OpRESTORE AI-Patient Navigator Study

NCT07474584 | Not Yet Recruiting

• 2 other identifiers: 199335OpRESTORE number
• Study Type: interventional
• Target: 1,389
• Locations: 1 country
• Sites: 1

Brief Summary

OpRESTORE is a national NHS service that supports UK veterans with complex physical health problems linked to their military service. Veterans referred to OpRESTORE often need care from many different specialists, including surgeons, pain teams, rehabilitation, and mental health services. Currently, decisions about which service is most appropriate are made by a multidisciplinary team (MDT) of clinicians. While effective, this process can be slow, resource-intensive, and sometimes difficult for patients to navigate. This study will develop and test a new digital "navigator" tool that uses artificial intelligence (AI) to support these referral decisions. The aim is to see whether the tool can safely and accurately match veterans to the right care pathway, while reducing delays and improving patient experience. The project will be carried out in several stages:

• Reviewing past OpRESTORE records to design the AI model.
• Testing the tool alongside the MDT ("shadow testing") to check whether its recommendations match the clinical decisions.
• Running a case-control study to compare outcomes between patients referred using AI support and those referred by the MDT alone.
• Creating and testing a structured self-referral form to make it easier for veterans to access care directly. The main outcome will be whether the AI tool makes the same referral decisions as the MDT. Other outcomes include patient satisfaction, quality of life, time taken to reach the right service, and overall costs. The study will recruit veterans aged 18 or older who are referred to OpRESTORE with a physical health need. It will run for two years. If successful, this approach could free up clinician time, shorten waits for treatment, and improve veterans' health and wellbeing, while laying the foundations for wider use of AI-supported navigation across the NHS.

Conditions

Veteran

Keywords

healthcare navigation; veteran healthcare; clinical AI

Outcome Measures

Primary Outcomes (1)

• Algorithm concordance against control

  Concordance between algorithm-generated care-pathway recommendations and multidisciplinary team (MDT) decisions. MDT decisions determine the most appropriate treatment pathway and are recorded in the MDT summary document and referral tracking database. Pathways correspond to specific NHS or third-sector services grouped into categories and subcategories (e.g., orthopaedic surgery clinic by joint; ENT services subdivided into ENT clinic or audiology; pain services subdivided into NHS clinics, named consultants, or third-sector programmes). Algorithm outputs are compared with MDT decisions and classified as: full match (category and subcategory), category match only, incorrect recommendation, or referral to MDT due to low algorithm confidence.

  At completion of both MDT decision and algorithm output generation (whichever occurs later), typically 8 weeks post-referral for prospective cases or after algorithm processing for retrospective data.

Secondary Outcomes (6)

• Patient Reported Outcomes (EQ5D-5L)

  From recruitment to 6 months post recruitment.

• Referral accuracy

  At the point of outcome decision compared to expert input within 3 months of referral.

• Patient reported experience measures

  From referral to 6 months post referral

• Pathway time efficiency

  From referral receipt to treatment pathway decision (algorithm-generated recommendation or MDT decision), up to 6 months.

• Cost per referral episode

  From referral until discharge from the service (typical no longer than 6 months).

Other Outcomes (1)

• Suitability for amputees

  Assessed after MDT outcome generated and for a period of 3 months after.

Study Arms (2)

Standard care - MDT pathway

ACTIVE COMPARATOR

The patient will run in the current OpRESTORE pathway. This means manual processing of their referral by the OpRESTORE healthcare navigation team, summarising of the medical picture, discussion at a multidisciplinary team meeting and agreement on a treatment outcome.

Other: OpRESTORE healthcare navigation

AI-OpRESTORE - automated pathway

EXPERIMENTAL

In this pathway data is automatically gathered from the patients themselves through self-referral, automated screening of their medical record and only where needed human input (by members of the OpRESTORE clinical team) or additional information. This information is then run through the outcome predicting algorithm which decides on a treatment outcome. The decision is consider final but for the purpose of this study is reviewed by members of the clinical team and clinical members of the research team to ensure clinical coherence and avoid harm to participants.

