Precision Health Psychology – Olga Perski's research group

The Precision Health Psychology Research Group studies how health behaviours unfold within individuals over time, and how digital interventions can deliver the right type of support, when and where each person needs it the most.

Precision Health Psychology Research Group

Olga Perski's research group works at the intersection of health psychology, addiction science and digital health. Our work integrates intensive longitudinal measurement, theory development, idiographic science, computational modelling and digital health technologies. The aim is to understand how health behaviours unfold in daily life, and to use this knowledge to develop digital interventions that tailor support to each individual's needs in the moment.

What we study

Health psychology. We study the interaction between mental and physical health, specifically understanding and predicting health behaviours and developing and evaluating behaviour change interventions.

Addictive behaviours. We focus on tobacco smoking, alcohol, cannabis and gambling. We want to understand why people use drugs or gamble, why it is so difficult to quit, and how we can develop and provide access to effective and engaging psychological support.

Digital interventions. We develop and evaluate digital behaviour change interventions (e.g., smartphone apps, websites and wearables), including their integration with human support (hybrid human-digital interventions), with a focus on acceptability, engagement and effectiveness.

Within-person processes. We seek to understand within-person processes which unfold over time (an idiographic perspective) and develop technology-mediated just-in-time adaptive interventions (JITAIs) which can provide the right type of support to individuals, when and where they most need it.

Methodology. We use mixed methods, spanning qualitative and quantitative approaches, including causal inference, theory development and refinement (specifically formal and computational modelling), complexity science, artificial intelligence and machine learning, optimisation trials (in particular single case experimental designs) and participatory methods. Open science is central to our research. 

Interdisciplinary collaboration. We collaborate closely with computer scientists, programmers, control systems engineers, human-computer interaction researchers and clinical and health psychologists.

Our research projects

Ongoing projects 

  • Time Matters – Uncovering dynamic mechanisms and optimising the intervention timing across the addictions
  • EMASENS – Developing a just-in-time adaptive intervention to prevent smoking lapses

Completed projects 

  • COMPLAPSE – Improving the precision of behaviour change theories: a dynamic computational model of lapse risk in smokers attempting to stop

For more information, see the Research projects tab.

Publications

All publications from group members

Research projects

Time Matters – Uncovering dynamic mechanisms and optimising the intervention timing across the addictions

Time Matters aims to address one of the greatest challenges in addiction: relapse prevention. The project conceptualises addictive behaviours as dynamical systems that evolve non-linearly over time and within individuals. Through collecting and modelling high-resolution data from smartphones and smartwatches in daily life, Time Matters will develop an adaptive algorithm capable of delivering the right type of support to each person, when and where they most need it. In doing so, the project will provide a new framework for understanding and preventing relapse across the addictions.

Funding: European Research Council (ERC-2025-StG) under Horizon Europe, Grant No. 101219875 (PI: Olga Perski).

Links: https://www.precisionhealthpsych.com/timematters

EMASENS – Developing a just-in-time adaptive intervention to prevent smoking lapses

The aim of EMASENS is to develop a smartphone-based stop smoking tool that provides personalised support to smokers in real time, when they most need it (a just-in-time adaptive intervention, JITAI). To provide this kind of support, we first need to understand when to send support and what type of support to send.

Stage 1: Predicting smoking lapses. We trained and tested group-level, individual-level and hybrid supervised machine learning algorithms in two studies: (1) a study using unprompted data entered by users of a popular smoking cessation app, and (2) a study using data from brief smartphone surveys together with passively collected smartwatch data. Individual-level and hybrid algorithms performed better than group-level algorithms, particularly when sensor data were included. The best-performing algorithm was selected as the basis for the intervention.

Stage 2: Developing and evaluating the intervention. Stage 2 forms part of Corinna Leppin's PhD project at University College London and is nearing completion. It focuses on developing the intervention messages using theory and behaviour change tools combined with extensive user testing and evaluating the intervention in a feasibility trial.

