Detecting Medical Simulation Errors with Machine learning and Multimodal Data

D. Di Mitri

    Research output: Contribution to conferencePaperAcademic

    49 Downloads (Pure)


    In this doctoral consortium paper, we introduce the CPR Tutor, an intelligent tutoring system for cardiopulmonary resuscitation (CPR) training based on the analysis of multimodal data. Using a multi-sensor setup, the CPR Tutor tracks the CPR execution of the trainee and generates automatic adaptive feedback to improve the trainee's performance. This research work is part of a PhD project entitled "Multimodal Tutor: adaptive feedback from multimodal experience capturing'', a project which investigates how to use multimodal and multi-sensor data to generate personalised feedback for training psycho-motor skills at the workplace or during medical simulations. In the CPR Tutor, we use Microsoft Kinect and Myo to track trainee's body position and the ResusciAnne QCPR manikin to get correct CPR performance metrics. We then use a validated approach, the Multimodal Pipeline, for the collection, storage, processing, annotation of multimodal data. This paper describes the preliminary results obtained in the first design of the CPR Tutor.
    Original languageEnglish
    Number of pages6
    Publication statusPublished - May 2019
    Event17th Conference on Artificial Intelligence in Medicine - Poznan, Poland
    Duration: 26 Jun 201929 Jun 2019


    Conference17th Conference on Artificial Intelligence in Medicine
    Abbreviated titleAIME 2019
    Internet address


    Dive into the research topics of 'Detecting Medical Simulation Errors with Machine learning and Multimodal Data'. Together they form a unique fingerprint.

    Cite this