LTLauren Thompson

Lauren Thompson

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Lauren Thompson has a total of 31 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Conversational AI to augment an in-person weight management programme: qualitative usability study of a functional prototype deployed in a deprived population (Preprint)

    by Samuel Downes, Lauren Thompson, Max Western, Kenton O'HAra, Amberly Brigden

    BACKGROUND Excess weight is disproportionately prevalent among individuals living in areas of deprivation, driven by a complex interplay of social, environmental and structural factors. Community-based, in-person weight-management programmes can be particularly effective for these populations. They are also typically static programmes designed for a cohort, limiting the level of personalisation to individual needs. In addition, they are constrained to in-session support, restricting the level of behaviour change support available within the user’s real-world lived context. Formative work indicated that a conversational AI-based tool could address these gaps as an adjunct to community-based support. However, evidence for conversational AI to augment such face-to-face programmes for deprived populations is currently scarce. OBJECTIVE This study aimed to explore a WhatsApp-based large language model (LLM) AI health coach as an adjunct to a community weight-management programme in a deprived UK setting, focusing on acceptability, longitudinal real-world usability, perceived utility and feature value, and implications for intervention optimisation. METHODS We conducted a qualitative usability study involving real-world longitudinal deployment of the AI health coach within Fit Robins, a 12-week community weight-management programme delivered in an area of deprivation in Bristol, UK. The intervention comprised a WhatsApp-based conversational AI coach powered by GPT-4o, incorporating sub-agents providing support across four domains: wellbeing, general health question-answering, diet and nutrition, and weight and waist monitoring. The system supported both AI-initiated prompts and user-initiated interactions. Participants (n=8) were recruited from Fit Robins and completed post-intervention semi-structured interviews. Data were analysed using framework analysis informed by the Technology Acceptance Model. Findings were translated into a structured table of changes using MoSCoW prioritisation. RESULTS Onboarding was described as straightforward, largely because WhatsApp was familiar and accessible, including for participants with lower technological confidence. Most participants derived value from the AI coach, but the type of value varied. Some used it primarily for functional support, including reminders, recipes, health information, and self-monitoring. Others engaged relationally, describing the coach as a source of encouragement, emotional support, and non-judgemental disclosure. Relational engagement appeared particularly meaningful for participants with greater psychosocial needs or weaker support networks. However, repetitive AI-initiated messages, limited contextual understanding, and insufficient variation in coaching style reduced engagement for some users. Participants recommended greater message variation, customisable reminders, improved onboarding for personalisation, proactive progress feedback, integration of activity or wearable data, and enhanced dietary self-monitoring. CONCLUSIONS A WhatsApp-based LLM AI health coach was broadly acceptable and usable as an adjunct to a community weight-management programme in this deprived UK setting, but user needs and preferences were heterogeneous. The distinction between relational and functional use emerged as a key design consideration. Hybrid human-AI interventions may be most useful when they extend, rather than replace, trusted in-person support, while enabling personalisation of timing, tone, and support type. Future optimisation should prioritise customisation, baseline personalisation, reduced repetitive prompting, stronger programme integration, and testing of additional features identified in the table of changes before formal effectiveness evaluation. CLINICALTRIAL N/A

  • Open Access

    Designing a Digital Augment to an In-Person Community Weight Management Programme in an Area of Deprivation: Qualitative and Participatory Research Study Using the Person-Based Approach (Preprint)

    by Samuel Downes, Emmanuel Mbuthia, Joanna Mclaughlin, Lauren Thompson, Max Western, Daisy England, Chris Stenner, Kenton O'HAra, Amberly Brigden

