Nutzung von KI-Technologien für Diagnostik und Gesprächsanalyse in der Psychotherapie: Potential und Herausforderungen

Zusammenfassung

Künstliche Intelligenz (KI) hat in den letzten Jahren große Fortschritte in der Medizin erzielt, insbesondere bei der Analyse medizinischer Bilddaten. Weniger im Fokus steht bislang ihr Potenzial als Analysetool für die Psychologie und Psychotherapie, obwohl aktuelle Entwicklungen zunehmend zeigen, dass KI-basierte Verfahren wertvolle Beiträge zur Diagnostik psychischer Störungen und zur Analyse psychotherapeutischer Gespräche leisten können. Ziel dieses Beitrags ist es, den internationalen Forschungsstand zu KI-basierten Werkzeugen und Techniken für Diagnostik und Gesprächsanalyse darzustellen, deren Potenziale und Grenzen kritisch zu diskutieren und zukünftige Anforderungen für eine verantwortungsvolle klinische Nutzung aufzuzeigen.

Abstract

In recent years, artificial intelligence (AI) has made great progress in medicine, particularly in the analysis of medical imaging data. Its potential as an analytical tool for psychology and psychotherapy, however, has received comparatively little attention, even though current developments increasingly demonstrate that AI-based methods can offer valuable contributions to the diagnosis of mental disorders and the analysis of psychotherapeutic conversations. The aim of this article is to present the international state of research on AI-based tools and techniques for diagnostics and conversation analysis, to discuss their potential and limitations critically, and to outline future requirements for their responsible clinical use.

Schlüsselwörter

Digitale Gesundheit - Künstliche Intelligenz - maschinelles Lernen - Psychotherapie

