Key learning from the development phase¶

Our development work with people who have lived experience of MLTCs together with care professionals, system managers, scientists, engineers and designers resulted in some key learnings which inform our approach and focus going into phase two.

Focus on working age population¶

During the development phase we picked up intersectional multi-variant MLTC extremes and included seldom heard voices across three groups: children & families, working age, and pre-frailty. Going into phase two, we prioritise the working age population, especially those with combined mental and physical health problems. This group experience surges of compound health/social pressures, and their needs are inadequately met. They also represent a key window for secondary prevention of MLTCs.

Focus on combined mental-physical and pain MLTCs¶

Our secondary care data analysis showed that those presenting with pain on a background of combined mental and physical MLTCs were the highest users of out of hours services, particularly in disadvantaged areas. Those with long-term pain or mental illness were also at greatest risk of accumulating additional conditions, indicating opportunities for early prevention. This resonates with our patient-partners’ experiences of MLTCs and their wishes to avert missed opportunities for prevention.

The phase two hub targets three areas for innovation in 1) prevention, 2) supported self-management, and 3) care navigation, as key areas which came up during the development phase.

Foundational People Insight models¶

Based on qualitative and quantitative information, we co-developed MLTC person maps, care journey and system models that will act as blueprints and underpin our innovation partnership.

Civic learning system¶

Residents from both our cities, with or without lived experience of MLTCs, supported our hub’s progressive use of linked data and AIs, drawing upon the wider participation work of the Liverpool City Region Civic Data Cooperative and Data into Action programme and the NHS Greater Glasgow and Clyde Safe Haven. Allied NIHR projects DynAIRx (MLTC AI to optimise medicines), have already involved our residents and their data in this way. Like DynAIRx, SysteMatic needs to find system solutions within existing resources, offering innovations that afford tangible relief of pressures for practitioners working in underfunded, understaffed services.

Engineering and physical sciences¶

To align the engineering and physical sciences (EPS) plans for Phase 2 with the MLTC requirements identified in Stage 1, we have ramped up the EPS participation in our work with stakeholders. This work has identified fundamental limitations of current digital health innovation, revealing siloed approaches that focus too narrowly on single LTCs and organisational boundaries and do not advance MLTC care. Our approach aims to translate complex, heterogeneous streams of physiological, behavioural and environmental data – including natural language feedback from patients – into holistic, actionable information for patients, clinicians and wider support networks. This requires interoperable computational methods to dynamically map and semantically integrate heterogeneous data streams into structured, interpretable representations of patient health that can support the reasoning of clinicians and patients. By facilitating bidirectional feedback between patients and systems, we ensure continuous improvement and a comprehensive view of patient health. Grounded in our collaborative technical assessments, we suggest that hierarchical digital twins can generate transformative care outcomes across person, population, and provider levels – ‘P^3’. We will fuse privacy-preserved ambient sensory information with wearable data and care records to engineer better integrated and targeted systems, particularly for our underserved communities. Our feedback mechanism from real-world community testbeds and health sciences into EPS will translate complex patient and practitioner experiences into precise computational challenges, ensuring our engineering and problem-solving stack remains adaptive, scientifically rigorous, and fundamentally responsive to real-world equity needs.