Course detail

Data visualization in Healthcare and Medicine

FEKT-MPC-VDZAcad. year: 2026/2027

The course Data Visualization in Healthcare and Medicine introduces students to the principles, methods, and tools used for effective visualization of clinical, epidemiological, laboratory, imaging, and other healthcare-related data. It combines theoretical foundations of data visualization with practical approaches applied in health informatics, medical research, and clinical decision-making. Students gain an overview of healthcare data standards (HL7, FHIR, DICOM), learn to work with time series, geographic data, cohort datasets, and high-dimensional data, and acquire essential skills in visual analytics and interpretation of artificial intelligence models. The course emphasizes the creation of clear, user‑centered visualizations, dashboards, and reports that support safe and informed decision‑making in healthcare. Practical computer labs and the development of an individual visualization project form an integral part of the course. 

Language of instruction

Czech

Number of ECTS credits

5

Mode of study

Not applicable.

Guarantor

Ing. Vratislav Harabiš, Ph.D.

Department

Department of Biomedical Engineering (UBMI)

Aims

The aim of the course Data Visualization in Healthcare and Medicine is to provide students with both the theoretical foundations and practical skills necessary for effective display, interpretation, and communication of healthcare data. After completing the course, students should be able to:

1. Understand the principles of data visualization – grasp basic visualization techniques, perceptual principles, and the rules for creating clear and comprehensible graphical outputs.
2. Navigate the types and structure of healthcare data – know the fundamental data standards and classifications used in healthcare (e.g., HL7, FHIR, DICOM) and their impact on the form of visualizations.
3. Apply appropriate visualization approaches to different types of data – create visualizations for time series, geographic data, cohort and population data, multisource and high-dimensional datasets.
4. Use modern tools for visualization and visual analytics – work with software and libraries for creating interactive charts, dashboards, and visual analytical applications.
5. Implement visualizations supporting clinical and managerial decision-making – create visualizations that help identify patterns, trends, and risks in clinical and epidemiological data.
6. Understand visualization in the context of machine learning and AI – explain models using methods such as SHAP or feature importance and visualize outputs of predictive models.
7. Adhere to ethical and security principles of working with data – respect personal data protection, minimize the risk of misleading or inaccurate visualizations, and support the safe use of data in healthcare.
8. Independently create a comprehensive visualization project – design, implement, and defend an original visualization solution using principles of data storytelling and best practices in the field.

Rules for evaluation and completion of the course

Assessment of computer exercises: max. 10 points
Final project defense: max. 40 points
Final exam assessment: max. 50 points
The final exam is designed to assess students’ knowledge of the principles applied in the visualization of medical data.

Study aids

Not applicable.

Prerequisites and corequisites

Not applicable.

Basic literature

PREIM, Bernhard; RAIDOU, Renata; SMIT, Noeska a LAWONN, Kai. Visualization, Visual Analytics and Virtual Reality in Medicine. Elsevier Science & Technology, 2023. ISBN 9780128231067. (CS)
ROWELL, Katherine L.; BETZENDAHL, Lindsay a BROWN, Cambria. Visualizing health and healthcare data: creating clear and compelling visualizations to "see how you're doing". Hoboken, New Jersey: Wiley, [2021]. ISBN 9781119680888. (CS)

Recommended reading

Not applicable.

Classification of course in study plans

  • Programme MPCN-BIO Master's

    specialization MPC-BIO_TECH , 1 year of study, winter semester, compulsory-optional
    specialization MPC-SPORT_TECH , 1 year of study, winter semester, compulsory-optional

  • Programme MPCN-BTB Master's 2 year of study, winter semester, compulsory-optional, profile core courses

Type of course unit

 

Lecture

26 hours, optionally

Teacher / Lecturer

Ing. Vratislav Harabiš, Ph.D.