    BACKGROUND Community-based, face-to-face programmes may be particularly valuable for underserved populations because they provide trusted relational support, peer learning, and accessible local delivery. However, these programmes often provide limited support between sessions or after completion. Hybrid interventions, which combine in-person support with digital components may help extend support while preserving the relational mechanisms of in-person delivery. However, there is limited published evidence exploring hybrid interventions in more deprived communities. OBJECTIVE This study undertook formative research to inform the design of a digital augmentation to an existing community-based weight management intervention delivered in an area of deprivation in South Bristol, United Kingdom. Specifically, this work aimed to (1) undertake multi-method primary qualitative research into participants’ experience of the existing intervention, (2) develop programme theory of the existing intervention, (3) co-develop opportunities to improve the intervention, and (4) develop specific design objectives and intervention features for the digital augment (guiding principles). METHODS We conducted a multi-method qualitative and participatory research study guided by the Person-Based Approach. The study was conducted alongside the Robins Foundation, who deliver group-based weight management programmes in areas of deprivation. Programme attendees participated in longitudinal ecological data collection using a conversational WhatsApp-based research tool, post-programme semi-structured interviews, and participatory research workshops. Delivery team members participated in workshops to develop programme theory and identify improvement opportunities. Interview and longitudinal chat-log data were analysed using framework analysis, providing empirical evidence to refine programme theory. Finally, qualitative findings were synthesised alongside workshop outputs, to derive guiding principles for digital augmentation. RESULTS Nine programme attendees participated in interviews, longitudinal WhatsApp-based data collection, and participatory research workshops. Delivery team members participated in planning workshops. Participants described the in-person programme as working primarily through trusted and credible delivery of health information, an inclusive group environment, peer learning, and support to develop personally relevant behaviour-change strategies. Social opportunity was the most prominent facilitator. Persistent challenges included missed-session learning gaps, limited recall of content, limited between-session support, variable support in home environments, and concern about sustaining change after programme completion. Synthesising these findings with findings from participatory workshops, we derived guiding principles proposing that a digital component should support familiarity and engagement before the programme begins, reinforce learning and personalised behaviour-change support between sessions, extend support after programme completion, and provide appropriate monitoring that benefits both participants and the delivery team. CONCLUSIONS This study provides formative evidence, synthesised into guiding principles for the design of a digital augment to a community-based weight management programme for underserved populations. Findings suggest that this digital augmentation should extend, rather than replace, the key relational and behavioural mechanisms of the face-to-face programme. Future work should focus on prototyping and evaluating the feasibility, acceptability, and usability of the proposed hybrid intervention.


  • Open Access

    A Health-Related Digital Ecological Momentary Assessment in Children (Aged 5– 11 Years): Systematic Review

    by Sydney Charitos, Lauren Thompson, Amberly Brigden, Jon Bird

    Background: Digital ecological momentary assessment (EMA) collects data on experiences as they occur in daily life, capturing dynamic, context-sensitive experiences often missed by retrospective reporting. While EMA shows promise for pediatric health research, preadolescents have distinct socioemotional and cognitive characteristics likely to affect engagement. Existing reviews have not focused on the acceptability and feasibility of EMA protocols for this age group. Objective: This review aimed to examine digital EMA protocols used with children aged 5‐11 years across health domains, focusing on protocol characteristics, acceptability, and feasibility. We address 3 research questions (RQs)—RQ1: What are the characteristics of these protocols? RQ2: What is the feasibility and acceptability of these protocols? RQ3: What are the characteristics of high and low response rate protocols? Methods: We searched 10 databases (CINAHL, Embase, ACM Digital Library, IEEE Xplore, Cochrane Library, PsycINFO, Web of Science, PubMed, Scopus, and MEDLINE) for peer-reviewed studies published up to October 2025. Eligible studies used EMA with children aged 5‐11 years to collect health data via digital devices. Two researchers independently screened studies (SC and LT); one (SC) conducted quality assessment and data extraction. Findings were narratively synthesized. Results: We identified 17 protocols across 37 studies. Most targeted nonclinical populations, used handheld devices, spanned 3‐28 days, and applied interval-contingent prompting (RQ1). Response rates were available or calculable for 15 of 17 protocols, ranging from 48% to 92% (RQ2). Six protocols reported response rates of ≥80%. However, key data required for pooling (eg, raw counts for planned vs completed prompts) were missing or selectively reported. This contributed to 13 of 17 protocols being rated at critical risk of bias (ROBINS-I, v2). As a result, the strength of evidence was limited by poor reporting and high risk of bias. Facilitators included uncomplicated, engaging technology, reminders, and caregiver involvement. Barriers included device burden, restricted device access, difficulty with accurate reporting, stigma, limited device awareness, and insufficient caregiver support. High-response protocols (≥80%) often involved older children or clinical groups, ≥3-week duration, fixed schedules (≥20 items per prompt, 3 or 4 times per day), timing customization, and incentives (RQ3). Conclusions: This review provides the first systematic synthesis on preadolescents, offering insight into EMA protocol design beyond prior work treating children as a single group. By examining 17 EMA protocols, the review identifies gaps in developmental appropriateness and reporting quality, highlighting where the evidence may differ from adolescent and adult EMA research. The results suggest that digital EMA for preadolescents requires greater focus on child-centered design to increase acceptability and adherence, alongside improved reporting standards, so protocols can be meaningfully compared. With these advances, EMA could be more effectively integrated into pediatric health monitoring, tailored to the needs of different age groups.


  • Open Access

    A Digital Intervention for Capturing Real-Time Health Data for Epilepsy Seizure Forecasting: Protocol for the ATMOSPHERE Study

    by Lauren Thompson, Emily Nielsen, Emily E V Quilter, Amelia Slay, Marceli Wac, Matthew Wragg, Samuel Downes, Phil Tittensor, Leandro Junges, Liz Stuart, et al.

