AI: New testing framework to ensure the quality of training data
24.09.2024
A testing framework has been developed at Germany’s national metrology institute, the Physikalisch-Technische Bundesanstalt (PTB), to ensure the quality of training data for medical AI applications. The framework, as well as a tool for the automated testing of algorithms, will be available to all developers.
FAQ: Interesting facts about DiGA development for providers
18.07.2024
In Germany, digital health applications (DiGA) are an important part of modern medicine. In addition to mobile apps, these also include web-based applications, software for medical devices, telemedicine platforms, VR applications and wearable sensors. It is important that they support, improve or enable healthcare through the use of digital technologies.
Empathic incubator: almost like in the womb
16.07.2024
Premature babies lying in incubators in intensive care units are often heavily wired. Researchers are striving to make this environment more comfortable for everyone involved, in particular by wirelessly monitoring the heart and breathing. The aim is to optimize neonatal intensive care by studying and improving the baby's sensory experience.
Carl von Ossietzky University of Oldenburg
Hearables: The new health centers on the ear
04.07.2024
Over the next five years, researchers from the Universities of Oldenburg and Bremen want to investigate what additional tasks hearing aids can take on as part of the HEARAZ (Hearable-centered Assistance: From Sensor to Participation) research training group.
YuriArcursPeopleImages
Artificial intelligence in the laboratory: current developments and applications
28.05.2024
Artificial intelligence (AI) has become an integral part of modern laboratories. AI systems based on machine learning and algorithmic analysis are used in various scientific and medical disciplines to automate processes, increase efficiency, and gain new scientific insights.
Alessandro Winkler/Universitätsklinikum Bonn
New diagnostic software improves analysis of kidney diseases
23.04.2024
Researchers at the University Hospital Bonn, in collaboration with the University of Bonn, have developed a computer method to determine whether protein excretion in urine is caused by a few severely damaged or many slightly damaged kidney filters. The innovative findings were published in the journal Kidney International.
AI recognizing heart failure through voice analysis
21.03.2024
In the future, artificial intelligence will monitor patients with advanced heart failure telemedically by the sound of their voice. This will make it possible to detect and treat deterioration at an early stage. The Berlin start-up Noah Labs UG has developed the AI required for this.
Kaunas University of Technology (KTU)
Monitoring Atrial Fibrillation with smart bracelet
30.01.2024
Atrial fibrillation, the most prevalent heart rhythm disorder impacting 33 million people worldwide, can have serious consequences if left untreated. To address this pressing issue, researchers have unveiled a technology aimed at identifying and managing individual factors contributing to atrial fibrillation.
XiXinXing
Evaluating brain tumours with artificial intelligence
22.12.2023
One application area of artificial intelligence (AI) is in medicine, especially in medical diagnostics. For instance, scans can be analysed automatically with the help of algorithms. An international and interdisciplinary team led by researchers from TU Darmstadt recently investigated whether AI can better evaluate images of brain tumours.
Fraunhofer IPA
DAIOR research project: Distributed AI improves telesurgery
14.12.2023
In the DAIOR research project, doctors and technicians are working on the evaluation of surgical data from multimodal sources using artificial intelligence (AI). One of the project goals is to support robot-assisted telesurgery in real time.
YuriArcursPeopleimages
Artificial intelligence: Will an algorithm soon be writing doctors' letters?
11.12.2023
Researchers at the Fraunhofer Institute for Intelligent Analysis and Information Systems IAIS are currently developing a "doctor's letter generator" that could soon produce documents in the shortest possible time. With 150 million doctors' letters being written in Germany every year, this would save hospitals and medical practices an enormous amount of time.
Universität Bayreuth
Kulmbach Live-in Lab: holistic research on digital health
07.12.2023
The possibilities for researching human behaviour with the help of artificial intelligence are being taken to the next level in Kulmbach: The Live-in Lab there is Europe's leading laboratory for digital, AI-supported research into human behaviour in everyday life. It has now been opened.
Singh et al. Physics of Fluids (2023) / MPI-CBG
New computer code for mechanics of tissues and cells in three dimensions
28.11.2023
Open-source supercomputer algorithm predicts patterning and dynamics of living materials and enables studying their behavior in space and time.
University of the Basque Country
Models that predict poor clinical outcome in COVID-19 patients
24.11.2023
Factors associated with hospital admissions, ICU stays and mortality in patients who have had SARS-CoV-2 are identified, and clinical prediction rules are developed.
Anja Stübner, EKFZ für Digitale Gesundheit
Informed consent to the use of personal health data
22.11.2023
Millions of people worldwide use health and wellness applications to record health-related parameters such as symptoms, step count or heart rate in their everyday lives. This citizen-generated health data provides previously unknown information about a person's experience of illness and health.
