Yousef Yousef

Yousef Yousef

Auto-generated profile, based on publicly available information

Yousef Yousef

University of Southampton

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 August 2026 in JMIR Mental Health
Verified
Journal Article
Open access
LSLucy Smith
Lucy Smith
YYYousef Yousef
Yousef Yousef
PWPiotr Wasilewski
Piotr Wasilewski
HDHajira Dambha-Miller
Hajira Dambha-Miller
AI-enabled self-management health tools are increasingly promoted within health care policy as part of digital self-management models for mental health care. However, development is concentrated on scalable, low-intensity interventions for common conditions, such as anxiety and depression, rather than on populations with the greatest clinical need, such as those with serious mental illness (SMI). This includes schizophrenia-spectrum and bipolar disorders, which remain comparatively underserved, despite experiencing a disproportionate burden of morbidity and service use. However, the clinical features of SMI—comprising fluctuating symptoms, multimorbidity, and elevated risk—may limit the suitability of low-intensity AI-driven self-management tools designed for mild-to-moderate conditions. In this Viewpoint, we argue that the scarcity of AI-enabled self-management tools for SMI reflects a structural feature of current innovation systems rather than one of technical infeasibility alone. Market incentives, regulatory pathways, and fragmented research pipelines favor low-risk, high-volume populations, thereby limiting development for clinically complex groups. Addressing this unevenness is essential and will require upstream intervention, including targeted public funding, improved data infrastructure, and administrative frameworks that support safe innovation in high-risk populations. Embedding equity for SMI as a primary design requirement will be necessary to ensure that AI-driven mental health tools do not reinforce current inequalities.

1 February 2026 in Digital Health
Verified
Journal Article
Open access
YYYousef Yousef
Yousef Yousef
JKJacob Keast
Jacob Keast
HDHajira Dambha-Miller
Hajira Dambha-Miller
Digital health adoption in the National Health Service (NHS) remains fragmented despite significant technological advances and substantial government investment in innovation initiatives. Many promising digital solutions fail to progress beyond pilot phases, with implementation remaining inconsistent across trusts despite national strategies including the 2022 digital health and social care plan. This Viewpoint examines the principal obstacles to digital health commercialisation within the NHS, focusing on regulatory complexity, organisational fragmentation, limited financial capacity and cultural resistance to change. We review existing support mechanisms including the Digital Technology Assessment Criteria (DTAC), NHS Innovation Accelerator and Clinical Entrepreneur Programme, highlighting their strengths and persistent limitations. To accelerate adoption, we propose two key reforms: formalising DTAC as a mandatory national standard with subsidised compliance pathways for small and medium-sized enterprises, and establishing a national ‘innovation passport’ that harmonises DTAC, Medicines and Healthcare products Regulatory Agency and procurement requirements into a single, transferable assessment. These reforms, complemented by strengthened procurement coordination and cultural change initiatives, could create a more predictable pathway for digital innovation while maintaining rigorous patient safety standards and enabling equitable access to validated digital health tools across the NHS.

31 October 2025 in medRxiv
Verified
Preprint
Open access
PDF file
TITassella Isaac
Tassella Isaac
AJAman Jat
Aman Jat
LSLucy Smith
Lucy Smith
YYYousef Yousef
Yousef Yousef
RVRishika Vashishtha
Rishika Vashishtha
HDHajira Dambha-Miller
Hajira Dambha-Miller
Background: Multimorbidity (the coexistence of two or more long-term conditions) is increasingly prevalent, particularly among older adults, and is a major driver of healthcare expenditure. However, healthcare costs reflect only part of the overall burden. Many people with multimorbidity also depend on social care services for personal support, mobility assistance, and social engagement to preserve independence and quality of life. Despite its significance for individuals, families, and the health system, the economic impact of social care needs related to multimorbidity has not been quantified at a population level in England. Methods: We conducted a retrospective, population-based cohort study of adults (≥18 years) with multimorbidity using data from the CPRD Gold and Aurum datasets covering 1987–2020. Social care needs were identified through coded indicators across three domains (personal care, mobility, and social interaction) and valued using 2019–2020 national unit costs from the Personal Social Services Research Unit (PSSRU). Adjusted per-capita costs were estimated via direct standardisation by age, sex, ethnicity, and socioeconomic deprivation. Results: The cohort comprised 5,771,603 adults with multimorbidity (mean age 56.5 years; 55.1% female). Among them, 800,309 individuals (13.9%) had at least one recorded social care need. Personal care accounted for the majority of costs (£3.66 billion; 84.3% of total), affecting 7.3% of the cohort with a mean annual expenditure of £8,736 per user. Mobility needs represented £336.8 million (7.8%) and social interaction needs £346 million (8.0%), with mean annual costs of £1,426 and £709 per user, respectively. Individuals with multiple needs (6.3% of the cohort) incurred mean annual costs of £9,076. Social care needs and costs were higher among older adults, women, and those living in more deprived areas. Conclusion: This study provides the first population-level estimate of social care costs associated with multimorbidity in England. Social care represents an important yet often overlooked component of the broader economic burden of multimorbidity. Costs are predominantly concentrated in personal care and vary systematically by demographic and socioeconomic factors, underscoring potential inequities in service access or provision. Integrating social care within multimorbidity strategies is essential to address the full scale of its societal impact.

22 April 2026 in JMIR Preprints
Verified
Preprint
Open access
LSLucy Smith
Lucy Smith
YYYousef Yousef
Yousef Yousef
PWPiotr Wasilewski
Piotr Wasilewski
HDHajira Dambha-Miller
Hajira Dambha-Miller
UNSTRUCTURED Artificial intelligence (AI)-enabled health tools are increasingly promoted within healthcare policy as part of digital self-management models for mental health care. However, development is concentrated on scalable, low-intensity interventions for common conditions such as anxiety and depression, rather than on populations with the greatest clinical need, such as those with serious mental illness (SMI). This includes schizophrenia-spectrum and bipolar disorders, for example, which remain comparatively underserved, although experiencing a disproportionate burden of morbidity and service use. The clinical features of SMI -comprising fluctuating symptoms, multimorbidity, and elevated risk limit the suitability of low-intensity AI-driven self-management tools designed for mild-to-moderate conditions. This Viewpoint argues that the scarcity of AI-enabled self-management tools for SMI reflects a common issue in current innovation systems rather than one of technical infeasibility alone. Market incentives, regulatory pathways, and fragmented research pipelines favour low-risk, high-volume populations, while limiting development for clinically complex groups. Addressing this unevenness is essential and will require upstream intervention, including targeted public funding, improved data infrastructure, and administrative frameworks that support safe innovation in high-risk populations. Embedding equity for SMI as a primary design requirement will be necessary to ensure that AI-driven mental health tools do not reinforce current inequalities.

28 May 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
LMLysanne Veerle Michels
Lysanne Veerle Michels
YYYousef Yousef
Yousef Yousef
HSHeidi Smith
Heidi Smith
HDHajira Dambha-Miller
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.