    Background: Epilepsy is a chronic neurological disorder marked by recurrent and apparently unpredictable seizures and associated with premature death, injury, and diminished quality of life. The unpredictability of seizures is a major concern for people with epilepsy. Thus, developing tools for seizure prediction is a research priority. The Artificial Intelligence to Optimise Seizure Prediction to Empower People With Epilepsy (ATMOSPHERE) project focuses on the development and evaluation of seizure forecasting technology involving mobile technology and machine learning to provide personalized seizure forecasting (risk of seizure in the near future). The project is informed by complex intervention frameworks, which recommend phases of development, feasibility study, clinical evaluation, and implementation. Objective: Objective 1 aims to conduct a feasibility study to test and refine the trial methods for a future clinical trial. Objective 2 aims to test and refine the data collection technology, considering usability and technical performance. Objective 3 aims to collect longitudinal data on seizures and their precipitants to refine seizure forecasting. Methods: This study is a single-arm, mixed methods feasibility study, testing a prototype of the data collection technology, with phase 2 testing a minimum viable product. In total, 60 participants will be recruited via specialist National Health Service epilepsy clinics. Inclusion criteria are adults with epilepsy, experiencing seizures twice per month, able to consent, and engage with technology. Clinicians will screen and gain consent to contact, with researchers obtaining full consent. Participants will be invited to complete the following study procedures: (1) onboarding, (2) use the data collection technology (phase 1 or 2) in their lived context for up to 6 months, (3) complete patient-reported outcome measures and capture clinical-reported outcome measures at baseline and 3 months, and (4) complete a qualitative interview exploring their views of the data collection technology. A study flow diagram will report recruitment rates (outcome 1), diversity of the recruited sample (outcome 2), barriers and facilitators to recruitment (outcome 3), retention rates (outcome 4), and barriers and facilitators to retention (outcome 5). To assess the data collection technology, quantitative technology use data and qualitative interview data will be analyzed to assess usability (outcome 6) and technical performance (outcome 7) of the data collection technology. These outcomes will inform iterative minimum viable product development and testing cycles with stakeholders. Results: Recruitment is planned to begin in quarter 1 of 2026, with data collection expected to be completed by quarter 2 of 2027. Data analysis will take place during quarter 3, and the results will be published in quarter 4. Conclusions: This project aims to improve clinical outcomes for people with epilepsy through seizure forecasting technology. To evaluate clinical outcomes, robust trial methodology is critical. This feasibility study will optimize methods for a future full-scale clinical trial as well as refine the seizure forecasting intervention. International Registered Report Identifier (IRRID): PRR1-10.2196/85993

  • Open Access

    A Digital Intervention for Capturing Real-Time Health Data for Epilepsy Seizure Forecasting: Protocol for the ATMOSPHERE Study (Preprint)

    by Lauren Thompson, Emily Nielsen, Emily E V Quilter, Amelia Slay, Marceli Wac, Matthew Wragg, Samuel Downes, Phil Tittensor, Leandro Junges, Liz Stuart, et al.

    BACKGROUND Epilepsy is a chronic neurological disorder marked by recurrent and apparently unpredictable seizures and associated with premature death, injury, and diminished quality of life. The unpredictability of seizures is a major concern for people with epilepsy. Thus, developing tools for seizure prediction is a research priority. The Artificial Intelligence to Optimise Seizure Prediction to Empower People With Epilepsy (ATMOSPHERE) project focuses on the development and evaluation of seizure forecasting technology involving mobile technology and machine learning to provide personalized seizure forecasting (risk of seizure in the near future). The project is informed by complex intervention frameworks, which recommend phases of development, feasibility study, clinical evaluation, and implementation. OBJECTIVE Objective 1 aims to conduct a feasibility study to test and refine the trial methods for a future clinical trial. Objective 2 aims to test and refine the data collection technology, considering usability and technical performance. Objective 3 aims to collect longitudinal data on seizures and their precipitants to refine seizure forecasting. METHODS This study is a single-arm, mixed methods feasibility study, testing a prototype of the data collection technology, with phase 2 testing a minimum viable product. In total, 60 participants will be recruited via specialist National Health Service epilepsy clinics. Inclusion criteria are adults with epilepsy, experiencing seizures twice per month, able to consent, and engage with technology. Clinicians will screen and gain consent to contact, with researchers obtaining full consent. Participants will be invited to complete the following study procedures: (1) onboarding, (2) use the data collection technology (phase 1 or 2) in their lived context for up to 6 months, (3) complete patient-reported outcome measures and capture clinical-reported outcome measures at baseline and 3 months, and (4) complete a qualitative interview exploring their views of the data collection technology. A study flow diagram will report recruitment rates (outcome 1), diversity of the recruited sample (outcome 2), barriers and facilitators to recruitment (outcome 3), retention rates (outcome 4), and barriers and facilitators to retention (outcome 5). To assess the data collection technology, quantitative technology use data and qualitative interview data will be analyzed to assess usability (outcome 6) and technical performance (outcome 7) of the data collection technology. These outcomes will inform iterative minimum viable product development and testing cycles with stakeholders. RESULTS Recruitment is planned to begin in quarter 1 of 2026, with data collection expected to be completed by quarter 2 of 2027. Data analysis will take place during quarter 3, and the results will be published in quarter 4. CONCLUSIONS This project aims to improve clinical outcomes for people with epilepsy through seizure forecasting technology. To evaluate clinical outcomes, robust trial methodology is critical. This feasibility study will optimize methods for a future full-scale clinical trial as well as refine the seizure forecasting intervention. INTERNATIONAL REGISTERED REPORT PRR1-10.2196/85993

