Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

  • Project No: NDORMS-2025/13
  • Intake: 2025

PROJECT OVERVIEW

Vertebral fractures (VFs) in adults over 50 years lead to reduced quality life, increased mortality and are strongly associated with osteoporosis and the risk of further fractures. While older adults with fractures at other sites such as the hip, shoulder, and wrist present to acute services for care and can be readily identified to be checked and managed for osteoporosis, most patients with vertebral fractures remain undiagnosed and go on to have further fractures. We know now around 10% of all CT scans that include the thoracic or lumbar spine will demonstrate vertebral fractures but less than 50% are reported and less than 10% lead to improvement in patient care.

A typical large hospital will have 50,000 to 150,000 CT scans per year in this age group and it is not possible to re-read these scans manually to find those with a VF. Artificial intelligence (AI) algorithms offer the opportunity to efficiently review 100,000 CTs scan rapidly to identify those with probable VF and flag these patients for more detailed clinical care. However, there is no evidence for the scale of benefits to patients and healthcare systems if a hospital uses AI to do this. This information is needed to justify the costs from using the AI and associated increase in patient assessments and treatments.

The ADOPT study has been set up with an NIHR grant to better understand the implementation challenges, clinical and cost effectiveness for using AI in the fracture setting. ADOPT has successfully implemented AI into 3 NHS hospitals to detect VFs and refer the patients for osteoporosis care and will describe the expected number of fractures avoided using the number of patients identified and recommended treatment using health economic models.

This DPhil will extend follow-up of these patient to compare the expected with the observed clinical and cost effectiveness using a matched historical control cohort within existing ethical approval. The specific objectives are:

  1. Systematic review of the clinical and cost benefits of Artificial Intelligence of Vertebral fractures
  2. Impact of AI on observed vs expected clinical outcomes using historical controls in Fracture Liaison Service (FLS) setting: 1 to 3 years follow-up
  3. Impact of AI on observed vs expected cost effective outcomes using historical controls in FLS setting: 1 to 3 years follow-up
  4. Description of barriers / challenges/ threats for sustained adoption of AI-enabled FLS in the NHS setting from perspectives of patients, clinicians and commissioners.

This DPhil project offers a unique opportunity to link AI methodologies with the integration of patient reported outcomes, hospital data sources including health economic data and implementation barriers to address a major challenge facing the NHS and healthcare systems across the globe.

TRAINING OPPORTUNITIES

 

The Botnar Research Centre plays host to the University of Oxford's Institute of Musculoskeletal Sciences, which enables and encourages research and education into the causes of musculoskeletal disease and their treatment. Training will be provided in techniques including:

1.         Biostatistics and epidemiology

2.         Health economics

3.         Vertebral fracture identification

4.         Ethical, information governance and IT considerations for the use of Artificial intelligence in the routine health care

5.         Qualitative methods

6.         Implementation science

A core curriculum of lectures will be taken in the first term to provide a solid foundation in a broad range of subjects including musculoskeletal biology, inflammation, epigenetics, translational immunology, data analysis and the microbiome.  Students will also be required to attend regular seminars within the Department and those relevant in the wider University.

Students will be expected to present data regularly in Departmental seminars and to attend external conferences to present their research globally, with limited financial support from the Department.

Students will also have the opportunity to work closely with the Pharmaco- and Device Epidemiology Group. Pharmaco- and Device epidemiology — Nuffield Department of Orthopaedics, Rheumatology and Musculoskeletal Sciences (ox.ac.uk)

Students will have access to various courses run by the Medical Sciences Division Skills Training Team and other Departments. All students are required to attend a 2-day Statistical and Experimental Design course at NDORMS and run by the IT department (information will be provided once accepted to the programme).

KEY PUBLICATIONS

1.         Mitchell RM, Jewell P, Javaid MK, McKean D, Ostlere SJ. Reporting of vertebral fragility fractures: can radiologists help reduce the number of hip fractures? Archives of osteoporosis. 2017;12(1):71. https://ncbi.nlm.nih.gov/pmc/articles/PMC5547187/pdf/11657_2017_Article_363.pdf

2.         Lems WF, Paccou J, Zhang J, Fuggle NR, Chandran M, Harvey NC, et al. Vertebral fracture: epidemiology, impact and use of DXA vertebral fracture assessment in fracture liaison services. Osteoporosis international : a journal established as result of cooperation between the European Foundation for Osteoporosis and the National Osteoporosis Foundation of the USA. 2021;32(3):399-411. 198_2020_5804_Article 1..13 (nih.gov)

3.         Drew S, Judge A, May C, Farmer A, Cooper C, Javaid MK, et al. Implementation of secondary fracture prevention services after hip fracture: a qualitative study using extended Normalization Process Theory. Implementation science : IS. 2015;10:57. Secondary prevention of fractures after hip fracture: a qualitative study of effective service delivery (nih.gov)

4.         Javaid MK, Sami A, Lems W, Mitchell P, Thomas T, Singer A, et al. A patient-level key performance indicator set to measure the effectiveness of fracture liaison services and guide quality improvement: a position paper of the IOF Capture the Fracture Working Group, National Osteoporosis Foundation and Fragility Fracture Network. Osteoporosis international : a journal established as result of cooperation between the European Foundation for Osteoporosis and the National Osteoporosis Foundation of the USA. 2020. Osteoporos Int. 2020; 31(7): 1193–1204. A patient-level key performance indicator set to measure the effectiveness of fracture liaison services and guide quality improvement: a position paper of the IOF Capture the Fracture Working Group, National Osteoporosis Foundation and Fragility Fracture Network (nih.gov)

5. Pinedo-Villanueva R, Burn E, Maronga C, Cooper C, Javaid MK. Expected Benefits and Budget Impact From a Microsimulation Model Support the Prioritization and Implementation of Fracture Liaison Services. J Bone Miner Res. 2023 Apr;38(4):499-511. doi: 10.1002/jbmr.4775. Epub 2023 Jan 31. PMID: 36662166. Expected Benefits and Budget Impact From a Microsimulation Model Support the Prioritization and Implementation of Fracture Liaison Services (wiley.com)

How to apply

Please contact the relevant supervisor(s), to register your interest in the project, and the departmental Education Team (graduate.studies@ndorms.ox.ac.uk), who will be able to advise you of the essential requirements for the programme and provide further information on how to make an official application.

Interested applicants should have, or expect to obtain, a first or upper second-class BSc degree or equivalent in a relevant subject and will also need to provide evidence of English language competence (where applicable). The application guide and form is found online and the DPhil or MSc by research will commence in October 2025.

Applications should be made to one of the following programmes using the specified course code.

D.Phil in Musculoskeletal Sciences (course code: RD_ML2)

MSc by research in Musculoskeletal Sciences (course code: RM_ML2)

 

For further information, please visit http://www.ox.ac.uk/admissions/graduate/applying-to-oxford.