The transmissions in the interpersonal communication in psychotherapy is very complex as both parties are simultaneous senders and recipients of non-verbal and verbal messages. To learn more about these transmissions, it is important in psychotherapy research to link the non-verbal communication to the verbal content and to explore the communication patterns that arise over time. Non-verbal communication is multimodal and includes, for example, body/head position and movements, facial expressions, eye movements or emotional prosody. These non-verbal signals also form part of the complex interactional synchronization patterns that include reflections of emotional expression. First results will be presented of an interdisciplinary project, in which the fields of psychology and data science are brought together. The aim of the study is to analyze all sessions of video-recorded psychodynamic psychotherapy with the help of AI-based methods such as machine learning and time series analyses to investigate what is transmitted non-verbally and which nonverbal interactive behavioral patterns develop between patient and therapist.