Other: AI-OpRESTORE healthcare navigator

Interventions

AI-OpRESTORE healthcare navigator OTHER

An algorithm is developed as part of this study that predicts a patients best treatment pathway based on basic demographic variables, targeted clinical questions and prior clinical records. This is the first version of this algorithm in development built on UK OpRESTORE veteran data and tested on this same population.

AI-OpRESTORE - automated pathway

OpRESTORE healthcare navigation OTHER

This is the current standard of care which is a human healthcare navigation pathway where information is extracted manually, and cases are discussed at the opRESTORE MDT for UK veterans.

Standard care - MDT pathway

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Meets criteria for referral to OpRESTORE service
• Age 18 years or older.
• Capacity to consent.
• Have a physical health need (e.g. not purely mental health, or seeking social care advice)

You may not qualify if:

• Referrals processed outside standard MDT workflow.
• Patients lacking capacity to consent.
• Prisoners.
• Acute presentation best managed by emergency services and not appropriate for OpRESTORE.

Sponsors & Collaborators

• Imperial College Healthcare NHS Trust: lead

Study Sites (1)

OpRESTORE, Imperial College Healthcare NHS trust

London, W2 1NY, United Kingdom

Location

Related Publications (24)

• Large O, Ward D, Refsum C, Atkinson I. Preparing the NHS for the AI Era: Why Smarter Triage and Navigation Mean Better Health Care. 2025.

  BACKGROUND

• FIT FOR THE FUTURE 10 Year Health Plan for England Executive Summary. 2025.

  BACKGROUND

• NHS England. Delivery plan for recovering access to primary care: update and actions for 2024-25 [Internet]. 2024 [cited 2024 Nov 5]. Available from: https://www.england.nhs.uk/long-read/delivery-plan-for-recovering-access-to-primary-care-update-and-actions-for-2024-25/

  BACKGROUND

• Hill A, Morrissey D, Marsh W. "It's the future, come on!": a think aloud study exploring clinicians' use of knowledge-based AI decision support. Int J Med Inform. 2025 Dec;204:106089. doi: 10.1016/j.ijmedinf.2025.106089. Epub 2025 Aug 21.

  PMID: 40850289 BACKGROUND

• Moser EC, Narayan G. Improving breast cancer care coordination and symptom management by using AI driven predictive toolkits. Breast. 2020 Apr;50:25-29. doi: 10.1016/j.breast.2019.12.006. Epub 2020 Jan 21.

  PMID: 31978814 BACKGROUND

• D'Amours G, Clausen M, Luca S, Reble E, Kodida R, Assamad D, Bernier F, Chad L, Costain G, Dhalla I, Faghfoury H, Friedman JM, Hewson S, Jamieson T, Silver J, Shuman C, Osmond M, Carroll JC, Jobling R, Laberge AM, Aronson M, Liston E, Lerner-Ellis J, Marshall C, Brudno M, Pham Q, Rudzicz F, Cohn R, Mamdani M, Smith M, Shastri-Estrada S, Seto E, Thorpe K, Ungar W, Hayeems RZ, Bombard Y. Genetics Navigator: protocol for a mixed methods randomized controlled trial evaluating a digital platform to deliver genomic services in Canadian pediatric and adult populations. BMJ Open. 2024 Sep 3;14(9):e090084. doi: 10.1136/bmjopen-2024-090084.

  PMID: 39231549 BACKGROUND

• Puthenpura V, Hunter M, Marks AM. "Techquity" in Pediatric, Adolescent, and Young Adult Oncology: Addressing Inequities Through Artificial Intelligence and Immersive Technologies. Pediatr Blood Cancer. 2025 Oct;72(10):e31909. doi: 10.1002/pbc.31909. Epub 2025 Jul 18.

