LMLysanne Veerle Michels

Lysanne Veerle Michels

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Lysanne Veerle Michels has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Are Large Language Models amplifying bias in medical science? (Preprint)

    by Hajira Dambha-Miller, Heidi Smith, Andrew Soltan, Lysanne Veerle Michels

    UNSTRUCTURED Large Language Models (LLMs) offer unprecedented efficiency across medical research, yet current evaluation focuses almost exclusively on output accuracy, neglecting critical issues of fairness, bias, and global representation. Because LLMs retrieve from and synthesize an evidence base already skewed toward high-income populations, their widespread adoption creates a feedback loop of recursive amplification that repeatedly surfaces dominant data while filtering out novel hypotheses and evidence from under-researched groups. Even if individual outputs remain factually accurate, this process risks creating an artificial scientific consensus that fails to reflect global health needs. Because standard disclosure rules cannot track how AI alters the broader literature landscape, evaluation paradigms must shift from checking study-level accuracy to measuring field-level representation. Establishing longitudinal literature-surveillance frameworks to monitor distributional skew, source diversity, and demographic representation, alongside strict reporting standards for model usage, is essential to prevent LLMs from exacerbating structural health inequities and undermining scientific validity.

  • Open Access

    When Innovation Leaves People Behind: Reframing Accountability in Commercial Digital Health

    by Hajira Dambha-Miller, Lucy Smith, Lysanne Veerle Michels

    Digital technologies are increasingly integrated across health care systems; however, accumulating evidence shows that these tools often perform unevenly across population groups. Biases in AI-enabled tools can reinforce existing health inequities, particularly when systems are developed and validated using datasets that exclude underserved populations. Studies demonstrate systematic underestimation of illness severity, diagnostic inaccuracies, and measurement bias affecting ethnic minority groups, rural populations, people with disabilities, people experiencing homelessness, and other groups with limited access to health care. These disparities highlight structural vulnerabilities in the data that inform machine learning systems, where socially patterned access to care shapes what is recorded and therefore learned. Commercial adoption patterns further exacerbate inequities due to socioeconomic gradients in digital engagement and a lack of accountability measures for adherence to regulatory frameworks within National Health Service procurement processes. In this Viewpoint, we argue that ensuring accountability in digital health care requires transparent reporting of subgroup performance, representative development of datasets, and ongoing monitoring of distributional impacts. Achieving equitable and reliable digital health care demands regulatory and methodological standards that prioritize fairness and generalizability within the commercialization sector and are monitored across the pre- and postdeployment life cycle.

  • Open Access

    Application of Artificial Intelligence in analysing meteorological data for health research: A rapid review

    by Lysanne Veerle Michels, Lucy Smith, Suzan Ghannam, Charles Gadd, Hajira Dambha-Miller

    Introduction: Artificial intelligence (AI) has rapidly advanced as a key analytical tool for processing complex datasets across disciplines, including environmental and health research. Meteorological data is increasingly used to understand and mitigate health risks, often linked to climate change. This rapid review aims to synthesise studies involving AI for meteorological data applications in health research to better understand its use. Methods: PubMed, Web of Science, and Scopus were systematically searched from 2020 to 2025 following a standardised framework in line with PRISMA-RR guidelines. Eligible studies included any empirical design involving human-related health research where AI techniques were applied to meteorological data. Two reviewers independently screened studies, extracted data, and synthesised findings narratively. Results: Twelve studies met eligibility criteria. Despite heterogeneity in study design and sample size, most examined the impact of extreme pollution levels and temperature variations on the prevalence and severity of respiratory, bacterial, and other diseases. AI methods primarily included Random Forest models, as well as time-series and clustering analyses. Model performance was commonly evaluated using sensitivity; however, methodological justification was often insufficiently recorded. Conclusion: Overall, findings suggest that incorporating meteorological variables enhances the prediction of health outcomes, although detailed population characteristics were frequently underreported. This restricts the generalisability and applicability of AI-driven health models incorporating meteorological data, with stronger methodological rigour and clearer reporting standards needed to support reliable future development.