Breath the spirit of MEDICA 2023 – Highlight tour with Director Christian Grosser
13.11.2023
Topics like artificial Intelligence, automation and robotics, and sustainability are shaking the medical industry – and both MEDICA and COMPAMED reflect that. We are walking through the trade show halls of MEDICA with Christian Grosser, Director Health & Medical Technologies at Messe Düsseldorf, to talk about this: What are his impressions of this year’s MEDICA and COMPAMED?
gpointstudio
Coronavirus: Model can predict the evolution of new variants
31.10.2023
An international research team from the University of Cologne and the Icahn School of Medicine, Mount Sinai (New York) has developed a model that predicts the likely evolution of variants of the SARS-CoV-2 virus.
wirestock
Collective intelligence can reduce medical misdiagnoses
30.10.2023
Researchers from the Max Planck Institute for Human Development, the Institute for Cognitive Sciences and Technologies (ISTC), and the Norwegian University of Science and Technology developed a collective intelligence approach to increase the accuracy of medical diagnoses.
BIPS
White paper: improving record linkage for health research
16.10.2023
In Germany, it is currently difficult to link health data from different sources. The Leibniz Institute for Prevention Research and Epidemiology – BIPS is now presenting a white paper on this topic.
Yulia_Panova
ScPoli enables multi-scale representations of cells and samples
12.10.2023
Computer scientists at Helmholtz Munich developed a generative model named ScPoli that performs data integration of high-quality large-scale datasets of single cells.
Photo courtesy of Temiloluwa Prioleau
Wearable devices show who may need more help managing diabetes
29.09.2023
A new Dartmouth study in the journal Science Advances suggests that how well people with diabetes manage their blood sugar depends on their experience with the condition and their overall success in controlling their glucose levels, as well as on the season and time of day.
paegagz
Algorithm to predict disease relapses
29.09.2023
A University of Texas at Arlington research team has received a $450,000 grant from the National Institute of General Medical Sciences to use statistical machine learning to review patient data and better predict which patients will need additional treatments.
Karin Kaiser / MHH
CALM-QE: Personalized diagnostics in asthma and COPD
27.09.2023
The MHH Children's Hospital is participating in a nationwide project to better predict individual disease courses in non-infectious lung diseases using standardised data from health care and environmental data.
davidpradoperucha
Cure Xchange Challenge: initiative to incubate innovations by healthcare start-ups
26.09.2023
Cure, a healthcare innovation campus in New York City, has opened applications for its Cure Xchange Challenge, a bold initiative to incubate innovations by healthcare start-ups and entrepreneurs across disciplines and sectors to responsibly and equitably use artificial intelligence (AI) in health.
European Society for Emergency Medicine
ChatGPT suggests most likely diagnoses in the emergency medicine department
25.09.2023
The artificial intelligence chatbot ChatGPT performed as well as a trained doctor in suggesting likely diagnoses for patients being assessed in emergency medicine departments.
AndersonPiza
Danger from chatbots: Do they need regulation as a medical device?
12.09.2023
Chatbots like ChatGPT have great potential for medicine. But their unregulated use in healthcare poses a great danger because of their inherent risks. A Nature Medicine article by Prof. Stephen Gilbert et al. calls for medical device approval for chatbots and applications based on them.
Dt. Leberstiftung
Predicting severe liver disease with simple tools
08.09.2023
A European consortium with the participation of the MHH is developing a new tool to determine the individual risk of liver fibrosis and liver cancer.
Shaiith
AI shows how Aspergillus fumigatus gets comfortable in the lungs
14.08.2023
Aspergillus fumigatus strains that infect humans have a significantly altered metabolism compared to other strains in the environment. At the same time, infection with the fungus leads to an apparent change in the human lung microbiome.
ORION_production
AI-supported mammography screening is found to be safe
11.08.2023
Mammography screening supported by artificial intelligence (AI) is a safe alternative to today’s conventional double reading by radiologists and can reduce heavy workloads for doctors.
Dr. Axel Loewe, KIT
Machine learning: artificial neural networks localize extrasystoles
03.08.2023
Researchers at Karlsruhe Institute of Technology (KIT) use machine learning for the non-invasive localization of ventricular extrasystoles. This may facilitate and improve future diagnosis and therapy.
istock.com/viorika
AI brings hope for children with lyosomal storage disease
20.07.2023
Artificial intelligence is becoming increasingly important in drug discovery. Advances in the use of Big Data, learning algorithms and powerful computers have now enabled researchers at the University of Zurich (UZH) to better understand a serious metabolic disease.
monkeybusiness
Into the hospital of the future: data, digitization and artificial intelligence
18.07.2023
Artificial intelligence (AI) and its use is on everyone's lips right now. How AI will change and shape our future is being hotly debated. AI applications are also trending in healthcare. But before they can deliver on their huge expectations, the basics have to be met.
EKFZ
AI against bowel cancer: research project DECADE
12.07.2023
The DECADE research project is the first to use swarm learning in cancer research. The German Cancer Aid is funding the joint project of several university hospitals with around 1.5 million euros.
