Center for Artificial Intelligence in Medicine

CAIM supports Ukrainian scientists

The Center for AI in Medicine supports scientists from Ukraine in these difficult times. Following the measures and call from the Swiss National Science Foundation to help Ukrainian researchers as well as the University of Bern’s initiative to solidarize with Ukraine and its universities, CAIM calls its members and partners to reach out and proactively seek ways to help our colleagues.

Contact info.caim@unibe.ch with ideas or requests for support.

Averting severe embolisms through artificial intelligence

Experts in laboratory medicine at Inselspital, Bern University Hospital, have developed a diagnostic prediction model in a long-term prospective multicenter study in collaboration with data scientists at the University of Bern, which provides treating physicians with an indicator to reliably diagnose HIT (heparin-induced thrombocytopenia) - a rare but life threatening complication for hospitalized patients after major surgery or severe inflammation. The diagnostic machine learning tool derived from this research in the field of laboratory medicine is unique in the world.

Read the media release...

Great Interest in the CAIM Research Symposium

The first Research Symposium of the Center for Artificial Intelligence in Medicine since its official opening in March 2021 was attended by more than 100 researchers from the Bernese ecosystem around the University and University Hospital. CAIM Director Raphael Sznitman was excited to witness the beginning of promising interdisciplinary scientific discussions in the wake of the two keynote speeches and during the networking breaks. "It is great to have such a vibrant community around AI research for healthcare here in Bern," he said.

Impressions CAIM Research Symposium 2022...

Amith Kamath and Charlotte Kern win CAIM Young Researcher Awards

The very translational research of PhD students Amith Kamath, ARTORG Center, University of Bern, and Charlotte Kern, Department of Clinical Pharmacology and Toxicology at the Inselspital, Bern University Hospital, has been recognized at the CAIM Research Symposium with one of the new CAIM Young Researcher Awards each. Awards were sponsored by the Bern Economic Development Agency with a total of CHF 1000. The research developed yet a bit further into a product (Amith Kamath) additionally received 16 hours worth of personalized entrepreneurial coaching by be-advanced.

Using interpretability to improve medical AI

The Medical Image Analysis lab at the ARTORG Center has just published a study where interpretability informed sample selection from a set of radiological images. The lab, which has focused on interpretability both as a means for more transparency in medical AI workings and as a tool to improve AI itself, reports that their novel sample selection approach based on graph analysis to identify informative samples in a multi-label setting improved model performance, learning rates, and robustness when compared to state-of-the-art Active Learning methods.

Learn more …

CAIM Research Symposium

On 24 November, 8.30-13.30h CAIM will be presenting updates on its funded research projects as well as two invited keynotes on AI for medicine opportunities and challenges at the University of Bern main building top floor event venue (Kuppelsaal). Meet our Executive team, our ethics specialists and the people behind our initiative DAIM and exchange ideas during coffee breaks!

Learn more and register...

"Artificial Intelligence Advances Medicine"

Stavroula Mougiakakou, head of Artificial Intelligence in Health and Nutrition at the ARTORG Center, conducts applied fundamental research and with her team aims to close the gap between theory and practice. In the highly interdisciplinary and very competitive field of AI in medicine she sees a clear need for rigorous scientific testing that can assure approaches, tools and processes that can benefit users. At CAIM, she is Co-Responsible for Education and leads the master program "AI in Medicine".

Read the interview...

Less radiation with AI-enhanced PET

PET/CT can be used to clarify tumor diseases regarding their extension and therapy response, as well as to answer neurological and cardiological questions. The Bern University Hospital uses the world's most sensitive PET scanners with comparatively low radiation exposure. AI-supported image attenuation could further lower radiation and result in better imaging, as demonstrated by the Nuclear Medicine Department in Nature Communications.

Learn more...

Maintaining a Mediterranean diet with your phone

Researchers at the ARTORG Center in collaboration with Oviva and with the Epidemiology, Biostatistics and Prevention Institute (EBPI), University of Zurich, have demonstrated that an AI system on a smartphone can effectively track whether a person is adhering to a Mediterranean diet (MD). MD can decrease the risk of non-communicable disease and prevent overweight and obesity. The feasibility study of the system was just published in Nature Scientific Reports.

Learn more…

MADiMa 2022

The main scope of MADiMa2022 is to bring together researchers from the diverse fields of engineering, computer science and nutrition who investigate the use of information and communication technologies for better monitoring, assessment, and management of food intake.

More information and how to submit...