Publications from the EMASENS project: 

  • Perski, O., Li, K., Pontikos, N., Simons, D., Goldstein, S. P., Naughton, F., & Brown, J. (2023). Classification of lapses in smokers attempting to stop: a supervised machine learning approach using data from a popular smoking cessation smartphone app. Nicotine and Tobacco Research, 25(7), 1330-1339.
  • Perski, O., Kale, D., Leppin, C., Okpako, T., Simons, D., Goldstein, S. P., ... & Brown, J. (2024). Supervised machine learning to predict smoking lapses from Ecological Momentary Assessments and sensor data: Implications for just-in-time adaptive intervention development. PLOS Digital Health, 3(8), e0000594.
  • Leppin, C., Okpako, T., Garnett, C., Perski, O., & Brown, J. (2025). Exploring perspectives on digital smoking cessation just-in-time adaptive interventions: A focus group study with adult smokers and smoking cessation professionals. PLOS Digital Health, 4(5), e0000705.
  • Leppin, C., Brown, J., Garnett, C., Kale, D., Okpako, T., Simons, D., & Perski, O. (2026). Optimising supervised machine learning algorithms predicting cigarette cravings and lapses for a smoking cessation just-in-time adaptive intervention (JITAI). Plos one, 21(5), e0349028.

Funding: Cancer Research UK (PI: Jamie Brown; Co-I: Olga Perski)

Links: https://www.precisionhealthpsych.com/emasens

COMPLAPSE – Improving the precision of behaviour change theories: a dynamic computational model of lapse risk in smokers attempting to stop

Cigarette smoking remains the leading preventable cause of premature morbidity and mortality in Europe and beyond. Gold-standard treatment for smoking cessation includes pharmacotherapy and behavioural support, but smoking lapses – which are influenced by momentary fluctuations in cigarette availability, stress and cravings – are a key source of treatment failure. COMPLAPSE developed and validated a formal, dynamical systems model of smoking lapse and relapse risk. The project combined scientific theory, patient perspectives and clinical know-how, and was interdisciplinary, drawing on know-how from behavioural science and from systems science and dynamical systems modelling. The resulting model can be used to simulate relapse risk and to inform personalised, evidence-based digital smoking cessation strategies.

Publications from the COMPLAPSE project

  • Perski, O., Allen, J., Kim, M., Pavel, M., Hankonen, N., & Hekler, E. (2026). Using Formal and Computational Modelling to Develop an Initial Within-Person System Dynamics Model of Relapse in Smoking Cessation: A Participatory, Iterative, Multi-Method Approach. Peer Community Journal. https://osf.io/preprints/osf/wx8s5
  • de Ron, J., Robinaugh, D., Borsboom, D., & Perski, O. (2025). Toward a Psychologist's Guide to Computational Modeling: An Interdisciplinary Scoping Review of Methods for Mechanistic Model Construction. https://osf.io/preprints/psyarxiv/y7w8j
  • Perski, O., & Allen, J. (2025). Formal, dynamical systems modelling to advance health psychology theories: Interdisciplinary working where psychology meets mathematics. European Health Psychologist, 23(5).
  • Perski, O., Copeland, A., Allen, J., Pavel, M., Rivera, D. E., Hekler, E., ... & Chevance, G. (2025). The iterative development and refinement of health psychology theories through formal, dynamical systems modelling: a scoping review and initial expert-derived ‘best practice’ recommendations. Health Psychology Review, 19(1), 1-44.

Funding: European Commission under the Horizon Europe Framework Programme, Grant No. 101065293 (PI: Olga Perski).

Links: https://www.precisionhealthpsych.com/complapse

Activities

Define & Conquer

Podcast: Define & Conquer


Scientific progress in health psychology is held back by pervasive issues, from how psychological constructs are defined and measured to how theories and frameworks are formalised. In the podcast series Define & Conquer, Olga Perski and Christoph Bamberg raise these challenges and discuss possible solutions with experts from the European Health Psychology Society (EHPS) Special Interest Group in Conceptualisation, Formalisation and Measurement and beyond.


Listen