  PMID: 40879575 BACKGROUND

• Sripa P, Hayhoe B, Garg P, Majeed A, Greenfield G. Impact of GP gatekeeping on quality of care, and health outcomes, use, and expenditure: a systematic review. Br J Gen Pract. 2019 May;69(682):e294-e303. doi: 10.3399/bjgp19X702209. Epub 2019 Mar 25.

  PMID: 30910875 BACKGROUND

• Ntais C, Kontodimopoulos N, Talias MA. Gatekeeping or Provider Choice for Sustainable Health Systems? A Literature Review on Their Impact on Efficiency, Access, and Quality of Services. J Mark Access Health Policy. 2024 Dec 6;12(4):378-387. doi: 10.3390/jmahp12040029. eCollection 2024 Dec.

  PMID: 39735248 BACKGROUND

• Naylor MD, Brooten DA, Campbell RL, Maislin G, McCauley KM, Schwartz JS. Transitional care of older adults hospitalized with heart failure: a randomized, controlled trial. J Am Geriatr Soc. 2004 May;52(5):675-84. doi: 10.1111/j.1532-5415.2004.52202.x.

  PMID: 15086645 BACKGROUND

• Rajabiun S, Cabral HJ, Chen CA, Lloyd-Travaglini C, Dugas JN, Amburgey D, Fitzgerald M, Lemon SC, Haas JS, Freund KM, Battaglia T; TRIP Consortium. Cost and activity analysis for a citywide patient navigation intervention to engage underserved patients in breast cancer treatment: Findings from the Translating Research Into Practice study. Cancer. 2025 Jan 1;131(1):e35671. doi: 10.1002/cncr.35671.

  PMID: 39748471 BACKGROUND

• Orme S, Zarkin GA, Dunlap LJ, Nordeck CD, Schwartz RP, Mitchell SG, Welsh C, O'Grady KE, Gryczynski J. Cost and Cost Savings of Navigation Services to Avoid Rehospitalization for a Comorbid Substance Use Disorder Population. Med Care. 2022 Aug 1;60(8):631-635. doi: 10.1097/MLR.0000000000001743. Epub 2022 Jun 10.

  PMID: 35687900 BACKGROUND

• Mullangi S, Worland SC, Dharmarajan K, Green RJ, Sachdeva K, Johnstone D, et al. Reduction in cancer spending due to patient navigation. JCO Oncol Pract. 2023 Nov;19(11_suppl):557-557.

  BACKGROUND

• Le Berre M, Maimon G, Sourial N, Gueriton M, Vedel I. Impact of Transitional Care Services for Chronically Ill Older Patients: A Systematic Evidence Review. J Am Geriatr Soc. 2017 Jul;65(7):1597-1608. doi: 10.1111/jgs.14828. Epub 2017 Apr 12.

  PMID: 28403508 BACKGROUND

• Manderson B, McMurray J, Piraino E, Stolee P. Navigation roles support chronically ill older adults through healthcare transitions: a systematic review of the literature. Health Soc Care Community. 2012 Mar;20(2):113-27. doi: 10.1111/j.1365-2524.2011.01032.x. Epub 2011 Oct 13.

  PMID: 21995806 BACKGROUND

• Ranaghan C, Boyle K, Meehan M, Moustapha S, Fraser P, Concert C. Effectiveness of a patient navigator on patient satisfaction in adult patients in an ambulatory care setting: a systematic review. JBI Database System Rev Implement Rep. 2016 Aug;14(8):172-218. doi: 10.11124/JBISRIR-2016-003049.

  PMID: 27635752 BACKGROUND

• Bush ML, Kaufman MR, Shackleford T. Adherence in the Cancer Care Setting: a Systematic Review of Patient Navigation to Traverse Barriers. J Cancer Educ. 2018 Dec;33(6):1222-1229. doi: 10.1007/s13187-017-1235-2.

