https://cdn.prod.website-files.com/5c17fc782f30f90cd15c25b4/63189857cdf8f072fcccfd5e_Thyroid.gif" alt="">

Source:

Ross Quinlan

Data Set Information:

From Garavan Institute Documentation: as given by Ross Quinlan 6 databases from the Garavan Institute in Sydney, Australia Approximately the following for each database:

2800 training (data) instances and 972 test instances Plenty of missing data 29 or so attributes, either Boolean or continuously-valued

2 additional databases, also from Ross Quinlan, are also here

Hypothyroid.data and sick-euthyroid.data Quinlan believes that these databases have been corrupted Their format is highly similar to the other databases

1 more database of 9172 instances that cover 20 classes, and a related domain theory

Another thyroid database from Stefan Aeberhard

3 classes, 215 instances, 5 attributes No missing values

A Thyroid database suited for training ANNs

3 classes 3772 training instances, 3428 testing instances Includes cost data (donated by Peter Turney)

Attribute Information:

N/A

:Link

https://archive.ics.uci.edu/ml/datasets/Thyroid+Disease

R. Quinlan. "Thyroid Disease," UCI Machine Learning Repository, 1986. [Online]. Available: https://doi.org/10.24432/C5D010.

BackgroundObservational studies have reported an association between coronavirus disease 2019 (COVID-19) risk and thyroid dysfunction, but without a clear causal relationship. We attempted to evaluate the association between thyroid function and COVID-19 risk using a bidirectional two-sample Mendelian randomization (MR) analysis.MethodsSummary statistics on the characteristics of thyroid dysfunction (hypothyroidism and hyperthyroidism) were obtained from the ThyroidOmics Consortium. Genome-wide association study statistics for COVID-19 susceptibility and its severity were obtained from the COVID-19 Host Genetics Initiative, and severity phenotypes included hospitalization and very severe disease in COVID-19 participants. The inverse variance-weighted (IVW) method was used as the primary analysis method, supplemented by the weighted-median (WM), MR-Egger, and MR-PRESSO methods. Results were adjusted for Bonferroni correction thresholds.ResultsThe forward MR estimates show no effect of thyroid dysfunction on COVID-19 susceptibility and severity. The reverse MR found that COVID-19 susceptibility was the suggestive risk factor for hypothyroidism (IVW: OR = 1.577, 95% CI = 1.065–2.333, P = 0.022; WM: OR = 1.527, 95% CI = 1.042–2.240, P = 0.029), and there was lightly association between COVID-19 hospitalized and hypothyroidism (IVW: OR = 1.151, 95% CI = 1.004–1.319, P = 0.042; WM: OR = 1.197, 95% CI = 1.023-1.401, P = 0.023). There was no evidence supporting the association between any phenotype of COVID-19 and hyperthyroidism.ConclusionOur results identified that COVID-19 might be the potential risk factor for hypothyroidism. Therefore, patients infected with SARS-CoV-2 should strengthen the monitoring of thyroid function.

As per the results of a large scale survey conducted across India in 2021, about *** percent of the respondents suffered from thyroid related problems. This was a slight fall in the share of people with thyroid issues when compared to the previous year of the survey.

Thyroid disease datasets typically contain information about patients, including various attributes such as age, sex, thyroid hormone levels (TSH, T3, T4), medical history, and possibly symptoms or other relevant factors. These datasets are valuable for research purposes, particularly in the fields of endocrinology, machine learning, and healthcare analytics.

Several datasets are available for research purposes, often sourced from hospitals, research institutions, or public health agencies. Here are some common sources where you might find thyroid disease datasets:

1. UCI Machine Learning Repository: This repository hosts various datasets for machine learning research, and it includes some datasets related to thyroid disease.

2. Kaggle: Kaggle is a platform for data science and machine learning competitions, and it also hosts datasets for various purposes. You might find thyroid disease datasets shared by users or organizations.

