Assistiv Systems builds a five-layer population intelligence pathway for the NHS — from geographic risk mapping to community screening and clinical referral. Identifying older adults at risk before crisis, not after.
A population of older adults too frail to be fully safe at home, but not yet eligible for formal NHS or social care support. One fall, one infection, or one carer breakdown from an avoidable acute admission.
The NHS frailty system is reactive. People appear in it when they arrive at A&E, or when crisis has already happened. Proactive community identification of frailty risk, before the system has to respond, barely exists at scale anywhere in the country.
For every older adult who loses their independence to an avoidable crisis, there is a family under strain, a carer invisible to health services, and a preventive opportunity that passed without anyone seeing it. Assistiv is designed to see it.
Each layer feeds the next — from public data ingestion through geographic risk mapping, community identification, precision screening, and clinical triage. The dataset becomes the competitive advantage as the system learns from every interaction.
Each layer is a distinct intelligence agent with its own data inputs, logic, and outputs — feeding the next in a closed loop. Layer 2 and Layer 4 are live prototypes. Layers 3 and 5 are designed and sequenced for Phase 2 and 3 development. The feedback loop from Layer 5 back to Layer 2 is the system's long-term competitive advantage.
The Frailty Emergence Probability model generates a composite risk score for each of Kent & Medway's 13 districts. Seventeen signals — falls rates, prescribing data, deprivation, isolation, winter mortality — normalised to a common scale and weighted by clinical significance.
A score of 65 means that district is substantially more at-risk than the England average across multiple measures simultaneously. The map routes preventive investment to where it will have the greatest effect.
When a UKHSA/Met Office Heat-Health or Cold-Health Alert is active for South East England, FEP scores for high-risk districts are uplifted and medication risk signals — anticholinergics, diuretics, hypnotics — are flagged for elevated clinical sensitivity. The same alert status is injected into RESILIENCE screening sessions in Layer 4.
† Dementia diagnosis rate below England average indicates unmet diagnostic need — not better performance.
RESILIENCE asks older adults about their everyday life in a voice-first interface powered by Claude Sonnet. It listens not just to what is said, but to how it is said — detecting hesitation, minimisation, and the fears that prevent honest disclosure. From one conversation: a Wellness Guide for the person, a clinical referral for the frailty team, and a population intelligence signal for commissioners.
Voice-first community frailty screen. Twelve conversational questions across six clinical domains. PRISMA-7 and FRAIL Scale scored in real time.
Independent observational questionnaire linked by consent only. Carer and person scores never cross until the clinical layer — divergence surfaces where it carries most value.
SimulationStructured referral centred on a Frailty Profile Radar — six domains at a glance. Minimisation flags, domain detail, CGA preparation brief.
SimulationPerson and carer profiles overlaid on one radar. Agreement confirms confidence. Divergence is a clinical signal — almost always indicating the person is understating difficulty.
SimulationPerson self-report, carer observation, and CGA findings on a single radar. Three independent perspectives — the highest-confidence signal in the system.
SimulationPopulation-level frailty interface for ICB commissioners. Ward-level risk mapping, referral forecasting, AI-synthesised commissioning brief.
When person self-report, carer observation, and CGA clinical assessment are overlaid on a single radar, three independent perspectives confirm or challenge each other. Convergence is confidence. Divergence is the signal — and almost always indicates that the person is understating genuine difficulty in ways that neither source alone could detect.
Every person receives a personalised Wellness Guide regardless of what they choose to share with clinical services. The guide belongs to them. Reciprocal value before any request for data.
Nothing happens without the person's permission. Every consent layer is granular, revocable, and explained in plain language. A person can receive their Wellness Guide and share nothing further — that is entirely their choice.
The older person, the carer, and the clinical team all want the same outcome: safe, well, and at home on the person's own terms. Assistiv closes the information gap between them without creating new asymmetries.
Claude Sonnet interprets spoken responses within a tightly defined clinical framework. The system learns through co-development with geriatricians and frailty practitioners — not independently. Every instruction set is validated with clinical expertise.
British Geriatrics Society self-screening frailty identification instrument, embedded invisibly across the twelve screening questions and scored in real time.
Fatigue, Resistance, Ambulation, Illness, and Loss of weight domains mapped across Physical Function, Nutrition, and Medical Burden question categories.
British Geriatrics Society framework informing question categories, clinical domain structure, and referral routing throughout the tool suite.
NHS RightCare Frailty Pathway informing clinical triage logic, referral routing, and priority weighting within the Clinical Referral tool.
Finnish multidomain intervention evidence underpinning the Wellness Guide structure — lifestyle, nutrition, cognitive activity, and social engagement domains.
Peer-reviewed ML study in Geriatric Nursing identifying self-reported pain, depression, and functional ability as the strongest frailty predictors — directly validating a conversational, voice-first approach over standardised forms.
All geographic signals drawn from public NHS sources: NHS Fingertips / OHID PHOF · NHSBSA EPD (practice level, Mar 2026) · ONS Census 2021 · IMD 2019 · CQC Register · DWP Attendance Allowance
Assistiv Systems is a working prototype developed in response to a real clinical need. The next stage is formal partnership — with NHS commissioners, ICBs, and clinical practitioners at the cutting edge of delivering support to this population.
Whether you want to explore a pilot, offer clinical expertise, or understand what the system does, we would welcome the conversation.