DAIM Lunch Talk

Dr. Lisa Koch, Institute for Ophthalmic Research, University of Tübingen, will present approaches "Towards Safe and Effective Medical Image Analysis Systems" at this lunchtime event in hybrid mode hosted by the ARTORG Center for Biomedical Engineering Research. This event runs under the umbrella of the initiative DAIM - Diversity for AI in Medicine. Participation is free. Please register.

Details and registration...

Bernese AI system receives FDA approval

An artificial intelligence system for brain tumor segmentation from multisequence MRI has received 510k clearance by the US American Food and Drug Administration on 29 September 2022. The system was developed by Prof. Dr. Mauricio Reyes and his team from the Medical Image Analysis lab, at the ARTORG Center and the Center of AI in Medicine, Univ. of Bern. Work on this important milestone by many talented PhD and Master students has started at the @MICCAI 2011 conference, receiving the 2016 MICCAI Young Scientist Publication Impact Award as well as the 2016 Ypsomed Innovation Award. It underlines the importance of Bernese research on a global scale.

Read the media release…

AI: Friend and helper of medical professionals?

AI is profoundly changing the healthcare system. This process poses various challenges for the medical profession. With the brochure "Artificial intelligence in everyday medical practice", the Swiss Medical Association FMH offers the medical profession an overview of AI in the medical environment. Ten demands raise awareness for the essential aspects of AI in medicine.

Read the FMH media release (German & French)...

Research Awards

CAIM launches its student research award! Apply from 6 September for best student project CAIM. Two winning projects will be announced at the CAIM Research Symposium on 24 November and will receive CHF 500 each.

Learn how to apply...

Smart Tools for Dexterity Home Training in Parkinson’s

Limited hand and finger movement due to Parkinson's disease can be counteracted to some degree with targeted physical therapy. To provide patients with individual training options at home, the Gerontechnology and Rehabilitation group at ARTORG Center has now evaluated the usability of two new interactive game sensor-based hand devices.

More about the study…

Making the most out of lab data

Every large hospital produces a wealth of data each day, holding the key to new insights into diseases and improved patient care. For machine learning and Big Data approaches to be utilized on this data, lab data needs to be FAIR: findable, accessible, interoperable, and reusable, propose a team of researchers from the Department of Clinical Chemistry at the Inselspital.

Read the study…

CAIM at Uni Bern Researchers’ Night

Save the Date!
Our Center will present itself to the broader public with an interactive discovery trip of what Artificial Intelligence means and does and how it is applied today (and tomorrow) in healthcare.

Learn more...

Sensor-based early detection of age-related diseases from home

Researchers at the University of Bern and Inselspital, Bern University Hospital have demonstrated how sensors that record movement patterns could help detect health problems in the elderly, including old-age depression, risk of falls or cognitive impairment, at an early stage. In the future, this could help seniors to live a self-determined life at home for longer and relieve increasing pressure on the healthcare system.

Read the media release...

Interview with neurosurgeon Andreas Raabe

In his career, neurosurgeon and clinic director Andreas Raabe has seen major developments in medical technology that open unprecedented possibilities for interventions on the brain and spine. With a keen interest in physics, he develops new technologies for the operating room emerging from practice at Inselspital together with the ARTORG Center.

Read the interview...

Hypo- and Hyperglycemia Prediction

Blood glucose decompensations of hospitalized patients poses a frequent and significant risk for patient outcomes and safety. A team of data scientists and doctors from the University of Bern and Bern University Hospital have generated a broadly applicable multiclass classification model for predicting decompensation events from patients’ electronic health records to indicate necessary adjustments in monitoring or therapy.

Read the study...

Esther Brill

Esther Brill is a PhD student in cognitive neuroscience at the University Hospital of Old Age Psychiatry and Psychotherapy Bern. As a digital native she considers connecting technology and clinical work essential to fight ever more prevalent neurodegenerative diseases such as dementia through computerized cognition games.

Read the interview...

ARTORG Center to develop digital care assistant with QUMEA

Together with digital health startup QUMEA, the ARTORG Center for Biomedical Engineering Research, University of Bern and the Bern University of Applied Sciences (BFH) have started a project to enable hospital care teams and doctors to adapt and improve care via sensor-based technology. The project is funded by an Innosuisse grant of CHF 1.2 million under the impulse program Swiss Innovation Power.

Read the QUMEA media release...

The virtual microphone

Scientists from Bern have shown in a feasibility study that artificial intelligence can help improve understanding in noisy environments. PD Wilhelm Wimmer explains in an interview with dezibel, pro audito, how exactly this works.

