Semi-Supervised Machine Learning Approaches for Thyroid Disease Prediction and its Integration With the Internet of Everything.

Melih Agraz

doi:10.9781/ijimai.2024.07.006

Authors

Melih Agraz Brown University

DOI:

https://doi.org/10.9781/ijimai.2024.07.006

Keywords:

FixMatch, IoE Medical Systems, Machine Learning, Thyroid Disease

Abstract

Thyroid disorders are critical conditions that considerably affect a person’s general health, and may lead to additional health complications. Notably, these conditions often remain undetected in individuals who show "normal" results on traditional thyroid function tests. To enhance the diagnostic accuracy for thyroid disorders, such as hypothyroidism and hyperthyroidism, this study leveraged digital health records and explored semisupervised learning methods. We intentionally removed the labels from subjects initially categorized as "normal," incorporating them into our dataset as unlabeled data. The goal was to overcome the limitations of conventional diagnostic techniques, which may fail to detect subtle imbalances in thyroid hormones. In pursuit of this objective, we employed a combination of semi-supervised learning methods, namely FixMatch, Co-training, and self-training, in conjunction with supervised learning algorithms, specifically Naive Bayes and logistic regression. Our findings indicate that the FixMatch algorithm surpassed traditional supervised learning methods in various metrics, including accuracy (0.9054), sensitivity (0.9494), negative predictive value (0.9365), and F1 score (0.9146). Additionally, we propose a framework for integrating these diagnostic tools into the Internet of Everything (IoE) to promote early detection and facilitate improved healthcare outcomes. This research highlights the potential of semi-supervised learning techniques in the diagnosis of thyroid disorders and offers a roadmap for harnessing the IoE in healthcare advancement.

Downloads

Download data is not yet available.

References

Q. Yu, J. Ren, Y. Fu, Y. Li, W. Zhang, “Cybertwin: An origin of next generation network architecture,” IEEE Wireless Communications, vol. 26, no. 6, pp. 111–117, 2019.

S. Abdelwahab, B. Hamdaoui, M. Guizani, A. Rayes, “Enabling smart cloud services through remote sensing: An internet of everything enabler,” IEEE Internet of Things Journal, vol. 1, no. 3, pp. 276–288, 2014.

M. Deore, U. Kulkarni, “MDFRCNN: Malware detection using faster region proposals convolution neural network,” International Journal of Interactive Multimedia and Artificial Intelligence, vol. 7, no. 4, pp. 146–162, 2022.

R. Quinlan, “Thyroid Disease.” UCI Machine Learning Repository, 1987. DOI: https://doi.org/10.24432/C5D010

A. Rghioui, A. Naja, J. L. Mauri, A. Oumnad, “An iot based diabetic patient monitoring system using machine learning and node mcu,” in Journal of Physics: Conference Series, vol. 1743, 2021, p. 012035, IOP Publishing.

N. E. Maghawry, S. Ghoniemy, “A proposed internet of everything framework for disease prediction,” International Journal of Online & Biomedical Engineering, vol. 15, no. 4, 2019.

G. B. Raja, C. Chakraborty, “Internet of things based effective wearable healthcare monitoring system for remote areas,” in Implementation of Smart Healthcare Systems using AI, IoT, and Blockchain, Elsevier, 2023, pp. 193–218.

C. Sivaparthipan, B. A. Muthu, G. Manogaran, B. Maram, R. Sundarasekar, S. Krishnamoorthy, C.-H. Hsu, K. Chandran, “Innovative and efficient method of robotics for helping the parkinson’s disease patient using iot in big data analytics,” Transactions on Emerging Telecommunications Technologies, vol. 31, no. 12, p. e3838, 2020.

A. Singh, A. Kumar, S. Namasudra, “Dnacds: Cloud ioe big data security and accessing scheme based on dna cryptography,” International Journal of Interactive Multimedia and Artificial Intelligence, vol. 18, no. 1, pp. 181–801, 2023.

J. Ahamed, A. Manan Koli, K. Ahmad, A. Jamal, B. Gupta, et al., “CDPSIoT: cardiovascular disease prediction system based on iot using machine learning,” International Journal of Interactive Multimedia and Artificial Intelligence, vol. 7, no. 4, pp. 78–86, 2022.

A. Mostbeck, G. Galvan, P. Bauer, O. Eber, K. Atefie, K. Dam, H. Feichtinger, H. Fritzsche, H. Haydl, H. Köhn, et al., “The incidence of hyperthyroidism in austria from 1987 to 1995 before and after an increase in salt iodization in 1990,” European Journal of Nuclear Medicine, vol. 25, pp. 367–374, 1998.