  • Open Access

    Equity Considerations in AI-Enabled Conversational Systems: A Cross-Sectional Comparative Study of Clinical Responses

    by Lysanne Veerle Michels, Yousef Yousef, Heidi Smith, Hajira Dambha-Miller

    Background: Artificial intelligence (AI)-enabled conversational tools are increasingly used for health information and clinical decision support. Concerns persist regarding systematic bias, limited transparency, and the potential to exacerbate health inequity in real-world use. Empirical evaluation of how these tools operationalise equity-relevant factors in clinical responses remains limited. We aimed to compare the inclusion of equity considerations across widely used AI tools in response to standardised health queries.Methods: In this cross-sectional comparative study, we developed clinical and health information queries reflecting patient and clinician perspectives across common scenarios. Responses were generated using multiple widely used AI tools (ChatGPT, Claude, Copilot, DeepSeek, Doubao, Gemini, and Grok). Queries were standardised and geolocation controlled to minimise localisation effects. Responses were assessed using a structured framework with inclusion of equity-relevant factors (age, sex or gender, ethnicity, socioeconomic context, and access to care), clarity of clinical guidance, and specification of non-diagnostic outputs.Findings: Substantial heterogeneity was observed. Grok demonstrated the highest inclusion of equity-relevant factors, followed by Claude and DeepSeek, whereas Doubao showed minimal inclusion. ChatGPT, Copilot, and Gemini showed intermediate performance. Age was referenced in over half of responses, whereas sex or gender and ethnicity were included in fewer than half. Socioeconomic context and access to care were infrequently represented. Although all AI tools provided clinical guidance, fewer than half explicitly specified outputs as non-diagnostic. Patterns of equity inclusion varied by geographic context across tools.Interpretation: AI tools demonstrate inconsistent and limited operationalisation of equity-relevant factors, with implications for clinical safety and differential performance across populations. Strengthening transparency requirements, embedding standardised equity evaluation frameworks, and aligning regulatory oversight with real-world deployment are essential to ensure these technologies mitigate rather than exacerbate health inequity.

  • Open Access

    When Innovation Leaves People Behind: Reframing Accountability in Commercial Digital Health (Preprint)

    by Hajira Dambha-Miller, Lucy Smith, Lysanne Veerle Michels

    UNSTRUCTURED Digital technologies are increasingly integrated across healthcare systems, yet accumulating evidence shows that these tools often perform unevenly across population groups. Biases in artificial intelligence‑enabled tools can reinforce existing health inequities, particularly when systems are developed and validated using datasets that exclude underserved populations. Studies demonstrate systematic underestimation of illness severity, diagnostic inaccuracies, and measurement bias affecting ethnic minority groups, rural populations, people with disabilities, homeless individuals, and other groups with limited access to healthcare. These disparities highlight structural vulnerabilities in the data that inform machine learning systems, where socially patterned access to care shapes what is recorded and therefore learned. Commercial adoption patterns further exacerbate inequities due to socioeconomic gradients in digital engagement. Ensuring accountability in digital health requires transparent reporting of subgroup performance, representative development of datasets, and ongoing monitoring of distributional impacts. Achieving equitable and reliable digital healthcare demands regulatory and methodological standards that prioritise fairness and generalisability.

