Artificial intelligence (AI) that can learn from expert medical knowledge will play an important role in the healthcare system and enable fundamental improvements regarding the accuracy and efficiency of image-based medical diagnosis and treatment.

CoCoAI aims at the empirically based development of information and communication technologies that support the cooperation between AI and humans in the best possible way. Future applications of AI in healthcare will not only improve the diagnostic quality, but also influence many ethical, legal, social, and economic aspects of modern medicine. The project is working toward overcoming the ethical and societal challenges arising from the integration of AI into existing structures of action. It develops methods that positively support the new understanding of the roles of the three main actors – patients, doctors, and AI engineers.

Methodological foundations for trilateral cooperation and communication are created through explainable AI procedures, modern human-computer interfaces, as well as ethical studies and workshops to define responsible research and innovation with AI. The project also develops guidelines for the design of future AI and image-based diagnostic systems from the interdisciplinary perspectives of machine learning, medical image analysis, user-centred design of human AI interfaces, visualization, and ethics of technology. These are intended to promote the acceptance of AI-based diagnoses, make their potentials available, and reduce risks. Together with the SME ThinkSono, a case study is planned for the practical implementation of an ultrasound-based diagnostic system for the detection of deep vein thrombosis, the most frequent cause of preventable deaths in hospitals.

On behalf of Universität zu Lübeck, ITAS will directly cooperate in CoCoAI with the University’s Institute for Electrical Engineering in Medicine (IME). ITAS will provide advice on issues related to Responsible Innovation (RI) and, in this context, participate in several workshops organized during the project. This includes, for instance, providing and introducing an explanation of what RI entails to all the stakeholders involved. In addition, it will advise on the development of an effective RI approach for a deep learning-based point-of-care solution for diagnosing deep vein thrombosis.

Link to the project’s official website: https://cocoai.uni-luebeck.de