Digital Health Interventions

Designing Digital Behaviour Change Interventions

Increasing Engagment With mHealth Apps

Gamification

Gamification refers to the use of game elements in a non-game setting. In the context of mobile health (mHealth) applications, gamification might directly promote engaging in a target behavior (e.g. physical exercise, filling a health survey) or facilitate attitude change and learning (e.g. health education). Personalisation is an important step in gamification design which could help avoid demotivating users by inadequate game element selection. We conducted a preliminary study investigating personalisation of game element selection in mHealth survey context (See article) and later analysed gamification impact on cognitive effort realted to completing these mHealth surveys (See preprint).

Designing Digital Behaviour Change Interventions

Which wearable can support well-being monitoring?

We compare quality of physiological signal captured by medical and consumer grade werables (See news) .

We are sharing the data from the laboratory study CogWear and reporting preliminary results of the real-life study in the short article titled Decoding Emotional Valence from Wearables: Can Our Data Reveal Our True Feelings?

SATO (ideaS expAnded wiTh bciO) design workflow

We created a guide for the incomers in the field on how to design digital health interventions with case studies from the Cancer Better Life Experience (CAPABLE) project. We also provide a checklist of the activities that should be performed during intervention planning as well as app design templates which bundle together relevant behaviour change techniques. See our article.

How to Improve Digital Wellbeing Interventions?

We conducted a pilot intervention on a healthy population to evaluate the impact of wellbeing activities included in the CAPABLE patient application to understand factors impacting engagement with the intervention. See poster

Personalising mHealth Interventions

A system that integrates data from various sources with the properties of interventions to predict patient adherence and facilitate development of positive health habits. The system utilize counterfactual examples to inform the personalisation of behaviour change interventions (BCI) (Work in progress)

Finding the best time to intervene

As a part of Cancer Patients Better Life Experience Project we develop models for personalised coaching and decision support. Our research investigated different machine learning approached to finding the best time to intervene in order to maximize patient's engagement.

From personalized timely notification to healthy habit formation: A feasibility study of reinforcement learning approaches on synthetic data

We created a simulator that mimics patient responses to activity suggestions based on Fogg’s behaviour model and used supervised and reinforcement learning methods to learn the best time of sending the patient prompts.

See presentation

Personality and habit formation: Is there a link?

We conducted a survey that elicited potential Virtual Coach users’ perceptions about the appropriate context for notification, aspects driving their motivation, and their ability to perform a selected activity in different circumstances.

See presentation (by Szymon Wilk)

Is it a good time to survey you? Cognitive load classification from blood volume pulse

To understand the cognitive demand caused by the surveys and to find the adequate time to prompt patients to complete them we carried out a feasibility study. In this study we developed a machine learning cognitive load detector from blood volume pulse captured by a photoplethysmography sensor.

Catching patient’s attention at the right time to help them undergo behavioural change: Stress classification experiment from Blood Volume Pulse

Focusing on managing stress via deep breathing intervention, we hypothesise that the patients are more likely to perform suggested breathing exercises when they need calming down. To prompt them at the right time, we developed a machine learning stress detector based on blood volume pulse that can be measured via consumer-grade smartwatches.

See presentation

Page updated

Google Sites

Report abuse