Keywords

Digital Health - Artificial Intelligence - Machine Learning - Psychotherapie

Publication History

Received: 02 September 2025

Accepted: 08 January 2026

Article published online:
27 February 2026

• Literatur

• 1 Lutz W, Schwartz B, Delgadillo J. Measurement-based and data-informed psychological therapy. Annu Rev Clin Psychol 2022; 18: 71-98
• 2 Lutz W, Schwartz B, Vehlen A. et al. Advances in personalization of psychological interventions. World Psychiatry 2025; 24: 343-345
• 3 Russell SJ, Norvig P. Artificial intelligence: a modern approach. Fourth Edition. Hoboken, NJ: Pearson; 2021
• 4 Han J, Zhang Z, Mascolo C. et al. Deep learning for mobile mental health: Challenges and recent advances. IEEE Signal Process Mag 2021; 38: 96-105
• 5 Mink F, Lutz W, Rafaeli E. et al. Validation and application of wrist-worn wearable physiological measures in psychotherapy. Cogn Ther Res 2025; 49: 902-919
• 6 Moshe I, Terhorst Y, Opoku Asare K. et al. Predicting symptoms of depression and anxiety using smartphone and wearable data. Front Psychiatry 2021; 12: 625247
• 7 Kross E, Verduyn P, Sheppes G. et al. Social media and well-being: Pitfalls, progress, and next steps. Trends Cogn Sci 2021; 25: 55-66
• 8 Eberhardt ST, Schaffrath J, Moggia D. et al. Decoding emotions: Exploring the validity of sentiment analysis in psychotherapy. Psychother Res 2025; 35: 174-189
• 9 Valstar M, Schuller B, Smith K. et al. AVEC 2013: The continuous audio/visual emotion and depression recognition challenge. In: Proceedings of the 3rd ACM international workshop on Audio/visual emotion challenge. Barcelona Spain: ACM; 2013: 3-10
• 10 Eyben F, Scherer KR, Schuller BW. et al. The Geneva minimalistic acoustic parameter set (GeMAPS) for voice research and affective computing. IEEE Trans Affect Comput 2016; 7: 190-202
• 11 Tellamekala MK, Sümer Ö, Schuller BW. et al. Are 3D face shapes expressive enough for recognising continuous emotions and action unit intensities?. 2022
• 12 Wagner J, Schiller D, Seiderer A. et al. Deep learning in paralinguistic recognition tasks: Are hand-crafted features still relevant?. In: Interspeech 2018. ISCA; 2018: 147-151
• 13 Tellamekala MK, Amiriparian S, Schuller BW. et al. COLD Fusion: Calibrated and ordinal latent distribution fusion for uncertainty-aware multimodal emotion recognition. IEEE Trans Pattern Anal Mach Intell 2024; 46: 805-822
• 14 Ekman P, Cordaro D. What is meant by calling emotions basic. Emot Rev 2011; 3: 364-370
• 15 Gebhard P, Schneeberger T, Baur T. et al. MARSSI: Model of appraisal, regulation, and social signal interpretation. 2018
• 16 Müller P, Heimerl A, Hossain SM. et al. Recognizing emotion regulation strategies from human behavior with large language models. 2024
• 17 Terhürne P, Schwartz B, Baur T. et al. Validation and application of the Non-Verbal Behavior Analyzer: An automated tool to assess non-verbal emotional expressions in psychotherapy. Front Psychiatry 2022; 13: 1026015
• 18 Terhorst Y, Sander LB, Ebert DD. et al. Optimizing the predictive power of depression screenings using machine learning. Digit Health 2023; 9 20552076231194939
• 19 Altmann U, Brümmel M, Meier J. et al. Movement synchrony and facial synchrony as diagnostic features of depression: A pilot study. J Nerv Ment Dis 2021; 209: 128-136
• 20 Joshi J, Dhall A, Goecke R. et al. Relative body parts movement for automatic depression analysis. In 2013 Humaine Association Conference on Affective Computing and Intelligent Interaction. Geneva, Switzerland: IEEE; 2013: 492-497
• 21 Hamilton M. A rating scale for depression. J Neurol Neurosurg Psychiatry 1960; 23: 56-62
• 22 Song S, Jaiswal S, Shen L. et al. Spectral representation of behaviour primitives for depression analysis. IEEE Trans Affect Comput 2022; 13: 829-844
• 23 Mundt JC, Vogel AP, Feltner DE. et al. Vocal acoustic biomarkers of depression severity and treatment response. Biol Psychiatry 2012; 72: 580-587
• 24 Stasak B, Epps J, Cummins N. et al. An investigation of emotional speech in depression classification. In: Interspeech 2016. ISCA; 2016: 485-489
• 25 Kumar P, Misra S, Shao Z. et al. Multimodal interpretable depression analysis using visual, physiological, audio and textual data. In 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). Tucson, AZ, USA: IEEE; 2025: 5305-5315
• 26 Paulick J, Rubel JA, Deisenhofer A-K. et al. Diagnostic features of nonverbal synchrony in psychotherapy: Comparing depression and anxiety. Cogn Ther Res 2018; 42: 539-551
