Core differentiator
AI personalisation & the intelligence layer

The intelligence layer turns continuous symptom tracking and biomarkers into clinically useful, explainable decision support. It improves consistency across a decentralised network while keeping clinicians in control.

Definition

What is Longitudinal Symptom Intelligence?

Longitudinal Symptom Intelligence continuously tracks symptoms over months and years, detecting trends, cycles, clusters, and correlations with lifestyle and treatment changes. It replaces static questionnaires with a living timeline that adapts as the person changes.

Signals it can surface
  • Baseline vs meaningful change (noise filtering)
  • Symptom clusters (e.g., sleep+mood+cognition)
  • Lagged correlations (e.g., stress preceding symptoms by 1–3 days)
  • Treatment response signals (pre/post change comparison)
  • Risk prompts (thyroid, metabolic, bone, mental health)
What it should not do
  • Autonomous diagnosis or prescribing
  • Over‑alarm based on single data points
  • Opaque “black‑box” recommendations without explanation
  • Replace clinician judgement or shared decision‑making
1) Symptom intelligence

Time‑series pattern detection

Learns each person’s baseline and flags meaningful change rather than noise. Useful for hot flushes, sleep, mood, cognition, pain.

2) Treatment modelling

Optimisation support

Suggests likely next steps for clinician review: formulation, route, timing, monitoring, and adherence prompts.

3) Risk profiling

Preventative scoring

Continuously updates cardio‑metabolic, bone, thyroid/metabolic, and mental health risks using symptoms + labs.

4) Triage

Red flags & prioritisation

Structures free‑text concerns into clinical categories and highlights urgent patterns for review.

5) Pathway engine

Personalised education

Recommends content and actions based on stage, symptoms, risks, and preferences — reducing overwhelm.

6) Population insight

Anonymised analytics

Aggregated insights for employers and public sector planning with strict privacy boundaries and no individual data sharing.

Safety principle
AI is used for decision support, transparency, and standardisation — never autonomous diagnosis. Clinicians maintain oversight and final accountability. Outputs must be explainable, auditable, and aligned to protocols.