P. A. Farling, “Thyroid disease,” British Journal of Anaesthesia, vol. 85, no. 1, pp. 15–28, 2000.

J. Muñoz-Ortiz, M. C. Sierra-Cote, E. Zapata-Bravo, L. ValenzuelaVallejo, M. A. Marin-Noriega, P. Uribe- Reina, J. P. Terreros-Dorado, M. Gómez-Suarez, K. Arteaga-Rivera, A. De-La-Torre, “Prevalence of hyperthyroidism, hypothyroidism, and euthyroidism in thyroid eye disease: a systematic review of the literature,” Systematic Reviews, vol. 9, no. 1, pp. 1–12, 2020.

L. Ozyilmaz, T. Yildirim, “Diagnosis of thyroid disease using artificial neural network methods,” in Proceedings of the 9th International Conference on Neural Information Processing, 2002, ICONIP’02, vol. 4, 2002, pp. 2033–2036, IEEE.

I. Kravets, “Hyperthyroidism: diagnosis and treatment,” American family physician, vol. 93, no. 5, pp. 363–370, 2016.

J. Kvetny, “The significance of clinical euthyroidism on reference range for thyroid hormones,” European Journal of Internal Medicine, vol. 14, no. 5, pp. 315–320, 2003.

K. Hedayat, J. Lapraz, “A new approach to biological modeling: Introduction to the biology of functions,” Theory Endobiogeny, vol. 15, pp. 215–254, 2019.

E. G. Keramidas, D. K. Iakovidis, D. Maroulis, S. Karkanis, “Efficient and effective ultrasound image analysis scheme for thyroid nodule detection,” in Image Analysis and Recognition: 4th International Conference, ICIAR 2007, Montreal, Canada, August 22-24, 2007. Proceedings 4, 2007, pp. 1052– 1060, Springer.

S. Razia, M. Rama Narasingarao, “A neuro computing frame work for thyroid disease diagnosis using machine learning techniques,” Journal of Theoretical and Applied Information Technology, vol. 95, pp. 1996–2005, 05 2017.

A. Andueza, M. Arco-Osuna, B. Fornés, R. Gonzalez Crespo, J. Martín Álvarez, “Using the statistical machine learning models arima and sarima to measure the impact of covid-19 on official provincial sales of cigarettes in spain,” International Journal of Interactive Multimedia and Artificial Intelligence, vol. 8, no. 1, pp. 73–87, 2023.

M. Qasim Gandapur, E. Verdú, “ConvGRU-CNN: Spatiotemporal deep learning for real-world anomaly detection in video surveillance system,” International Journal of Interactive Multimedia and Artificial Intelligence, vol. 8, no. 4, pp. 88–95, 2023.

M. Martín Merino, A. J. López Rivero, V. Alonso, M. Vallejo, A. Ferreras, “A clustering algorithm based on an ensemble of dissimilarities: An application in the bioinformatics domain,” International Journal of Interactive Multimedia and Artificial Intelligence, vol. 7, no. 6, pp. 6–13, 2022.

G. Turk, M. Ozdemir, R. Zeydan, Y. Turk, Z. Bilgin, E. Zeydan, “On the identification of thyroid nodules using semi-supervised deep learning,” International Journal for Numerical Methods in Biomedical Engineering, vol. 37, no. 3, p. e3433, 2021.

K. Zhang, Z. Li, C. Cai, J. Liu, D. Xu, C. Fang, P. Huang, Y. Wang, M. Yang, S. Chang, “Semi- supervised graph convolutional networks for the domain adaptive recognition of thyroid nodules in cross-device ultrasound images,” Medical Physics, vol. 50, pp. 7806–7821, 2023.

W. Yang, J. Zhao, Y. Qiang, X. Yang, Y. Dong, Q. Du, G. Shi, M. B. Zia, “Dscgans: Integrate domain knowledge in training dual-path semi-supervised conditional generative adversarial networks and s3vm for ultrasonography thyroid nodules classification,” in Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part IV 22, 2019, pp. 558–566, Springer.

S. H. Requena, J. M. G. Nieto, A. Popov, I. N. Delgado, “Human activity recognition from sensorised patient’s data in healthcare: A streaming deep learning-based approach,” International Journal of Interactive Multimedia and Artificial Intelligence, vol. 8, no. 1, pp. 23–37, 2023.

S. Razia, M. N. Rao, “Machine learning techniques for thyroid disease diagnosis-a review,” Indian Journal of Science and Technology, vol. 9, no. 28, pp. 1–9, 2016.

