idw – Informationsdienst Wissenschaft
Nachrichten, Termine, Experten
Nachrichten, Termine, Experten
An interdisciplinary project team is conducting research into the privacy-preserving use of large language models in the health sector. Called ILLUMINATION, the project brings together technical, legal, medical and human-centered perspectives to develop an application for the clinical setting that will help medical personnel to prioritize emergency patients more quickly. The German Federal Ministry of Education and Research is funding ILLUMINATION for three years with a total of around 1.7 million euros. Led by the CISPA Helmholtz Center for Information Security, the five project partners are coming together today at the Charité in Berlin for the project launch.
Medical care requires extensive speech and text processing: Recording patient data and symptoms, inquiring about medical histories and classifying complaints – medical staff have to document and assess all this information, often under time pressure. In theory, large language models (LLMs) are already capable of performing these tasks far more efficiently than humans. In practice, however, this poses considerable risks to data protection and privacy. In order to reliably protect sensitive patient data while harnessing the advantages of LLMs for medical care, ILLUMINATION is developing legally compliant privacy methods for LLM-based applications.
LLMs can support medical staff in emergency units
ILLUMINATION focuses on developing a privacy-friendly LLM-based application to support medical staff in pre-triaging patients in emergency units. The idea is for patients to be able to share their complaints with the LLM via interactive chats. The LLM will then analyze the symptoms and suggest how to prioritize the patients. Based on this preliminary work, the medical staff will establish further vital parameters and decide on further treatment. Franziska Boenisch, project coordinator of ILLUMINATION and Faculty at CISPA, explains the project’s overall objective: “We want to use LLMs to relieve the burden on doctors in the time-critical environment of emergency units. Due to privacy risks, the use of LLMs in pre-triage has not been possible to date.”
Combining prediction quality with privacy-friendliness
In very specific contexts such as emergency care, large language models can only deliver high-quality predictions if they have been specifically trained for the respective area of application. For this reason, the project team will have to feed its application with real patient data from previous triage processes. To prevent this sensitive data from leaking to either the LLM operators or the application’s subsequent users, the project team is developing privacy methods based on Differential Privacy. Franziska Boenisch explains: “Differential Privacy is a mathematical framework which can guarantee that an individual’s data remains private. This means that the LLM can learn from the population, i.e. from the sum of all the training data it is fed, but not from the individual data of a single patient. Conversely, this also guarantees that no individual has too great an influence on the system and its predictions.”
Interdisciplinarity offers a holistic perspective
The German Federal Ministry of Education and Research is sponsoring ILLUMINATION with a total of around 1.7 million euros over a period of almost three years. In order to achieve a holistic perspective on the use of large language models in the medical field, ILLUMINATION brings together Charité – Universitätsmedizin Berlin, Heidelberg University, Freie Universität Berlin, as well as the startup algonaut under the coordination of CISPA. The interdisciplinary project team unites experts and perspectives from the fields of medicine, law, human-centered computing, LLM-based prototype development, and machine learning.
ILLUMINATION is sponsored by the Federal Ministry of Education and Research.
About CISPA
The CISPA Helmholtz Center for Information Security is a German national Big Science institution within the Helmholtz Association. CISPA researchers explore all aspects of information security. They address the pressing global challenges in cybersecurity, data protection and trustworthy artificial intelligence. Conducting modern foundational research as well as innovative application-oriented research, they work to protect the digital space and improve industrial applications and products. CISPA promotes scientific talent, supports promising founders, and trains experts and executives for business and industry. In this way, it carries its research findings into society and strengthens Germany’s as well as Europe’s competitiveness.
https://cispa.de/en
Dr. Franziska Boenisch
Dr. Adam Dziedzic
CISPA Helmholtz Center for Information Security
Stuhlsatzenhaus 5
66123 Saarbrücken, Germany
boenisch@cispa.de
dziedzic@cispa.de
The ILLUMINATION project was launched today.
CISPA
Merkmale dieser Pressemitteilung:
Journalisten, Wissenschaftler
Informationstechnik, Medizin
überregional
Forschungsprojekte, Kooperationen
Englisch
The ILLUMINATION project was launched today.
CISPA
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).