3. Healthcare Databases: Some hospitals or healthcare institutions maintain databases with anonymized patient data, including information about thyroid diseases. Access to these datasets may require appropriate permissions and approvals due to privacy concerns.

4. Research Publications: Researchers often publish datasets along with their research papers. Searching through academic journals and repositories may lead you to relevant datasets related to thyroid diseases.

When working with any healthcare-related dataset, it's crucial to handle the data with care, ensuring patient privacy and adhering to ethical guidelines and regulations such as HIPAA (in the United States) or GDPR (in the European Union), depending on the jurisdiction.

If you need assistance finding a specific dataset or have other questions about thyroid disease datasets, feel free to ask!

As per the results of a large scale survey conducted across India in 2021, about ** percent of the respondents above 60 years of age suffered from thyroid problems. Whereas around **** percent of the respondents below 19 years of age reported to have thyroid issues.

The Thyroid Gland Dataset typically used in machine learning and data science projects is designed to analyze and predict thyroid-related conditions. Here’s an overview of what you might find in such a dataset:

Dataset Overview

1. Purpose:

   • To predict thyroid conditions based on various features such as age, symptoms, and test results.
   • To explore relationships between different features and thyroid disease.

2. Common Columns:

   • Age: Age of the patient.
   • Lithium: Indicates if the patient is taking lithium (often used as a mood stabilizer).
   • Goitre: Presence of goitre (an enlarged thyroid gland).
   • Tumor: Presence of a thyroid tumor.
   • Hypopituitary: Indicates if there is hypopituitarism (a condition where the pituitary gland is underactive).
   • Psych: Psychological condition of the patient.
   • TSH (Thyroid Stimulating Hormone): A hormone that stimulates thyroid function.
   • T3 (Triiodothyronine): A thyroid hormone.
   • TT4 (Total Thyroxine): A measure of the total thyroxine level in the blood.
   • T4U (Thyroxine Uptake): A measure of how well the thyroid is functioning.
   • FTI (Free Thyroxine Index): An index used to assess thyroid function.

3. Target Variable:

   • Target: Indicates the presence or absence of thyroid disease. This could be binary (e.g., 0 for no disease, 1 for disease) or categorical.

4. Possible Features and Analysis:

   • Exploratory Data Analysis (EDA): Understand the distribution of features, check for missing values, outliers, and correlations.
   • Feature Encoding: Convert categorical features into numerical values if necessary for machine learning models.
   • Data Visualization: Create histograms, heatmaps, and scatter plots to visualize relationships between features.

Example Dataset Information

Usage

• Predictive Modeling: Train models to predict thyroid conditions based on the features.
• Feature Importance: Determine which features are most important for predicting the target variable.
• Data Cleaning and Preparation: Handle missing values, encode categorical variables, and normalize data if required.

Example Code to Display Dataset Info

import pandas as pd

# Load the dataset
df = pd.read_csv('/kaggle/input/thyroid-gland-dataset/hypothyroid.csv')

# Display dataset information
print("Dataset Info:")
print(df.info())

# Display the first few rows
print("
First few rows of the dataset:")
print(df.head())

# Describe the dataset
print("
Dataset Description:")
print(df.describe())

This code will give you an overview of the dataset, including data types, missing values, and basic statistics.

Supplementary Material 2 Supporting information files_data set2

Demographic, lifestyle and clinical factors by treated thyroid disorders (TDC) in men and women, KORA population S1-S4.

