Apat, H.K., Bhaisare, K., Sahoo, B., Maiti, P., Energy Efficient Resource Management in Fog Computing Supported Medical Cyber-Physical System. 2020 International Conference on Computer Science, Engineering and Applications (ICCSEA), Gunupur, India, pp. 1–6, 2020.
25. Mutlag, A.A., Ghani, M.K.A., Arunkumar, N., Mohammed, M.A., Mohd, O., Enabling technologies for fog computing in healthcare IoT systems. Future Gener. Comput. Syst., 90, 62–78, 2019.
26. Singh, S., Bansal, A., Sandhu, R., Sidhu, J., Fog computing and IoT based healthcare support service for dengue fever. Int. J. Pervasive Comput. Commun., 14, 2, 197–207, Jun. 2018.
27. Akintoye, S.B., Bagula, A.B., Isafiade, O.E., Djemaiel, Y., Boudriga, N., Data Model for Cloud Computing Environment. e-Infrastructure and e-Services for Developing Countries. AFRICOMM 2018. Lecture Notes of the Institute for Computer Sciences Social Informatics and Telecommunications Engineering, vol. 275, 2019.
28. Kraemer, F.A., Braten, A.E., Tamkittikhun, N., Palma, D., Fog Computing in Healthcare-A Review and Discussion. IEEE Access, 5, 9206–9222, 2017.
29. Khan, S., Parkinson, S., Qin, Y., Fog computing security: a review of current applications and security solutions. J. Cloud Comput., 6, 1, 19, 2017.
30. Al Hamid, H.A., Rahman, Sk Md M., Shamim Hossain, M., Almogren, A., Alamri, A., A Security Model for Preserving the Privacy of Medical Big Data in a Healthcare Cloud Using a Fog Computing Facility With Pairing-Based Cryptography. IEEE Access, 5, 22313–22328, 2017.
31. Ghosh, A.M., Halder, D., Hossain, S.A., Remote health monitoring system through iot. 2016 International Conference on Informatics Electronics and Vision (ICIEV), pp. 921–926, 2016.
32. Alihamidi, I., Ait Madi, A., Addaim, A., Proposed Architecture of e-health IoT. 2019 International Conference on Wireless Networks and Mobile Communications (WINCOM), Fez, Morocco, pp. 1–7, 2019.
1 *Corresponding author: [email protected]
3
Study of Thyroid Disease Using Machine Learning
Shanu Verma*, Rashmi Popli and Harish Kumar
J.C. Bose University of Science and Technology, Faridabad, India
Abstract
Thyroid problems occur due to the deficiency of iodine. It is a major health problem among the population living with iodine deficiency, and this endocrine disorder has seen common problems everywhere. Thyroid function test based on the value of TSH, T3 and T4, may indicate thyroid dysfunction and may indicate symptoms and signs that are diagnostic of hyperthyroidism or hypothyroidism. Hyperthyroidism in the gland that contains a high amount of thyroid hormone. Hypothyroidism is a gland that does not fabricate thyroid hormone that perform impaired metabolic functions. Graves is the biggest disease in hypothyroidism which is associated with eye disease. An exceptional type of cancer occurring in the thyroid is a thyroid cancer that infects the gland at the base of the neck. Thyroid cancer disease has been increasing for the past few years. Endocrinologists believe that this is due to the use of new technology, i.e., machine learning, intensive learning allows the detection of thyroid cancer that may not have been detected in the past. According to the Cancer Registry, thyroid cancer is the second more common cancer among women of all cancers, with cancer in thyroid occurring at only 3.5%. This chapter studies thyroid disease using machine learning algorithm.
Keywords: Thyroid, thyroid cancer, hypothyroidism, hyperthyroidism, machine learning, classification algorithm
3.1 Introduction
In India, thyroid disorder is the most common endocrine diseases. About 42 lakh population in India is affected by thyroid disorders. The type of thyroid disorder depends on various characteristics such as sex, iodine levels, age, and more [1]. Hyperthyroidism is one of the primary causes of thyroid cancer, although some researchers suggest that up to 20% of people with hyperthyroidism may be prone to thyroid cancer [15].
Thyroid cancer occurs when the thyroid produces hormones that control your heart rate, blood pressure, weight, and body temperature. It shows no signs or symptoms, and when it grows a lump on the neck that can be felt through the skin, the voice has changed and it has become hoarse. There are various classes of thyroid cancer. Some are growing very gradually and others can be very violent. Globally, thyroid cancer accounts for 32% and the incidence of new cases is 3 lakh per year. In addition, 32,000 thyroid cancer patients die annually.
3.2 Related Works
Over the years, many researchers worldwide worked in machine learning, deep learning, artificial intelligence, predictive analytics, and data science in health-related illness about future challenges and opportunities. Although some research works have been done to determine these possible causes, effects, and solutions, yet it is still a global problem. This chapter will study of thyroid disease using machine learning. Various researchers has studied research work basis for our research and understanding. There are some research papers in this regard are described below.
Parry and Kripke [11] have discussed thyroid effect on women mood disorders. Women have a higher risk of premenstrual, peripartum, and perimenopause that may occur in puberty with oral contraceptive onset and depressive illness. This paper study case reports of various persons and suggest some treatment guidelines such as Treatment-Resistant Unipolar Depression and Rapid Cycling Mood disorders. The conclusion of this paper is that, as compared to men, women have high number of depression.
Razia et al. [20] have studied various machine learning algorithms and comparison between them to achieve better accuracy in the prediction of thyroid disease. The conclusion of this paper is that the decision trees has better accuracy as compared to the naïve Bayes, SVM, and, multi-linear regression.
Pakdel and Ghazavi [12] have described selenium effect on Thyroid disorders. This paper conducts literature survey over the past 20 years’ (1995–2014) papers and discussed that this topic has increased in recent years. This literature paper was restricted to two index such as Social Science Citation Index and Science Citation Index Expanded and performing searching using keyword. The conclusion of this research is that similar studies have to be carried within next 5 years.
Priyanka et al. [1] have studied thyroid disease among women from rural and urban populations in Bangalore. It is described in this letter that every eight women in Bangalore are suffering from thyroid disease. This study was done at the actual hospital in Bangalore.
Godara [17] have predicted thyroid disease using machine learning technique. The method used to detect thyroid disease such as support vector machine and logistic regression on basis of recall, F-measure, error, ROC, and precision. To compare these techniques, Weka version is used.
Mathew [16] have studied thyroid cancer in South India. This study based on population taken from the Registry Program of National Cancer from 2005 to 2014. This paper studies the thyroid cancer patient in Thiruvananthapuram district and compares it with the other four regions Delhi, Mumbai, Bangalore, and Chennai. This paper found that Thiruvananthapuram has a higher rate of thyroid cancer in patients than in the other four regions.
3.3