• 27 Lutz W, Prinz JN, Schwartz B. et al. Patterns of early change in interpersonal problems and their relationship to nonverbal synchrony and multidimensional outcome. J Couns Psychol 2020; 67: 449-461
• 28 Ramseyer FT. Motion energy analysis (MEA): A primer on the assessment of motion from video. J Couns Psychol 2020; 67: 536-549
• 29 Baltrusaitis T, Robinson P, Morency L-P. OpenFace: An open source facial behavior analysis toolkit. In 2016 IEEE Winter Conference on Applications of Computer Vision (WACV). Lake Placid, NY, USA: IEEE; 2016: 1-10
• 30 Jennissen S, Huber J, Ditzen B. et al. Association between nonverbal synchrony, alliance, and outcome in psychotherapy: Systematic review and meta-analysis. Psychother Res 2025; 35: 1213-1228
• 31 Schwartz B, Rubel JA, Deisenhofer A-K. et al. Movement-based patient-therapist attunement in psychological therapy and its association with early change. Digit Health 2022; 8 205520762211290
• 32 Tal S, Ben-David Sela T, Dolev-Amit T. et al. Reactivity and stability in facial expressions as an indicator of therapeutic alliance strength. Psychother Res 2025; 35: 454-468
• 33 Schoenherr D, Strauss B, Stangier U. et al. The influence of vocal synchrony on outcome and attachment anxiety/avoidance in treatments of social anxiety disorder. Psychotherapy 2021; 58: 510-522
• 34 Tschacher W, Ribeiro E, Gonçalves A. et al. Electrodermal synchrony of patient and therapist as a predictor of alliance and outcome in psychotherapy. Front Psychol 2025; 16: 1545719
• 35 Uhl J, Altmann U, Rafaeli E. et al. Within- and between therapist variability in movement and physiological synchrony and its effects on symptom change. Psychophysiology 2025; 62: e14742
• 36 Aafjes-van Doorn K, Cicconet M, Cohn JF. et al. Predicting working alliance in psychotherapy: A multi-modal machine learning approach. Psychother Res 2025; 35: 256-270
• 37 Nasir M, Baucom B, Bryan C. et al. Modeling vocal entrainment in conversational speech using deep unsupervised learning. IEEE Trans Affect Comput 2022; 13: 1651-1663
• 38 Curto D, Clapés A, Selva J. et al. Dyadformer: A multi-modal transformer for long-range modeling of dyadic interactions. 2021
• 39 Lutz W, Schwartz B, Delgadillo J. Measurement-based and data-informed psychological therapy. Annu Rev Clin Psychol 2022; 18: 71-98
• 40 Baur T, Clausen S, Heimerl A. et al. NOVA: A Tool for Explanatory Multimodal Behavior Analysis and Its Application to Psychotherapy. In: Ro YM, Cheng W-H, Kim J, et al., Hrsg. MultiMedia modeling: 26th international conference, MMM 2020, Daejeon, South Korea, January 5-8, 2020 : proceedings. Cham: Springer; 2020: 577-588
• 41 Heimerl A, Weitz K, Baur T. et al. Unraveling ML models of emotion with NOVA: Multi-level explainable AI for non-experts. IEEE Trans Affect Comput 2022; 13: 1155-1167
• 42 Hallmen T, Schiller D, Vehlen A. et al. DISCOVER: A data-driven interactive system for comprehensive observation, visualization, and exploration of human behavior. Front Digit Health 2025; 7: 1638539
• 43 Lutz W, Schwartz B, Deisenhofer A-K. et al. Ein offenes transtheoretisches Therapie- und Trainingsmodell (4TM): Konzept für eine evidenzbasierte und personalisierte Psychotherapie-Praxis sowie Aus- und Weiterbildung. Psychother 2024; 69: 5-14
• 44 Eberhardt ST, Vehlen A, Schaffrath J. et al. Development and validation of large language model rating scales for automatically transcribed psychological therapy sessions. Sci Rep 2025; 15: 29541
• 45 Haltaufderheide J, Ranisch R. The ethics of ChatGPT in medicine and healthcare: A systematic review on Large Language Models (LLMs). Npj Digit Med 2024; 7: 183
• 46 Timmons AC, Duong JB, Simo Fiallo N. et al. A call to action on assessing and mitigating bias in artificial intelligence applications for mental health. Perspect Psychol Sci 2023; 18: 1062-1096
• 47 Wu X, Zhao H, Zhu Y. et al. Usable XAI: 10 strategies towards exploiting explainability in the LLM era. 2024
• 48 Stade EC, Stirman SW, Ungar LH. et al. Large language models could change the future of behavioral healthcare: A proposal for responsible development and evaluation. Npj Ment Health Res 2024; 3: 12
• 49 Lutz W, Bommer J, Strauß B. Aus- und Weiterbildung psychotherapeutischer Kompetenzen: Stand der Forschung und neue Entwicklungen. PPmP - Psychother·Psychosom·Med Psychol 2024; 74: 471-473
• 50 Bommer J, Schaffrath J, Deisenhofer A-K. et al. Die Umsetzung von klinischen Basisfertigkeiten durch angehende Psychotherapeut:innen im Verlauf ihrer psychotherapeutischen Aus- und Weiterbildung. PPmP - Psychother·Psychosom·Med Psychol 2025; 75: 197-203