  • Open Access

    Correction: Exploring the Use of Smartwatches and Activity Trackers for Health-Related Purposes for Children Aged 5 to 11 years: Systematic Review

    by Lauren Thompson, Sydney Charitos, Jon Bird, Paul Marshall, Amberly Brigden

    [This corrects the article DOI: 10.2196/62944.].

  • Open Access

    Correction: Exploring the Use of Smartwatches and Activity Trackers for Health-Related Purposes for Children Aged 5 to 11 years: Systematic Review (Preprint)

    by Lauren Thompson, Sydney Charitos, Jon Bird, Paul Marshall, Amberly Brigden

    Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author).

  • Open Access

    Challenges When Co-Designing With Children in the Classroom

    by Sydney Charitos, Lauren Thompson, Amberly Brigden, Erin Brady, Erin Dooley, Katerina Wintle, Jon Bird


  • Open Access

    Exploring the Use of Smartwatches and Activity Trackers for Health-Related Purposes for Children Aged 5 to 11 years: Systematic Review

    by Lauren Thompson, Sydney Charitos, Jon Bird, Paul Marshall, Amberly Brigden

    Background: Digital health interventions targeting behavior change are promising in adults and adolescents; however, less attention has been given to younger children. The proliferation of wearables, such as smartwatches and activity trackers, that support the collection of and reflection on personal health data highlights an opportunity to consider novel approaches to supporting health in young children (aged 5-11 y). Objective: This review aims to investigate how smartwatches and activity trackers have been used across child health interventions (for children aged 5-11 y) for different health areas, specifically to identify the population characteristics of those being targeted, describe the characteristics of the devices being used, and report the feasibility and acceptability of these devices for health-related applications with children. Methods: We searched 10 databases (CINAHL, Embase, ACM Digital Library, IEEE Xplore, Cochrane Library, PsycINFO, Web of Science, PubMed, Scopus, and MEDLINE) to identify relevant literature in March 2023. The inclusion criteria for studies were as follows: (1) peer-reviewed, empirical studies; (2) published in English; (3) involved a child aged 5 to 11 years using a smartwatch for health-related purposes. Two researchers independently screened articles to assess eligibility. One researcher extracted data relating to the 3 aims and synthesized the results using narrative and thematic synthesis. Results: The database searches identified 3312 articles, of which 15 (0.45%) were included in this review. Three (20%) articles referred to the same intervention. In 77% (10/13) of the studies, the devices were used to target improvements in physical activity. Other applications included using smartwatches to deliver interventions for emotional regulation and asthma management. In total, 9 commercial devices were identified, many of which delivered minimal data feedback on the smartwatch or activity tracker, instead relying on a partner app running on a linked parental smartphone with greater functionality. Of the 13 studies, 8 (62%) used devices designed for adults rather than children. User feedback was positive overall, demonstrating the acceptability and feasibility of using these devices with children. However, the studies often lacked a child-focused approach, with 3 (23%) studies gathering user feedback only from parents. Conclusions: Interventions involving smartwatches and activity trackers for children aged 5 to 11 years remain limited, primarily focusing on enhancing physical activity, with few studies investigating other health applications. These devices often provide limited data feedback and functionality to support children’s independent engagement with the data, relying on paired smartphone apps managed by caregivers, who control access and facilitate children’s interaction with the data. Future research should adopt child-centered methods in the design and evaluation of these technologies, integrating children’s perspectives alongside their caregivers, to ensure that they are not only feasible and acceptable but also meaningful and effective for young children. Trial Registration: PROSPERO CRD42022373813, https://tinyurl.com/4kxu8zss