00
Executive Summary
The NHS spends hundreds of millions annually on diagnostic imaging for head and neck conditions — many of which could be identified faster, cheaper, and more accurately through an entirely different modality: sound.
The ADMS uses an array of MEMS microphones and inertial sensors embedded in a flexible mesh to passively
capture the acoustic signatures of bones, joints, tendons, arteries, and soft tissues during natural movement.
A 5–10 minute session produces a structured, AI-interpreted output that supports evidence-based triage decisions
— without radiation, specialist attendance, or invasive procedure.
Primary Benefit
First-line
triage tool
Replaces unnecessary CT/MRI referrals at primary and secondary care level
Financial Case
£2M–£8M
Annual saving per Trust. System-wide adoption: potentially hundreds of millions per year
Long-Term Value
Data
atlas
Population-scale biomechanical dataset for predictive and preventative medicine
01
The Diagnostic Gap
Static Imaging Blindspot
CT and MRI capture anatomy at rest. A cervical joint that misaligns only at 35° of rotation appears entirely normal on static scan — yet symptoms are real and disabling.
Referral Cost Pressure
A single MRI costs £350–£800. Head and neck imaging referrals have risen 23% over five years. ADMS is designed as upstream triage — reducing unnecessary scan orders at source.
Subjective Symptom Gap
Vague or unusual presentations lead to repeated consultations, misclassification, and inappropriate mental health referrals. Objective acoustic data removes this ambiguity.
Diagnostic Delay & Harm
Patients with hidden mechanical or vascular causes — ligament instability, arterial compression, CSF anomalies — can wait months or years for correct diagnosis while harm accumulates.
02
The Acoustic Solution
Different biological structures transmit and reflect sound differently — a principle already exploited in
geophysics to map underground formations, and in medical ultrasound. Applied passively to the human
head and neck, it becomes a precision diagnostic instrument.
Acoustic Tissue Signature Palette
Bone · Joint
Misalignment, degeneration, bone-on-bone contact
200–2,000 Hz
Tendon · Ligament
Laxity, micro-tear, instability, stretch injury
500–5,000 Hz
Artery · Vessel
Stenosis, compression, partial blockage, vascular anomaly
20–500 Hz
Fluid · Soft Tissue
CSF flow issues, oedema, soft tissue stress
10–200 Hz
Muscle Fibre
Tone abnormalities, spasm, nerve-related tension
50–400 Hz
Cranial · Intracranial
Intracranial pressure change, CSF event, vascular collapse
5–100 Hz
Technology Precedent — This Is Not Speculative
Geophysicists map underground formations using seismic sound. Smartphone IMUs track motion to sub-degree precision. Medical ultrasound already proves sound reveals internal anatomy non-invasively. ADMS combines these established domains in a novel configuration: passive acoustic listening, synchronised with motion data, analysed by AI trained on anatomical ground truth.
03
Clinical Pathway
ADMS is a triage adjunct — not a replacement for indicated imaging or specialist assessment. The clinician retains full authority over escalation and final decision.
01
Patient Presents
GP / ENT / ED head or neck complaint
02
ADMS Session
5–10 min acoustic-motion map
03
AI Analysis
Tissue type · source location · confidence
04
Triage Decision
Low / Moderate / High complexity flag
05
Targeted Action
Discharge · referral · urgent imaging
04
Clinical Safety & Risk
HIGH
False Negative: Missed Serious Pathology
ADMS must not be used to rule out serious conditions. It functions as a triage supplement, not a diagnostic replacement. Clinical protocols must specify mandatory escalation thresholds.
HIGH
AI Misclassification
All AI outputs carry uncertainty. Clinician override is always available. Confidence intervals and output explainability are embedded requirements — not optional design features.
MED
Infection Control
Single-use liners or validated decontamination protocols required. Materials must be compatible with standard NHS cleaning agents. IPC compliance assessed before clinical deployment.
MED
Patient Harm During Movement Replication
Patients with acute or unstable cervical pathology should not reproduce provocative movements without clinical supervision. Contraindication screening protocol required before each session.