As per the results of a large scale survey conducted across India in 2019, about ** percent of the severely obese respondents suffered from thyroid problems. Whereas only ***** percent of the respondents in the normal to overweight weight range reported to have thyroid problems.

snapshot-tab-pane Thyroid Gland Disorder Treatment Market Size 2024-2028The thyroid gland disorder treatment market size is forecast to increase by USD 848.5 million at a CAGR of 5.01% between 2023 and 2028.The market is experiencing significant growth, driven by increasing awareness programs for thyroid disorders worldwide. This trend is particularly prominent in emerging economies, where the prevalence of thyroid conditions is rising due to changing lifestyles and dietary habits. However, the market's growth is not without challenges. Established players in the market hold a high entry barrier due to their extensive research and development capabilities and strong market presence. Iodine deficiency remains a significant cause of thyroid disorders, making it essential for governments and healthcare organizations to implement prevention programs. Telemedicine and remote monitoring solutions enable endocrinology consultations, expanding access to care and supporting medical tourism, while also enhancing the efficiency of medical diagnostics for patients seeking treatment across borders. As a result, new entrants must invest heavily in research and development to offer innovative solutions and differentiate themselves from competitors.Despite these challenges, the market presents substantial opportunities for companies seeking to capitalize on the growing demand for effective thyroid disorder treatments. Strategic collaborations, product innovation, and expanding into emerging markets are potential avenues for companies to gain a competitive edge and drive growth In the market.What will be the Size of the Thyroid Gland Disorder Treatment Market during the forecast period? Request Free SampleThe market encompasses a range of conditions, including hyperthyroidism and hypothyroidism, such as Hashimoto's thyroiditis and euthyroid sick syndrome. This market is driven by various factors, including the aging global population and the increasing prevalence of thyroid disorders. Medical technology advances continue to shape the landscape, with customized medicine techniques and novel medicines emerging.Diagnostic technologies, including thyroid function tests and ultrasound imaging, facilitate accurate diagnosis. Market growth is further fueled by the rise in conditions like Graves' disease and iodine deficiency. Overall, the thyroid gland disorder market is experiencing significant activity and growth, with ongoing innovation in diagnostic and therapeutic approaches.How is the Thyroid Gland Disorder Treatment Industry segmented?The industry research report provides comprehensive data (region-wise segment analysis), with forecasts and estimates in "USD million" for the period 2024-2028, as well as historical data from 2018-2022 for the following segments.Type HypothyroidismHyperthyroidismDistribution Channel OfflineOnlineGeography North America USCanadaEurope GermanyUKAsiaRest of World (ROW) By Type InsightsThe hypothyroidism segment is estimated to witness significant growth during the forecast period. Hypothyroidism occurs when the thyroid gland fails to produce adequate thyroid hormones, which can lead to health complications such as obesity, infertility, joint pain, and cardiovascular diseases. Women are more susceptible to this condition than men, and geriatric populations are also at a higher risk. Hypothyroidism often goes unnoticed during its early stages, but if left untreated, it can lead to significant health issues. Diagnostic resources, including diagnostic facilities, diagnostic labs, and diagnostic technologies, play a crucial role in identifying thyroid disorders.Thyroid function tests, such as the Bloom Thyroid Test, are essential in diagnosing hypothyroidism. Treatment options include medication, such as Thyroxine, and customized medicine techniques. Endocrinology consultations, surgery, and radioactive iodine therapy are also viable treatment methods. Alternative therapies, such as home care testing kits and iodine supplements, are gaining popularity. Environmental conditions and certain diseases, such as Hashimoto's thyroiditis and iodine deficiency disorders, can contribute to the development of hypothyroidism. Mental duress and euthyroid sick syndrome can also impact thyroid function. The financial burden of thyroid disorder treatment can be significant, making healthcare access and affordability crucial concerns for patients.Get a glance at the market report of share of various segments Request Free SampleThe Hypothyroidism segment was valued at USD 1.64 billion in 2018 and showed a gradual increase during the forecast period.Regional AnalysisNorth America is estimated to contribute 37% to the growth of the global market during the forecast period. Technavio's analysts have elaborately explained the regional trends a

