Markus Bödenler

Accessing and understanding medication information can be challenging for many people, especially when patient information leaflets (PILs) are long, complex, and printed in small font. This study presents MediChat, an open-source, locally executable chatbot designed to provide reliable, easy-to-read answers to medication-related questions based exclusively on official PILs. MediChat follows a retrieval-augmented generation (RAG) architecture: PILs from the Austrian Medicinal Product Index are received via API, converted to text, split into overlapping chunks, embedded, and stored in a Chroma vector database. From there the top-k relevant chunks are retrieved, and Llama 3.1 generates German responses based on this evidence. The system was evaluated using a hybrid framework. Quantitatively, 200 yes/no questions across ten drugs were answered with 80% accuracy, overall precision 0.977, recall 0.686, F1-score 0.806, and a mean response time of 727 ms. Qualitatively, two personas were used in eight simulated dialogues. Response times were around 1.1–1.3 s, and task completion exceeded 85% with high ratings for relevance and quantity. These results indicate that an open-source RAG chatbot can deliver leaflet-grounded, user-friendly medication information and provide a reproducible template for future healthcare chatbot evaluations.

This study presents the development of a customizable rule-based engine, integrated into the LETHE Clinical Trial Management System (CTMS), designed to enhance clinical decision-making in a multidomain intervention for dementia risk reduction. The rule engine allows health professionals to create and personalize rules based on patient-specific profiles and evolving clinical knowledge, enabling more precise interventions. The system was developed through a collaborative approach with one health professional and employs a JSON based rules engine for flexible rule creation and implementation. Its application in the LETHE project, a randomized control trial involving 156 participants across multiple centers, demonstrates the potential of tailored digital interventions in improving clinical outcomes. Future enhancements will focus on broadening the system’s usability and automating patient-specific tasks to streamline care.

Among elderly individuals, dementia stands as a prominent contributor to disability. However, multidomain lifestyle interventions have emerged as a promising approach for enhancing cognition. Taking a progressive step, integrating digital elements such as a mobile intervention application for elderly participants becomes crucial. Hence, it’s crucial to identify the usage patterns of intervention features. Our aim was to implement a usage tracking mechanism and analyze usage trends and feature preferences over the initial six months of a clinical trial across various clinical sites, comparing intervention and control groups. Our findings reveal the differences in usage between the groups and highlight the most used features.

Effective medication management poses significant challenges, particularly when navigating multiple medications with intricate dosages and schedules. This paper presents a prototype mobile application to streamline information retrieval from dense medication leaflets. By utilizing automated information extraction based on large language models, the application seamlessly retrieves pertinent details from the Austrian medicinal product index upon scanning the medication package. This extracted information is organized and displayed within the app, ensuring clarity and accessibility for users. In addition to this core functionality, the application offers a suite of features tailored to facilitate effective medication management. By integrating comprehensive medication information with practical medication management tools, the application empowers users to navigate complex medication regimes with confidence and ease.

Dementia, the most severe expression of cognitive impairment, is among the main causes of disability in older adults and currently affects over 55 million individuals. Dementia prevention is a global public health priority, and recent studies have shown that dementia risk can be reduced through non-pharmacological interventions targeting different lifestyle areas. The FINnish GERiatric Intervention Study to Prevent Cognitive Impairment and Disability (FINGER) has shown a positive effect on cognition in older adults at risk of dementia through a 2-year multidomain intervention targeting lifestyle and vascular risk factors. The LETHE project builds on these findings and will provide a digital-enabled FINGER intervention model for delaying or preventing the onset of cognitive decline. An individualised ICT-based multidomain, preventive lifestyle intervention program will be implemented utilising behaviour and intervention data through passive and active data collection. Artificial intelligence and machine learning methods will be used for data-driven risk factor prediction models. An initial model based on large multinational datasets will be validated and integrated into an 18-month trial integrating digital biomarkers to further improve the model. Furthermore, the LETHE project will investigate the concept of federated learning to, on the one hand, protect the privacy of the health and behaviour data and, on the other hand, to provide the opportunity to enhance the data model easily by integrating additional clinical centres.

