AI and Information Integration Aid Therapy Decisions

The physician would not have to gather information from separate sources, saving valuable time, and would also be informed of specific guidelines issued by medical specialist societies, which will be integrated automatically into the system, providing valuable support. Ultimately, the algorithms will link the case at hand with a comprehensive database of similar cases.

In addition, the system will help determine the best possible course of therapy by enabling physicians with different specialties to access one central system to view all relevant information, including X-ray and magnetic resonance imaging (MRI) images, tissue analyses, genetic parameters, lab values, and relevant data from the patient's electronic medical record (EMR). The algorithms will then search for similar patterns that could deliver insight into the case at hand. For example, did surgery outperform radiation therapy in similar cases? Does an ongoing course of chemotherapy bring the anticipated success, or should it be ceased?

“When it comes to detecting relevant patterns and correlations in complex data volumes, computers are now better than humans," said professor of medical imaging Horst Hahn, PhD, director of Fraunhofer MEVIS. “This does not mean, however, that computers will make therapy decisions. They will simply support physicians with database-driven knowledge.”

“The applications developed in collaboration with Fraunhofer MEVIS will support our customers to increase diagnostic quality and to make better decisions for their patients,” said Walter Maerzendorfer, president of diagnostic imaging at Siemens Healthineers. “Thanks to this research alliance and the merits of intelligent data integration, we take the next step towards evidence based medicine.”

Most of the information in clinics and medical practices is stored digitally, but until now image data, findings, lab values, digital patient records, and surgery reports have been handled separately. A current trend aimed at data integration into one unified software framework will eventually enable faster handling of medical information and is laying the foundation for more efficient interaction between different specialties and more precise and personalized clinical decisions.