Thyroid diseases are common, and use of levothyroxine is increasing worldwide. We investigated the influence of gender, race and socioeconomic status on the diagnosis and treatment of thyroid disorders using data from the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil), a multicenter cohort study of civil servants (35-74 years of age) from six Brazilian cities. Diagnosis of thyroid dysfunction was by thyrotropin (TSH), and free thyroxine (FT4) if TSH was altered, and the use of specific medications. Multivariate logistic regression models were constructed using overt hyperthyroidism/hypothyroidism and levothyroxine use as dependent variables and sociodemographic characteristics as independent variables. The frequencies of overt hyper- and hypothyroidism were 0.7 and 7.4%, respectively. Using whites as the reference ethnicity, brown, and black race were protective for overt hypothyroidism (OR=0.76, 95%CI=0.64-0.89, and OR=0.53, 95%CI=0.43-0.67, respectively, and black race was associated with overt hyperthyroidism (OR=1.82, 95%CI=1.06-3.11). Frequency of hypothyroidism treatment was higher in women, browns, highly educated participants and those with high net family incomes. After multivariate adjustment, levothyroxine use was associated with female gender (OR=6.06, 95%CI=3.19-11.49) and high net family income (OR=3.23, 95%CI=1.02-10.23). Frequency of hyperthyroidism treatment was higher in older than in younger individuals. Sociodemographic factors strongly influenced the diagnosis and treatment of thyroid disorders, including the use of levothyroxine.

Autoimmune thyroid diseases (AITD) are common, affecting 2-5% of the general population. Individuals with positive thyroid peroxidase antibodies (TPOAbs) have an increased risk of autoimmune hypothyroidism (Hashimoto's thyroiditis), as well as autoimmune hyperthyroidism (Graves' disease). As the possible causative genes of TPOAbs and AITD remain largely unknown, we performed GWAS meta-analyses in 18,297 individuals for TPOAb-positivity (1769 TPOAb-positives and 16,528 TPOAb-negatives) and in 12,353 individuals for TPOAb serum levels, with replication in 8,990 individuals. Significant associations (P<5×10−8) were detected at TPO-rs11675434, ATXN2-rs653178, and BACH2-rs10944479 for TPOAb-positivity, and at TPO-rs11675434, MAGI3-rs1230666, and KALRN-rs2010099 for TPOAb levels. Individual and combined effects (genetic risk scores) of these variants on (subclinical) hypo- and hyperthyroidism, goiter and thyroid cancer were studied. Individuals with a high genetic risk score had, besides an increased risk of TPOAb-positivity (OR: 2.18, 95% CI 1.68–2.81, P = 8.1×10−8), a higher risk of increased thyroid-stimulating hormone levels (OR: 1.51, 95% CI 1.26–1.82, P = 2.9×10−6), as well as a decreased risk of goiter (OR: 0.77, 95% CI 0.66–0.89, P = 6.5×10−4). The MAGI3 and BACH2 variants were associated with an increased risk of hyperthyroidism, which was replicated in an independent cohort of patients with Graves' disease (OR: 1.37, 95% CI 1.22–1.54, P = 1.2×10−7 and OR: 1.25, 95% CI 1.12–1.39, P = 6.2×10−5). The MAGI3 variant was also associated with an increased risk of hypothyroidism (OR: 1.57, 95% CI 1.18–2.10, P = 1.9×10−3). This first GWAS meta-analysis for TPOAbs identified five newly associated loci, three of which were also associated with clinical thyroid disease. With these markers we identified a large subgroup in the general population with a substantially increased risk of TPOAbs. The results provide insight into why individuals with thyroid autoimmunity do or do not eventually develop thyroid disease, and these markers may therefore predict which TPOAb-positives are particularly at risk of developing clinical thyroid dysfunction.

This dataset is a cleaned, transformed, and research-informed version of the original Thyroid Disease records compiled by the Garavan Institute and J. Ross Quinlan (1984–1987). It contains 9,000+ patient records with lab values, clinical history, and diagnosis outcomes. All missing values (?) were removed, and redundant or conflicting entries were dropped.

The dataset is valuable for Healthcare and Medical Research focused on thyroid-related Health Conditions. It supports Multiclass Classification problems in Artificial Intelligence and Data Analytics, particularly within Computer Science and Healthcare domains.

