Thyroid disorders, including hypothyroidism, hyperthyroidism, and thyroid malignancies, are among the most common metabolic and endocrine conditions worldwide. Traditional diagnosis relies on clinical symptoms, physical evaluation, and biochemical assays. These assays measure levels of thyroid hormones, such as thyroid-stimulating hormone (TSH), Free T3 and Free T4, and thyroid antibodies (TPOAb). In addition, diagnosis uses ultrasound examinations and fine-needle aspiration biopsies. While established pathways are helpful, standard clinical cutoffs can sometimes miss subtle dysfunctions or fail to capture complex individual physiological variations. Machine learning (ML) has become increasingly essential in thyroid disease prediction by handling complex diagnostic variables and reducing diagnostic errors.

Supervised and unsupervised learning models

All machine learning models can be divided into two categories: supervised and unsupervised learning models, depending on the data they work with. Supervised models, such as logistic regression, decision trees, and neural networks, work with labeled data featuring explicitly defined outcomes. For example, each sample has a pre-defined target label like “hypothyroid” or “euthyroid”. These models generate predictions on new unlabeled data, usually referred to as validation samples. For this purpose, they use trained prediction values from the training set of labeled data.

Unsupervised models, such as K-means clustering, work with unlabeled data to discover hidden patterns or underlying structural distributions without pre-defined target labels.

Logistic regression models

Logistic Regression (LR) is a foundational statistical and machine learning model. It maps input features to a probability score using the sigmoid function. For thyroid disease prediction, it frequently serves as a powerful baseline model, achieving high classification accuracies on structured thyroid datasets. Because the model outputs explicit regression coefficients, medical researchers can directly translate them into odds ratios. These ratios quantify how much a single unit change in a biomarker, such as TSH, alters thyroid disorder risk.

However, LR relies on manual pre-modeled outcome-predictor relationships, often requiring manual feature engineering and complex data normalization. Oftentimes, a patient record has missing laboratory values, such as an unmeasured Free T3 test. Therefore, the missing data must be handled beforehand through imputation techniques.

Decision trees and extreme gradient boosting

Decision Trees are non-parametric supervised learning models that split data recursively based on feature thresholds. For example, these thresholds can be specific cutoff values for TSH or Free T4 levels. These models effectively capture non-linear relationships and interactions between various clinical parameters, such as age, sex, and hormone profiles. Unlike LR models, they do not require complex data normalization.

XGBoost is an advanced gradient-boosting ensemble framework that builds sequential decision trees, where each new tree corrects the residual errors of previous ones. XGBoost consistently ranks among the top-performing algorithms for tabular medical datasets by minimizing bias and variance, preventing overfitting on noisy clinical datasets, and handling missing values effectively.

Neural networks for thyroid disease prediction

Recent advancements in deep learning have dramatically enhanced how neural networks process data for thyroid disease prediction and classification. For example, they process image data, such as ultrasound scans, and numerical data, such as age, gender and TSH levels.

Medical imaging, particularly thyroid ultrasonography, relies on Convolutional Neural Networks (CNNs, shown in Figure 1) and specialized deep learning architectures to distinguish between benign and malignant thyroid nodules. Researchers frequently employ standard or retrained backbone CNNs, such as ResNet, via transfer learning to evaluate radiomics features like nodule shape, margins, echogenicity, and calcifications.

Joint predictive models, such as hybrid and radiomics-clinical fusion models, merge numerical patient metrics with quantitative image radiomics features. Fusing these data streams helps optimize diagnostic workflows and minimizes the necessity for invasive fine-needle aspiration biopsies on benign nodules.

Figure 1. The workflow for thyroid nodule classification using convolutional neural networks with ResNet18 and feature extraction. Evaluation indicators are used to evaluate the effect of model classification. In addition, a heatmap was employed to visualize the prediction results, by which authors extracted and analyzed the highlighted areas. Adapted from J. Yang et al 2022 [5].

How ML can change clinical practice

In thyroid disease prediction, performance evaluation ensures high validation standards and reliability before deployment. For example, evaluation uses metrics like AUC, F1 score, precision, and recall. In addition, feature extraction isolates essential clinical variables and radiomic biomarkers to catch subtle physiological variations early.

Bias and explainability in thyroid disease prediction

Key potential risks associated with almost every advanced ML model include algorithm bias from non-representative training datasets. In addition, the “black-box” nature makes clinical interpretability difficult. To fix bias, we need to build training sets that genuinely represent diverse patient groups. We also need to use smart data adjustments to stop health disparities from happening.

Tackling the “black-box” problem involves integrating explainable AI frameworks, such as SHapley Additive exPlanations (SHAP, shown in Figure 2). These frameworks, in turn, mathematically expose how specific features drive a prediction. Keeping these tools safe, fair and reliable comes down to regular check-ups on how models perform. In addition, teams with varied perspectives need to guide their use. Finally, doctors need to stay directly involved to oversee every decision before AI enters day-to-day clinical work.