Read the interview...

Workshop Medical Decision Support

Interdisciplinary workshop by the Technical University of Munich (TUM) tailored specifically to the needs of medical professionals and part of the TUM working group "AI for Doctors". The hybrid workshop features examples from dermatology, neuroradiology, opthalmology and pathology, a keynote by Ben Glocker (Imperial College London) and a presentation on Explainable AI by Mauricio Reyes (CAIM).

More information and registration...

AI for diabetes project MELISSA launched

The EU Research Project “MELISSA: Mobile Artificial Intelligence Solution for Diabetes Adapted Care” was launched today by a consortium of 12 partners, comprising the ARTORG Center Artificial Intelligence in Health and Nutrition (AIHN) lab, University of Bern. AIHN is the artificial intelligence expert in the project and initiated it in collaboration with Debiotech.

More about MELISSA…

Ana Leni Frei

Ana Leni Frei does her PhD in computational pathology on cell interactions in rectal cancer. She hopes to help build AI tools that can assist pathologists to understand changes that occur in the tumor microenvironments of patients receiving neoadjuvant chemoradiotherapy and hopefully understand why 20% of them do not respond to the therapy.

Read the interview...

CAIM participates in AI Med Summit

Just a year old, CAIM was nominated as 'Best Hospital/Institution of the Year' at the Ai Med Summit 2022. Our center was honored to present our activities to renowned AI research institutions and industry from around the world in San Francisco, USA on 25 May 2022. Although we did not bag the win this time, we take the nomination as an incentive for excellence in research and translation for next year.

More on the event...

CAIM first year recap

CAIM celebrates its first anniversary with this retrospective from Director Raphael Sznitman on the milestones achieved so far.

Watch the video statement...

Using AI for patient well-being

In a recent interview with Netzwoche, CAIM Director Raphael Sznitman has emphasized the importance of real-world AI solutions to make a real difference to patient care. Referring to the first round of CAIM funded projects, he said: "All the projects aim for a tangible patient benefit – which is important to us at CAIM, as we do not want to develop technology without real added value."

Read the entire interview (in German)...

Strange dreams help your brain learn better

A study by the University of Bern Department of Physiology suggests that dreams—especially those that simultaneously appear realistic, but, upon a closer look, bizarre—help our brain learn and extract generic concepts from previous experiences. The study, carried out within the Human Brain Project and published in eLife, offers a new theory on the significance of dreams using machine learning inspired methodology and brain simulation.

Read the study and press release...

Lunch Talk on Medical Robotics & AI

Keynote on "Cognition-guided Robotics and Embedded AI for Surgeons" by Prof. Dr. Franziska Mathis-Ullrich, Health Robotics & Automation Laboratory, Karlsruhe Institute of Technology. This brown bag lunch talk is held at the ARTORG Center for Biomedical Engineering Research and marks the start of a the DAIM initiative to foster diversity and inclusion for AI in medicine research.

Program & registration...

2nd Bern Data Science Day

Second Event on data science research at the University of Bern, including artificial intelligence applications for healthcare. CAIM acts as co-sponsor of the Bern Data Science Day and presents its research in poster sessions.

More information and progam...

Predicting Urinary Infection with AI

In a special Issue on Urinary Stones and Infections of Diagnostics, the Inselspital, the University of Cologne and the University of Bern have published a recent AI-guided analysis of urine samples from emergency patients. The assessment of 3835 samples revealed that AI can safely rule out urinary infections in 96 percent of cases. However, for a high-confidence AI prediction of positive infections and infection types, using UFC parameters alone is not sufficient.

Read the study...

Launch of DAIM - Diversity for AI in Medicine

The Center for Artificial Intelligence in Medicine (CAIM) launches an initiative for diversity and inclusion in AI research for healthcare with a keynote lecture by the renowned robotics specialist Prof. Franziska Mathis-Ullrich.

Learn more...

Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer

Hybrid seminar of the Institute for Informatics as part of the Computer Vision Group Open Seminars series. Greg Yang from Microsoft Research gives a two-part talk: The first half will target general practitioners or empirical researchers in machine learning, while the second half targets those who are more theoretically curious.

More information...

Cortical oscillations in neural networks

Dealing with uncertainty is a big challenge for our brain. Led by the University of Bern, researchers from Heidelberg University, the Jülich Research Centre and Graz University of Technology have identified a new computation role for cortical oscillations that support sampling-based computations in spiking neural networks.

Read the study...