Missing values have been removed and categorical flags (t/f) converted to boolean (True/False). Meaningful multiclass target labels were created based on clinical diagnosis codes, including handling ambiguous cases. Data types were adjusted for compatibility with machine learning workflows using tools like pandas, NumPy, and scikit-learn.

This dataset is suitable for users of all skill levels—Beginner, Intermediate, and Advanced—interested in exploring Classification, Feature Extraction, Data Cleaning, and Exploratory Data Analysis in healthcare datasets. Visualizations can be developed using Matplotlib and Seaborn to better understand thyroid disease patterns.

Boolean fields (t/f) were converted to True/False, and a meaningful target variable was created based on clinically grounded groupings described in the research article “Thyroid Disease Prediction Using Selective Features and Machine Learning Techniques” (PMCID: PMC9405591).

The original diagnosis strings (e.g., A|B) were resolved to reflect the most likely class, and diagnoses were mapped into simplified, interpretable categories suitable for classification tasks (e.g., hypothyroid, hyperthyroid, normal, etc.).

This version is optimized for machine learning applications such as:

• Classification of thyroid status (e.g., binary or multi-class)

• Feature selection and model evaluation

• Clinical decision support research

• Ideal for healthcare ML projects, educational purposes, and benchmarking thyroid disorder prediction models.

As per the results of a large scale survey conducted across India in 2021, about ** percent of the respondents living in Chandigarh suffered from thyroid problems. Only around **** percent of respondents from Pune reported to have thyroid problems that year.

The Thyroid Disorder market is projected to reach $17.26 billion by 2033. Explore market size, growth trends, competitive analysis, and revenue forecasts from Strategic Revenue Insights.

Explore the burgeoning Silent Thyroiditis market, projected to reach USD 1,500 million by 2025 with a 6.5% CAGR. Discover key drivers, emerging trends, and regional growth opportunities for thyroid disorder treatments.

Background and objectiveAdequate iodine status and normal thyroid hormone synthesis are important for optimal child development. In this study, we explored whether young children’s developmental status is associated with thyroid dysfunction in an area of chronic excessive iodine exposure.MethodsWe included 298 children between 18 and 48 months of age residing in Algerian refugee camps. Early child development was measured using the Ages and Stages Questionnaires, third edition (ASQ-3), consisting of five domains: Communication, Gross Motor, Fine Motor, Problem Solving and Personal-Social. Due to poor discriminatory ability in the Gross Motor domain, the total ASQ-3 scores were calculated both including and excluding this domain. Urinary iodine concentration (UIC), thyroid hormones (TSH, FT3 and FT4), thyroid antibodies and serum thyroglobulin (Tg) were measured.ResultsThe median UIC was 451.6 μg/L, and approximately 72% of the children had a UIC above 300 μg/L. Furthermore, 14% had thyroid disturbances, of whom 10% had TSH outside the reference range. Children with thyroid disturbances and TSH outside the reference ranges had lower odds of being among the 66% highest total ASQ scores, with adjusted odds ratios (95% CI) of 0.46 (0.23, 0.93) and 0.42 (0.19, 0.94), respectively.ConclusionWe found an association between thyroid dysfunction and poorer developmental status among children with excessive iodine intake. The high iodine intake may have caused the thyroid dysfunction and hence the delayed developmental status; however, other influential factors cannot be excluded. Optimal child development is important for a sustainable future. With iodine excess being an increasing problem globally, this subject should be further explored.

Gender specific and overall hazard ratios (HR) and 95%CI for developing an ischemic cerebrovascular event according to thyroid disorders at baseline.

The Underactive Thyroid Treatment market, a vital segment of the larger endocrine disorder treatment landscape, addresses the growing health concern related to thyroid dysfunction, particularly hypothyroidism. Hypothyroidism occurs when the thyroid gland does not produce enough hormones, leading to a slowd...