  • Open Access

    Environmental Scanning of Climate Adaptation Tools in Healthcare

    by Lysanne Veerle Michels, Heidi Smith, Lucy Smith, Hajira Dambha-Miller

    Introduction: Extreme weather events are increasing in frequency and intensity due to climate change, contributing to substantial morbidity and mortality globally, particularly among vulnerable populations. In the UK, climate adaptation within health systems remains insufficiently developed. However, there is limited understanding of the tools currently available for the identification and management of populations at risk during extreme weather. This study aims to systematically characterise UK-based climate adaptation tools used in healthcare settings. Methods: Environmental scanning was conducted, because no centralised database exists for climate adaptation tools in healthcare, and many relevant resources are not captured in traditional academic or grey literature repositories. Structured Google searching by two independent reviewers enabled identification of publicly available and practice-oriented tools accessed in real-world settings. Eligible resources included UK-based tools designed for healthcare professionals, local authorities, or patients that incorporate meteorological data to mitigate climate-related health risks. Results: Nine tools met inclusion criteria, comprising e-learning platforms, online dashboards, integrated clinical software, and structured workflows. Most targeted healthcare professionals, with few targeting local authorities and none targeting patient self-management. Data inputs and outcomes measures were heterogeneous, spanning risks related to heat, cold, flooding, and air pollution. Reporting was inconsistent, as nearly half the tools were not publicly accessible and all demonstrated limited transparency. Conclusion: The current landscape of UK climate adaptation tools in healthcare is fragmented, with variability in accessibility, evidence, and scope. Clearer reporting and greater coordination in how such tools are catalogued may support more consistent and equitable responses to climate-related health risks.

  • Open Access

    Application of Artificial Intelligence in Analysing Meteorological Data for Health Research: A Rapid Review

    by Lysanne Veerle Michels, Lucy Smith, Suzan Ghannam, Charles Gadd, Hajira Dambha-Miller

    Artificial intelligence (AI) has rapidly advanced as a key analytical tool for processing complex datasets across disciplines, including environmental and health research. Meteorological data is increasingly used to understand and mitigate health risks, often linked to climate change. This rapid review aims to synthesise studies involving AI for meteorological data applications in health research to better understand its use. PubMed, Web of Science, and Scopus were systematically searched from 2020 to 2025 following a standardised framework in line with PRISMA-RR guidelines. Eligible studies included any empirical design involving human-related health research where AI techniques were applied to meteorological data. Two reviewers independently screened studies, extracted data, and synthesised findings narratively. Twelve studies met eligibility criteria. Despite heterogeneity in study design and sample size, most examined the impact of extreme pollution levels and temperature variations on the prevalence and severity of respiratory, bacterial, and other diseases. AI methods primarily included Random Forest models, as well as time-series and clustering analyses. Model performance was commonly evaluated using sensitivity; however, methodological justification was often insufficiently recorded. Overall, findings suggest that incorporating meteorological variables enhances the prediction of health outcomes, although detailed population characteristics were frequently underreported. This restricts the generalisability and applicability of AI-driven health models incorporating meteorological data, with stronger methodological rigour and clearer reporting standards needed to support reliable future development.

  • Top Cited Papers
    Open Access

    Wearable Device–Based Measurement of Physical Activity in Populations at Risk of Health Inequity: A Scoping Review

    by Lucy Smith, Lysanne Veerle Michels, Aman Jat, James Faulkner, Jacob Keast, Hajira Dambha-Miller

    Background: Accurate and consistent measurement of physical activity (PA) is essential for evaluating interventions, informing clinical and public health decision-making, and enabling comparisons across populations. Wearable device–based measures are increasingly used to quantify PA, but the extent to which populations at risk of health inequity, as defined by established equity frameworks, are represented in wearable-based PA studies, and whether measurement protocols are appropriate and comparable across these groups, remains insufficiently characterised. Aim: To synthesise evidence on the use of wearable devices for measuring PA in populations at risk of health inequity, as defined by the PROGRESS-Plus and CORE20PLUS5 frameworks, and to identify methodological features relevant to equity in PA measurement. Methods: A scoping review was conducted in accordance with PRISMA-ScR guidelines. PubMed, Scopus, Web of Science, and grey literature were searched for peer-reviewed randomised controlled trials published between January 2020 and October 2025. Eligible studies quantitatively measured PA using pedometers, accelerometers, or smartwatches in populations at risk of health inequity. Data were extracted on study design, population characteristics, device type and placement, monitoring protocols, and equity-related considerations. Results: Of 1,027 records screened, 13 studies met inclusion criteria. Wrist-worn pedometers and hip-worn accelerometers were most common. Adaptations were minimal and largely limited to language translation. Several high-risk equity groups according to the frameworks used including LGBTQ+, people experiencing homelessness, those with learning difficulties, substance misuse, and justice system involvement were absent. Conclusions: This review demonstrates that wearable-based PA measurement has been applied to only a narrow subset of populations at risk of health inequity, with notable gaps across several key PROGRESS-Plus and CORE20PLUS5 groups. Methodological adaptations to support equitable measurement were uncommon and largely superficial, raising concerns about the appropriateness, acceptability, and comparability of PA data generated in these contexts. Addressing these methodological and reporting deficiencies is essential to strengthen the evidence base and prevent the widening of inequities in PA surveillance and intervention evaluation.


