Better4All Personalized Intervention Pilot Study

Overview

The BETTER4U project (Preventing obesity through Biologically and bEhaviorally Tailored inTERventions for you) is funded by the European Union (EU) and involves an international consortium consisting of 28 partners across Europe, Israel, and Australia. The project started in November 2023 and will run until October 2027. The main aim of BETTER4U is to improve weight management through a tailor-made intervention, the "BETTER4ALL personalized intervention", using modern monitoring tools and artificial intelligence (AI), including machine learning (ML) practices. In the context of the BETTER4U project, the present Pilot Study aims to a) evaluate the usability, feasibility and acceptability of the BETTER4U mobile application ("BETTER4U App") and Intervention Platform that will be used to monitor and collect data from participants in the BETTER4ALL personalized intervention (randomized controlled trial; RCT) and b) collect data to evaluate and improve the BETTER4U causal AI models for the prevention of weight gain, before deploying them at large scale, as well as test and identify the optimal ways of delivering the AI-based interventions to the participants. The study will be conducted in seven sites in Cyprus, France, Greece, Poland, Portugal, Spain, and Sweden. The BETTER4All Pilot Study will be a longitudinal, correlational, observational study, including a total of n=490 participants, equally distributed among the seven sites (i.e. n=70 per site). Specifically, n=60 (± 3-5) "general population" participants (henceforth: "end-users" of the wearables and the BETTER4U App) and n=10 (± 3-5) healthcare or other types of providers (henceforth: potential "implementers" of the BETTER4U intervention) will constitute each site's sample. The study will involve the following two components: a) the administration of the wearables (smartwatches) to the "end-users" and their registration to and training on the BETTER4U App, to be used for a total duration of three weeks (21 days). During this period, their lifestyle behaviours (i.e. "BETTER4U Core Behavioural Indicators - BCBIs", such as eating occasions, physical activity, sedentary time, sleep etc.) and "living environment indicators - LEIs"; (e.g. access to parks in your area, distance from your home to your work place etc.) will be recorded daily, either in an automated way via the wearables or self-reported by the end-users through the App; and b) the registration to and training on the BETTER4U Intervention Platform of the "implementers" for a total duration of one week (7 days), during which they will be asked to test the platform's functionalities using synthetic data. The implementers will also be provided with the wearables and the App (similarly to the end-users) for one week only to allow collection of additional data that will help verify the accuracy of the algorithms in the gathered data from the wearables/monitoring tools regarding BCBIs and LEIs. Overall, the outcomes and the findings of the Pilot Study will be used to further refine, optimize, and adjust the tools for the BETTER4ALL RCT, according to the feedback received by both end-users' and implementers' perspectives.

Detailed description

The BETTER4All Pilot Study is a multicenter, longitudinal, observational study designed to assess the usability, feasibility, and acceptability of the BETTER4U App and BETTER4U Intervention Platform, both of which integrate real-time behavioral monitoring and artificial intelligence (AI)-driven decision support tools. Conducted in seven European countries (Cyprus, France, Greece, Poland, Portugal, Spain, and Sweden), the study includes approximately 490 adult participants split into two groups: (a) "end-users" from the general population, who will use wearable devices and the mobile App for 21 days, and (b) "implementers," healthcare professionals who will test the intervention platform for 7 days using synthetic and self-recorded data.

The BETTER4U system employs Bluetooth Low Energy (BLE) smartwatches for passive data collection, including accelerometer signals, heart rate variability, sleep structure, and geolocation data. Data from the wearables and smartphone sensors are processed using AI and machine learning algorithms to derive behavioral indicators such as physical activity, eating, sleep patterns (termed BETTER4U Core Behavioral Indicators - BCBIs), and contextual environmental factors (Living Environment Indicators - LEIs). These indicators are calculated both locally and on secure servers via structured data pipelines, ensuring privacy and GDPR compliance.

Data collection comprises three sources: (1) passively collected wearable/App data, (2) online questionnaires via RedCap (e.g., IPAQ, GAD-2, PHQ-2, EQ-5D-5L, PSQI, Mini-EAT), and (3) "ground truth" data logged by implementers to validate algorithmic outputs. Engagement metrics, such as app usage duration and feature interaction frequency, are also automatically recorded. Feedback on usability and feasibility is collected via validated tools, including the System Usability Scale (SUS), MAUQ, AIM, IAM, and FIM.

