Digital Biomarkers: Hack Your Metabolic Code! Fall 2025, University of St.Gallen
Next-generation Wearable Sensors for Biopsychosocial Care in Mental Health (BMJ Digital Health and AI 2025) Digital phenotyping of diet, physical activity, and glycemia in adults (npj Digital Medicine, 2024), Predicting postprandial glucose excursions to personalize dietary interventions for type-2 diabetes management (Scientific Reports 2025) Drunk Driving Detection in a Vehicle Using Driver Monitoring Cameras and Real-Time Vehicle Data (ACM CHI 2025)
What are recent developments in digital biomarkers? A digital biomarker is quantifiable and objective behavioral or physiological data collected through digital devices. Digital biomarkers explain and predict health-related outcomes and can be classified depending on their purpose (e.g., risk, diagnostic, monitoring, prognostic, predictive, or response biomarkers). They can be gathered continuously and non-invasively, providing valuable insights into an individual’s health status. Digital biomarkers can revolutionize healthcare by enabling remote monitoring, personalized, just-in-time adaptive interventions (e.g., digital therapeutics), and early detection of diseases.
To this end, the question arises of how to develop evidence-based digital biomarkers that allow medical doctors and other caregivers to scale and tailor long-term treatments to individuals in need at sustainable costs. This lecture aims to help students and upcoming healthcare executives better understand digital biomarkers’ relevance, development, and assessment at the intersection of health economics, information systems research, computer science, and medicine.
After the course, students will be able to…
- understand the relevance of digital biomarkers for the prevention, management, and treatment of disease
- understand several classes of digital biomarkers
- know how to design and evaluate digital biomarkers
- know digital health technologies used for digital biomarker development
- assess data of a digital biomarker study in the area of metabolic health
- propose digital biomarkers for healthy longevity (e.g., biological age)
- discuss the advantages and disadvantages of digital biomarkers
Course Content
- On the relevance of digital biomarkers for the prevention, management, and treatment of disease
- Classification of digital biomarkers
- Study designs for digital biomarkers
- Assessment of digital biomarkers
- Advantages and disadvantages of digital biomarkers
Course structure
This block course is structured in three parts, with on-site sessions and complementary online exercises. In the first part, an overview of digital biomarkers is provided. In the second part, a controlled laboratory experiment is conducted with the course participants to develop a digital biomarker in metabolic health. For this purpose, physiological data will be collected (e.g., using wearables). Students will learn about their metabolic health with the help of generative AI tools, incl. large language models. In the third part, students in groups will assess digital biomarker data and design a digital biomarker for healthy longevity, for example, determining biological age. The groups will finally present and discuss their results with fellow students. Moreover, coaching sessions are offered to support the students in preparing their presentations. Complementary learning material and multiple-choice questions are provided online.
Course literature
- Adler, D. A., Wang, F., Mohr, D. C., Estrin, D., Livesey, C., & Choudhury, T. (2022). A call for open data to develop mental health digital biomarkers. BJPsych Open, 8(2), e58, Article e58. 10.1192/bjo.2022.28
- Brasier, N., Mahato, K., Princip, M., Gonçalves, V.M., Mutyiamana, C., Bourke, S., Goldhahn, J., Barata, F., von Känel, R., Schaffarczyk, D., Kowatsch, T., Wang, J. (forthcoming) Next-generation Wearable Sensors for Biopsychosocial Care in Mental Health – a Narrative review, BMJ Digital Health and AI.
- Brügger, V., Kowatsch, T., Jovanova, M. (forthcoming) Predicting postprandial glucose excursions to personalize dietary interventions for type-2 diabetes management, Scientific Reports
- Deuber, R., Langer, P., Kraus, M., Pfäffli, M., Bantle, M., Barata, F., von Wangenheim, F., Fleisch, E., Weinmann, W., Wortmann, F. (2025) Moving Beyond the Simulator: Interaction-Based Drunk Driving Detection in a Real Vehicle Using Driver Monitoring Cameras and Real-Time Vehicle Data, In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI ’25). Association for Computing Machinery, New York, NY, USA, Article 84, 1–25. 10.1145/3706598.3714007 ***Best Paper Award***
- Coravos, A., Khozin, S., & Mandl, K. D. (2019). Developing and adopting safe and effective digital biomarkers to improve patient outcomes. npj Digital Medicine, 2(1). 10.1038/s41746-019-0090-4
- Dunn, J., Kidzinski, L., Runge, R., Witt, D., Hicks, J. L., Schüssler-Fiorenza Rose, S. M., Li, X., Bahmani, A., Delp, S. L., Hastie, T., & Snyder, M. P. (2021). Wearable sensors enable personalized predictions of clinical laboratory measurements. Nature Medicine, 27(6), 1105-1112. 10.1038/s41591-021-01339-0
- Manta, C., Patrick-Lake, B., & Goldsack, J. C. (2020). Digital Measures That Matter to Patients: A Framework to Guide the Selection and Development of Digital Measures of Health. Digital Biomarkers, 4(3), 69-77. 10.1159/000509725
- Naegelin, M., Weibel, R. P., Kerr, J. I., Schinazi, V. R., La Marca, R., von Wangenheim, F., Hoelscher, C., & Ferrario, A. (2023). An interpretable machine learning approach to multimodal stress detection in a simulated office environment. J Biomed Inform, 139, 104299. 10.1016/j.jbi.2023.104299
- Shim, J., Fleisch, E., & Barata, F. (2023). Wearable-based accelerometer activity profile as digital biomarker of inflammation, biological age, and mortality using hierarchical clustering analysis in NHANES 2011–2014. Scientific Reports, 13(1), 9326. 10.1038/s41598-023-36062-y
- Sim, I. (2019). Mobile Devices and Health. N Engl J Med, 381(10), 956-968. 10.1056/NEJMra1806949
- Tams, S., Hill, K., de Guinea, A. O., Thatcher, J., & Grover, V. (2014). NeuroIS – Alternative or Complement to Existing Methods? Illustrating the Holistic Effects of Neuroscience and Self-Reported Data in the Context of Technostress Research. Journal of the Association for Information Systems, 15(10), Article 1. 10.17705/1jais.00374
Summary
Digital Biomarkers: Hack Your Metabolic Code! (11,801), University of St.Gallen, Fall 2025, 2 ECTS
Lecturer
