idw – Informationsdienst Wissenschaft
Nachrichten, Termine, Experten
Nachrichten, Termine, Experten
Pancreatic cancer is among the most aggressive cancers and has a poor prognosis. The partners in the RELEVIUM EU project aim to improve palliative care and quality of life for patients with advanced pancreatic cancer using digital tools and an AI-supported multimodal intervention. Researchers at the Fraunhofer Institute for Industrial Mathematics ITWM are using explainable artificial intelligence (XAI) methods to help implement personalized treatment plans and strengthen patients’ well-being and self-management.
Pancreatic cancer accounts for two to three percent of all malignant tumors and has a high mortality rate. It is usually already at an advanced stage when diagnosed, largely because its symptoms are nonspecific. The tumor tends to metastasize aggressively. Patients experience severe symptoms such as pain, muscle wasting and significant weight loss. Treatment strategies focus primarily on hospital-based palliative oncology care. Digital tools have tremendous potential to improve palliative and supportive oncology care and to overcome the limitations of exclusive in-person care. The EU-funded RELEVIUM project (see below) comes in precisely here, addressing unmet needs in supportive care through innovative AI-based solutions. The project partners believe that a personalized approach combining tailored nutrition plans, physical activity and pain management strategies with chemotherapy could significantly improve patients’ quality of life. The interdisciplinary project consortium is developing digital tools for targeted intervention planning, independent self-management, personalized treatment plans and improved communication between healthcare professionals and patients.
Fraunhofer ITWM develops AI algorithms for personalized exercise therapy
Physicians need comprehensive data on patients’ health and well-being in order to plan supportive therapy. Patients receiving outpatient care are given sensor-equipped smartwatches and access to a smartphone app to simplify and largely automate data collection. These devices track patients’ pain levels, nutrition and physical activity. Algorithms developed for the project use this data to recommend individualized interventions to medical professionals. The resulting personalized treatment plans are then displayed on patients' mobile apps and recorded with their wearables.
Exercise therapy is a key element of this comprehensive treatment approach. Fraunhofer ITWM researchers use knowledge-based algorithms and explainable artificial intelligence (XAI) models to adjust physical activities such as endurance and strength training based on the data collected. Sports medicine specialists at the Johannes Gutenberg University Mainz continuously monitor the exercise recommendations. The algorithms collect feedback from various training sessions, allowing future workouts to be tailored automatically to each patient. “Exercise can significantly improve physical well-being. With regular physical activity tailored to their needs, patients report having more strength for daily activities, feeling less fatigued and enjoying a much better quality of life,” says Alexander Scherrer, Senior Consultant for Optimization in Life Sciences at Fraunhofer ITWM. “The same AI-based approach to refining and adapting exercise plans can also be applied to nutrition and pain and stress management. For years, medicine focused primarily on treatment. Now, patient care and satisfaction are increasingly taking center stage,” he adds.
AI-based monitoring and intervention planning
The project partners use the captured data to develop models that can predict disease progression and identify potential benefits of lifestyle changes. This data-driven approach helps clarify what is affecting patient health. “The data provides valuable input for developing medical models and designing effective interventions. Explainable artificial intelligence methods help us understand the factors that affect health,” explains Fraunhofer ITWM research scientist Jonas Flechsig.
A dashboard summary helps patients and physicians better manage the disease and make informed treatment decisions. “The data is analyzed, transformed into meaningful indicators of patient condition and then displayed on the dashboard. This analysis helps develop causal models to predict disease progression and provide an early warning of any decline in patient quality of life. The analysis results must be understandable and must be used ethically for intervention planning,” says Scherrer. “It is also important to emphasize that the digital tools and assistance systems are intended solely to aid in decision-making. Healthcare professionals remain responsible for determining what action to take.”
A study explores how personalized, AI-powered digital support can improve quality of life
A multicenter randomized clinical trial involving roughly 50 participants is assessing the effectiveness of the AI-powered components. Every one to two weeks, physical activity, nutrition and pain management plans are adjusted based on the data collected remotely through smartwatches and the mobile app. The purpose of the study is to assess how the proposed personalized treatment plans affect quality of life for patients with advanced pancreatic cancer. It will also evaluate the cost-effectiveness of the intervention, its potential to promote equal opportunity in health and its ability to ease the stress experienced by patients’ families in different European countries.
EU project RELEVIUM
Funded by:
The project is funded by the European Union’s Horizon Europe framework program for research and innovation.
Duration:
September 2022 through November 2026
Project partners:
The project consortium consists of 17 partners from 10 countries.
• University Medical Center Mainz (project coordinator)
• Johannes Gutenberg University Mainz
• Fraunhofer Institute for Industrial Mathematics ITWM
• Ethniko Kentro Erevnas Kai Technologikis Anaptyxis
• Charokopeio Panepistimio
• EXUS Software Ltd.
• Ainigma Technologies BV
• MCS Data Labs GmbH
• Futuro Perfecto Innovación DL
• Institut Curie
• Rambam Health Cooperation
• Sihtasutus Põhja-Eesti Regionaalhaigla
• Institut Jules Bordet
• DBS Diadikasia
• European Nutrition for Health Alliance ENHA
• Centre for Social Innovation
• Rosenbaum Consulting Ltd.
https://www.fraunhofer.de/en/press/research-news/2026/november-2026/improving-qu...
Dr. Jonas Flechsig (left) and Prof. Alexander Scherrer (right) from Fraunhofer ITWM are working on A ...
Copyright: © Fraunhofer ITWM
Merkmale dieser Pressemitteilung:
Journalisten
Elektrotechnik, Ernährung / Gesundheit / Pflege, Informationstechnik, Mathematik, Medizin
überregional
Forschungsprojekte, Kooperationen
Englisch
Dr. Jonas Flechsig (left) and Prof. Alexander Scherrer (right) from Fraunhofer ITWM are working on A ...
Copyright: © Fraunhofer ITWM
Sie können Suchbegriffe mit und, oder und / oder nicht verknüpfen, z. B. Philo nicht logie.
Verknüpfungen können Sie mit Klammern voneinander trennen, z. B. (Philo nicht logie) oder (Psycho und logie).
Zusammenhängende Worte werden als Wortgruppe gesucht, wenn Sie sie in Anführungsstriche setzen, z. B. „Bundesrepublik Deutschland“.
Die Erweiterte Suche können Sie auch nutzen, ohne Suchbegriffe einzugeben. Sie orientiert sich dann an den Kriterien, die Sie ausgewählt haben (z. B. nach dem Land oder dem Sachgebiet).
Haben Sie in einer Kategorie kein Kriterium ausgewählt, wird die gesamte Kategorie durchsucht (z.B. alle Sachgebiete oder alle Länder).