Figure 2: Example of SHAP values of important features which impact the model output. Large positive SHAP values indicate that the feature’s specific value pushes the model’s prediction toward a positive outcome (such as a higher risk of thyroid disease), while large negative SHAP values pushes the prediction toward a negative outcome (such as a lower risk of thyroid disease, or a normal euthyroid state). Adopted from C. J. Ejiyi et al 2026 [6]

Author: Lucia Buljac (University of Split, Faculty of Science)

Key references

1. Alkhazzar, H., & Moslem, B. (2024). Thyroid Disease Prediction Using Machine Learning Model: Decision Tree. EDRAAK, 2024, 84–100. https://doi.org/10.70470/edraak/2024/011
2. Chaganti, R., Rustam, F., De La Torre Díez, I., Mazón, J. L. V., Rodríguez, C. L., & Ashraf, I. (2022). Thyroid Disease Prediction Using Selective Features and Machine Learning Techniques. Cancers, 14(16), 3914. https://doi.org/10.3390/cancers14163914
3. Hu, M., Asami, C., Iwakura, H., Nakajima, Y., Sema, R., Kikuchi, T., Miyata, T., Sakamaki, K., Kudo, T., Yamada, M., Akamizu, T., & Sakakibara, Y. (2022). Development and preliminary validation of a machine learning system for thyroid dysfunction diagnosis based on routine laboratory tests. Communications Medicine, 2, Article 71. https://doi.org/10.1038/s43856-022-00071-1
4. Chan, W.-K., Sun, J.-H., Liou, M.-J., Li, Y.-R., Chou, W.-Y., Liu, F.-H., Chen, S.-T., & Peng, S.-J. (2021). Using Deep Convolutional Neural Networks for Enhanced Ultrasonographic Image Diagnosis of Differentiated Thyroid Cancer. Biomedicines, 9(12), 1771. https://doi.org/10.3390/biomedicines9121771 Cited by: 38
5. Yang, J., Shi, X., Wang, B., Qiu, W., Tian, G., Wang, X., Wang, P., & Yang, J. (2022). Ultrasound Image Classification of Thyroid Nodules Based on Deep Learning. Frontiers in Oncology, 12, 905955. https://doi.org/10.3389/fonc.2022.905955
6. Ejiyi, C.J., Eze, F.O., Hossin, M.A. et al. A robust framework for clinically interpretable hypothyroidism diagnosis with Polynomial-SHAP and DeepSeqNet. J Big Data 13, 63 (2026). https://doi.org/10.1186/s40537-025-01332-1

The post How machine learning helps with thyroid disease prediction appeared first on InnoThyroGen EU Project.

The InnoThyroGen project will host an upcoming online webinar titled “Guide to performing Polygenic Risk Score analyses by Bayesian multiple regression (SBayesR) on summary statistics.” Lucia Buljac (University of Split, Faculty of Science; PMFST) will deliver the webinar.

The webinar will take place on 24 September 2026 from 10:00 to 11:00 (CEST). Researchers, students, and other interested participants are welcome to join.

From summary statistics to polygenic risk scores

The webinar will focus on Polygenic Risk Score (PRS) analyses using Bayesian multiple regression with SBayesR.

First, participants will learn about the role of summary-level genetic data in PRS analyses. They will also explore how researchers can apply SBayesR as a Bayesian multiple regression approach.

Polygenic Risk Scores combine information from many genetic variants. As a result, they can help estimate an individual’s genetic predisposition to a particular trait or condition.

The session will also introduce the analytical approach behind PRS. In addition, participants will learn how methods such as SBayesR can work with genome-wide summary statistics.

Supporting knowledge sharing within InnoThyroGen

This webinar forms part of the InnoThyroGen webinar series. The series promotes knowledge exchange and helps build research capacity across the project and the wider research community.

Moreover, the webinars bring together expertise in genomics, statistical methods, and predictive approaches. Through these activities, InnoThyroGen aims to strengthen research excellence in personalised and predictive medicine.

👉 Register here: https://events.teams.microsoft.com/event/7e3002c8-41dd-431d-b060-7665ff2e6ef8@87a0831f-e02e-499b-9c7f-1eabc7c9c06b?source=copyLinkLegacyShareLinkDialog

The post InnoThyroGen webinar on Polygenic Risk Score analyses using SBayesR appeared first on InnoThyroGen EU Project.

Over five days, participants explored key methods and tools used in human genetics and genome-wide association studies (GWAS). The programme combined lectures, hands-on computer workshops, invited lectures, group discussions and interactive sessions.

The Summer School gradually moved from fundamental statistical and computational skills to advanced genomic analyses. Participants worked with tools and methods used in modern genetic research and had many opportunities to discuss their work with lecturers and fellow participants.

Day 1 – Building the foundations

The Summer School began with a Welcome and Meet-the-participants Session, which introduced the programme and gave participants an opportunity to get to know each other.

The first lectures focused on the statistical foundations needed for genetic studies. Nikolina Pleić introduced key statistical concepts through the two-part lecture Introduction to Statistics for Genetic Studies.

In the afternoon, participants moved from theory to practical work. Andrea Gelemanović led two computer workshops on Linux. The sessions covered both basic and more advanced Linux usage and prepared participants for the computational work planned for the following days.

Day 2 – Human genetics, GWAS and R

Day 2 introduced participants to human genetics and genome-wide association studies.

Andrea Gelemanović opened the day with Introduction to Human Genetics & GWAS. Nikolina Pleić then continued with two sessions on Statistical Models for GWAS.

Participants also strengthened their practical data analysis skills. During two computer workshops, Andrea Gelemanović introduced R, from the initial setup and data types to data manipulation and visualisation.

The day ended with a group discussion on Open Science, Ethics & Methodological Pitfalls in GWAS. The session encouraged participants to look beyond technical analysis and consider broader methodological and research challenges.

Day 3 – Quality control and population structure

The third day focused on important steps that researchers perform before and during GWAS analyses.

Following an invited lecture by Lennart C. Karssen (PolyOmica, The Netherlands), Andrea Gelemanović introduced participants to Quality Control for GWAS. Participants then applied these concepts during a practical workshop using PLINK 2.0.

The afternoon focused on population structure. Nikolina Pleić first introduced the topic through a lecture and then guided participants through a practical PLINK 2.0 workshop.

The day concluded with a lecture on Association Analysis, preparing participants for more advanced analyses on Day 4.

Day 4 – From association analysis to functional annotation

Day 4 continued with advanced GWAS methods and their practical application.

