eprintid: 3480 rev_number: 9 eprint_status: archive userid: 2 dir: disk0/00/00/34/80 datestamp: 2022-09-06 17:30:02 lastmod: 2023-07-18 23:30:11 status_changed: 2022-09-06 17:30:02 type: article metadata_visibility: show creators_name: Chaganti, Rajasekhar creators_name: Rustam, Furqan creators_name: De La Torre Díez, Isabel creators_name: Vidal Mazón, Juan Luis creators_name: Rodríguez Velasco, Carmen Lilí creators_name: Ashraf, Imran creators_id: creators_id: creators_id: creators_id: juanluis.vidal@uneatlantico.es creators_id: carmen.rodriguez@uneatlantico.es creators_id: title: Thyroid Disease Prediction Using Selective Features and Machine Learning Techniques ispublished: pub subjects: uneat_eng divisions: uneatlantico_produccion_cientifica divisions: uninimx_produccion_cientifica divisions: uninipr_produccion_cientifica divisions: unic_produccion_cientifica full_text_status: public keywords: machine learning; thyroid prediction; forward feature selection; bidirectional feature elimination abstract: Thyroid disease prediction has emerged as an important task recently. Despite existing approaches for its diagnosis, often the target is binary classification, the used datasets are small-sized and results are not validated either. Predominantly, existing approaches focus on model optimization and the feature engineering part is less investigated. To overcome these limitations, this study presents an approach that investigates feature engineering for machine learning and deep learning models. Forward feature selection, backward feature elimination, bidirectional feature elimination, and machine learning-based feature selection using extra tree classifiers are adopted. The proposed approach can predict Hashimoto’s thyroiditis (primary hypothyroid), binding protein (increased binding protein), autoimmune thyroiditis (compensated hypothyroid), and non-thyroidal syndrome (NTIS) (concurrent non-thyroidal illness). Extensive experiments show that the extra tree classifier-based selected feature yields the best results with 0.99 accuracy and an F1 score when used with the random forest classifier. Results suggest that the machine learning models are a better choice for thyroid disease detection regarding the provided accuracy and the computational complexity. K-fold cross-validation and performance comparison with existing studies corroborate the superior performance of the proposed approach. date: 2022-08 publication: Cancers volume: 14 number: 16 pagerange: 3914 id_number: doi:10.3390/cancers14163914 refereed: TRUE issn: 2072-6694 official_url: http://doi.org/10.3390/cancers14163914 access: open language: en citation: Artículo Materias > Ingeniería Universidad Europea del Atlántico > Investigación > Producción Científica Universidad Internacional Iberoamericana México > Investigación > Producción Científica Universidad Internacional Iberoamericana Puerto Rico > Investigación > Producción Científica Universidad Internacional do Cuanza > Investigación > Producción Científica Abierto Inglés Thyroid disease prediction has emerged as an important task recently. Despite existing approaches for its diagnosis, often the target is binary classification, the used datasets are small-sized and results are not validated either. Predominantly, existing approaches focus on model optimization and the feature engineering part is less investigated. To overcome these limitations, this study presents an approach that investigates feature engineering for machine learning and deep learning models. Forward feature selection, backward feature elimination, bidirectional feature elimination, and machine learning-based feature selection using extra tree classifiers are adopted. The proposed approach can predict Hashimoto’s thyroiditis (primary hypothyroid), binding protein (increased binding protein), autoimmune thyroiditis (compensated hypothyroid), and non-thyroidal syndrome (NTIS) (concurrent non-thyroidal illness). Extensive experiments show that the extra tree classifier-based selected feature yields the best results with 0.99 accuracy and an F1 score when used with the random forest classifier. Results suggest that the machine learning models are a better choice for thyroid disease detection regarding the provided accuracy and the computational complexity. K-fold cross-validation and performance comparison with existing studies corroborate the superior performance of the proposed approach. metadata Chaganti, Rajasekhar; Rustam, Furqan; De La Torre Díez, Isabel; Vidal Mazón, Juan Luis; Rodríguez Velasco, Carmen Lilí y Ashraf, Imran mail SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, juanluis.vidal@uneatlantico.es, carmen.rodriguez@uneatlantico.es, SIN ESPECIFICAR (2022) Thyroid Disease Prediction Using Selective Features and Machine Learning Techniques. Cancers, 14 (16). p. 3914. ISSN 2072-6694 document_url: http://repositorio.unini.edu.mx/id/eprint/3480/1/cancers-14-03914-v2.pdf