Embedded Feature Selection Augmented Thyroid Disorder Prediction using MLP
DOI:
https://doi.org/10.24203/5rxj7f54Keywords:
Thyroid Disorder, Feature Selection, Classification, Deep Neural Network, MLPAbstract
Due to its considerable fatality rate and increasing frequency, thyroid disorders pose a severe hazard to people's health in the modern era. Thus, it has become a useful topic to predict thyroid disease early on using a few basic physical indications that are gathered from routine physical examinations. Being aware of these thyroid-related signs is crucial from a clinical standpoint in order to forecast outcomes and offer a solid foundation for additional diagnosis. However, manual analysis and prediction are difficult and tiring due to the vast volume of data. Our goal is to use a variety of bodily signs to swiftly and reliably predict thyroid disorders. This research presents a novel prediction model for thyroid disorders. We provide a deep neural network and embedded feature selection method-based algorithm for predicting thyroid disorders. Based on the LinearSVC algorithm, this embedded feature selection method selects a subset of characteristics that are strongly linked with thyroid condition by employing the L1 norm as a penalty item. We feed these features into the deep neural network that we constructed. To improve the performance of the predictor, gradient varnishing or explosion is avoided by initializing the network's weight using the He initializer. The predictor is evaluated using a number of indicators like accuracy, recall, precision and F1-score. The results indicate that our model achieves 98.3%, 98.1%, 98.0% and 0.982 respectively, and that its average AUC score is 0.98, indicating that the approach we proposed is effective and trustworthy for predicting thyroid disorders.
References
Li, J., et al. (2018). "Automatic Detection of Thyroid Nodules in Ultrasound Images Using Convolutional Neural Networks." IEEE Transactions on Medical Imaging, 37(9), 1942–1951.
Zhang, Y., et al. (2020). "Thyroid Nodule Characterization Using 3-D Shear Wave Elastography With Convolutional Neural Networks: A Diagnostic Accuracy Study." Frontiers in Oncology, 10, 559688.
Wang, H., et al. (2019). "Predicting Thyroid Dysfunction Using Personalized Feature Selection Techniques and Ensemble Learning Models." Journal of Medical Systems, 43(12), 348.
Jiang, Y., et al. (2021). "Deep Learning for Thyroid Dysfunction Prediction Using Electronic Health Records." Journal of Medical Internet Research, 23(6), e27271.
Smith, B., et al. (2017). "A Bayesian Networks Approach for Predicting Thyroid Nodule Malignancy in Indeterminate Cases." Expert Systems with Applications, 88, 256–264.
Yang, L., et al. (2022). "Integrating Genetic and Clinical Information Improves Thyroid Disease Prediction." Frontiers in Genetics, 13, 781350.
Wu, Y., et al. (2019). "A Multi-Modal Deep Neural Network for Joint Analysis of Clinical Notes and Microscopic Pathology Images in Thyroid Cancer Detection." IEEE Journal of Biomedical and Health Informatics, 23(4), 1610–1620.
Chen, X., et al. (2021). "Comprehensive Analysis of Thyroid Disorder Prediction Using Multi-Modal Data With Deep Learning." Frontiers in Endocrinology, 12, 689040.
Zhang, X., et al. (2019). "Transfer Learning Based Convolutional Neural Network for Differential Diagnosis of Thyroid Nodules in Ultrasound Images." Frontiers in Endocrinology, 10, 286.
Wu, H., et al. (2020). "Transfer Learning for Thyroid Nodule Classification in Ultrasound Images." Frontiers in Oncology, 10, 176.
Park, H., et al. (2021). "Interpretable Thyroid Nodule Malignancy Prediction Using an Attention Mechanism." Journal of Digital Imaging, 34(5), 1144–1153.
Liang, Y., et al. (2022). "Explainable Deep Learning for Thyroid Disease Diagnosis: A Systematic Review." Frontiers in Endocrinology, 13, 850.