Inti Zlobec elected Digital Pathology Professor

The University of Bern has elected Inti Zlobec as Professor of Digital Pathology as of April 2022. The position is one of several new professorships in the field of artificial intelligence and digitalization in medicine that have been created as part of a new research focus in this area.

Read more...

3rd Swiss Emergency Telemedicine Congress

Virtual Congress on eEmergency Medicine and Digital Health featuring presentations on mixed-reality team training for medical first responders, social humanoid robots, Ethics and AI, the digital hospital of the future, VR in acute care, and a Canadian perspective on digital emergency medicine.

Program...

Bernese Covid-19 project featured on Swedish television

Alexander Norén, technical correspondent at the Swedish television has visited Bern to realize a report on a joint project of the Inselspital, Bern University Hospital and the University of Bern for AI-assisted prediction of the severity of a Covid-19 infection progression. The research evaluates extensive clinical, image-morphological and laboratory data with machine learning.

Watch the report...

AI enables personalized treatment of myocarditis

A research team from the University of Bern and Inselspital, University Hospital Bern is investigating and developing innovative approaches that will enable personalized diagnosis and treatment of myocarditis. Artificial intelligence will allow individual risk assessment and progression prognosis in the future. The project has received funding from the CAIM Research Project Fund for 2022/23.

Read the media release...

Training emergency teams in virtual reality

In emergency medicine, all members of the treatment team are crucial to the health and survival of patients. Training routines ensure that the decisive moves are made correctly – and virtual reality is a great tool for this. Tanja Birrenbach explains in an interview how she plans and researches VR trainings for emergency teams and which developments in this area will be topic of the Emergency Telemedicine Congress she co-hosts on 30 March.

Read the interview...

AI helps to dose Parkinson's medication

For people suffering from Parkinson's disease, the correct adjustment of medication is crucial. Too little doesn't help, too much is counterproductive. But how much is right? Together with the Gerontechnology and Rehabilitation group at the ARTORG Center the iHomeLab of the Lucerne University of Applied Sciences and Arts have developed a sensor system and a modified smartwatch that help to find the right dosage.

Read the media release of the HS Lucerne (in German)...

AI is a valuable tool for the medical community

Report by the Schweizerische Ärztezeitung on the one-year anniversary of CAIM. Julia Rippstein describes how CAIM targets challenges arising from the introduction of digital technologies into the medical sector. In this effort, CAIM aims to bring together physicians and engineers to put new technologies at the service of patients.

Read the report (French or German)...

Master's Open Days: 22-24 March

Get insights into the University of Bern Master's programs on this three day event and learn more about the new program Artificial Intelligence in Medicine (AIM)!
On 22-23 March there will be intro lectures on the MSc AIM and the possibility to check out a few courses. On 24 March, you can interact with the lecturers in an online session. Program details will follow on 17 February.

Learn more and register...

Brainweek Bern: Consciousness

The Brainweek Bern 2022 takes places from 14 to 17 March and is focused on "consciousness". On Monday and Tuesday, there will be lectures by experts in neurology, psychology, psychiatry and neuroscience. On Wednesday, interested parties can attend a commented film evening on Locked-In-Syndrome and on Friday there will be a panel discussion on "News on Living with Dementia" with representatives from Inselspital, UPD and the University of Bern.

Website Brainweek...

Are Large-scale Datasets Necessary for Self-Supervised Pre-training?

Zoom seminar of the Institute for Informatics as part of the Computer Vision Group Open Seminars series. Alaa El-Nouby from Meta AI Research and Inria Paris asks "Are Large-scale Datasets Necessary for Self-Supervised Pre-training?"

More information...

Bayesian prevalence estimation in a nosocomial outbreak

Nosocomial pathogens in hospitals require strict screening and prevention. To better understand their dynamics and the impact of control measures, a team of infectiologists, data scientists and clinical chemists from the Inselspital applied a Bayesian hierarchical model to a nosocomial outbreak. Authors conclude that such models provide a more flexible platform to study transmission dynamics.

Read the study...

PhD thesis defense Narayan Schütz

The ARTORG Center congratulates Narayan Schütz for successfully defending his PhD project “Towards Unobtrusive Sensor-Derived Digital Measures of Health in Aging” at the Gerontechnology and Rehabilitation (GER) lab on 16 February 2022! Narayan has evaluated the use of sensor-derived digital measures to monitor health in older adults, demonstrating good acceptance of contactless technologies and promising early evidence of clinical utility.

