TKTimo K. Koch

Timo K. Koch

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Timo K. Koch has a total of 43 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Examining reliance patterns on AI advice in medical imaging: a mixed-methods, randomised, crossover experiment

    by Susanne Gaube, Ekaterina Jussupow, Eesha Kokje, Timo K Koch, Jowaria Khan, Elizabeth Bondi-Kelly, Andreas Schicho, Felipe C Kitamura, Timur Ezer, Juergen Mottok, et al.

  • Open Access

    Brief speech samples reveal emotional states in daily life

    by Timo K Koch, Gabriella M Harari, Samuel D Gosling, Zachariah Marrero, Ramona Schoedel, Markus Bühner, Clemens Stachl

    Does our speech—“what” we say and “how” we say it—reveal how we subjectively feel in daily life? Speech and emotion are often thought to be linked, but most supporting evidence comes from controlled laboratory settings and focuses on expressed, enacted, or externally labeled emotions, leaving open the question of whether naturalistic speech reflects subjective emotional experience in daily life. To address this question, we extracted both modern foundation-model embeddings and established speech-analysis variables from brief, prompted smartphone recordings, including Linguistic Inquiry and Word Count features and prosodic descriptors, and used them as inputs to supervised machine learning models predicting concurrent self-reported emotional states (934 participants; 12,285 observations). Cross-validated models evaluated on unseen participants captured information about self-reported emotional states (contentment: median Spearman ρ = 0.37; sadness: ρ = 0.24; arousal: ρ = 0.35), with spoken content represented by foundation-model text embeddings carrying the strongest emotional signal. Interpretability analyses provided further insights into the linguistic characteristics of everyday emotional language. These findings provide large-scale evidence that brief speech samples contain information about subjective emotional states in daily life.

  • Open Access

    Contextualizing Smartphone-Typed Language With User Input Intention

    by Florian Bemmann, Timo K. Koch, Maximilian Bergmann, Clemens Stachl, Daniel Buschek, Ramona Schoedel, Sven Mayer

  • Open Access

    From Embeddings to Explainability: A Tutorial on Large-Language-Model-Based Text Analysis for Behavioral Scientists

    by Rudolf Debelak, Timo K. Koch, Matthias Aßenmacher, Clemens Stachl

    Large language models (LLMs) are transforming research in psychology and the behavioral sciences by enabling advanced text analysis at scale. Their applications range from the analysis of social media posts to infer psychological traits to the automated scoring of open-ended survey responses. However, despite their potential, many behavioral scientists struggle to integrate LLMs into their research because of the complexity of text modeling. In this tutorial, we aim to provide an accessible introduction to LLM-based text analysis, focusing on the Transformer architecture. We guide researchers through the process of preparing text data, using pretrained Transformer models to generate text embeddings, fine-tuning models for specific tasks such as text classification, and applying interpretability methods, such as Shapley additive explanations and local interpretable model-agnostic explanations, to explain model predictions. By making these powerful techniques more approachable, we hope to empower behavioral scientists to leverage LLMs in their research, unlocking new opportunities for analyzing and interpreting textual data.


  • Open Access

    A Tutorial on Tailored Simulation-Based Sample-Size Planning for Experimental Designs With Generalized Linear Mixed Models

    by Florian Pargent, Timo K. Koch, Anne-Kathrin Kleine, Eva Lermer, Susanne Gaube

    When planning experimental research, determining an appropriate sample size and using suitable statistical models are crucial for robust and informative results. The recent replication crisis underlines the need for more rigorous statistical methodology and adequately powered designs. Generalized linear mixed models (GLMMs) offer a flexible statistical framework to analyze experimental data with complex (e.g., dependent and hierarchical) data structures. However, available methods and software for a priori sample-size planning for GLMMs are often limited to specific designs. Tailored data-simulation approaches offer a more flexible alternative. Based on a practical case study in which we focus on a binomial GLMM with two random intercepts and discrete predictor variables, the current tutorial equips researchers with a step-by-step guide and corresponding code for conducting tailored a priori sample-size planning with GLMMs. We not only focus on power analysis but also explain how to use the precision of parameter estimates to determine appropriate sample sizes. We conclude with an outlook on the increasing importance of simulation-based sample-size planning.


  • Open Access

    Insights on the Current State and Future Outlook of AI in Health Care: Expert Interview Study

    by Pia Hummelsberger, Timo K Koch, Sabrina Rauh, Julia Dorn, Eva Lermer, Martina Raue, Matthias F C Hudecek, Andreas Schicho, Errol Colak, Marzyeh Ghassemi, et al.

    Background: Artificial intelligence (AI) is often promoted as a potential solution for many challenges health care systems face worldwide. However, its implementation in clinical practice lags behind its technological development. Objective: This study aims to gain insights into the current state and prospects of AI technology from the stakeholders most directly involved in its adoption in the health care sector whose perspectives have received limited attention in research to date. Methods: For this purpose, the perspectives of AI researchers and health care IT professionals in North America and Western Europe were collected and compared for profession-specific and regional differences. In this preregistered, mixed methods, cross-sectional study, 23 experts were interviewed using a semistructured guide. Data from the interviews were analyzed using deductive and inductive qualitative methods for the thematic analysis along with topic modeling to identify latent topics. Results: Through our thematic analysis, four major categories emerged: (1) the current state of AI systems in health care, (2) the criteria and requirements for implementing AI systems in health care, (3) the challenges in implementing AI systems in health care, and (4) the prospects of the technology. Experts discussed the capabilities and limitations of current AI systems in health care in addition to their prevalence and regional differences. Several criteria and requirements deemed necessary for the successful implementation of AI systems were identified, including the technology’s performance and security, smooth system integration and human-AI interaction, costs, stakeholder involvement, and employee training. However, regulatory, logistical, and technical issues were identified as the most critical barriers to an effective technology implementation process. In the future, our experts predicted both various threats and many opportunities related to AI technology in the health care sector. Conclusions: Our work provides new insights into the current state, criteria, challenges, and outlook for implementing AI technology in health care from the perspective of AI researchers and IT professionals in North America and Western Europe. For the full potential of AI-enabled technologies to be exploited and for them to contribute to solving current health care challenges, critical implementation criteria must be met, and all groups involved in the process must work together.