Sharma, A., et al. (2020). "Challenges in Deploying Artificial Intelligence Models in Clinical Practice for Thyroid Nodule Diagnosis." Frontiers in Endocrinology, 11, 575.
Zhang, L., et al. (2021). "Ethical Concerns and Bias in Artificial Intelligence Applications for Thyroid Disorder Predictions: A Scoping Review." Frontiers in Endocrinology, 12, 722752.
Wang, Y., et al. (2018). "Deep Convolutional Neural Network-Based Image Analysis for Classifying Thyroid Nodules in Ultrasound Images." Medical Engineering & Physics, 57, 15–26.
Jiang, Y., et al. (2020). "Comparison of Machine Learning Models for Thyroid Disorder Diagnosis: A Systematic Review." Frontiers in Endocrinology, 11, 384.
Li, M., et al. (2022). "Federated Learning for Collaborative Diagnosis of Thyroid Disorders: A Comprehensive Review." IEEE Journal of Biomedical and Health Informatics, 26(4), 1203–1215.
Zhang, W., et al. (2023). "Advances in 3D Imaging for Thyroid Nodule Analysis: A Comprehensive Review." Journal of Clinical Medicine, 12(1), 36.
Liu, F., et al. (2019). "Robustness of Convolutional Neural Networks for Thyroid Nodule Classification: A Cross-Vendor Study." Ultrasound in Medicine & Biology, 45(6), 1475–1483.
Xu, Y., et al. (2021). "Mitigating the Impact of Small Sample Sizes in Deep Learning Models for Thyroid Disorder Prediction." Frontiers in Endocrinology, 12, 716999.
Kim, J., et al. (2020). "Deep Learning-Based Stratification of Thyroid Nodule Pathology: A Multicenter Study." Thyroid, 30(5), 762–772.
Wu, J., et al. (2022). "Personalized Therapeutic Strategy Recommendation for Thyroid Cancer Patients Using Deep Neural Networks." Frontiers in Oncology, 12, 810887.
Thyroid Imaging Network (TINet). Retrieved from [https://www.thyroidimaging.net/](https://www.thyroidimaging.net/)
ThyroNet Consortium. Retrieved from [https://www.thyronet.org/](https://www.thyronet.org/)
Guo, H., et al. (2021). "Impact of Deep Neural Networks on Clinical Decision-Making in Thyroid Disorder Diagnosis: A Systematic Review." Frontiers in Endocrinology, 12, 625280.
Zhao, S., et al. (2022). "Integrating Deep Neural Networks into Electronic Health Records for Real-Time Thyroid Disorder Predictions." Journal of Medical Internet Research, 24(1), e32753.
Das, D., et al. (2020). "Deploying Deep Neural Networks in Low-Resource Settings for Efficient Thyroid Disorder Screening: Opportunities and Challenges." Frontiers in Public Health, 8, 585888.
Patel, M., et al. (2021). "Challenges and Opportunities for Implementing Deep Neural Networks in Remote and Underserved Regions for Thyroid Disorder Diagnosis." Frontiers in Digital Health, 3, 678122.
Wong, W., et al. (2019). "Public Perceptions and Knowledge About Artificial Intelligence-Driven Thyroid Diagnosis: A Cross-Sectional Study." Frontiers in Endocrinology, 10, 544.
X. Glorot and Y. Bengio, Understanding the difficulty of training deep feedforward neural networks, in Proceedings of the Thirteenth International Conference on Artificial Intelli-gence and Statistics, PMLR, vol. 9, pp. 249256, Sardinia, Italy, May 2010.
K. He, X. Zhang, S. Ren, and J. Sun, Delving deep into rectifiers: surpassing human-level performance on ImageNet classification, in Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 10261034, Santiago, Chile, December 2015.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Mir Saleem, Shabir Najar, Malik Akhtar Rasool
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The articles published in International Journal of Computer and Information Technology (IJCIT) is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
