| _version_ | 1866901530508001280 |
|---|---|
| author | Ms. Hiralkumari Babulal Chauhan |
| author_facet | Ms. Hiralkumari Babulal Chauhan |
| contents | <p>The Heart disease is a leading cause of morbidity and death worldwide, so, requiring accurate and reliable prediction models. The study draws upon a comprehensive dataset containing clinical and demographic data collected from a various population on earth. We assessed performance in terms of prediction accuracy, sensitivity, specificity and Area under the receiver operating characteristic curve through a rigorous evaluation. It explores the impact of various factors like feature selection, data pre-processing and model optimization, etc., on the performance of each technique. The results of comparative analysis provide valuable insights of the strengths Deep learning using TansorFlow platform for heart disease prediction. The research also, guides researchers and practitioners in selecting the most applicable technique. It have citations selected from recent and reputable sources to support the analysis and findings. Furthermore, the study highlights the importance of continuously improving prediction models to enhance heart disease diagnosis and intervention strategies. The study divided into sections, namely: literature, Methodology of algorithms, database exploration and processing, results comparison, conclusion and limitation with future work.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_18610028 |
| institution | Zenodo |
| language | |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | An Empirical Evaluation of Regression, AdaBoost and TensorFlow Models for Heart Disease Prediction Ms. Hiralkumari Babulal Chauhan <p>The Heart disease is a leading cause of morbidity and death worldwide, so, requiring accurate and reliable prediction models. The study draws upon a comprehensive dataset containing clinical and demographic data collected from a various population on earth. We assessed performance in terms of prediction accuracy, sensitivity, specificity and Area under the receiver operating characteristic curve through a rigorous evaluation. It explores the impact of various factors like feature selection, data pre-processing and model optimization, etc., on the performance of each technique. The results of comparative analysis provide valuable insights of the strengths Deep learning using TansorFlow platform for heart disease prediction. The research also, guides researchers and practitioners in selecting the most applicable technique. It have citations selected from recent and reputable sources to support the analysis and findings. Furthermore, the study highlights the importance of continuously improving prediction models to enhance heart disease diagnosis and intervention strategies. The study divided into sections, namely: literature, Methodology of algorithms, database exploration and processing, results comparison, conclusion and limitation with future work.</p> |
| title | An Empirical Evaluation of Regression, AdaBoost and TensorFlow Models for Heart Disease Prediction |
| url | https://doi.org/10.5281/zenodo.18610028 |