Automated audio analysis of carotid artery blood flow sounds

While arteriosclerosis is asymptomatic until complications occur, the secondary conditions it causes (stroke or heart attack) are the most common cause of premature death in industrialized countries. According to the WHO, the estimated prevalence of arteriosclerosis in middle-aged men is about 20 percent. But since examinations are only performed in case of apparent diseases causing vascular damage, the actual frequency of occurrence cannot be determined.

The challenge

The carotid flow profile says a lot about the condition of blood vessels. It may be possible to use this information to assess the risk of a stroke, and to measure and check the condition of existing or emerging arteriosclerosis. Aside from prediction and diagnosis, therapy support is possible as well. The efficiency of treatment with medications can be monitored, and with regular measurement, an active warning can even be issued in the future in order to ensure rapid intervention and avoid an emergency situation, on a patient-specific basis and with the help of artificial intelligence. Overall the emphasis on preventive healthcare has to increase considerably in the future in order to promote the health of society and individuals.


Our contribution

The aforementioned approaches are being incorporated into the development of the "BodyTune" mobile auscultation measurement device. This is based on a sound recorder used to record a personalized audio signal of carotid sounds (flow, turbulence, intensity) that is pre-processed locally using a mobile system (smartphone). A data analytics engine will create an individual patient carotid profile with the help of AI-based self-learning algorithms. Irregularities/regularities are to be identified with the help of regular control measurements. The large volume of audio signals and patient-specific data is intended to technically support corresponding analyses and predictions. Aside from the hardware, development will also include the artificial intelligence algorithms and a supporting infrastructure. Expensive clinical emergency treatment can be reduced with relatively low effort and the quality of life for affected individuals can be improved.   



The project objective is to use the automated analysis of body sounds, using carotid stenosis as an example, to improve the early diagnosis of illness and care for at-risk patients on the one hand and, on the other hand, to individualize therapy and improve patient compliance and inclusion.

Fraunhofer ISST is dedicating itself to data processing, the data infrastructure, and the selection or implementation of suitable algorithms within the project.



  • IDTM GmbH, Castrop-Rauxel
  • Fraunhofer ISST, Dortmund


  • hsg Bochum
  • Essen University Hospital



  • Subsidized by the state of North Rhine-Westphalia and the European Union (EU EFRE) under project number LS-2-2-038a.
  • Term: 2.5 years
  • Project start: November 2019