BACKGROUND: Genetic testing rapidly penetrates into all medical specialties and medical students must acquire skills in this area. However, many of them consider it difficult. Furthermore, many find these topics less appealing and not connected to their future specialization in different fields of clinical medicine. Student-centred strategies such as problem-based learning, gamification and the use of real data can increase the appeal of a difficult topic such as genetic testing, a field at the crossroads of genetics, molecular biology and bioinformatics. METHODS: We designed an electronic teaching application which students registered in the undergraduate Medical Biology course can access online. A study was carried out to assess the influence of implementation of the new method. We performed pretest/posttest evaluation and analyzed the results using the sign test with median values. We also collected students' personal comments. RESULTS: The newly developed interactive application simulates the process of molecular genetic diagnostics of a hereditary disorder in a family. Thirteen tasks guide students through clinical and laboratory steps needed to reach the final diagnosis. Genetics and genomics are fields strongly dependent on electronic databases and computer-based data analysis tools. The tasks employ publicly available internet bioinformatic resources used routinely in medical genetics departments worldwide. Authenticity is assured by the use of modified and de-identified clinical and laboratory data from real families analyzed in our previous research projects. Each task contains links to databases and data processing tools needed to solve the task, and an answer box. If the entered answer is correct, the system allows the user to proceed to the next task. The solving of consecutive tasks arranged into a single narrative resembles a computer game, making the concept appealing. There was a statistically significant improvement of knowledge and skills after the practical class, and most comments on the application were positive. A demo version is available at https://medbio.lf2.cuni.cz/demo_m/ . Full version is available on request from the authors. CONCLUSIONS: Our concept proved to be appealing to the students and effective in teaching medical molecular genetics. It can be modified for training in the use of electronic information resources in other medical specialties.

• Klíčová slova
• Bioinformatics, E-learning, Gamification, Genomics, Interactive teaching application, Medical databases, Medical genetics, Problem-based learning,
• MeSH
• genetické nemoci vrozené diagnóza   MeSH
• genetické testování * MeSH
• lékařská genetika výchova   MeSH
• lidé MeSH
• molekulární medicína výchova   MeSH
• počítačem řízená výuka * MeSH
• problémově orientovaná výuka MeSH
• studium lékařství pregraduální metody   MeSH
• uživatelské rozhraní počítače MeSH
• videohry MeSH
• výpočetní biologie výchova   MeSH
• vyučování MeSH
• Check Tag
• lidé MeSH
• Publikační typ
• časopisecké články MeSH
• hodnotící studie MeSH

During the lockdown of universities and the COVID-Pandemic most students were restricted to their homes. Novel and instigating teaching methods were required to improve the learning experience and so recent implementations of the annual PhysioNet/Computing in Cardiology (CinC) Challenges posed as a reference. For over 20 years, the challenges have proven repeatedly to be of immense educational value, besides leading to technological advances for specific problems. In this paper, we report results from the class 'Artificial Intelligence in Medicine Challenge', which was implemented as an online project seminar at Technical University Darmstadt, Germany, and which was heavily inspired by the PhysioNet/CinC Challenge 2017 'AF Classification from a Short Single Lead ECG Recording'. Atrial fibrillation is a common cardiac disease and often remains undetected. Therefore, we selected the two most promising models of the course and give an insight into the Transformer-based DualNet architecture as well as into the CNN-LSTM-based model and finally a detailed analysis for both. In particular, we show the model performance results of our internal scoring process for all submitted models and the near state-of-the-art model performance for the two named models on the official 2017 challenge test set. Several teams were able to achieve F1scores above/close to 90% on a hidden test-set of Holter recordings. We highlight themes commonly observed among participants, and report the results from the self-assessed student evaluation. Finally, the self-assessment of the students reported a notable increase in machine learning knowledge.

• Klíčová slova
• atrial fibrillation, deep learning, electrocardiogram, gamification,
• MeSH
• algoritmy MeSH
• COVID-19 * diagnóza   MeSH
• elektrokardiografie metody   MeSH
• fibrilace síní * diagnóza   MeSH
• kontrola infekčních nemocí MeSH
• lidé MeSH
• strojové učení MeSH
• umělá inteligence MeSH
• Check Tag
• lidé MeSH
• Publikační typ
• časopisecké články MeSH