The innovative power of the German capital in the area of AI is not only noticeable in the high-profile areas of business intelligence and process management, but is also demonstrated by the excellent work of the AI companies which deal intensively with intelligent health and represent about 10 per cent of the Berlin AI ecosystem.
AI systems from Berlin are used in a variety of ways: they help in the diagnosis and data analysis of specific disease patterns, but are also used in operation planning and in supporting the internal processes of hospitals. Apps for intelligent data recording and analysis in the field of prevention are being developed in the context of fitness and health. Chatbots, i.e. systems with which people can communicate in natural language, also accompany patients during the healing process.
A number of start-ups in Berlin are pushing the boundaries of traditional healthcare with innovative solutions which could also break new ground on the international stage - always at the interface between business and research.
More than 250 million mammographies were performed worldwide in 2018, illustrating the enormous effort and repetitive work to which radiologists are exposed every day. The Berlin AI Venture Studio Merantix has developed with its Vara Healthcare project an MDD-certified deep learning technology for the radiological detection of breast cancer, which is aimed at facilitating the work of doctors. With the software solution, negative results of mammographic examinations can be excluded with a high degree of certainty and effectiveness and radiologists alerted about conspicuous results and actual findings. Nocturne GmbH, on the other hand, deals with the precise acquisition and measurement of landmarks of the retina, the optic nerve head and the macula as well as their analysis using AI-based software. The clinical application, developed by the research team of the NeuroCure Excellence Cluster of Charité Berlin, should be ready for the market by 2020 and provide neurologists with a reliable tool for diagnosing retinal diseases. The innovative PeakProfiling solution also focuses on the well-being of patients and the support of doctors in their daily work, albeit in a different field: depression and ADHD are two widespread diseases in Germany, but they are not always detected early enough or even at all. The Berlin-based voice and sound analysis tool, which can record emotional and physical states using AI technology, is intended to help better identify psychological and neurological diseases and determine therapies more efficiently.
One Berlin start-up which symbolises the rapid rise of health apps like no other is Ada Health. The team of doctors, scientists and engineers was founded in 2012 and its AI-supported, free app helps people to better understand their state of health and gives advice on possible treatment. Ada has now become the number one medical app in over 130 countries and is designed to help identify early warning signs of illness, reduce the number of unnecessary visits to the doctor and thus lessen the effective cost of healthcare.
While Ada focuses on the entire health spectrum, Lindera concentrates on the oldest people in our society. Falls among senior citizens cost health insurance companies as much as the treatment of diabetes per case per year, often lead to death, and are avoidable if the risk factors are known. With its mobility test, the 3D image analyses gait movement with a simple smartphone camera and artificial intelligence. In addition, the young Berlin start-up digitises the analysis of risk factors and the planning of measures to prevent falls in old age, systematize care documentation, reduce costs and relieve the burden on relatives and caregivers.
Everyday life for the hard of hearing and deaf persons is problematic, especially in public areas, due to high noise levels, but the founders Peter Udo Diehl and Elias Sprengel have set themselves the goal of sustainably improving their quality of life. Since 2017, the Audatic team has been working on using deep learning technology to modify audio signals so that annoying background noises can be filtered out using a smartphone in conjunction with conventional hearing aids. In addition to the desired cooperations with hearing aid and cochlear implant manufacturers, the young company hopes to gain access to the lucrative smartphone and headphone market with its AI solution.
Visual Article: © Uhura Digital for Berlin Partner for Economics and Technology GmbH
Universities and research institutions
Academic research in the field of AI health in the German capital is diverse and innovative, with Charité Berlin's projects leading the way. Currently, more than 20 working groups are working there to improve treatment and care in the health sector with the help of AI in cooperation with other research institutes such as the Technical University of Berlin (TU Berlin), the Max Dellbrück Center, the Humboldt University (HU Berlin), the Free University (FU Berlin), the HTW Berlin, the DFKI and several Fraunhofer institutes.
BigMedilytics (Big Data for Medical Analytics) is the largest EU-funded initiative to transform the region's healthcare system through Big Data, rapidly increasing productivity due to cost savings, improved patient treatment outcomes and better access to preventive healthcare. In a total of 12 pilot projects, the three most important topic areas from the point of view of prevention, diagnosis, treatment and care - public health and management of chronic diseases, oncology as well as the industrialization of the healthcare system – are being dealt with.
In the current clinical practice of medical imaging, diagnostic decisions are often made on the basis of qualitative image markers, leading to uncertainties in diagnosis and long training periods. The DFG-funded research group BIOQIC is therefore researching and developing biophysical-based quantitative medical imaging for use in clinical pilot studies. Further development of medical imaging would also benefit cancer research, as enormous data sets are generated today which analyse and characterise tumours in unprecedented molecular detail. In order to integrate and interpret this complex wealth of data, new computational methods are becoming a central aspect of cancer research. These methods will also be needed in clinical oncology, as more and more patients are receiving therapies based on integrated molecular profiles. CompCancer, a DFG-funded research group at Charité, has therefore focused on the development of novel computational methods and solutions in cancer research.
Feverish research is also being carried out into innovative solutions for stroke, which is the second most frequent cause of death worldwide with a total of 260,000 sick people in Germany every year. The PREDICTioN2020 project, headed by Dr. Dietmar Frey, has with the use of artificial intelligence developed an innovative simulation model which enables predictive diagnostics in stroke treatment using digital medical imaging. ai4medicine, another project of Charité Berlin, is seamlessly integrated and enables individualised therapy recommendations for stroke patients using modern AI technology and the HealthAdvisor app.
Established companies and institutions
In addition to pioneering research and development of health solutions in start-ups, universities and research institutions, national and international companies are also involved in the use of artificial intelligence in the area of AI health.
The SAHRA (Smart Analysis Health Research Access) project of the AOK NordOst was originally one of 13 lighthouse projects of the "Smart Data - Innovations from Data" technology programme of the Federal Ministry of Economics and Technology (BMWi). SAHRA was conceived as a data analysis and cooperation platform in healthcare research and now makes it possible to securely and legally combine billing and treatment data with study and registration data and to make it accessible to researchers and other users.
The Hungarian company turbine was founded to enable researchers to more effectively plan and develop life-saving therapies before carrying out time-consuming and costly biological experiments. As part of Bayer's G4A Accelerator 2016 and in close cooperation with the pharmaceutical giant an AI software solution was developed in Berlin which predicts how a cancer will respond to treatment while helping to develop new medicines.
Exciting times for artificially intelligent health - Made in Berlin.