scholarly journals Expanded and Filtered Features based ELM Model for Thyroid Disease Classification

Author(s):  
Kapil Juneja

Abstract Thyroid disorder affects the regulation of various metabolic processes throughout the human body. The structural and functional disorders can affect the body as well as the brain. The computer-aided diagnosis system can identify the kind of Thyroid disease. One such machine learning framework is presented in this paper to recognize disease existence and type. In this paper, a fuzzy adaptive feature filtration, expansion, and again filtration based model is presented for generating the most relevant and contributing features. This two-level filtration model is processed in a controlled fuzzy-based multi-measure evaluation. At the first level, the composite-fuzzy measures are combined with expert’s recommendations for identifying the ranked and relevant features. At the second level, the statistical computation based distance measure is applied for expanding the featureset. The fuzzification is applied to expanded featureset for transiting the continuous values to fuzzy-values. At this level, the fuzzy-based composite-measure is applied for selecting the most contributing and relevant features over the expanded dataset. This processing featureset is processed by the ELM classifier to predict the disease existence and class. Five experiments are conducted on two datasets for validating the performance and reliability of the proposed framework. The comparative analysis is conducted against the NaiveBayes, Decision Tree, Decision Forest, Random Tree, Multilevel Perceptron, and RBF Networks. The analysis outcome is taken in terms of accuracy, error, and relevancy based parameters. The proposed framework clams the significant gain in accuracy, relevancy, and reduction in the error rate.

Author(s):  
Kirthi Sampath K. ◽  
Haritha S. ◽  
Mahesh B.

<p class="abstract"><strong>Background:</strong> It is a well-known fact that the skin is referred to as a window or mirror to the body. The present study was undertaken to know the spectrum of cutaneous manifestations in endocrinological disorders.</p><p class="abstract"><strong>Methods:</strong> A total of 500 patients with endocrinological disorders attending the Medical and Dermatology OPD at Dr. PSIMS&amp;RF were studied. Among the 500 cases studied, 417 patients had diabetes, 81 cases had thyroid disorder and 2 patients had Addison’s disease.<strong></strong></p><p class="abstract"><strong>Results:</strong> Most common dermatoses observed in patients with diabetes mellitus were infections {(fungal 25.3%), bacterial (6.92%), viral (5.42%)} followed by eczemas (13.2%), psoriasis (8.13%). Among 81 patients with thyroid disease, 78 patients were hypothyroid and 3 patients had hyperthyroidism and skin manifestations were observed in 55 (67%) of the patients with thyroid disorders. Most common dermatoses observed in patients with hypothyroidism were fungal infections (23.07%), urticaria (19.23%), xerosis (13.46%), bacterial infections (13.46%), psoriasis (11.53%). All 3 hyperthyroid patients have shown skin manifestations. 2 patients had diffuse hair loss and 1 patient had vitiligo. 2 cases of Addison’s disease were observed and both of them showed diffuse hyperpigmentation with accentuation over palmar creases, knuckles and gums.</p><p><strong>Conclusions:</strong> The present study shows the wide range of skin lesions in patients with endocrinological disorders paerticularly diabetes mellitus and thyroid disease. Through knowledge of the associated skin lesions helps in early diagnosis of underlying endocrine abnormality and thereby appropriate treatment provided at the earliest helps in preventing complications. </p>


2011 ◽  
Vol 26 (S2) ◽  
pp. 158-158
Author(s):  
I. Ioancio ◽  
R. Trascu ◽  
I. Turcu ◽  
L. Spiru

