idw – Informationsdienst Wissenschaft
Nachrichten, Termine, Experten
Nachrichten, Termine, Experten
At MEDICA 2025, Fraunhofer FIT will present a novel solution called “AI-enabled data for medicine”, which combines transparency, traceability, and capacity building in the use of medical data for artificial intelligence. The aim is to make the development and application of AI-driven methods in healthcare more understandable, verifiable, and practice-oriented.
At the heart of the exhibit is an interactive dashboard that visualizes and explains how AI models are trained on medical data from various sources. The system is based on the TrainVis platform, which was specifically developed to make the influence of different data sources and data subsets visible during the training process. Using a model for skin cancer detection – trained on image data from multiple sources – the platform clearly demonstrates how the model’s behavior evolves across different subsets of the dataset during learning. Through multiple visualization layers, users can easily trace how individual datasets or classes contribute to the model’s overall performance.
The dashboard provides several levels of analysis, combining dataset statistics, training metrics, and confusion matrices. Users can interactively explore the training process, identify classification errors, and analyze accuracy both overall and for specific data subsets. Color-coded visualizations and both relative and absolute metrics reveal how data quality and distribution impact model performance. As a result, the dashboard serves as a tool that makes the complex mechanisms of machine learning not only measurable but also intuitively understandable – an essential step toward creating transparent and trustworthy AI systems in medical contexts.
>>Expanding Training Opportunities in Data Literacy and Artificial Intelligence
In addition to its technological developments, Fraunhofer FIT is continuously expanding its training and continuing education programs in the fields of data literacy and artificial intelligence. The Fraunhofer FIT Learning Center, operating as an extension of the Fraunhofer Academy, consolidates the development, delivery, and quality assurance of certified professional education programs.
These programs are aimed at professionals in medicine, nursing, administration, and engineering who wish to use AI-based methods safely and responsibly. Fraunhofer FIT combines practice-oriented teaching concepts with scientific excellence, offering hybrid learning formats that blend in-person sessions with interactive online modules.
The courses cover topics such as data analysis, AI management, data protection, generative AI, and human-AI teaming. By using virtual learning labs and browser-based exercises, participants can explore real-world application scenarios and directly transfer their experiences into their daily work. In doing so, the Learning Center strengthens digital sovereignty in healthcare and empowers professionals to competently assess and safely apply AI technologies.
Visit us at MEDICA, November 17–20, 2025, at the Fraunhofer joint booth in Hall 10, D22.
Dashboard for analyzing a binary AI classification using data from multiple sources. The sources and ...
Copyright: © Fraunhofer FIT
Criteria of this press release:
Journalists, Scientists and scholars
Information technology, Medicine
transregional, national
Research results, Transfer of Science or Research
English
Dashboard for analyzing a binary AI classification using data from multiple sources. The sources and ...
Copyright: © Fraunhofer FIT
You can combine search terms with and, or and/or not, e.g. Philo not logy.
You can use brackets to separate combinations from each other, e.g. (Philo not logy) or (Psycho and logy).
Coherent groups of words will be located as complete phrases if you put them into quotation marks, e.g. “Federal Republic of Germany”.
You can also use the advanced search without entering search terms. It will then follow the criteria you have selected (e.g. country or subject area).
If you have not selected any criteria in a given category, the entire category will be searched (e.g. all subject areas or all countries).