  • Open Access

    Equity in Physical Activity Interventions to Promote Health: A Scoping Review of Trials

    by Lysanne Veerle Michels, Lucy Smith, Jacob Keast, Hajira Dambha-Miller

    Physical activity (PA) improves health and well-being, and helps prevent long-term conditions. Yet opportunities to be active are not evenly distributed, with social, economic, and environmental disadvantages constraining access to PA among populations who may benefit most. Since the extent to which PA interventions incorporate equity considerations remains insufficiently characterised, risking exacerbation of health inequity, this scoping review aims to synthesise trial evidence on interventions of PA to improve health outcomes in populations at risk of health inequity as defined by the PROGRESS-Plus and CORE20PLUS5 frameworks. PubMed, Web of Science, and Scopus were searched for randomised controlled trials of PA interventions with at-risk populations published between 2020 and 2025. Study characteristics, intervention design, and equity-relevant factors were extracted. Two reviewers independently screened and synthesised findings narratively. Results indicate that of 2,480 articles identified, 23 trials met eligibility criteria. Most reported positive effect of PA on health outcomes amongst at-risk populations, including weight loss, improved motor skills and gait speed, reduced anxiety and PTSD, and fewer fractures or hospital visits. Interventions commonly included strength and balance training, group exercise, stretching, and aerobic fitness. UK-based studies and subgroup analyses by e.g. sex or age were largely absent, and many populations at risk of health inequity were underrepresented. Explicit equity considerations throughout design, implementation, or evaluation were rare across trials and few assessed differential effects between social or economic groups. Integrating equity frameworks and engaging with at-risk populations is recommended in future physical activity interventions to mitigate exacerbation of health inequity.

  • Open Access

    Digital Fatigue and Computerised Health Technologies: A Rapid Review (Preprint)

    by Lysanne Veerle Michels, Suzan Ghannam, Lucy Smith, Glenn Simpson, Hajira Dambha-Miller

    BACKGROUND Artificial intelligence (AI) is increasingly integrated into computerised health technologies. While these promise improved diagnostic accuracy, efficiency, and clinical outcomes, concerns are emerging regarding digital fatigue. Prolonged or poorly designed interactions with digitised tools such as decision support systems or self-management applications can contribute to disengagement and cognitive exhaustion in both patients and healthcare professionals, potentially resulting in mental health symptoms. OBJECTIVE To conduct a rapid review of studies utilising computerised health technologies, with a focus on how digital fatigue is defined and measured, and its impact on patients and healthcare professionals. METHODS This work followed a standardised framework in line with PRISMA-ScR guidelines. PubMed, Web of Science, and Scopus were systematically searched from inception to 2025. Eligible studies reported digital fatigue or similar constructs related to computerised health technologies. Two reviewers independently screened studies, extracted data using a piloted standardised form, and synthesised findings. RESULTS Six studies met inclusion criteria. Across settings, digital fatigue was linked to techno-overload, system complexity and burnout, yet terminology and measurement lacked consistency. Proposed mitigation strategies included refining alert specificity, aligning system design with workflow demands, and enhancing user-centred support. However, details on the computerised technologies used in included studies and the role of AI therein are largely missing, as are details on the conditions and participant demographics to which these are applied. CONCLUSIONS Digital fatigue is an under-recognised mental barrier to sustained use of computerised health technologies. Standardised definition and measurement of digital fatigue is needed to clarify its impact and guide the design of interventions that support long-term adoption and well-being among patients and healthcare professionals.