The programme began with an invited lecture by Maxim Freydin (King’s College London, United Kingdom). Participants then worked on Association Analysis using PLINK 2.0 and GEMMA under the guidance of Nikolina Pleić.

The next computer workshop focused on Functional Annotation. Participants explored several widely used tools and resources, including COLOC, FUMA, GTEx and LocusZoom.

In the afternoon, invited members took part in an InnoThyroGen R&I Lab. Meanwhile, Summer School participants had the opportunity to explore Belgrade through a guided city tour.

Day 5 – Polygenic Risk Scores and advanced genomics

The final day brought together several advanced approaches in genetic research.

Andrea Gelemanović started the programme with a hands-on workshop on meta-analysis using METAL. Afterwards, Lucia Buljac introduced the concept of Polygenic Risk Scores (PRS).

Participants then put this knowledge into practice during a computer workshop on PRS using SBayesR and SBayesRC.

The final lecture, led by Andrea Gelemanović and Nikolina Pleić, explored Advanced Genomics Approaches, including machine learning and Mendelian randomization.

The Summer School concluded with a Q&A session, course feedback and closing, giving participants and lecturers a final opportunity to exchange ideas and reflect on the five-day programme.

Five days of learning and collaboration

The 2nd InnoThyroGen Summer School combined theoretical knowledge with practical experience. Participants developed skills in statistics, Linux, R, GWAS, quality control, population structure, association analysis, functional annotation, meta-analysis and Polygenic Risk Scores.

Just as importantly, the Summer School created a space for discussion, knowledge exchange and collaboration among researchers interested in genetics and genomics.

Through activities such as the Summer School, InnoThyroGen continues to strengthen research capacity and knowledge exchange in genomics and personalised medicine.

📢 Stay tuned for updates, follow our channels, and don’t miss the chance to join the next InnoThyroGen Summer School!

FOTO

The post 2nd InnoThyroGen Summer School brings genomics and GWAS training to Belgrade appeared first on InnoThyroGen EU Project.

📅 September 8–12, 2026

📍 Institute of Molecular Genetics and Genetic Engineering (IMGGE), University of Belgrade, Serbia

Participants will engage in practical sessions covering:

• Introduction to the Linux command line and R programming language;
• Foundations of statistics for genetic studies;
• Genome-wide association studies (GWAS), from quality control and statistical models to association analysis;
• Polygenic risk scores (PRS), from theory to implementation;
• Advanced approaches, including population structure, functional annotation, meta-analysis, machine learning, and Mendelian randomisation to drive personalized medicine strategies.

The School is organized as part of the Horizon Europe project InnoThyroGen – an EU-funded initiative dedicated to advancing innovative, personalized solutions for thyroid disease diagnosis and treatment.

🔗 Learn more about the InnoThyroGen project here.

Who Should Apply?

We welcome 25–30 participants, primarily young researchers (MSc students, PhD candidates, postdoctoral researchers), though experienced scientists interested in bioinformatics are also encouraged to apply. No prior coding or computational experience is required – just motivation and curiosity.

Important Dates

• Summer School: September 8–12, 2026
• Registration Deadline: September 1, 2026

Venue

Institute of Molecular Genetics and Genetic Engineering (IMGGE), University of Belgrade

Belgrade, Serbia

Registration & Costs

✅ Participation is free of charge.

Spots are limited and will be allocated on a first-come, first-served basis.

👉 Register here

Registration includes:

• Full participation in the Summer School
• All course materials
• Daily coffee breaks and lunch

Please note: Travel and accommodation expenses are not covered.

📩 If you have any questions, write to us at: summer.school@innothyrogen.eu

We look forward to welcoming you to Belgrade for another dynamic week of learning, collaboration, and discovery in bioinformatics!

The post 2nd InnoThyroGen Summer School of Bioinformatics Opens Registration appeared first on InnoThyroGen EU Project.

When researchers discover that two things are associated, an important question always follows: does one actually cause the other?

For example, people with low vitamin D levels may have a higher risk of developing certain diseases. Individuals with obesity often have altered thyroid hormone levels. Patients with autoimmune thyroid diseases frequently have other immune-related conditions.

But are these relationships truly causal, or are they simply correlations influenced by other factors such as lifestyle, age, diet, or underlying health conditions?

Distinguishing correlation from causation is one of the greatest challenges in medical research. This is where Mendelian randomization (MR) has emerged as a powerful tool in modern genetic epidemiology.

Why Observational Studies Are Not Enough

Traditional observational studies can identify associations between a potential risk factor (called an exposure) and a disease (the outcome). However, these associations may be affected by confounding factors or reverse causation.

Imagine that researchers observe people with lower thyroid hormone levels also have a higher risk of cardiovascular disease. Does reduced thyroid function increase cardiovascular risk? Or do other factors, such as obesity, physical inactivity, medication use, or chronic illness, influence both thyroid function and heart disease?

Similarly, if patients with a particular disease have lower vitamin D concentrations, we cannot immediately conclude that vitamin D deficiency caused the disease. The disease itself may reduce vitamin D levels, or both may be influenced by completely different factors.

Randomized controlled trials (RCTs) are considered the gold standard for establishing causality because participants are randomly assigned to different interventions. Unfortunately, RCTs are often expensive, time-consuming, and sometimes impossible or unethical to perform.

Mendelian randomization offers an elegant alternative.

What Is Mendelian Randomization?

Mendelian randomization is a statistical method that uses naturally occurring genetic variation to investigate whether an observed association between a risk factor and a disease is likely to be causal.

The method is based on a simple biological principle first described by Gregor Mendel: genetic variants are randomly inherited from parents at conception. This natural random allocation resembles the randomization process used in clinical trials.