  PMID: 28567667 BACKGROUND

• Robinson-White S, Conroy B, Slavish K, Rosenzweig M. Patient Navigation in Breast Cancer: A Systematic Review. Cancer Nurs [Internet]. 2010;33(2). Available from: http://journals.lww.com/cancernursingonline

  BACKGROUND

• Desveaux L, McBrien K, Barnieh L, Ivers NM. Mapping variation in intervention design: a systematic review to develop a program theory for patient navigator programs. Syst Rev. 2019 Jan 8;8(1):8. doi: 10.1186/s13643-018-0920-5.

  PMID: 30621796 BACKGROUND

• Roland KB, Milliken EL, Rohan EA, DeGroff A, White S, Melillo S, Rorie WE, Signes CC, Young PA. Use of Community Health Workers and Patient Navigators to Improve Cancer Outcomes Among Patients Served by Federally Qualified Health Centers: A Systematic Literature Review. Health Equity. 2017 May 1;1(1):61-76. doi: 10.1089/heq.2017.0001. eCollection 2017.

  PMID: 28905047 BACKGROUND

• McBrien KA, Ivers N, Barnieh L, Bailey JJ, Lorenzetti DL, Nicholas D, Tonelli M, Hemmelgarn B, Lewanczuk R, Edwards A, Braun T, Manns B. Patient navigators for people with chronic disease: A systematic review. PLoS One. 2018 Feb 20;13(2):e0191980. doi: 10.1371/journal.pone.0191980. eCollection 2018.

  PMID: 29462179 BACKGROUND

• Genoff MC, Zaballa A, Gany F, Gonzalez J, Ramirez J, Jewell ST, Diamond LC. Navigating Language Barriers: A Systematic Review of Patient Navigators' Impact on Cancer Screening for Limited English Proficient Patients. J Gen Intern Med. 2016 Apr;31(4):426-34. doi: 10.1007/s11606-015-3572-3. Epub 2016 Jan 19.

  PMID: 26786875 BACKGROUND

• Budde H, Williams GA, Winkelmann J, Pfirter L, Maier CB. The role of patient navigators in ambulatory care: overview of systematic reviews. BMC Health Serv Res. 2021 Oct 28;21(1):1166. doi: 10.1186/s12913-021-07140-6.

  PMID: 34706733 BACKGROUND

• Ali-Faisal SF, Colella TJ, Medina-Jaudes N, Benz Scott L. The effectiveness of patient navigation to improve healthcare utilization outcomes: A meta-analysis of randomized controlled trials. Patient Educ Couns. 2017 Mar;100(3):436-448. doi: 10.1016/j.pec.2016.10.014. Epub 2016 Oct 17.

  PMID: 27771161 BACKGROUND

Study Officials

• Shehan Hettiaratchy, FRCS MD

  Imperial College Healthcare NHS Trust

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Natalia L Sanchez-Thompson, MRCS MSc

CONTACT

+447791700255; natalia.sanchez-thompson@nhs.net

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: PARTICIPANT
• Purpose: HEALTH SERVICES RESEARCH
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Model Details: * Prospective 50:50 randomisation within a single pathology group. * The intervention group will undergo algorithm-supported triage and referral, while the control group will follow standard MDT-led referral. * Each algorithm-generated output will be reviewed by a triage nurse (as per current practice) and a second independent clinician from the research team. If there are concerns about the appropriateness of the recommendation, the case will be referred to the MDT. * In such cases, the final MDT outcome will serve as the reference standard to determine whether the algorithm's recommendation was appropriate. * Blinding is not possible in this phase due to the nature of the intervention. * Given the speed of algorithmic processing, no delays in patient care are anticipated, though this will be actively monitored and reported.

Study Record Dates

• First Submitted: March 4, 2026
• First Posted: March 16, 2026
• Study Start: May 1, 2026
• Primary Completion (Estimated): May 1, 2027
• Study Completion (Estimated): November 1, 2027
• Last Updated: March 16, 2026

Record last verified: 2026-03

Data Sharing

• IPD Sharing: Will not share

Locations

GB (1)