Enhancing thyroid disease prediction and comorbidity management through advanced machine learning frameworks
Thyroid disease is one of the most prevalent endocrine disorders worldwide, necessitating precise and efficient diagnostic models for improved clinical outcomes. This study proposes a Hybrid Feature Selection and Deep Learning Framework (HFSDLF) that integrates Random Forests with Principal Componen...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2025-12-01
|
| Series: | Clinical eHealth |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2588914125000024 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590014575280128 |
|---|---|
| author | P. Sanju N. Syed Siraj Ahmed P. Ramachandran P. Mohamed Sajid R. Jayanthi |
| author_facet | P. Sanju N. Syed Siraj Ahmed P. Ramachandran P. Mohamed Sajid R. Jayanthi |
| author_sort | P. Sanju |
| collection | DOAJ |
| description | Thyroid disease is one of the most prevalent endocrine disorders worldwide, necessitating precise and efficient diagnostic models for improved clinical outcomes. This study proposes a Hybrid Feature Selection and Deep Learning Framework (HFSDLF) that integrates Random Forests with Principal Component Analysis (PCA) and L1 regularization for effective feature selection and classification. Utilizing the UCI Thyroid Dataset, the framework combines the strengths of deep learning-based feature extraction and traditional machine learning classifiers. The Random Forest classifier achieved the highest accuracy of 96.30 %, outperforming other models such as Decision Trees and Logistic Regression, with notable improvements in sensitivity and specificity. The novelty of this work lies in its hybrid approach to feature selection, which reduces dimensionality while retaining the most informative features, and its application of an optimized Random Forest model for enhanced classification accuracy. Comparative analysis with existing methods further highlights the superiority of the proposed framework in terms of accuracy and processing efficiency. This research addresses key limitations of existing approaches and contributes to the field by demonstrating a scalable and interpretable solution for thyroid disease diagnosis. The proposed framework provides a benchmark for future studies, underscoring the importance of hybrid methodologies in medical data analysis. |
| format | Article |
| id | doaj-art-df4bb504cb654e6faf60327119308537 |
| institution | Kabale University |
| issn | 2588-9141 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Clinical eHealth |
| spelling | doaj-art-df4bb504cb654e6faf603271193085372025-01-24T04:45:33ZengKeAi Communications Co., Ltd.Clinical eHealth2588-91412025-12-018716Enhancing thyroid disease prediction and comorbidity management through advanced machine learning frameworksP. Sanju0N. Syed Siraj Ahmed1P. Ramachandran2P. Mohamed Sajid3R. Jayanthi4Department of Computer Science and Engineering, University College of Engineering, Tindivanam, Anna University, India; Corresponding author.School of Computer Science Engineering and Information Science, Presidency University, Bangalore, IndiaDepartment of MCA, Parul Institute of Engineering and Technology, Parul University, P.O.Limda, Tal.waghodia, Dist., Vadodra, IndiaDepartment of ECE, C. Abdul Hakeem College of Engineering and Technology, Melvisharam, IndiaDepartment of MCA, Dayananda Sagar College of Engineering, Kumaraswamy Layout, Bangalore 560078, IndiaThyroid disease is one of the most prevalent endocrine disorders worldwide, necessitating precise and efficient diagnostic models for improved clinical outcomes. This study proposes a Hybrid Feature Selection and Deep Learning Framework (HFSDLF) that integrates Random Forests with Principal Component Analysis (PCA) and L1 regularization for effective feature selection and classification. Utilizing the UCI Thyroid Dataset, the framework combines the strengths of deep learning-based feature extraction and traditional machine learning classifiers. The Random Forest classifier achieved the highest accuracy of 96.30 %, outperforming other models such as Decision Trees and Logistic Regression, with notable improvements in sensitivity and specificity. The novelty of this work lies in its hybrid approach to feature selection, which reduces dimensionality while retaining the most informative features, and its application of an optimized Random Forest model for enhanced classification accuracy. Comparative analysis with existing methods further highlights the superiority of the proposed framework in terms of accuracy and processing efficiency. This research addresses key limitations of existing approaches and contributes to the field by demonstrating a scalable and interpretable solution for thyroid disease diagnosis. The proposed framework provides a benchmark for future studies, underscoring the importance of hybrid methodologies in medical data analysis.http://www.sciencedirect.com/science/article/pii/S2588914125000024Machine learningThyroid diseaseThyoid eye diseaseEndocrine disorder |
| spellingShingle | P. Sanju N. Syed Siraj Ahmed P. Ramachandran P. Mohamed Sajid R. Jayanthi Enhancing thyroid disease prediction and comorbidity management through advanced machine learning frameworks Clinical eHealth Machine learning Thyroid disease Thyoid eye disease Endocrine disorder |
| title | Enhancing thyroid disease prediction and comorbidity management through advanced machine learning frameworks |
| title_full | Enhancing thyroid disease prediction and comorbidity management through advanced machine learning frameworks |
| title_fullStr | Enhancing thyroid disease prediction and comorbidity management through advanced machine learning frameworks |
| title_full_unstemmed | Enhancing thyroid disease prediction and comorbidity management through advanced machine learning frameworks |
| title_short | Enhancing thyroid disease prediction and comorbidity management through advanced machine learning frameworks |
| title_sort | enhancing thyroid disease prediction and comorbidity management through advanced machine learning frameworks |
| topic | Machine learning Thyroid disease Thyoid eye disease Endocrine disorder |
| url | http://www.sciencedirect.com/science/article/pii/S2588914125000024 |
| work_keys_str_mv | AT psanju enhancingthyroiddiseasepredictionandcomorbiditymanagementthroughadvancedmachinelearningframeworks AT nsyedsirajahmed enhancingthyroiddiseasepredictionandcomorbiditymanagementthroughadvancedmachinelearningframeworks AT pramachandran enhancingthyroiddiseasepredictionandcomorbiditymanagementthroughadvancedmachinelearningframeworks AT pmohamedsajid enhancingthyroiddiseasepredictionandcomorbiditymanagementthroughadvancedmachinelearningframeworks AT rjayanthi enhancingthyroiddiseasepredictionandcomorbiditymanagementthroughadvancedmachinelearningframeworks |