This concept is illustrated in Figure 1. While participants in randomized controlled trials are randomly assigned to intervention or control groups by the investigator, individuals in Mendelian randomization studies are naturally “allocated” to different levels of an exposure through the random inheritance of genetic variants at conception.

This natural randomization helps minimise confounding and enables researchers to investigate causal relationships using observational data.

Because genetic variants are assigned before birth, they are generally not influenced by lifestyle, environmental exposures, disease progression, or most confounding factors encountered in observational studies.

In Mendelian randomization, genetic variants associated with an exposure serve as instrumental variables (or genetic instruments) that allow researchers to estimate the causal effect of that exposure on a disease outcome.

Figure 1. Mendelian randomization as a natural analogue of a randomized controlled trial. In randomized controlled trials, participants are randomly assigned to intervention or control groups by the investigator. In Mendelian randomization, the random allocation of genetic variants at conception creates groups that are generally balanced with respect to confounding factors, allowing causal relationships to be investigated using observational data. Adapted from Davey Smith & Ebrahim (2005).

How Does Mendelian Randomization Work?

The basic concept is straightforward.

First, researchers identify genetic variants that are robustly associated with a specific exposure, such as:

• thyroid-stimulating hormone (TSH)
• free thyroxine (fT4)
• vitamin D levels
• body mass index
• cholesterol concentrations
• inflammatory biomarkers

These variants are identified through large genome-wide association studies (GWAS), often involving hundreds of thousands of participants.

Next, researchers examine whether the same genetic variants are also associated with a disease outcome.

If genetic variants that increase (or decrease) the exposure consistently lead to a higher (or lower) disease risk, this provides evidence supporting a causal relationship.

In other words, instead of asking:

“Do people with higher TSH develop disease more often?”

MR asks:

“Do people who are genetically predisposed to have higher TSH throughout their lives also have a different risk of developing disease?”

Why Is Mendelian Randomization So Powerful?

One of the major strengths of MR is its ability to reduce bias.

Because genetic variants are inherited before birth:

• they usually cannot be changed by disease,
• they are independent of lifestyle factors,
• they are less affected by confounding than conventional observational studies.

As a result, MR often provides stronger evidence about causality than observational research alone.

Importantly, MR does not completely replace randomized clinical trials. Instead, it complements them by helping researchers prioritize which biological pathways are most promising for further investigation and potential therapeutic intervention.

The Three Core Assumptions

For Mendelian randomization to provide reliable causal estimates, three key assumptions must be satisfied.

1. Relevance

The genetic variants must be strongly associated with the exposure of interest.

2. Independence

The genetic variants should not be associated with confounding factors that influence both the exposure and the disease.

3. Exclusion Restriction

The genetic variants should influence the disease only through the exposure being studied, and not through alternative biological pathways.

Researchers routinely evaluate these assumptions using a range of statistical sensitivity analyses, helping ensure that the conclusions are as robust as possible.

Mendelian Randomization in Thyroid Research

Mendelian randomization has become an increasingly valuable tool for understanding thyroid biology.

Researchers have applied MR to investigate questions such as:

• Do thyroid hormone levels causally influence cardiovascular disease?
• Does thyroid function affect obesity or metabolic syndrome?
• Is vitamin D involved in autoimmune thyroid diseases?
• Does thyroid function influence bone health or cognitive decline?
• Are circulating biomarkers involved in thyroid cancer development?

Rather than relying solely on observational associations, MR allows researchers to determine whether these relationships are likely to reflect genuine biological mechanisms.

Such evidence is particularly valuable when identifying potential therapeutic targets or deciding whether an intervention is likely to improve patient outcomes.

Mendelian Randomization in the InnoThyroGen Project

Within the InnoThyroGen project, Mendelian randomization is used to identify biomarkers and biological factors that are likely to play a causal role in thyroid diseases.

By integrating large-scale genome-wide association study (GWAS) data with advanced statistical methods, MR enables us to distinguish variables that are merely associated with thyroid disease from those that are more likely to contribute directly to disease development.

This information is particularly valuable for the development of the integrated thyroid disease risk prediction tool being developed within InnoThyroGen.

Rather than selecting biomarkers based solely on observational associations, MR helps prioritise variables with evidence of causality for inclusion alongside polygenic risk scores (PRS) and clinical characteristics.

Combining genetic predisposition captured by PRS with causally relevant biomarkers has the potential to improve risk prediction, support earlier identification of individuals at increased risk, and contribute to more personalised approaches to thyroid disease prevention and management.

Together, Mendelian randomization and polygenic risk scores form complementary components of the InnoThyroGen analytical pipeline, providing the evidence needed to develop a robust and clinically relevant integrated risk prediction tool.

Looking Ahead

The rapid growth of publicly available genetic datasets has transformed Mendelian randomization into one of the most widely used approaches in genetic epidemiology.

Today, researchers can investigate thousands of potential causal relationships using data from international biobanks and collaborative genome-wide association studies involving hundreds of thousands—or even millions—of participants.

As these resources continue to expand, Mendelian randomization will play an increasingly important role in identifying disease mechanisms, guiding drug development, and advancing precision medicine.

For projects such as InnoThyroGen, this means moving beyond identifying simple associations towards understanding why diseases develop and which biological pathways offer the greatest potential for prevention, diagnosis, and treatment.

Ultimately, Mendelian randomization is helping researchers answer one of the most fundamental questions in medicine: what truly causes disease?

