Artificial intelligence for the early detection of pulmonary embolism

TU computer scientists lead new joint project EVA-KI with 1.7 million euros in funding

2020/11/20 by

The earlier a pulmonary embolism is detected, the better the chances of recovery. In the future, artificial intelligence (AI) will help physicians to identify embolisms correctly and quickly on X-rays. With this goal, the joint project EVA-KI – Establishment of a platform for the development and validation of AI solutions in clinical routine – is now starting.

In order to make exact diagnoses, the AI algorithms train continually with structured data from clinical operations and validate their results themselves. In addition, the project will investigate to what extent experienced and inexperienced physicians can be influenced in their diagnosis by the results. The data should only improve the basis for a diagnosis – it cannot and should not replace the experience of the physicians.

The consortium of scientists from Darmstadt, Essen, Göttingen and Munich is led by Dr. Anirban Mukhopadhyay and Prof. Dr. Dieter Fellner from the Department of Computer Science at the TU Darmstadt. The German Federal Ministry of Health is funding the project with 1.7 million euros as part of the digital innovations for improving patient-centered care in the healthcare system.