Fraunhofer IGD
Digital patient model: decision support for physicians and cost-saver
10.07.2023
New perspectives for the healthcare sector: The support system for decision-making developed as part of the MED²ICIN project should increase the treatment success rate. It supports physicians in their decision-making process by pooling all of the information on an individual patient and comparing this to that of cohorts made up of similar individuals.
EKFZ/ A. Stübner
Chatbots like ChatGPT: approval as medical devices
06.07.2023
The new Nature Medicine paper by Prof. Stephen Gilbert, et. al. addresses one of the most pressing international issues of our time: How to regulate Large Language Models (LLMs) in general and specifically in health.
yavdat
AI enables first integrated single-cell atlas of the lung
15.06.2023
Can a human organ be mapped on a single-cell level to learn more about each individual cell? And can we learn how different these cells are from person to person? Helmholtz Munich researchers and their collaborators have taken up this challenge and developed the Human Lung Cell Atlas using artificial intelligence (AI)-based techniques.
Swen Reichhold
Infectious diseases: digital 'vaccine library' against pandemics
12.06.2023
The Institute for Drug Discovery led by Humboldt Professor Jens Meiler is to receive 1.9 million dollars (1.77 million euros) for the development of vaccines. The international Coalition for Epidemic Preparedness Innovations (CEPI) will fund computer-aided vaccine development at Leipzig University with the aim of building a digital ‘vaccine library’ of components and virtual antigen designs.
Karin Kaiser / MHH
Cardiovascular diseases: individual risk assessment with ACRIBiS
08.06.2023
MHH Cardiology participates in a nationwide project to improve risk assessment thanks to structured and standardized data.
tommyandone
Heart failure: AI identifies five subtypes
01.06.2023
Five subtypes of heart failure that could potentially be used to predict future risk for individual patients have been identified in a new study led by UCL (University College London) researchers.
Anna Schroll/Leibniz-HKI
Model shows intestinal bacteria influence growth of fungi
22.05.2023
The bacteria present in the intestine provide information about the quantities of fungi of the potentially disease-causing Candida genus.
University of Surrey
UK AI world leader in identifying location and expression of proteins
18.05.2023
A new advanced artificial intelligence (AI) system has shown world-leading accuracy and speed in identifying protein patterns within individual cells.
Universidad de Barcelona
Rare disease diagnosis: AI algorithms do not include human diversity
17.05.2023
Most of the AI-generated algorithms have databases with populations of European origins and they ignore the genetic and morphological diversity of human populations of around the world.
Fraunhofer IDMT
EEG as an example of data protection for biosignals
16.05.2023
The “NEMO” project is exploring anonymisation techniques, using the example of electroencephalograms (EEG).
Okrasyuk
Map of spinal cord formation gives new knowledge on diseases of the nervous system
03.05.2023
Researchers at Karolinska Institutet in Sweden have mapped how cells in the human spinal cord are formed in the embryo and what genes control the process.
Manuta
Big Data: predictive model for complications in diabetes
01.05.2023
For their research, the team led by Rainer Oberbauer, Head of the Division of Nephrology and Dialysis at MedUni Vienna's Department of Medicine III, and Mariella Gregorich from MedUni Vienna's Center for Medical Data Science drew on data from major international studies.
Agnes Toth-Petroczy, Nature Communications
New tool facilitates clinical interpretation of genetic information
27.04.2023
Max Planck and Harvard research teams develop DeMAG, a new method shared as an open-source web server (demag.org) to help interpret mutations in disease genes and improve clinical decision-making.
DZHK
Collaborative and sustainable - the DZHK's clinical research platform
26.04.2023
At the German Center for Cardiovascular Research (DZHK), clinical study data and samples belong not to individual clinics but to a superordinate structure - the DZHK. The basis for this is the collaborative clinical research platform launched ten years ago, which makes data and samples from all DZHK studies uniformly recordable.
westend61
Platform for the rapid development of digital health applications
03.04.2023
Fraunhofer FIT presents a toolbox for the rapid development of digital health applications. It can help to respond to urgent needs in the healthcare market. The platform integrates applications, methods and solutions from several national and European research projects.
Bielefeld University/Sarah Jonek
Predicting outbreak of ALS disease with AI methods
08.03.2023
Using artificial intelligence (AI) methods, researchers led by Professor Dr Alexander Schönhuth from Bielefeld University’s Faculty of Technology have succeeded in recording and deciphering the genotype profiles of 3,000 ALS patients and thus learning more about the development of the disease.
Pressmaster
AI analyses cell movement under the microscope
22.02.2023
The enormous amount of data obtained by filming biological processes using a microscope has previously been an obstacle for analyses.
University of Gothenburg
AI supports doctors’ hard decisions on cardiac arrest
21.02.2023
Researchers at the University of Gothenburg have developed three such systems of decision support for cardiac arrest that may, in the future, make a major difference to doctors’ work.