Author: Nikolina Pleić (University of Split, School of Medicine)

Key References

1. Davey Smith G, Ebrahim S. ‘Mendelian randomization’: can genetic epidemiology contribute to understanding environmental determinants of disease? International Journal of Epidemiology. 2003;32(1):1–22. https://doi.org/10.1093/ije/dyg070
2. Davey Smith G, Hemani G. Mendelian randomization: genetic anchors for causal inference in epidemiological studies. Human Molecular Genetics. 2014;23(R1):R89–R98. https://doi.org/10.1093/hmg/ddu328
3. Davies NM, Holmes MV, Davey Smith G. Reading Mendelian randomisation studies: a guide, glossary, and checklist for clinicians. BMJ. 2018;362:k601. https://doi.org/10.1136/bmj.k601
4. Lawlor DA, Harbord RM, Sterne JAC, Timpson N, Davey Smith G. Mendelian randomization: using genes as instruments for making causal inferences in epidemiology. Statistics in Medicine. 2008;27:1133–1163. https://doi.org/10.1002/sim.3034

The post Mendelian Randomization: Using Genetics to Uncover the Causes of Disease appeared first on InnoThyroGen EU Project.

The InnoThyroGen project will host an upcoming online webinar titled “Step-by-step systematic reviews: Turning questions into reliable evidence”, delivered by Andrea Gelemanović, PhD (University of Split School of Medicine).

The webinar will take place on 6 May 2026 at 14:00 (CEST) and is open to researchers, students, and all interested participants.

From research questions to reliable evidence

The session will provide a structured overview of the key steps involved in designing and conducting systematic reviews and meta-analyses. Participants will gain insights into how to formulate precise research questions, develop comprehensive search strategies, assess study quality, and synthesise findings into robust, evidence-based conclusions.

Tools, frameworks, and common challenges

In addition, the webinar will introduce widely used tools and frameworks such as PROSPERO, PRISMA, and the Cochrane Database of Systematic Reviews, while also addressing common challenges including publication bias and reproducibility.

Supporting knowledge sharing within InnoThyroGen

Originally delivered as part of the internal InnoThyroGen workshop series, this webinar is now being made available to a broader audience in order to support knowledge sharing and strengthen research capacity in the field of evidence-based medicine.

👉 Register here: https://events.teams.microsoft.com/event/1fe00d6d-e6ab-4847-b0cb-f54a73a727d9@87a0831f-e02e-499b-9c7f-1eabc7c9c06b

The post InnoThyroGen webinar on systematic reviews and meta-analyses appeared first on InnoThyroGen EU Project.

On 20 April 2026, Split hosted a public event focused on thyroid health titled:
“Modern diagnostics and treatment of the most common thyroid diseases”, followed by a round table “Thyroid: Your Energy Control Centre.”

The event was organised by the Academy of Medical Sciences of Croatia – Split Branch (AMZH Split) in co-organisation with the Croatian Medical Association – Split Branch (HLZ Split) and the Centre for Culture and Lifelong Learning “Zlatna vrata”.

It brought together healthcare professionals, researchers, students, patient representatives and the general public.
At the same time, the event aimed to raise awareness of thyroid diseases and promote personalised approaches to treatment.

From Lecture to Round Table: A Structured Programme

The programme began with a public lecture organised by AMZH Split in collaboration with HLZ Split and “Zlatna vrata”.

Firstly, Assist. Prof. Dubravka Brdar delivered a lecture on modern diagnostics and treatment of thyroid diseases.
She explained current clinical approaches, from laboratory testing to imaging and therapy options.
In addition, she highlighted the importance of personalised medicine and the role of genetics in treatment decisions.

Following the lecture, the event continued with a round table “Thyroid: Your Energy Control Centre.”
This discussion was organised as part of the Festival of Science 2026 in collaboration with:

• Academy of Medical Sciences of Croatia – Split Branch
• Teaching Institute of Public Health of Split-Dalmatia County
• Faculty of Health Studies, University of Split
• University of Split School of Medicine

Bringing Together Experts and Stakeholders

The round table gathered experts and stakeholders from different fields, including clinicians, researchers and patient representatives.

The discussion featured:

• Assist. Prof. Dubravka Brdar, MD, PhD (KBC Split)
• Prof. Tatijana Zemunik, MD, PhD (University of Split School of Medicine)
• Dr. Nikolina Pleić (University of Split School of Medicine)
• Volga Družijanić (patient representative)

The session was moderated by: Assoc. Prof. Anamarija Jurčev Savičević, MD, PhD (Teaching Institute of Public Health of Split-Dalmatia County)

Participants discussed key topics such as early detection, treatment pathways and public awareness.
Moreover, the discussion created space for open exchange between science, healthcare and society.
As a result, it encouraged dialogue and mutual understanding.

Raising Awareness Through Public Engagement

The event also received media attention and reached a wider audience beyond the venue itself.
This is especially important because thyroid diseases affect a significant portion of the population.

By presenting scientific knowledge in an accessible way, the event helped citizens better understand their own health.
At the same time, it encouraged early diagnosis and proactive health management.

Impact of InnoThyroGen Thyroid Event Split

The event delivered several important outcomes:

• increased awareness of thyroid health among the general public
• stronger knowledge exchange between healthcare professionals and researchers
• promotion of personalised medicine and genetic approaches
• improved visibility of the InnoThyroGen project at the local level
• engagement of multiple stakeholder groups

Consequently, InnoThyroGen thyroid event Split supported both dissemination and public engagement objectives.

Conclusion

The Split thyroid event successfully combined expert knowledge with public engagement.
Through lectures and discussion, it highlighted both challenges and opportunities in thyroid care.

As a result, InnoThyroGen thyroid event Split represents an important step toward better awareness, earlier diagnosis and more personalised treatment.

Stay Connected

Stay tuned for more events and updates.
Follow InnoThyroGen on LinkedIn, X, Facebook and Instagram to stay informed.

The post InnoThyroGen Thyroid Event in Split: Modern Diagnostics and Patient Perspectives appeared first on InnoThyroGen EU Project.