G. Chaubey, D. Bisen, S. Arjaria, V. Yadav, “Thyroid disease prediction using machine learning approaches,” National Academy Science Letters, vol. 44, no. 3, pp. 233–238, 2021.

Z. J. Peya, M. K. N. Chumki, K. M. Zaman, “Predictive analysis for thyroid diseases diagnosis using machine learning,” in 2021 International conference on science & contemporary technologies (ICSCT), 2021, pp. 1–6, IEEE.

L. Royakkers, J. Timmer, L. Kool, R. Van Est, “Societal and ethical issues of digitization,” Ethics and Information Technology, vol. 20, pp. 127–142, 2018.

T. Jacquemard, C. P. Doherty, M. B. Fitzsimons, “The anatomy of electronic patient record ethics: a framework to guide design, development, implementation, and use,” BMC Medical Ethics, vol. 22, no. 1, pp. 1–14, 2021.

K. M. Besher, Z. Subah, M. Z. Ali, “Iot sensor initiated healthcare data security,” IEEE Sensors Journal, vol. 21, no. 10, pp. 11977–11982, 2020.

M. E. Shipe, S. A. Deppen, F. Farjah, E. L. Grogan, “Developing prediction models for clinical use using logistic regression: an overview,” Journal of thoracic disease, vol. 11, no. Suppl 4, p. S574, 2019.

P. Schober, T. R. Vetter, “Logistic regression in medical research,” Anesthesia & Analgesia, vol. 132, no. 2, pp. 365–366, 2021.

S. Joshi, B. Pandey, N. Joshi, “Comparative analysis of naive bayes and j48 classification algorithms,” International Journal of Advanced Research in Computer Science and Software Engineering, vol. 5, no. 12, pp. 813– 817, 2015.

R. Rajeswari, K. Juliet, D. Aradhana, “Text classification for student data set using naive bayes classifier and knn classifier,” International Journal of Emerging Trends & Technology in Computer Science, vol. 43, no. 1, pp. 8– 12, 2017.

B. Bustami, “Penerapan algoritma naive bayes untuk mengklasifikasi data nasabah asuransi,” TECHSI- Jurnal Teknik Informatika, vol. 5, no. 2, 2013.

H. Muhamad, C. A. Prasojo, N. A. Sugianto, L. Surtiningsih, I. Cholissodin, “Optimasi naïve bayes classifier dengan menggunakan particle swarm optimization pada data iris,” Journal Teknologi Informasi dan Ilmu Komputer, vol. 4, no. 3, p. 180, 2017.

K. Sohn, D. Berthelot, N. Carlini, Z. Zhang, H. Zhang, C. A. Raffel, E. D. Cubuk, A. Kurakin, C.-L. Li, “Fixmatch: Simplifying semi-supervised learning with consistency and confidence,” Advances in neural information processing systems, vol. 33, pp. 596–608, 2020.

A. Blum, T. Mitchell, “Combining labeled and unlabeled data with co-training,” in Proceedings of the eleventh annual conference on Computational learning theory, 1998, pp. 92–100.

G. P. Redmond, “Thyroid dysfunction and women’s reproductive health,” Thyroid, vol. 14, no. 3, Supplement 1, pp. 5–15, 2004.

R. Sharma, G. K. Mahanti, C. Chakraborty, G. Panda, A. Rath, “An iot and deep learning-based smart healthcare framework for thyroid cancer detection,” ACM Transactions on Internet Technology, 2023.

X. Zhang, V. C. Lee, J. Rong, J. C. Lee, F. Liu, “Deep convolutional neural networks in thyroid disease detection: a multi-classification comparison by ultrasonography and computed tomography,” Computer Methods and Programs in Biomedicine, vol. 220, p. 106823, 2022.

X. Zhang, V. C. Lee, J. Rong, J. C. Lee, J. Song, F. Liu, “A multi-channel deep convolutional neural network for multi-classifying thyroid diseases,” Computers in Biology and Medicine, vol. 148, p. 105961, 2022.

H. Lu, M. Wang, W. Zhao, T. Su, J. Yang, “Hyperthyroidism progress prediction with enhanced lstm,” in Web and Big Data: 4th International Joint Conference, APWeb-WAIM 2020, Tianjin, China, September 18-20, 2020, Proceedings, Part II 4, 2020, pp. 209–217, Springer.

A. Santillan, R. C. Tomas, R. Bangaoil, R. Lopez, M. H. Gomez, A. Fellizar, A. Lim, L. Abanilla, M. C. Ramos, L. Guevarra, et al., “Discrimination of malignant from benign thyroid lesions through neural networks using ftir signals obtained from tissues,” Analytical and Bioanalytical Chemistry, vol. 413, pp. 2163–2180, 2021.