Large amounts of data are needed to train accurate robust machine learning models, but the acquisition of these data is complicated due to strict regulations. While many business sectors often have unused data silos, researchers face the problem of not being able to obtain a large amount of real-world data. This is especially true in the healthcare sector, since transferring these data is often associated with bureaucratic overhead because of, for example, increased security requirements and privacy laws. Federated Learning should circumvent this problem and allow training to take place directly on the data owner’s side without sending them to a central location such as a server. Currently, there exist several frameworks for this purpose such as TensorFlow Federated, Flower, or PySyft/PyGrid. These frameworks define models for both the server and client since the coordination of the training is performed by a server. Here, we present a practical method that contains a dynamic exchange of the model, so that the model is not statically stored in source code. During this process, the model architecture and training configuration are defined by the researchers and sent to the server, which passes the settings to the clients. In addition, the model is transformed by the data owner to incorporate Differential Privacy. To trace a comparison between central learning and the impact of Differential Privacy, performance and security evaluation experiments were conducted. It was found that Federated Learning can achieve results on par with centralised learning and that the use of Differential Privacy can improve the robustness of the model against Membership Inference Attacks in an honest-but-curious setting.

Purpose: Recent developments in hardware design enable the use of fast field‐cycling (FFC) techniques in MRI to exploit the different relaxation rates at very low field strength, achieving novel contrast. The method opens new avenues for in vivo characterizations of pathologies but at the expense of longer acquisition times. To mitigate this, we propose a model‐based reconstruction method that fully exploits the high information redundancy offered by FFC methods.Methods: The proposed model‐based approach uses joint spatial information from all fields by means of a Frobenius ‐ total generalized variation regularization. The algorithm was tested on brain stroke images, both simulated and acquired from FFC patients scans using an FFC spin echo sequences. The results are compared to three non‐linear least squares fits with progressively increasing complexity.Results: The proposed method shows excellent abilities to remove noise while maintaining sharp image features with large signal‐to‐noise ratio gains at low‐field images, clearly outperforming the reference approach. Especially patient data show huge improvements in visual appearance over all fields.Conclusion: The proposed reconstruction technique largely improves FFC image quality, further pushing this new technology toward clinical standards.

Purpose: Recent developments in hardware design enable the use of Fast Field-Cycling (FFC) techniques in MRI to exploit the different relaxation rates at very low field strength, achieving novel contrast. The method opens new avenues for in vivo characterisations of pathologies but at the expense of longer acquisition times. To mitigate this we propose a model-based reconstruction method that fully exploits the high information redundancy offered by FFC methods. Methods: The proposed model-based approach utilizes joint spatial information from all fields by means of a Frobenius - total generalized variation regularization. The algorithm was tested on brain stroke images, both simulated and acquired from FFC patients scans using an FFC spin echo sequences. The results are compared to three non-linear least squares fits with progressively increasing complexity. Results: The proposed method shows excellent abilities to remove noise while maintaining sharp image features with large signal-to-noise ratio gains at low-field images, clearly outperforming the reference approach. Especially patient data shows huge improvements in visual appearance over all fields. Conclusion: The proposed reconstruction technique largely improves FFC image quality, further pushing this new technology towards clinical standards.

Many smart magnetic resonance imaging (MRI) probes provide response to a biomarker based on modulation of their rotational correlation time. The magnitude of such MRI signal changes is highly dependent on the magnetic field and the response decreases dramatically at high fields (>2 T). To overcome the loss of efficiency of responsive probes at high field, with fast‐field cycling magnetic resonance imaging (FFC‐MRI) we exploit field‐dependent information rather than the absolute difference in the relaxation rate measured in the absence and in the presence of the biomarker at a given imaging field. We report here the application of fast field‐cycling techniques combined with the use of a molecular probe for the detection of Zn²⁺ to achieve 166 % MRI signal enhancement at 3 T, whereas the same agent provides no detectable response using conventional MRI. This approach can be generalized to any biomarker provided the detection is based on variation of the rotational motion of the probe.