Evaluation of Dora Care for Supporting Fracture Liaison Services (FLS)

A Prospective, Mixed-Methods Feasibility Study to Evaluate the Agreement, Safety, and Acceptability of 'Dora Care', an Automated AI Voice Assistant, for Supporting Clinical Pathways in a Fracture Liaison Service.

What is the study about? This study is testing "Dora", an AI-powered assistant that can make phone calls to patients, for use in the Fracture Liaison Service (FLS). The FLS is a clinic that helps prevent more bone fractures after an initial "fragility fracture" (a break that happens easily, usually due to osteoporosis).

Why is this being done? FLS clinicians often have to spend a lot of time on routine phone calls for assessments and follow-ups. If Dora can safely and accurately collect patient information, it might save time for staff and still give patients a good experience.

What will happen to patients in the study? Invitation and consent - Patients with a new fragility fracture who are eligible will be invited to take part after informed consent.

Dora call - Patients will receive an automated phone call from Dora, at the start of their FLS pathway and at follow-up.

At intake, Dora will ask about risk factors for bone problems (e.g., smoking, alcohol use, family fracture history).

At follow-up, Dora will ask about medication use, side effects, falls, or new fractures.

Clinician call - Soon after, patients will have their usual phone appointment with an FLS clinician, who asks similar questions.

Surveys/interviews - Patients will be asked to complete a short questionnaire and take part in an optional interview to say how they felt about talking to Dora.

What about clinicians? Clinicians involved in the FLS pathway will be asked to complete a short survey and to take part in an optional interview to understand how useful Dora's reports might be in their work.

Who can take part? Patients - Age 50+, English-speaking, with a new fragility fracture, and able to use the phone.

Clinicians - Those working in FLS or similar bone health services. How long will it take? Each patient might be involved for up to about 7 months. The whole study will take about a year.

Study Overview

• Status: Not yet recruiting
• Conditions: Osteoporosis; Telemedicine; Bone Health; Outpatient; Automation; AI (Artificial Intelligence); Risk Assesment
• Intervention / Treatment: Device: Dora call

Detailed Description

Fragility fractures are common and are associated with substantial morbidity, mortality, and healthcare costs. Fracture Liaison Services (FLS) are internationally recognised as an effective model for secondary fracture prevention; however, FLS pathways can be resource-intensive and place a significant burden on clinical staff, particularly for standardised intake risk assessment and longer-term follow-up conversations related to medication adherence, side effects, and interval clinical events.

Dora Care is a cloud-based, standalone software product that delivers automated natural-language telephone calls to patients using an AI voice assistant. Dora Care can be configured to conduct structured clinical or administrative conversations where a validated protocol exists and returns a structured summary of the interaction for healthcare teams to review. Dora Care is not intended for clinical diagnosis and, in this study, is used as an adjunct to standard Fracture Liaison Service care rather than a replacement for clinician review.

This prospective, mixed-methods feasibility study evaluates whether Dora Care can support elements of the FLS pathway by assessing agreement between patient-reported information collected by Dora Care and information collected by an FLS clinician during routine care, evaluating safety when Dora Care is deployed in this context, and exploring acceptability and usability for both patients and clinicians.

Study design and setting This is a prospective, single-arm feasibility study conducted in NHS hospital-based Fracture Liaison Services, initially at University College London Hospitals NHS Foundation Trust, with additional potential recruitment sites. All patient participants receive a Dora Care telephone call in addition to their routine FLS telephone consultation.

The study includes two linked components:

Patient pathway component (live, within routine care): Patients receive an automated Dora Care call followed by their standard clinician-led FLS telephone consultation. Patient-reported questionnaires are collected after Dora Care interactions, and a subset of participants is invited to take part in qualitative interviews.

Clinician usability component (simulated): Clinicians review anonymised, mock Dora Care outputs derived from the study and provide feedback via questionnaires and interviews. This component is conducted separately from live patient care to broaden clinician participation and minimise patient safety risk.

Interventions and procedures Participants may contribute data at one or more routine FLS timepoints, including an intake assessment and follow-up assessments during ongoing management.

Prior to the standard clinician consultation, Dora Care conducts an automated telephone call to collect patient-reported information relevant to the FLS pathway. Following the Dora Care call, patients proceed with their routine clinician-led FLS consultation, during which clinicians independently collect and document clinical information as part of standard care. Clinicians are aware that a Dora Care call has taken place but are not provided with Dora Care outputs for the purposes of agreement evaluation.

Patients are invited to complete usability and satisfaction questionnaires following Dora Care interactions, and a subset of patients participates in semi-structured qualitative interviews to explore experience and acceptability. Clinicians participating in the usability component complete questionnaires and interviews based on simulated review of Dora Care outputs.

Data collection and ethics Data are collected from Dora Care call outputs, routine clinician documentation within electronic health records, and participant-completed questionnaires and interviews. Data are pseudonymised and handled in accordance with the Declaration of Helsinki, Good Clinical Practice, ISO 14155:2020, the UK Data Protection Act 2018, and UK GDPR.

The study is conducted as an adjunct to standard care, and participants retain access to usual clinical support throughout. Ethical approval and relevant NHS governance approvals are obtained prior to study initiation, and device-related adverse events and device deficiencies are monitored and reported in accordance with regulatory requirements.

• Study Type: Interventional
• Enrollment (Estimated): 217
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Ernest Lim, MBBS, BSC; Phone Number: +447585554340; Email: el@ufonia.com
• Study Contact Backup: Name: Ellie C Hawkins, MSc; Phone Number: +447780951175; Email: ech@ufonia.com

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

• Access to and ability to use a telephone for automated conversations as part of a routine, FLS phone pathway. This includes patients who are:
• Adults aged ≥50 years.
• Presenting with a new fragility fracture requiring FLS assessment.
• Able to provide informed consent.
• English speaking.
• Reside in the UK.