LOW
Direct Patient Harm
ADMS emits no energy into the body. Session duration is short; skin irritation risk minimal with hypoallergenic materials. EMC compliance required in clinical environments.
Governance Requirement
A Clinical Safety Case under DCB0129/DCB0160 is required before any clinical deployment. A Clinical Oversight Committee (radiologists, neurologists, ENT, patient safety lead) must be established. Adverse events must integrate with the NHS NRLS reporting system.
05
Evidence Pathway
Phase 1 · 0–6 months
Laboratory Acoustic Validation
Cadaveric & phantom studies
Characterise frequency-specific signatures per tissue type. Establish repeatability. Target: coefficient of variation <10% across 3 prototype units.
Phase 2 · 6–12 months
Healthy Volunteer Baseline Study
n=100+
Population-level acoustic baselines stratified by age, sex, BMI. Required to train AI classification models and define normal reference ranges.
Phase 3 · 12–30 months
Prospective Comparison vs. MRI/CT
n=500+ · ISRCTN pre-registered
Primary endpoints: sensitivity ≥85%, specificity ≥80% for major diagnostic categories. Validated across demographic subgroups.
Phase 4 · 24–36 months
MHRA/UKCA Registration
Class IIa device · SaMD assessment
Conformity assessment with UK Approved Body. SaMD assessed under IMDRF framework. NICE ESF Tier D applies to AI component.
Phase 5 · 36+ months
NICE Submission
HTA / MTEP cost-effectiveness
Full HTA submission. Cost-effectiveness modelling (ICER per QALY). Medical Technologies Evaluation Programme pathway.
≥85%
Sensitivity
Protects against false negatives in serious pathology
≥75%
Specificity
Prevents unnecessary escalation from false positives
≥90%
NPV
Vascular and neurological categories specifically
All
Subgroups
Age >65, high BMI, paediatric populations required
06
Data Governance & GDPR
ADMS generates novel biometric data — acoustic signatures of internal anatomy — constituting special
category health data under UK GDPR Article 9. A comprehensive data governance framework is
a prerequisite for any clinical deployment.
Lawful Basis
Article 9(2)(h) — medical diagnosis and treatment — with explicit patient consent. Research use governed by separate ethics approval and data sharing agreements.
Data Architecture
Raw audio never transmitted externally. Only processed feature vectors exported for AI training. NHS-approved cloud infrastructure only (NHS Digital / NHSX compliant).
DPIA Requirement
Mandatory before deployment. Novel biometric data type triggers high-risk processing classification under ICO guidance. DPO sign-off required at each Trust.
NHS DSPT Compliance
Full compliance with NHS Data Security and Protection Toolkit. Annual certification required for any system accessing NHS patient data or networks.
Research Biomechanics Atlas
Anonymised acoustic data governed by REC approval, Data Access Agreement, and published governance policy. NHS-owned dataset.
Retention & Deletion
Clinical data retained per NHS Records Management Code of Practice (8 years post-episode). Right to erasure applied where technically feasible.
07
Inviting Conversation
This proposal is presented at concept stage to invite clinical and academic review.
No commitment is implied or sought. No clinical claims are made pending evidence development.
Proposed Next Steps
A
Feasibility Discussion
We welcome an initial conversation with NHS Innovations or a willing clinical lead to explore whether this concept aligns with current diagnostic priorities.
B
Academic Partnership
Actively seeking a university or NHS research partner to co-develop the laboratory validation phase — the essential first step before any clinical work begins.
C
Innovation Programme
This concept may be a candidate for NHS Clinical Entrepreneur Programme, Innovate UK Smart Grants, SBRI Healthcare, or Academic Health Science Networks — subject to further assessment.
D
MHRA Pre-Submission
Early dialogue with MHRA Innovation Office to confirm device classification and identify the correct regulatory pathway before significant development investment is made.
"The body generates diagnostic information that current technology does not capture. This proposal invites conversation about whether it should."
ADMS · NHS Innovation Brief · 2026 · Concept Stage · All financial figures are indicative modelled estimates. No clinical efficacy claims are made.