Biomedicine (WP6)

WP6 aims to integrate artificial intelligence, computational modelling and behavioural data in the field of personalised prevention. AI enables the processing and interpretation of large and heterogeneous biomedical datasets, accelerates the development of innovative treatment approaches and supports personalised medicine.

The main objectives of the project are to create a module for the continuous testing of patients’ cognitive functions and to develop digital twins for predicting health outcomes. The planned outputs of WP6 are a utility model, a methodology, a software platform and validated technology for improving quality of life.

What problem does the WP solve, and why is it important?

01

The development of new treatments is a time-consuming process

02

Current practice lacks mechanisms for providing personalised and targeted care

03

Predicting the future course of a patient’s health is currently a challenging task

04

There is a lack of tools for the continuous monitoring of patients’ health

05

Patients’ quality of life is limited by the lack of modern diagnostic and therapeutic tools

Examples of use / areas of application and benefits

Clinical care

Ongoing patient monitoring
Simulation of treatment scenarios

Pharmaceuticals

In silico clinical studies
Analysis of heterogeneous data

IT and Digital Health

Software platforms
Integration with wearable electronics (wearables)

Prevention

Personalised prevention
Risk stratification of the population

Key people

WP Leader

doc. MUDr. Marián Hajdúch, Ph.D.

Institute of Molecular and Translational Medicine (IMTM) | UPOL LF

Marián Hajdúch works at Palacký University in Olomouc as a leading expert in the field of translational medicine and biomedical research. Within the project, he is responsible for coordinating Work Package 6 (WP6), where he focuses on the integration of artificial intelligence approaches in biomedicine, particularly the development of cognitive AI models and collaboration with project partners. He has extensive experience of international research projects (e.g. H2020, EATRIS) and has long been bridging the gap between academic research and clinical and applied practice.

doc. MUDr. Marián Hajdúch, Ph.D.

| LF UPOL

Biomedicine

prof. RNDr. Olga Štěpánková, CSc.

| CIIRC CTU

Bioinformatics

doc. PhDr. Jaroslav Mužík, DrSc.

| UJAK

Bioengineering

Participating institutions

Used technologies and procedures

Linking the cognitive module and the digital twin
Prediction of survival and healthy lifespan
Longitudinal data collection
Digital tests: Stroop, N-back

What-if simulations (interventions)
Dynamic integration of cognitive data into the model
Machine learning models: random forest, LSTM, autoencoders
Models: Cox, gradient boosting, Bayes, DNN

Achieved and planned results

2027

A validated, functional prototype of a software platform for the collection and processing of sensitive data, suitable for user data management and building on the development of a digital twin in preventive medicine

Ztech – proven technology

2028

A verified, working prototype of a software platform linking cognitive testing and a digital twin

Ztech – proven technology

2029

A verified, working prototype of a software platform linking musculoskeletal testing and a digital twin

Ztech – proven technology

2031

A validated, working GUI prototype for the analysis of cognitive and musculoskeletal functions

Ztech – proven technology