models like FCMIM + SVM and GNB also performed well, with FCMIM + SVM on the Cleveland dataset achieving an accuracy of 92.37%, 89% sensitivity, and 98% specificity and with GNB on the Z-Alizadeh Sani, Statlog, and Cardiovascular disease datasets achieving 95.43%, 93.3%, and 73.2% accuracies, 95.84%, 89.2%, and 69.3% sensitivities, 94.44%, 96.7%, and 77% specificities, and 96.77%, 92.1%, and 71.9% F1 scores.

Techniques:

Journal: Scientific Reports

Article Title: An extensive experimental analysis for heart disease prediction using artificial intelligence techniques

doi: 10.1038/s41598-025-90530-1

Figure Lengend Snippet: Results of classifiers (in %) with RF Importance.

Article Snippet: Models like FCMIM + SVM and GNB also performed well, with FCMIM + SVM on the Cleveland dataset achieving an accuracy of 92.37%, 89% sensitivity, and 98% specificity and with GNB on the Z-Alizadeh Sani, Statlog, and Cardiovascular disease datasets achieving 95.43%, 93.3%, and 73.2% accuracies, 95.84%, 89.2%, and 69.3% sensitivities, 94.44%, 96.7%, and 77% specificities, and 96.77%, 92.1%, and 71.9% F1 scores.

Techniques:

Journal: Scientific Reports

Article Title: An extensive experimental analysis for heart disease prediction using artificial intelligence techniques

doi: 10.1038/s41598-025-90530-1

Figure Lengend Snippet: Results of classifiers (in %) with LDA.

Article Snippet: Models like FCMIM + SVM and GNB also performed well, with FCMIM + SVM on the Cleveland dataset achieving an accuracy of 92.37%, 89% sensitivity, and 98% specificity and with GNB on the Z-Alizadeh Sani, Statlog, and Cardiovascular disease datasets achieving 95.43%, 93.3%, and 73.2% accuracies, 95.84%, 89.2%, and 69.3% sensitivities, 94.44%, 96.7%, and 77% specificities, and 96.77%, 92.1%, and 71.9% F1 scores.

Techniques:

Journal: Scientific Reports

Article Title: An extensive experimental analysis for heart disease prediction using artificial intelligence techniques

doi: 10.1038/s41598-025-90530-1

Figure Lengend Snippet: Results of classifiers (in %) with PCA.

Article Snippet: Models like FCMIM + SVM and GNB also performed well, with FCMIM + SVM on the Cleveland dataset achieving an accuracy of 92.37%, 89% sensitivity, and 98% specificity and with GNB on the Z-Alizadeh Sani, Statlog, and Cardiovascular disease datasets achieving 95.43%, 93.3%, and 73.2% accuracies, 95.84%, 89.2%, and 69.3% sensitivities, 94.44%, 96.7%, and 77% specificities, and 96.77%, 92.1%, and 71.9% F1 scores.

Techniques:

Journal: Scientific Reports

Article Title: An extensive experimental analysis for heart disease prediction using artificial intelligence techniques

doi: 10.1038/s41598-025-90530-1

Figure Lengend Snippet: Performance of proposed model and state-of-the-art models.

Article Snippet: Models like FCMIM + SVM and GNB also performed well, with FCMIM + SVM on the Cleveland dataset achieving an accuracy of 92.37%, 89% sensitivity, and 98% specificity and with GNB on the Z-Alizadeh Sani, Statlog, and Cardiovascular disease datasets achieving 95.43%, 93.3%, and 73.2% accuracies, 95.84%, 89.2%, and 69.3% sensitivities, 94.44%, 96.7%, and 77% specificities, and 96.77%, 92.1%, and 71.9% F1 scores.

Techniques: