Listening...

Search Results

No Results

    See all results

    Sorry, I don't understand. Please try again
    1. UK/
    2. How we work/
    3. Using AI to Address Inequalities in Lung Cancer Outcomes
    JJ_Photo_Nurse_using_digital_tablet_with_patient_GettyImages_1719538625.jpg

    Using AI to Address Inequalities in Lung Cancer Outcomes

    This pioneering project leverages artificial intelligence (AI) and machine learning (ML) to tackle disparities in lung cancer diagnosis and access to care. It brings together NHS providers, local authorities, and industry partners to create a data-driven framework for improving early detection and reducing health inequalities.
    Public-private partnerships are 100% essential. The NHS simply doesn’t have the resources at local level to innovate and then scale up. We need industry to bring upfront investment, expertise, and delivery capability. The J&J collaborative working framework has been instrumental - not just in providing funding, but in offering project management expertise and strategic guidance. That’s often the most expensive and overlooked part of innovation.
    Dr John Chinegwundoh, Consultant Respiratory Physician and Trust Lead for Health Equity at Kingston and Richmond NHS Foundation Trust
    Background

    Lung cancer remains one of the most prevalent and deadly cancers in the UK, with significant disparities in outcomes due to unequal access to early diagnosis and screening services.1,2 In many cases, low screening uptake, variability in GP awareness, reliance on emergency presentations, and limited outreach resources hinder timely diagnosis and equitable care.

    Partnership and Solution

    The partnership between Johnson & Johnson , Kingston and Richmond NHS Foundation Trust and South-West London ICB, employed a predictive AI model to identify high-risk individuals for lung cancer who either are less likely to have engaged with lung health checks or sit outside the lung cancer screening criteria. It integrates socio-economic, demographic and behavioural data to tailor outreach strategies and improve screening uptake or early referral for diagnostic scans.

    The pilot phase will lay the foundation for a scalable, impactful model of care.

    AI Predictive Modelling:

    • Identifies underserved populations
    • Optimises outreach and resource allocation

    Community Engagement:

    • Collaborates with local stakeholders to raise awareness
    • Addresses cultural and systemic barriers to access

    Pilot Testing and Scalability:

    • Uses historical screening data to validate the model
    • Applies learnings to the Kingston Hospital and South West London rollout, with plans to expand regionally
    Benefits

    For patients:

    • Earlier detection and improved survival
    • Equitable access to care, through targeting underserved populations
    • Tailored outreach and engagement through personalised strategies

    For Kingston & Richmond NHS Foundation Trust and South West London Integrated Care Board:

    • Enhanced system efficiency
    • Strategic alignment, through supporting key NHS priorities
    • Scalable innovation, designed to be replicable across other regions

    Collaboration to address disparities in lung cancer diagnosis and treatment outcomes by leveraging artificial intelligence (AI)

    PDF Download (58 KB)

    1 Cancer Research UK (2025) Lung cancer statistics. Available at: https://www.cancerresearchuk.org/health-professional/cancer-statistics/statistics-by-cancer-type/lung-cancer#lung_stats0 (Accessed October 2025)

    2 Rivera, M. P., Katki, H. A., Tanner, N. T., Triplette, M., Sakoda, L. C., Wiener, R. S., Cardarelli, R., Carter-Harris, L., Crothers, K., Fathi, J. T., Ford, M. E., Smith, R., Winn, R. A., Wisnivesky, J. P., Henderson, L. M., & Aldrich, M. C. (2020) Addressing disparities in lung cancer screening eligibility and healthcare access. an official American Thoracic Society statement. American Journal of Respiratory and Critical Care Medicine, 202(7), e95–e112. Available at: https://doi.org/10.1164/rccm.202008-3053st (Accessed October 2025)

    CP-564898 | February 2026