The primary technical aim is to verify and refine the causal AI models developed in earlier project phases (WP5), ensuring the system is optimized for personalized intervention delivery in the upcoming BETTER4ALL randomized controlled trial (WP7).

Interventions

• Behavioral BETTER4U Mobile App and Wearable Use (End-User Group)
  Participants from the general population ("end-users") will use a smartwatch and the BETTER4U mobile app for 21 days. The app passively collects data (physical activity, sleep, eating behaviors, environment), while participants may self-report certain behaviors. The goal is to assess the usability, feasibility, and acceptability of the tools and to collect real-world behavioral data for refining AI models.
• Behavioral BETTER4U Intervention Platform Testing (Implementer Group)
  Healthcare professionals and other potential implementers will test the BETTER4U Intervention Platform and mobile app for 7 days. They will assess system usability, complete synthetic case simulations, and provide daily feedback via Google Forms. They also wear the smartwatch and use the app for data validation purposes. The goal is to evaluate platform usability and collect ground-truth data for validating AI algorithm outputs.

Primary outcome measures

• System Usability Scale (SUS) Score - End-Users [Time frame: Day 21 (end of participation period for end-users)]
• System Usability Scale (SUS) Score - Implementers [Time frame: Day 7 (end of participation period for implementers]
• Acceptability of Intervention Measure (AIM) Score - End-Users [Time frame: Day 21]
• AIM Score - Implementers [Time frame: Day 7]
• Feasibility of Intervention Measure (FIM) Score - End-Users [Time frame: Day 21]
• FIM Score - Implementers [Time frame: Day 7]
• Intervention Appropriateness Measure (IAM) Score - End-Users [Time frame: Day 21]
• IAM Score - Implementers [Time frame: Day 7]

Secondary outcome measures (4)

• mHealth App Usability Questionnaire (MAUQ) Score - Implementers [Time frame: Day 7]
• App Usage - Number of Logins (End-Users) [Time frame: Day 21]
• App Usage - Time Spent per Module (End-Users) [Time frame: Day 21]
• Thematic Analysis of Open Feedback (Qualitative) [Time frame: Day 21 (end-users) / Day 7 (implementers)]

Eligibility criteria

Inclusion criteria

• Age: Participants aged 18-65 years to represent the adult general population.
• Body Mass Index (BMI):

• Overweight or obesity group: BMI ≥ 25 kg/m².
• Normal weight group: BMI 18.5-24.9 kg/m².
• Technology Use:

• Willingness and ability to use wearable devices and an Android mobile application for the duration of the study.
• Owning a smartphone device with the Android operating system.
• Eating utensil technique: dominant hand gestures that correspond to handling of food via a fork or a spoon.
• Language Proficiency: Ability to read and understand the language in which the mobile app and study materials are provided.
• Consent: Willing to provide informed consent to participate in the study.
• Residency: Must be a resident of one of the seven participating countries.
• Availability: Able to participate for the full three-week duration of the study and comply with the study protocol.

Exclusion criteria

• Health Conditions: Pregnant or breastfeeding women, as they might have different lifestyle behaviours or health needs.
• Physical Limitations: Any physical or mental condition that would prevent the participant from using the wearable device or mobile application as intended.
• Eating utensil technique: eating food with chopsticks on a daily or regular basis.
• Technical Incompatibility: Individuals who do not own a compatible smartphone or are unable to use the provided wearable devices for technical reasons.

Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.

Healthy volunteers: Yes

Study design

Allocation

Non-randomized

Model

Parallel assignment

Masking

Open label

Primary purpose

Prevention

Study locations

Cyprus · 1 center

• University of Cyprus (Ucy) — Nicosia

France · 1 center

• Universite Lyon 1 Claude Bernard (Ucbl) — Villeurbanne

Greece · 1 center

• Harokopio University — Athens

Poland · 1 center

• Uniwersytet Swps (Swps) — Wroclaw

Portugal · 1 center

• Centro de Estudos E Investigacao Em Dinamicas Sociais E Saude Associacao Sem Fins Lucrativ — Lisbon

Spain · 1 center

• Universidad de Navarra (Unav) — Pamplona

Sweden · 1 center

• Karolinska Institutet — Huddinge

Identifiers

NCT: NCT07120802 · B4U101080117

Primary sources (government registries)

• ClinicalTrials.gov (US NIH)

View this study on ClinicalTrials.gov ↗