Exclusion Criteria:

• Severe cognitive impairment precluding meaningful telephone interaction or informed consent.
• Patients already established on long-term osteoporosis treatment.
• Terminal illness with a life expectancy <12 months.
• Current participation in another clinical trial altering standard of care thus altering the care schedule.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Other
• Allocation: N/A
• Interventional Model: Single Group Assignment
• Masking: None (Open Label)

Number of Arms

1

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: Patient population receiving Dora call; Patient participant will receive a Dora call in addition to their standard care clinical appointment call	Device: Dora call; Patient participant will recieve a Dora call in addition to their standard clinical care telephone appointment

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Agreement (concordance) between Dora Care and clinician-collected data (Intake and Follow-up)	Concordance for predefined variables collected by Dora Care versus those routinely collected by an FLS clinician during baseline care consultation (slot-level agreement; categorical variables via % agreement and Cohen's kappa; continuous variables via ICC and/or Bland-Altman).	Intake assessment and Follow-up assessment (planned at 16 weeks)

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Medication adherence rate	Medication adherence rate	16 week follow up where available
Incidence of patient-reported medication side effects	Incidence and type of side effects from anti-osteoporosis medications.	16 weeks and 24 weeks
Incidence of new fragility fractures	The incidence of reports of new fragility fractures will be tabulated and presented as frequencies and percentages.	16 weeks and 24 weeks
Incidence of patient-reported falls	Incidence of falls reported by patients at follow-up, presented as frequencies and percentages.	16 weeks and 24 weeks
Patient satisfaction scores with Dora Care (adapted Client Satisfaction Questionnaire)	Patient satisfaction with the Dora Care AI assistant measured using three questions adapted from the Client Satisfaction Questionnaire (CSQ-8) on a 4-point Likert scale. Scores reported as means, standard deviations, and medians.	Baseline (intake assessment), 16 weeks, and 24 weeks
Patient usability scores (System Usability Scale)	10-item System Usability Scale (SUS) on a 5-point Likert scale, reported as means, standard deviations, medians, and ranges.	Baseline (intake assessment), 16 weeks and 24 weeks
Qualitative themes from patient interviews on experience and acceptability of Dora Care	Thematic analysis of semi-structured interviews identifying patterns related to usability, acceptability, and perceived impact of Dora Care on the FLS patient journey.	Through study completion, an average of 12 months
Clinician usability scores (System Usability Scale)	10-item System Usability Scale (SUS) on a 5-point Likert scale, reported as means, standard deviations, medians, and ranges.	Through study completion, an average of 12 months
Clinician experience themes (qualitative interviews)	Thematic analysis of semi-structured interviews with FLS clinicians to identify patterns related to usability, acceptability, and perceived impact of Dora Care outputs on clinical workflow and decision-making.	Through study completion, an average of 12 months

Other Outcome Measures

Outcome Measure	Measure Description	Time Frame
Safety Monitoring: Incidence of Device-related Serious Adverse Events (SAEs)	Device-related SAEs (death, life-threatening illness, hospitalisation, permanent disability) occurring within 14 days of Dora Care call, reported as incidence per 100 calls with exact 95% CI.	Through study completion, an average of 12 months
Safety Monitoring: Missed urgent clinical conditions identified	Number of urgent clinical conditions (e.g., osteonecrosis of the jaw) not identified by Dora Care but subsequently identified during standard care clinical interaction, reported as incidence per 100 calls with exact 95% CI. Acceptance criterion: <0.5%.	Through study completion, an average of 12 months
Safety Monitoring: Privacy and data security breaches	Additional Safety Monitoring: Confidentiality violations Incidence per 100 calls ± exact 95 % CI	Through study completion, an average of 12 months
Safety Monitoring: Incidence of system failures affecting patient safety	Technical failures preventing or impeding patient assessments (e.g., call disconnections, data transfer errors, software bugs), reported as incidence per 100 calls with exact 95% CI. Acceptance criterion: <3%.	Through study completion, an average of 12 months
Safety Monitoring: Inappropriate clinical advice potentially causing harm	Number of instances where harmful advice from Dora Care led to incorrect management, reported as incidence per 100 calls with exact 95% CI. Acceptance criterion: <1%.	Through study completion, an average of 12 months

Collaborators and Investigators

• Sponsor: Ufonia
• Collaborators: University College London Hospitals; University of York
• Investigators: Study Director: Aisling Higham, FRCOphth, MSc, MBBS, Ufonia

Study record dates

Study Major Dates

• Study Start (Estimated): February 1, 2026
• Primary Completion (Estimated): August 1, 2027
• Study Completion (Estimated): December 1, 2027

Study Registration Dates

• First Submitted: January 29, 2026
• First Submitted That Met QC Criteria: March 5, 2026
• First Posted (Actual): March 11, 2026

Study Record Updates

• Last Update Posted (Actual): March 11, 2026
• Last Update Submitted That Met QC Criteria: March 5, 2026
• Last Verified: March 1, 2026

More Information

Terms related to this study

• Keywords: Telemedicine; Triage; Medical Device; Rheumatology; Bone Health; AI (Artificial Intelligence); Fracture Liason Services; Conversational AI; Telephone Consultation; Voice AI
• Additional Relevant MeSH Terms: Bone Diseases; Musculoskeletal Diseases; Metabolic Diseases; Bone Diseases, Metabolic; Nutritional and Metabolic Diseases; Osteoporosis
• Other Study ID Numbers: DORA-FLS-CIP/v1.5; 362559 (Other Identifier: IRAS); 10102111 (Other Grant/Funding Number: Innovate UK)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No