On 19 March 2026, the Forum of Patients of Serbia (FPS) organised a co-design workshop in Belgrade titled:
“The Patient Journey in Thyroid Diseases – From Diagnosis to Treatment.”

The workshop gathered patients, healthcare professionals, researchers and stakeholders to discuss real-life challenges in thyroid disease management.
At the same time, the event aimed to strengthen dialogue and improve healthcare practices through a personalised medicine approach.

InnoThyroGen Co-Design Workshop Belgrade: A Structured Dialogue

The workshop followed a structured programme that combined patient experiences with clinical and scientific perspectives.

Firstly, participants shared their personal journeys, focusing on early symptoms, the path to diagnosis and treatment challenges.
Secondly, medical experts presented the clinical perspective, highlighting system limitations and opportunities for improvement.

Finally, a joint discussion allowed participants to identify key gaps and explore possible solutions.
This format ensured that both patient voices and expert knowledge were equally represented.

Key Challenges in the Patient Journey

Several important challenges were identified during the discussion:

• long waiting times for diagnosis and specialist consultations
• limited access to endocrinologists, especially outside major cities
• delays in achieving stable and effective therapy

These issues clearly show the need for more efficient healthcare pathways and better coordination within the system.

Early Detection and the Role of Primary Healthcare

Participants emphasised the importance of early diagnosis and prevention.
In addition, they highlighted the role of primary healthcare in recognising symptoms and guiding patients toward specialist care.

Moreover, there is a strong need for improved public awareness and education.
Screening initiatives, such as thyroid ultrasound campaigns, were identified as highly effective and in demand.

Personalised Medicine and the Role of InnoThyroGen

A key part of the discussion focused on genetics and personalised medicine.
Participants recognised the potential of genetic testing for earlier detection, risk assessment and tailored treatment approaches.

Importantly, the planned pilot genetic test within the InnoThyroGen project was highlighted as a major step forward.
This initiative supports the transition toward more personalised and precise healthcare solutions.

Patient Perspective and Support Systems

The workshop also highlighted the importance of patient involvement in healthcare decision-making.
In addition, the role of patient organisations and psychological support was recognised as essential.

These elements contribute to better treatment outcomes and improved quality of life for patients.
Therefore, strengthening patient support systems remains a key priority.

From Discussion to Recommendations

Based on the exchange, several practical recommendations were identified:

• improve access to specialist care and reduce waiting times
• strengthen the role of primary healthcare in early detection
• enhance public and patient education
• develop preventive programmes and screening initiatives
• support the use of genetic testing for personalised treatment
• involve patients more actively in decision-making
• improve data collection and healthcare registries

These recommendations provide a clear roadmap for future improvements in thyroid disease management.

Impact of InnoThyroGen Co-Design Workshop Belgrade

The workshop delivered strong results across several areas:

• valuable insights into real patient experiences
• clear identification of system-level challenges
• practical recommendations for improving healthcare pathways
• increased visibility of the InnoThyroGen project
• strengthened collaboration between patients, clinicians and researchers

In addition, the event achieved significant media coverage, with multiple online publications highlighting the importance of early diagnosis and personalised medicine.

Consequently, InnoThyroGen co-design workshop Belgrade contributed directly to stakeholder engagement, dissemination and long-term project impact.

Conclusion

The Belgrade co-design workshop demonstrated the value of combining patient experience with clinical expertise.
Through open dialogue and structured discussion, the event identified key challenges and proposed actionable solutions.

As a result, InnoThyroGen co-design workshop Belgrade represents an important step toward more patient-centred and personalised approaches in thyroid healthcare.

Stay Connected

Stay tuned for upcoming consultations and project activities.
Follow InnoThyroGen on LinkedIn, X, Facebook and Instagram to stay informed and get involved.

The post InnoThyroGen Co-Design Workshop in Belgrade: Understanding the Patient Journey in Thyroid Diseases appeared first on InnoThyroGen EU Project.

On 7 March 2026, the Split Riva hosted the public science event Znanost u prolazu.
The event was organised by the Association Znanost u prolazu with support from the European initiative Science Comes to Town 2026.

It aimed to bring science closer to citizens through short talks and direct interaction with researchers.
As a result, visitors of all ages had the opportunity to engage with science in an open and accessible way.

InnoThyroGen at Znanost u prolazu: Explaining Science in Everyday Language

At the event, Dr. Nikolina Pleić and Dr. Andrea Gelemanović from MEFST represented the InnoThyroGen project.
They delivered short lectures designed for a general audience, focusing on how modern science helps us understand health and disease.

Firstly, Dr. Pleić presented “How Statistics and Genetics Help Us Understand Thyroid Disease.”
She explained how large datasets, including hormonal, clinical and genetic data, are analysed using modern statistical methods.
In addition, she showed how these approaches help detect disease patterns, estimate individual risk and support personalised treatment.

Moreover, she connected these concepts directly to the InnoThyroGen project, making complex research easier to understand.

From Data to Discovery: A Second Perspective

In the second lecture, Dr. Andrea Gelemanović presented “Hidden Patterns of Health and Disease.”
She focused on how bioinformatics and computational biology reveal molecular patterns linked to ageing and chronic conditions.

Furthermore, she explained how combining biological data with advanced analytics can support earlier diagnosis.
At the same time, this approach enables more personalised prevention strategies.

As a result, the audience gained a clearer understanding of how data-driven science is shaping modern healthcare.

Open Dialogue and Public Engagement

One of the key strengths of the event was direct interaction between scientists and citizens.
Visitors asked questions, shared their perspectives and engaged in informal discussions with researchers.

This open format helped break down barriers between science and the public.
In addition, it showed that complex topics such as genomics and personalised medicine can be communicated in a simple and relatable way.