Syllabus

1. Introduction to Data Visualization in Healthcare: Overview of tools (Tableau, Power BI, Python, R, DICOM viewers)
2. Data Literacy and Working with Medical Data: Types of variables and appropriate chart types, common pitfalls in graph interpretation, sources of bias in healthcare data
3. Healthcare Data Standards: HL7, FHIR, DICOM
4. Visualization of Time Series in Medicine: Vital signs, monitoring, wearable devices
5. Spatial and Geographic Data Visualization: Morbidity, incidence, infectious disease spread, Choropleth maps, interpolation, heatmaps, GIS in healthcare (QGIS, ArcGIS), Epidemiological case studies (e.g., COVID‑19)
6. Cohort Visualization and Survival Analysis: Cohort studies, survival analysis basics, Kaplan–Meier curves and interpretation
7. Visualizing Multisource and High‑Dimensional Data: Laboratory data, genomics, proteomics, t‑SNE, PCA, UMAP for medical datasets, Patient clustering and phenotyping
8. Medical Imaging Modalities and Visualization (DICOM): CT, MRI, PET, ultrasound – data structure basics, Image processing fundamentals, 2D vs. 3D visualization, segmentation, volume rendering
9. Visualization for Clinical Decision‑Making: Clinical scoring systems (NEWS, SOFA, CHA₂DS₂‑VASc), Risk and uncertainty visualization
10. Interactive Dashboards in Healthcare: Power BI / Tableau / Shiny / Plotly, Dashboards for clinics, labs, hospital management, Filtering, drill‑down, personalization
11. Visualization for Artificial Intelligence and Machine Learning in Medicine: Feature importance, partial dependence, SHAP, Visualizing model training and performance
12. Ethics, Safety, and Regulation of Visualization in Medicine: GDPR, HIPAA, anonymization, Visualization that avoids misleading interpretation, Impact on clinical decision‑making
13. Semester Project – Presentations and Critical Review

Exercise in computer lab

39 hours, compulsory

Teacher / Lecturer

Ing. Vratislav Harabiš, Ph.D.

Syllabus

1. Introduction to Tools and Working with Data: Overview of tools (Python + Jupyter, Power BI / Tableau), Data import, CSV, XLSX, JSON formats, basic operations
2. Data Cleaning and Preparation in Healthcare: Data quality assessment: missing values, outliers, units, data transformations: normalization, pivoting, merging tables, anonymization and pseudonymization on a training dataset
3. Visualization of Basic Statistical Characteristics: Histograms, boxplots, violin plots, density plots, group comparisons (patients vs. controls)
4. Time Series Visualization – Vital Signs and Measurements: Working with data from monitors / wearables, trends, smoothing, anomaly detection, multi‑series visualization (e.g., heart rate, SpO₂, temperature)
5. Visualization of Geographic and Epidemiological Data: GIS layers, spatial joins, choropleth maps, heatmaps, point maps
6. Cohort Data Visualization and Survival Analysis: Working with cohort datasets, Kaplan–Meier curves and censoring, Stratification by diagnosis / therapy
7. Visualization of Multivariate and High‑Dimensional Data: Heatmaps, clustermaps, correlation matrices, PCA, t‑SNE, UMAP – step‑by‑step, interpreting results in medical contexts
8. Working with Medical Imaging (DICOM): DICOM metadata, image loading, displaying CT/MRI slices in different planes, windowing, filters, simple segmentation
9. Interactive Dashboards I – Clinical and Laboratory Data: building dashboards with filters, slicers, interactive components,visualizing patient trends
10. Interactive Dashboards II – Epidemiology and Hospital Management: Multi‑page dashboards,Geodata + time dimension
11. Visualizing Machine Learning Models: Interpretable vs. black‑box models, SHAP values, feature importance, partial dependence, risk prediction visualization (e.g., readmission risk)
12. Final Project Development – Workshop: Project consultations, dataset selection, methods, tools, interim presentation of project concept
13. Student Project Presentations: Presentation and defense of solutions, discussion of methods, visualization quality, interpretation. final reflection and improvement suggestions

Regular individual preparation for activities in the semester

30 hours, optionally

Teacher / Lecturer

Ing. Vratislav Harabiš, Ph.D.

Syllabus

Studenti a studentky se pravidelně připravují na cvičení, studují výukové podklady z přednášek, ze cvičení a z vlastních poznámek.

 

Individual preparation for a final exam

30 hours, optionally

Teacher / Lecturer

Ing. Vratislav Harabiš, Ph.D.

Syllabus

Studium výukových materiálů, doporučené literatury popř. jiných relevantních zdrojů, popř. vlastních poznámek.