AI-assisted Diagnosis, Triage and Assessment of Hearing Loss and Tinnitus
Trial statusNot yet recruiting
Trial phaseNot listed
Trial typeObservational
Biological sexAll
Age18+
SponsorRoyal Cornwall Hospitals Trust
About this trial
Hearing loss affects approximately 11 million people in the UK, while tinnitus impacts around 7 million. Both conditions can significantly reduce quality of life and are linked to poorer mental health and employment challenges. Each year, tinnitus alone accounts for more than one million GP appointments, and patients referred to hospital ear, nose and throat (ENT) services often face long delays, sometimes exceeding a year, before their first assessment.
To address this demand, the Royal Cornwall Hospitals NHS Trust has developed a virtual ENT clinic. Patients undergo a validated hearing test in person and complete online questionnaires. Clinicians then review these data to determine next steps, which may include discharge with advice, referral for imaging, or a face-to-face consultation. Initial trials demonstrated that the majority of patients could be managed virtually, substantially reducing waiting times. However, clinicians must still review every case, limiting capacity for patients who require direct care.
This project builds on the virtual clinic by introducing artificial intelligence (AI) to support the assessment process. Using explainable AI methods, the system will be trained to replicate clinician-level decision-making while providing transparent reasoning for its recommendations. The study will evaluate how closely AI-generated outcomes align with clinician assessments, with all cases continuing to receive a clinician's final review. Clinicians will not be aware of the recommendations produced by the AI tool, but the study aims to measure how concordant AI recommendations are with clinician assessments.
If the AI tool's clinical recommendations closely align with clinician recommendations (the gold standard for care), the AI tool could be introduced as a clinical recommendation assistant tool, streamlining the triage and management of hearing loss and tinnitus, enabling clinicians to focus on complex cases, accelerating access to care, and improving efficiency.
Eligibility criteria
This trial does not accept healthy volunteersQualifiers
Patients assessed in the RCHT virtual hearing loss and tinnitus clinic.
Presenting symptoms of hearing loss and/or tinnitus.
Ability to provide informed consent to participate in the study.
Disqualifiers
Individuals under 18 years of age.
Patients unable to provide informed consent.
Patients without sufficient English proficiency where translation services cannot be arranged.
Cases where data quality is insufficient for analysis.
Trial population
The study population comprises adult patients managed through the virtual hearing loss and tinnitus clinic, in the Ear, Nose and Throat Department at the Royal Cornwall Hospitals Trust. Patients included are seen in the virtual clinic during the study period, as well as clinical staff involved in reviewing and making decisions within the service. Patient data are analysed observationally, and a subset of patients and clinicians may be invited to provide questionnaire or interview data to explore experiences of the AI-assisted clinic. Patients will comprise of those living in the county of Cornwall and considered under the care of the Royal Cornwall Hospitals Trust.
Trial design
Design model
Other
Time perspective
Other
Treatments tested in this trial
Artificial Intelligence (AI) Assisted Clinical Decision Support Tool for managing Hearing Loss and Tinnitus
DeviceAn explainable AI-based clinical decision support tool within an existing virtual hearing loss and tinnitus clinic. The tool provides non-binding triage and investigation recommendations based on routinely collected patient data, with all final clinical decisions remaining the responsibility of the clinician and no change to standard care pathways
Treatment groups
1,500 Participants
are divided into 3 treatment groupsGroup A: Phase 1 - Patients undergoing the standard virtual hearing loss and tinnitus clinic1 intervention
Group B: Phase 2 - Patients undergoing the AI-assisted virtual hearing loss and tinnitus clinic1 intervention
Group C: Phase 2 - Staff involved in providing an AI-assisted virtual hearing loss and tinnitus clinic1 intervention
Trial outcomes
Primary outcomes
1
MRI internal auditory meatus (IAM) referral recommendation
Agreement between the clinical outcomes generated by the AI clinical decision support system and the clinician-derived "gold standard" outcomes within the virtual hearing loss and tinnitus clinic. Agreement will be evaluated for: MRI internal auditory meatus (IAM) referral recommendation (binary outcome: yes/no). Agreement will be quantified using sensitivity and specificity with 95% confidence intervals, derived from contingency tables and one-vs-rest analyses for categorical outcomes, as specified in the statistical analysis plan.
Time frame
March 2026 - August 20262
Clinical triage outcome
Agreement between the clinical outcomes generated by the AI clinical decision support system and the clinician-derived "gold standard" outcomes within the virtual hearing loss and tinnitus clinic. Agreement will be evaluated for: Clinical triage outcome (categorical outcome: refer to face-to-face ENT clinic, refer to audiology, refer to audiology plus hearing therapy, or discharge). Agreement will be quantified using sensitivity and specificity with 95% confidence intervals, derived from contingency tables and one-vs-rest analyses for categorical outcomes, as specified in the statistical analysis plan.
Time frame
March 2026 - August 2026Secondary outcomes
1
Patient experience and satisfaction with the AI-assisted virtual hearing loss and tinnitus clinic
Patient experience and satisfaction with the AI-assisted virtual hearing loss and tinnitus clinic, assessed using structured satisfaction questionnaires administered by telephone. Outcomes will include: Quantitative measures (e.g. Likert-scale ratings of confidence, satisfaction, and acceptability), and Qualitative data from open-ended responses and semi-structured interviews, analysed using a directed content analysis informed by the NASSS framework.
Time frame
August 2026 - August 20272
Staff experience, usability, and acceptability of the AI-assisted clinical decision support system
Staff experience, usability, and acceptability of the AI-assisted clinical decision support system, explored through qualitative interviews with clinicians and relevant stakeholders involved in delivering or implementing the virtual clinic pathway.
Time frame
August 2026 - August 2027Sponsors and contacts
Click on the lead sponsor to view all of their trials.
Royal Cornwall Hospitals Trust
Lead sponsor
University of Exeter
Collaborator
University of Birmingham
Collaborator
Source ClinicalTrials.gov
This trial is not recruiting at the moment. You can still explore other options: