In order to achieve breakthroughs, medical research requires enormous amounts of data. More is more is the motto. High computer capacities and lots of data can help to develop new diagnoses and treatment methods. The LOOP Zurich plays a pioneering role here, as became clear at the annual event.
The healthcare system collects a lot of data every day: Blood values or results from tissue samples, ultrasound or MRI scans. They are used for diagnosis and are then archived. But what if computer systems could learn independently, with the help of artificial intelligence, from the data collected from patients and even develop new diagnoses and treatments? The evaluation of large amounts of data in medicine is one of the dominant topics in health research. Where do we stand today - and what are the prospects? These were the questions that took center stage at The LOOP Zurich's annual event. THE LOOP Zurich is a translational research center with a focus on precision medicine. The event took place last week at the UZH.
Since 2020, the scientists at The LOOP Zurich have been researching precision and data-driven medicine. It is cutting-edge research that is being carried out here with the participation of UZH, ETH and the four university hospitals - also thanks to the support of foundations. "Research costs money - but gives a lot back to society," emphasized Beatrice Beck Schimmer, Director of University Medicine Zurich, in her opening speech.
An important project of The LOOP Zurich is the development of the Biomedical Informatics Platform (BMIP), which provides data for research projects in accordance with the FAIR principle. "FAIR" stands for Findable, Accessible, Interoperable and Reusable. By 2025, The LOOP Zurich aims to establish the BMIP for the exchange of research and health data. The Zurich University Medical Center commissioned the project and the government of the Canton of Zurich provided the necessary funding.
Scientists who wish to access collected health data for their studies are supported with their applications, such as with the data management concept or data protection and ethical requirements. It would take just a few weeks to go from research proposal to data analysis, said Gunnar Rätsch, ETH Professor of Biomedical Informatics.
Christian Wolfrum, ETH Vice President for Research, emphasized the added value that will arise for patients from the biomedical informatics platform. In future, other hospitals and other data from the field of public health, such as health tracking data, will also have to be integrated, says Wolfrum.
Markus Rudin, Professor Emeritus of Molecular Imaging and Functional Pharmacology, emphasized the clinical translation that characterizes The LOOP Zurich projects. "The Loop insists that research results go back to the patients," he said, underlining what he had said with the help of two projects, which he presented in short video sequences. "INTeRCePT " - researches blood cancer and lymphoma in children and adults. "StimuLOOP", on the other hand, aims to treat walking disorders in Parkinson's or stroke patients and thus improve their quality of life. Thanks to their precision medicine approach, both projects enable the targeted, successful and gentle treatment of patients.
Computer systems can already independently analyze health data, learn from it and even derive treatment recommendations. Fabian Theis, Professor of Mathematical Modeling of Biological Systems at the Technical University of Munich and Director of the Institute of Computational Biology at Helmholtz Zentrum München, who was invited to the annual event as a guest speaker, reported on the opportunities this means for patients and how artificial intelligence is used in practice.
Artificial intelligence describes the ability of computer programs to learn. There are two ways to achieve this learning, said Theis. The first way describes supervised learning: researchers show the computer a large number of similar things and, depending on the question, teach it what is right or wrong, healthy or sick. The idea behind it: If the computer receives enough input, its algorithm can eventually make the distinction itself. In this way, it can take a lot of work off the doctors' hands. But there is a second way to use artificial intelligence: In this case, the computer receives as little assistance as possible; it should be able to learn without supervision. Mathematician Fabian Theis uses this method for single cell analysis, for example: The computer receives data on individual cells and their metabolism - and has to find patterns in it. This makes it possible to discover new connections.
Jens Selige, Managing Director of The LOOP Zurich, presented two winning projects, which are chosen at the annual event. The young researchers had applied for the tender and prevailed against other projects. This is linked to generous financial support for their platform projects.
Sebastiano Caprara, presented the first winning project "Biomedical Informatics Imaging Platform" (BMI2). BMI2 consists of a consortium of different hospitals. Caprara works at Balgrist University Hospital and currently heads the Digital Medicine Unit there. The BMI2 project collects image data, for example from MRIs, and analyzes it using so-called segmentation, a branch of digital image processing and computer vision. "Analyzing the results leads to more precise diagnoses, for example in the case of damage to individual vertebrae," says Caprara.
The second winning project was presented by Marco Bühler. He works as a pathologist at the University Hospital Zurich. Under the name "POLAR", the researchers in the consortium want to collect data from patients with lymphoma. This includes anamnesis data, data from imaging, protein analysis and pathology as well as genetic data. All this data, which is currently still recorded in different databases, is to flow into a single database. "We want to compile the world's largest data set on lymphoma with the aim of bringing knowledge back to patients in the clinic and contributing to a cure," said Bühler.
The program was rounded off with a panel of experts who discussed the importance of data for the future of medical research from various perspectives. Emanuela Keller, UZH Professor of Neurointensive Care Medicine and Head Physician of the Neurointensive Care Unit at the USZ, described how artificial intelligence (AI) in intensive care medicine can provide decision support for the treatment of patients, but also how potential conflicts can arise if the AI's recommendations do not match the doctors' empirical knowledge. Gunnar Rätsch, Fabian Theis and Michael Krauthammer, Professor of Medical Informatics at UZH, explained how data could be used for research purposes using modern processing methods and which data protection aspects need to be taken into account. UZH lawyer and physician Kerstin Vokinger spoke about the data protection challenges we will face in the future, especially in Switzerland with its federalist legal system - as there are still several cantonal data protection laws in Switzerland.
The LOOP Zurich is a translational research center focusing on precision medicine in Zurich. It combines basic biomedical research and bioinformatics from the two universities, ETH Zurich and the University of Zurich, with clinical research from four university hospitals. The aim is to use translational research to rapidly develop new treatment methods for the benefit of patients.