Impact of InnoThyroGen at Znanost u prolazu

Participation in the event delivered several important outcomes:

• increased visibility of the InnoThyroGen project among the general public
• improved understanding of genomics, data science and personalised medicine
• strong engagement with citizens of all age groups
• direct communication between researchers and the public
• promotion of science as accessible and relevant to everyday life

Consequently, InnoThyroGen at Znanost u prolazu contributed to strengthening public trust in science and raising awareness of modern healthcare approaches.

Conclusion

Znanost u prolazu successfully demonstrated how science can be brought out of the laboratory and into public spaces.
Through clear communication and open dialogue, the event connected research with everyday life.

Therefore, InnoThyroGen at Znanost u prolazu represents an important step in promoting scientific literacy and public engagement.

Stay Connected

Stay tuned for more outreach events and project updates.
Follow InnoThyroGen on LinkedIn, X, Facebook and Instagram to stay informed and involved.

The post InnoThyroGen at Znanost u prolazu: Bringing Science to the Split Riva appeared first on InnoThyroGen EU Project.

Thyroid gland is an organ located in the lower front part of the neck. The main function of the thyroid gland is to produce triiodothyronine (T3) and thyroxine (T4). Thyroid hormones are key regulators of basal energy expenditure and metabolism, regular cell development and differentiation, neurodevelopmental processes in the first years of life, linear growth, body composition, and weight. Normal thyroid function is regulated by the hypothalamic thyrotropin-releasing hormone (TRH) that stimulates the release of the thyroid-stimulating hormone (TSH) from the pituitary gland. In turn, TSH drives the synthesis and secretion of thyroid hormones from the thyroid gland. TSH and TRH levels increase when circulating thyroid hormone levels are low, and vice versa. Serum TSH and free thyroxine (FT4) concentrations are routinely used to assess thyroid function of an individual in everyday clinical practice. Free T3 or free T4 measures an active thyroid hormone which is not bound to protein, and is able to affect body tissues. Total T3 or total T4 measures the bound and free hormone, which can be influenced by protein levels in the blood. Tests measuring free hormones more accurately reflect how the thyroid gland is functioning.

Common Thyroid Disorders: Hypothyroidism and Hyperthyroidism

Hypothyroidism: Causes, Symptoms and Treatment

Hypothyroidism is a condition characterized by reduced production and secretion of thyroid hormones. In primary hypothyroidism, the thyroid gland cannot produce adequate thyroid hormones. The less commonly seen secondary hypothyroidism results from abnormal pituitary gland function. The main indicator of the hypothyroid condition is a low level of thyroid hormones and an elevated TSH level. The most common cause of hypothyroidism is Hashimoto’s thyroiditis. Patients with hypothyroidism require lifelong thyroid hormone replacement treatment with levothyroxine. The primary goal of treatment is to provide the appropriate daily dose of thyroid hormone to restore normal thyroid function for each individual patient.

Hashimoto’s Thyroiditis as a Cause of Hypothyroidism

Hashimoto’s thyroiditis is an autoimmune disease in which a dysfunctional immune system leads to chronic damage of thyroid tissue, followed by replacement of the damaged areas with scar tissue and lymphocytes. This diagnosis is more common in women, and its prevalence increases with age. The disease is characterized by positive antibodies against thyroglobulin and thyroid peroxidase. Metabolism slows down due to a decline in hormone levels. Patients most often complain of fatigue, poor concentration and memory, sensitivity to cold, constipation, weight gain, hair loss, low mood, a sensation of choking or tightness in the neck, and lack of motivation.

Hyperthyroidism: Symptoms, Risks and Management

Hyperthyroidism is a condition of excessive production and secretion of thyroid hormones into the blood. The main indicators are elevated levels of thyroid hormones and a decreased level of TSH. An accelerated metabolism of substances and nutrients in the body may lead to the development of other health problems after a prolonged period of hyperthyroidism. In most cases, the cause of hyperthyroidism is Basedow–Graves disease, but other possible causes include multinodular toxic goiter, toxic adenoma, and thyroid inflammation. Untreated hyperthyroidism can cause cardiac arrhythmias, congestive heart failure, osteoporosis, adverse obstetric outcomes, and metabolic derangements such as increased resting energy expenditure and gluconeogenesis. Treatment should be patient-centered and individualized, taking into account age, comorbidities, severity of hyperthyroidism, likelihood of remission, plans for pregnancy, available surgical expertise, and patient preferences.

Basedow–Graves Disease and Autoimmune Hyperthyroidism

Basedow–Graves disease is an autoimmune disorder that occurs more frequently in younger women. It is manifested by diffuse enlargement of the thyroid gland, which can be accompanied by bulging eyes. A hallmark of the disease is the presence of antibodies against thyroglobulin, thyroid peroxidase, and TSH receptor. Patients most commonly complain of palpitations, accelerated digestion, weight loss despite increased appetite, feeling hot and sweating, insomnia, changes in the menstrual cycle and sexual desire, nervousness, and trembling hands. In patients with Graves’ disease, treatment should focus on controlling hyperthyroidism with the anticipated eventual remission of Graves’ disease with antithyroid drugs. Antithyroid drugs decrease thyroid hormone synthesis and secretion. In patients who do not achieve remission, or in those whose hyperthyroidism remits and then recurs, definitive therapy with radioactive iodine or thyroidectomy should be considered.

Multinodular Toxic Goiter and Toxic Adenoma

Multinodular toxic goiter is a disease characterized by multiple nodules in the thyroid gland that secrete thyroid hormones excessively without regulation by the pituitary gland. A toxic adenoma is a type of benign tumor that similarly excessively secretes thyroid hormones. Toxic nodular goitre and toxic adenoma are mostly treated with radioactive iodine or thyroidectomy.