BackgroundAlzheimer disease (AD) is one of the most common neurodegenerative disorders (prevalence boosts from 0.2% in patients aged 55-65 up to 27% in patients aged 85+ years. Clinical manifestations of psychiatric disorders accompanying hypo- and hyper-thyroid function can mimic cognitive impairment.ObjectivesOur study aimed at studying the relationship between thyroid pathology, anxiety disorder and Alzheimer disease (AD).MethodsOur longitudinal, prospective research followed 49 patients with thyroid disorders (aged 50-85 years, 93.5 females); 63.3% (n = 31) had coexisting dementia and thyroid disease while 36.7% (n = 18) were dementia-cleared (10 had mild cognitive impairment (MCI) and 8 - anxiety and/or depression); we cross/analyzed control (n = 18) and target (n = 31) groups.ResultsIn the target group, 64.5% (n = 20) had hypothyroidism, 22.6% (n = 7) had euthyroid function and 12.9% (n = 4) had hyperthyroidism. The prevalence of anxiety and depression was higher in the hypothyroidism + dementia group (55.5%, n = 11) than in the hypothyroidism-only group (44.4%, n = 8). Most controls (77.8%, n = 14) had hypothyroidism while 22% (n = 4) had normal thyroid function.ConclusionsAnxiety disorder had a greater prevalence both in the group with dementia + thyroid disease and in the MCI group. Hypothyroidism was the dominant thyroid disorder in both groups. The early diagnostic and treatment of thyroid disease is expected to improve prognosis and evolution of future cognitive disorders (MCI & AD).


Genetika ◽  
2015 ◽  
Vol 47 (2) ◽  
pp. 523-534
Author(s):  
M. Yasodha ◽  
P. Ponmuthuramalingam

In the present scenario, one of the dangerous disease is cancer. It spreads through blood or lymph to other location of the body, it is a set of cells display uncontrolled growth, attack and destroy nearby tissues, and occasionally metastasis. In cancer diagnosis and molecular biology, a utilized effective tool is DNA microarrays. The dominance of this technique is recognized, so several open doubt arise regarding proper examination of microarray data. In the field of medical sciences, multicategory cancer classification plays very important role. The need for cancer classification has become essential because the number of cancer sufferers is increasing. In this research work, to overcome problems of multicategory cancer classification an improved Extreme Learning Machine (ELM) classifier is used. It rectify problems faced by iterative learning methods such as local minima, improper learning rate and over fitting and the training completes with high speed.


Author(s):  
Poonam Rani ◽  
Seema Gupta ◽  
Gaurav Gupta

Background: Deficiency of vitamin D is quite prevalent among elderly population or postmenopausal women worldwide and may affect various function of the body. The status of its deficiency with their relation with other variables are not well explored in perimenopausal women.Methods: 100 perimenopausal women from the department of obstetrics and gynaecology were selected without having known risk of thyroid disorder and cardiovascular disease. The age group criteria for these women were 40 to 50 years. Thyroid profile including TSH, T3, and T4 were estimated by using enzyme linked immunesorbent assay. Serum levels of 25(OH) D3 was estimated by using spectrophotometric method. Lipid profile including TC, TG and HDL-C were estimated CHOD-POD method, GPO-PAP method, and CHOD-POD/Phosphotungustate method. LDL-C was calculated by friedewald formula.Results: There 58 women were presented with insufficient amount of vitamin D. They were characterised with increased BMI, elevated thyrotropin alongwith lower concentrations of T3 and T4. Increased levels of TC, TG and LDL-cholesterol alongwith lower concentration of HDL-C were also observed in women with vitamin d deficiency. Women having vitamin D deficiency were presented with overweight (OR-18.0, p-value=<0.001) and dyslipidemia (OR-12.13, p-value≤0.001). Vitamin D was negatively correlated with variable i.e. BMI, TSH, TC, TG and LDL-C. This negative association was significant (<0.001) while HDL-C and T4 were positively correlated with vitamin D levels in this study population.Conclusions: Vitamin D deficiency frequently occurs in middle aged perimenopausal women. Negative correlation of it with BMI, TSH and lipid variables may suggest the development of cardiovascular disease and hypothyroidism in coming years. Vitamin D supplements or vitamin D containing diet and regular exposure to sun is highly recommended to perimenopausal women.


2011 ◽  
Vol 64 (3-4) ◽  
pp. 183-187 ◽  
Author(s):  
Ljiljana Todorovic-Djilas ◽  
Tijana Icin ◽  
Jovanka Novakovic-Paro ◽  
Ivana Bajkin