  • Open Access

    Insights on the Current State and Future Outlook of AI in Health Care: Expert Interview Study (Preprint)

    by Pia Hummelsberger, Timo K Koch, Sabrina Rauh, Julia Dorn, Eva Lermer, Martina Raue, Matthias F C Hudecek, Andreas Schicho, Errol Colak, Marzyeh Ghassemi, et al.

    BACKGROUND Artificial intelligence (AI) is often promoted as a potential solution for many challenges health care systems face worldwide. However, its implementation in clinical practice lags behind its technological development. OBJECTIVE This study aims to gain insights into the current state and prospects of AI technology from the stakeholders most directly involved in its adoption in the health care sector whose perspectives have received limited attention in research to date. METHODS For this purpose, the perspectives of AI researchers and health care IT professionals in North America and Western Europe were collected and compared for profession-specific and regional differences. In this preregistered, mixed methods, cross-sectional study, 23 experts were interviewed using a semistructured guide. Data from the interviews were analyzed using deductive and inductive qualitative methods for the thematic analysis along with topic modeling to identify latent topics. RESULTS Through our thematic analysis, four major categories emerged: (1) the current state of AI systems in health care, (2) the criteria and requirements for implementing AI systems in health care, (3) the challenges in implementing AI systems in health care, and (4) the prospects of the technology. Experts discussed the capabilities and limitations of current AI systems in health care in addition to their prevalence and regional differences. Several criteria and requirements deemed necessary for the successful implementation of AI systems were identified, including the technology’s performance and security, smooth system integration and human-AI interaction, costs, stakeholder involvement, and employee training. However, regulatory, logistical, and technical issues were identified as the most critical barriers to an effective technology implementation process. In the future, our experts predicted both various threats and many opportunities related to AI technology in the health care sector. CONCLUSIONS Our work provides new insights into the current state, criteria, challenges, and outlook for implementing AI technology in health care from the perspective of AI researchers and IT professionals in North America and Western Europe. For the full potential of AI-enabled technologies to be exploited and for them to contribute to solving current health care challenges, critical implementation criteria must be met, and all groups involved in the process must work together.

  • Top Cited Papers
    Open Access

    Effects of fact‐checking warning labels and social endorsement cues on climate change fake news credibility and engagement on social media

    by Timo K. Koch, Lena Frischlich, Eva Lermer

    Online fake news can have noxious consequences. Social media platforms are experimenting with different interventions to curb fake news' spread, often employing them simultaneously. However, research investigating the interaction of these interventions is limited. Here, we use the heuristic‐systematic model of information processing (HSM) as a theoretical framework to jointly test two interventions against fake news that are implemented at scale by social media platforms: (1) adding warning labels from fact checkers to initiate systematic processing and (2) removing social endorsement cues (e.g., engagement counts) to reduce the influence of this heuristic cue. Moreover, we accounted for dispositions previously found to affect a person's response to fake news through motivated reasoning or cognitive style. An online experiment in Germany (N = 571) confirmed that warning labels reduced the perceived credibility of a fake news post exaggerating the consequences of climate change. Warning labels also lowered the (self‐reported) likelihood to amplify fake news. Removing social endorsement cues did not have an effect. In line with research on motivated reasoning, left‐leaning individuals perceived the climate fake news to be more credible and reported a higher likelihood to amplify it. Supporting research on cognitive style, participants with lower educational levels and a less analytic thinking style also reported a higher likelihood of amplification. Elaboration likelihood was associated only with age, involvement, and political leaning, but not affected by warning labels. Our findings contribute to the mounting evidence for the effectiveness of warning labels while questioning their relevance for systematic processing.


  • Open Access

    Who should do as AI say? Only non-task expert physicians benefit from correct explainable AI advice

    by Susanne Gaube, Harini Suresh, Martina Raue, Eva Lermer, Timo Koch, Matthias Hudecek, Alun D. Ackery, Samir C. Grover, Joseph F. Coughlin, Dieter Frey, et al.

    Artificial intelligence (AI)-generated clinical advice is becoming more prevalent in healthcare. However, the impact of AI-generated advice on physicians’ decision-making is underexplored. In this study, physicians received X-rays with correct diagnostic advice and were asked to make a diagnosis, rate the advice’s quality, and judge their own confidence. We manipulated whether the advice came with or without a visual annotation on the X-rays and whether it was labeled as coming from an AI or a human radiologist. Overall, receiving annotated advice from an AI resulted in the highest diagnostic accuracy. Physicians rated the quality of AI advice higher than human advice. Neither manipulation had strong effects on participants’ confidence. Importantly, the results varied among task experts and non-task experts, with only the latter considerably benefiting from correct explainable AI advice. These findings raise important considerations for the deployment of diagnostic advice in healthcare.