Steffen T. Eberhardt

The Trier Treatment Navigator (TTN) is an adaptive feedback system for psychotherapy developed within ongoing research on measurement-based care and quality assurance. To accommodate different implementation environments, the TTN is available in two operational settings: TN-PRO for private outpatient practice and TN-HUB for research clinics and training centers. Both share the same core architecture but differ in their feature configurations and technical requirements. Key components include routine outcome monitoring, individualized treatment recommendations, early warning signals for patients at risk of unfavorable treatment response, and clinical support tools to guide treatment adaptation. The system is a non-commercial scientific project aimed at investigating the outcomes and processes of data-informed psychotherapy. Future work will focus on technological innovation and exploratory dissemination in private practice. This article aims to describe the conceptual framework, core components, and implementation settings of the TTN for clinicians, researchers, and training institutions interested in feedback-informed treatment and measurement-based care.

Rating scales have shaped psychological research, but are resource-intensive and can burden participants. Large Language Models (LLMs) offer a tool to assess latent constructs in text. This study introduces LLM rating scales, which use LLM responses instead of human ratings. We demonstrate this approach with an LLM rating scale measuring patient engagement in therapy transcripts. Automatically transcribed videos of 1,131 sessions from 155 patients were analyzed using DISCOVER, a software framework for local multimodal human behavior analysis. Llama 3.1 8B LLM rated 120 engagement items, averaging the top eight into a total score. Psychometric evaluation showed a normal distribution, strong reliability (ω = 0.953), and acceptable fit (CFI = 0.968, SRMR = 0.022), except RMSEA = 0.108. Validity was supported by significant correlations with engagement determinants (e.g., motivation, r = .413), processes (e.g., between-session efforts, r = .390), and outcomes (e.g., symptoms, r = − .304). Results remained robust across bootstrap resampling and cross-validation, accounting for nested data. The LLM rating scale exhibited strong psychometric properties, demonstrating the potential of the approach as an assessment tool. Importantly, this automated approach uses interpretable items, ensuring clear understanding of measured constructs, while supporting local implementation and protecting confidential data.

Traditional rating scales have shaped psychological research, but are resource-intensive and can burden participants. Large Language Models (LLMs) offer a tool to assess latent constructs in text. This study introduces LLM rating scales, a rating method that uses LLM responses instead of human ratings. Its application is demonstrated based on the development and validation of an LLM rating scale measuring patient engagement in transcripts of psychological therapies. Automatically transcribed videos of 1,131 sessions from 155 patients were analyzed using DISCOVER, a software framework for local multimodal human behavior analysis. The Llama 3.1 (8B) LLM rated 120 items on patient engagement, with the top eight items averaged to create a total engagement score ranging from 0 (low) to 100 (high). Psychometric properties were evaluated using the original sample, bootstrap resampling, and test folds. The LLM rating scale demonstrated normal distribution, strong reliability (ω = .953) and acceptable fit (CFI = .968, SRMR = .022), except RMSEA = .108. Validity was supported by significant correlations with engagement determinants (e.g., motivation, r = .413), processes (e.g., between-session efforts, r = .390), and outcomes (e.g., symptoms, r = −.304). Results remained robust across bootstrap and cross-validation analyses accounting for the hierarchical data structure. The LLM rating scale exhibited strong psychometric properties for measuring patient engagement, demonstrating the potential of the LLM rating scale approach as a psychological assessment tool. Importantly, this automated approach uses interpretable items, ensuring clear understanding of measured constructs, while supporting local implementation and protecting confidential data.

Background: In this paper, we present the conceptual background and clinical implications of a research-based transtheoretical treatment and training model (4TM). Method: The model implements findings from psychotherapy outcome, process, and feedback research into a clinical and training framework that is open to future research. Results: The framework is based on interventions targeting patient processes on a behavioral, cognitive, emotional, motivational, interpersonal, and systemic/socio-cultural level. The 4TM also includes a data-based decision support and feedback system called the Trier Treatment Navigator (TTN). Conclusion: We discuss important problems associated with clinical orientations solely based on one school of thought. We then contrast these concerns with a clinical and training framework that embraces ongoing research, serving as a guiding structure for process-based transtheoretical interventions. Such research-based psychological therapy can take both traditional and novel clinical developments as well as findings from psychotherapy research into account and be adaptively disseminated to a variety of patient populations.

Given the importance of emotions in psychotherapy, valid measures are essential for research and practice. As emotions are expressed at different levels, multimodal measurements are needed for a nuanced assessment. Natural Language Processing (NLP) could augment the measurement of emotions. The study explores the validity of sentiment analysis in psychotherapy transcripts. We used a transformer-based NLP algorithm to analyze sentiments in 85 transcripts from 35 patients. Construct and criterion validity were evaluated using self- and therapist reports and process and outcome measures via correlational, multitrait-multimethod, and multilevel analyses. The results provide indications in support of the sentiments' validity. For example, sentiments were significantly related to self- and therapist reports of emotions in the same session. Sentiments correlated significantly with in-session processes (e.g., coping experiences), and an increase in positive sentiments throughout therapy predicted better outcomes after treatment termination. Sentiment analysis could serve as a valid approach to assessing the emotional tone of psychotherapy sessions and may contribute to the multimodal measurement of emotions. Future research could combine sentiment analysis with automatic emotion recognition in facial expressions and vocal cues via the Nonverbal Behavior Analyzer (NOVA). Limitations (e.g., exploratory study with numerous tests) and opportunities are discussed.

Zusammenfassung: Hintergrund: In diesem Beitrag werden die konzeptionellen Grundlagen sowie die klinischen Implikationen eines forschungsbasiertentranstheoretischenTherapie- undTrainingsmodells (4TM) vorgestellt; dieses kann das Fundament für eine zukünftige evidenzbasierte und personalisierte Psychotherapiepraxis sowie Aus- und Weiterbildung in der Psychotherapie darstellen.Ziel der Arbeit: Ableitung und Darstellung eines wissenschaftlich basierten, offenen transtheoretischen Rahmenmodells für die Psychotherapiepraxis sowie Aus- und Weiterbildung in der Psychotherapie.Methode: Das Modell versucht, Erkenntnisse aus der Psychotherapieforschung zu differenziellen Behandlungsergebnissen, der Feedback-Forschung, der Forschung zu Therapeutenunterschieden sowie der Forschung zu Veränderungsprozessen und modernen technischen Entwicklungen in ein offenes konzeptionelles Rahmenmodell für die klinische Praxis und Ausbildung zusammenzuführen.Ergebnisse: Das Modell basiert auf Interventionen, die bei Patient:innen Veränderungsprozesse auf Verhaltens-, kognitiver, emotionaler, motivationsbezogener, zwischenmenschlicher und systemischer/soziokultureller Ebene auslösen. Das 4TM umfasst außerdem ein datenbasiertes Entscheidungs- und Rückmeldesystem namens Trier Therapie Navigator (TTN).Diskussion: Es werden wichtige Probleme einer rein schulenbasierten Ausrichtung der Psychotherapie in Deutschland diskutiert und diese dem offenen Rahmen eines forschungs-, rückmeldungs- und prozessorientierten Konzepts als Leitfaden für transtheoretische Interventionen gegenübergestellt. Dieses Konzept kann eine Orientierung für eine wissenschaftsbasierte Psychotherapie, unter Berücksichtigung traditioneller sowie neuer klinischer Entwicklungen und Erkenntnisse aus der Psychotherapieforschung, bieten. Es kann sowohl an unterschiedliche Patientenpopulationen als auch kultursensitiv angepasst werden.