Introduction, Autoimmune diseases are chronic conditions initiated by the loss of immunological tolerance to self-antigens. They constitute heterogeneous group of disorders, in which multiple alterations in the immune system result in a spectrum of syndromes that either target specific organs or affect the body systematically. Recent epidemiological studies have shown a possible shift of one autoimmune disease to another or the fact that more than one autoimmune disease may coexist in a single patient or in the same family. Numerous autoimmune diseases have been shown to coexist frequently with thyroid autoimmune diseases. Autoimmune thyroid disease and other organ specific non-endocrine autoimmune diseases. This part of the study reviews the prevalence of autoimmune thyroid disease coexisting with: pernicious anaemia, vitiligo, celiac disease, autoimmune liver disease, miastenia gravis, alopecia areata and sclerosis multiplex, and several recommendations for screening have been given. Autoimmune thyroid disease and other organ non-specific non-endocrine autoimmune diseases. Special attention is given to the correlation between autoimmune thyroid disease and rheumatoid arthritis, systemic lupus erythematosus, syndrome Sj?gren, systemic sclerosis and mixed connective tissue disease. Conclusions. Screening for autoimmune thyroid diseases should be recommended in everyday clinical practice, in patients with primary organ-specific or organ non-specific autoimmune disease. Other?wise, in patients with primary thyroid autoimmune disease, there is no good reason of seeking for all other autoimmune diseases, although these patients have a greater risk of developing other autoimmune disease. Economic aspects of medicine require further analyzing of these data, from cost/benefit point of view to justified either mandatory screening or medical practitioner judgment.


2017 ◽  
Vol 2017 ◽  
pp. 1-9 ◽  
Author(s):  
Mara Ventura ◽  
Miguel Melo ◽  
Francisco Carrilho

Introduction.Selenium is a micronutrient embedded in several proteins. In adults, the thyroid is the organ with the highest amount of selenium per gram of tissue. Selenium levels in the body depend on the characteristics of the population and its diet, geographic area, and soil composition. In the thyroid, selenium is required for the antioxidant function and for the metabolism of thyroid hormones.Methods.We performed a review of the literature on selenium’s role in thyroid function using PubMed/MEDLINE.Results.Regarding thyroid pathology, selenium intake has been particularly associated with autoimmune disorders. The literature suggests that selenium supplementation of patients with autoimmune thyroiditis is associated with a reduction in antithyroperoxidase antibody levels, improved thyroid ultrasound features, and improved quality of life. Selenium supplementation in Graves’ orbitopathy is associated with an improvement of quality of life and eye involvement, as well as delayed progression of ocular disorders. The organic form of selenium seems to be the preferable formulation for supplementation or treatment.Conclusion.Maintaining a physiological concentration of selenium is a prerequisite to prevent thyroid disease and preserve overall health. Supplementation with the organic form is more effective, and patients with autoimmune thyroiditis seem to have benefits in immunological mechanisms. Selenium supplementation proved to be clinically beneficial in patients with mild to moderate Graves’ orbitopathy.


Author(s):  
Pramod Sekharan Nair ◽  
Tsrity Asefa Berihu ◽  
Varun Kumar

Gangrene disease is one of the deadliest diseases on the globe which is caused by lack of blood supply to the body parts or any kind of infection. The gangrene disease often affects the human body parts such as fingers, limbs, toes but there are many cases of on muscles and organs. In this paper, the gangrene disease classification is being done from the given images of high resolution. The convolutional neural network (CNN) is used for feature extraction on disease images. The first layer of the convolutional neural network was used to capture the elementary image features such as dots, edges and blobs. The intermediate layers or the hidden layers of the convolutional neural network extracts detailed image features such as shapes, brightness, and contrast as well as color. Finally, the CNN extracted features are given to the Support Vector Machine to classify the gangrene disease. The experiment results show the approach adopted in this study performs better and acceptable.


2021 ◽  
Vol 8 (05) ◽  
pp. 272-274
Author(s):  
Abirbhab Pal

Lupus is a multisystem disease affecting almost all systems including the immune system of our body. Its aetiology is not known. Lupus involving kidneys causes lupus nephritis and adds more complications in the multisystem disease. Lupus or systemic lupus erythematosus (SLE) is a multifactorial chronic disease involving multiple systems of the body. It is autoimmune1 in nature. There is increase in maternal and fetal risk of mortality and morbidity in lupus with pregnancy. The rate of pregnancy loss is 1.7 %2 in active SLE during initial first trimester and the most common adverse morbidity causing factor of fetomaternal side.3 There can be an increase in fetal mortality and morbidity associated with lupus nephritis.4,5 There is increased risk of intrauterine growth restriction (IUGR) / neonatal lupus / gestational diabetes mellitus / osteoporosis / HELLP syndrome / preeclampsia. Associated thyroid disorder is increased with preterm pregnancy.