Thyroid Tumors and Thyroid Cancer

A tumor is an abnormal accumulation of tissue. Tumors can be benign or malignant. The etiology of thyroid carcinoma is not fully understood. However, it is known that a higher risk is present in females, individuals with a family history of cancer, those who have been exposed to radiation, and that it occurs more frequently after the age of thirty.

Benign Thyroid Tumors: Follicular Adenoma

Follicular adenoma is the most common epithelial benign tumor. It occurs in all age groups, but more often in young adults. These are solitary, spherical formations with a diameter of less than 3 cm. Adenomas may be functional (toxic) or non-functional. Functional adenomas produce thyroid hormones uncontrollably, without activation of the pituitary gland.

Malignant Thyroid Tumors: Types and Treatment Options

Malignant tumors of the thyroid gland are very rare and account for about 1% of all malignant tumors. They can be differentiated (papillary and follicular) or undifferentiated (medullary and anaplastic). Differentiated tumor cells resemble normal tissue cells. Tumors made up of such cells respond better to treatment. Undifferentiated tumors are made up of cells that do not resemble normal tissue, so they behave more aggressively and require a more aggressive approach to treatment. Malignant tumors occur somewhat more frequently in women, typically between 30 and 45 years of age. Treatment options are determined by the type and stage of thyroid cancer. Surgically removing the thyroid gland is a common approach. Any remaining cancer cells are then treated with radioactive iodine therapy. After surgical removal of the thyroid gland, patients need to take thyroid hormone replacement therapy for the rest of their lives to maintain normal physiological processes. External beam radiation therapy may be an option for individuals whose aggressive or advanced thyroid tumors do not respond to standard care.

Papillary Thyroid Carcinoma

Papillary carcinoma is the most common thyroid cancer. This type of cancer has the best prognosis. It is more often diagnosed before the age of 40. It can remain localized in the gland for years, but in some patients, metastases to the cervical lymph nodes are already present at the time of diagnosis.

Follicular Thyroid Carcinoma

Follicular carcinoma is the second most common type of thyroid cancer. It occurs mainly in middle-aged and older individuals. This type of cancer is more aggressive than papillary thyroid carcinoma, but likewise has a good prognosis for recovery.

Medullary Thyroid Carcinoma

Medullary carcinoma is a rare type of thyroid cancer. It occurs in middle and late adulthood, usually sporadically as a solitary thyroid nodule. The prognosis of medullary thyroid cancer is usually not as favorable as that of differentiated thyroid cancers.

Anaplastic Thyroid Carcinoma

Anaplastic carcinoma is the rarest histological type of thyroid cancer, but it is extremely aggressive. Compared with other types of thyroid carcinoma, it unfortunately has the worst prognosis.

Current Research and Advances in Thyroid Disease Treatment

Since thyroid disorders are largely a consequence of a hectic lifestyle, it is important to introduce some changes in an individual’s daily life. In the treatment of thyroid disease, in addition to medication, the importance of a proper diet is also emphasized. The diet should be varied and balanced, with frequent fluid intake. There is no specific diet therapy for thyroid problems, but the Mediterranean diet is recommended, as it has proven to be extremely beneficial for a wide range of health problems. It is important to emphasize the importance of consuming minimally processed foods or avoiding industrially prepared foods that are abundant in stores. Selenium and selenoproteins are important in the creation and metabolism of thyroid hormones. They have an anti-inflammatory effect, can reduce the titer of thyroid peroxidase antibodies, have a positive effect on hypothyroidism, and result in a reduction in the required dose of levothyroxine.

In addition to existing diagnostic methods, additional research is being conducted for the purpose of earlier detection of diseases, personalized medicine, and better treatment methods. The association of various inflammatory parameters with thyroid disorders is being investigated to serve as additional diagnostic tools. The involvement of various genes in thyroid diseases is also being examined, which could be useful in a personalized approach to patients in the future. Several international ultrasound-based thyroid nodule risk stratification systems have been developed with the goal of reducing unnecessary biopsies. Less invasive alternatives to surgery for low-risk thyroid cancer, such as active surveillance and minimally invasive interventions, are being explored. New systemic therapies are now available for patients with advanced thyroid cancer. The progress of targeted therapy and biomarker research in thyroid cancer represents a possible change in therapeutic methods aimed at precision and individualization.

Author: Marija Banović (Polyclinic Leptir)

References

1. Patil N, Rehman A, Anastasopoulou C, et al. Hypothyroidism. [Updated 2024 Feb 18]. In: StatPearls [Internet]. Treasure Island (FL): StatPearls Publishing; 2025 Jan-. Available from: https://www.ncbi.nlm.nih.gov/books/NBK519536/
2. Mathew P, Kaur J, Rawla P. Hyperthyroidism. [Updated 2023 Mar 19]. In: StatPearls [Internet]. Treasure Island (FL): StatPearls Publishing; 2025 Jan-. Available from: https://www.ncbi.nlm.nih.gov/books/NBK537053/
3. Guo M, Sun Y, Wei Y, Xu J and Zhang C. (2024) Advances in targeted therapy and biomarker research in thyroid cancer. Front. Endocrinol. 15:1372553. doi: 10.3389/fendo.2024.1372553
4. Brčić L, Barić A, Gračan S, Brdar D, Torlak Lovrić V, Vidan N, Zemunik T, Polašek O, Barbalić M, Punda A, Boraska Perica V. (2016): Association of established thyroid peroxidase autoantibody (TPOAb) genetic variants with Hashimoto’s thyroiditis, Autoimmunity, DOI: 10.1080/08916934.2016.1191475

The post Thyroid Diseases: Symptoms, Causes, Diagnosis and Treatment appeared first on InnoThyroGen EU Project.