More on his research…

PhD thesis defense Angela Botros

Congratulations to Angela Botros, Gerontechnology and Rehabilitation (GER) lab, for successfully defending her PhD project on 15 February 2022! Angela has been investigating “Unsupervised health monitoring in home-like environments” in collaboration with the Department of Neurology at Inselspital with a special focus on tracking symptoms of Parkinson’s disease.

Browse her research…

CAIM funds five translational projects

Twenty teams submitted their projects to the first CAIM Research Projects Fund call. After a peer-reviewed assessment by external reviewers and a pitching round, the CAIM Management and Steering Committee have selected five projects to be funded with up to CHF 100,000 each over the coming 24 months.

Learn more about the projects...

Generative Learning Trilemma with Accelerated Diffusion Models

Online seminar on Zoom of the Institute for Informatics as part of the Computer Vision Group Open Seminars series. Doctor Arash Vahdat from NVIDIA Research will speak on "Tackling the Generative Learning Trilemma with Accelerated Diffusion Models".

More information...

CNN quantifies ureteral stent encrustations

Location and extent of encrustation in ureteral stents for different diseases may be informative for patient management and the development of newer stent generations. The Urogenital Engineering Lab at ARTORG has investigated stent encrustation patterns from stone and kidney transplant patients in collaboration with the Inselspital and the Cantonal Hospital Olten, quantifying them via a Convolutional Neural Network (CNN) model.

Show the study results…

AI to prevent malnutrition in hospitals

Used smartly, machine learning could help healthcare workers as well as patients prevent malnutrition in patients during hospital stays. The Artificial Intelligence in Health and Nutrition Laboratory, ARTORG Center, has now developed an AI-powered system that can automatically determine energy and macronutrient intake for each patient based on pre- and post-meal images, and evaluated it in a study.

Learn more...

A leap forward in epilepsy research

Can days with increased risk of epileptic seizures be predicted? Dr. Maxime Baud is researching this question as an SNSF Eccellenza Professor at the University of Bern. For people suffering from epilepsy, his project holds hope.

Read the interview...

1st Joint DACH Symposium on Digital Pathology & AI

Together with colleagues and experts from Germany and Austria, the Swiss Consortium on Digital Pathology is organizing a first joint symposium for Digital Pathology and Artificial Intelligence on 3 February 2022.

Learn more and register...

Suyi Hu wins tinnitus research award

No two tinnitus patients are the same. Therefore, Suyi Hu from the Hearing Research Lab, Inselspital and ARTORG Center Uni Bern, wants to develop a generative computer model that can use artificial intelligence to make individualized tinnitus diagnoses and predict the treatment success of individual therapies for each patient. For his research, he was awarded the 2022 Research Prize of the Swiss Tinnitus League on January 8.

Details on the project...

Challenge of Uncertainty Estimation and Robustness

Online seminar on Zoom of the Institute for Informatics as part of the Computer Vision Group Open Seminars series. Doctor Andrey Malinin, Yandex Research, will give a talk "Tackling the Challenge of Uncertainty Estimation and Robustness to Distributional Shift in Real-World applications".

More information...

AI assets in ophthalmology

The eye as a window to the body - that is one distant application goal of AI in ophthalmology, which will then work closely with cardiology, neurology or rheumatology. Raphael Sznitman explains in a video interview with DocCheck which possibilities are and will be open to ophthalmologists thanks to AI tools.

Watch the interview...

Bern Data Science Initiative launched

The Bern Data Science Initiative, BeDSI, is an initiative of data driven research groups and research centers of the University of Bern. It is designed to weave a flexible network lead by scientists into the university’s traditional structures to foster the work of data and simulation driven research groups. The BeDSI Launch Event took place on December 6, 2021. In an interview, Christiane Tretter (Founding und Ad-interim Chair BeDSI, Professor of Mathematics), Raphael Sznitman (Ad-interim Co-Chair BeDSI, Professor of Artificial Intelligence in Medical Imaging) and Tobias Hodel (Professor of Digital Humanities), explain why this network is so important for the future.

Read the interview...

PeriVision wins EIT Wild Card

PeriVision, a MedTech spin-off from the ARTORG Center (AI in Medical Imaging lab) has won a prestigious European Wild Card in the 2021 challenge. The Bernese startup will be receiving an investment of EUR 1.5M along with specific coaching, which the founders will use to finalize their first product and prepare its EU and US market launch. PeriVision aims to reimagine glaucoma patient monitoring by making visual field testing much more patient-friendly and cost-efficient.

Learn more …