2021 ◽  
Vol 2 (1) ◽  
pp. 29-34
Author(s):  
Hassanein Fadel Mohammed ◽  
Sarah Hassan Jaber

This study for the diagnosis of thyroid using pcsk9.The current study was conducted on seventy women patients suffering from thyroid disease attending in Center for diabetes and Endocrinology Unit in each of Al-Sadder Teaching Hospital and AL FURAT AL AWSAT Hospital in Al-Najaf province/ Iraq, and during the period from September until December 2017. The sample patients were divided into four study groups: premenopausal hypothyroidism patients group (20), postmenopausal hypothyroidism (15), premenopausal hyperthyroidism patients groups (17), and postmenopausal hyperthyroidism (18). The control group composed of 18 healthy women, also divided into premenopausal control and postmenopausal control.  The results indicated a significant increase (p<0.05) in pcsk9 in hypothyroidism patients compared with the control group, while a significant decrease (p<0.05) in pcsk9 in hyperthyroidism patients compared with the control group.  The results indicated a significant decrease (p<0.05) in pcsk9 in premenopausal hyperthyroidism patients compared with the control group, and a significant decrease (p<0.05) in pcsk9 in postmenopausal hyperthyroidism patients compared with the control group. The results indicated a significant increase (p<0.05) in pcsk9 in premenopausal hypothyroidism patients compared with the control group, and a significant increase (p<0.05) in pcsk9 in the postmenopausal hypothyroidism patients compared with the control group, also a significant increase in pcsk9 in postmenopausal than premenopausal.


2015 ◽  
Vol 22 (10) ◽  
pp. 1289-1297
Author(s):  
Liaqat Ali ◽  
Muhammad Tahir Mohy U Din ◽  
Imtiaz Ahmed ◽  
Rehan Riaz

Background: Thyroid hormones have many effects on cardiovascular function,and deficiency or excess of thyroid hormones can result in cardiac dysfunction. Abnormalitiesof the cardiovascular system are often identified during examination of hyperthyroid andhypothyroid patients. Objective: The aim of this study was to address the effects of thyroidhormones on the cardiovascular system and the clinical relevance of the cardiovascularresponse to thyroid dysfunction. Study Design: Cross sectional study. Setting: The studywas conducted at Allied Hospital / Punjab Medical College Faisalabad and PINUM HospitalFaisalabad. Period: October 2014 to August 2015. Materials and Methods: Total 100 patientswith thyroid disease (Hypo/hyperthyroidism) were enrolled in the study. Any patient age ≥20years, that had documented history of thyroid disease (Hypothyroidism or hyperthyroidism) oron medications for thyroid disorder was recruited in this study. Results: Total 100 consecutivepatients with abnormal thyroid function tests who fulfill the inclusion and exclusion criteriawere enrolled in the study. Mean age was 47.9 ± 23.20 years. 16 % were male and 84%were female. Majority of the patients 37( 37%) were in age group 51 - 60 years. 53 % weresuffering from overt hyperthyroidism and 31 % were suffering from hypothyroidism. Subclinicalhyperthyroidism and hypothyroidism was present in 7% and 9% patients respectively. Goiterwas present in 24 % patients. Atrial fibrillation was observed in 34% hyperthyroid patients.Overall 23% were diabetics and 25% had H/O hypertension. Dyslipidemia was present in20% hyperthyroid and 25% hypothyroid patients. Echocardiography was performed in 19%patients. 7% patients undergone thyroid surgery. Overall 11% patients were suffering from CCF.Pulmonary hypertension was observed in 17% hyperthyroid and 35.48% hypothyroid patients.MeanFT4 in hypothyroid patients was 1.16±022 ng/dl. Mean TSH was 10.92±21.09 (μIU/ml)in hypothyroid and 0.19±0.14 (μIU/ml) in hyperthyroid patients. Conclusions: The outcomeof this study suggests that patients with untreated overt / subclinical thyroid dysfunction are atincreased risk of cardiovascular complications.


Sign in / Sign up

Export Citation Format

Share Document