Artificial Intelligence

1. What is Artificial Intelligence (AI)?

Also known as Machine Learning (ML), AI is the empowerment of computer systems to be able to perform tasks requiring human intelligence. Examples of this include speech recognition, translation between languages and visual perception. From an orthopaedic perspective, the ability for a computer to recognise failing implants, such as total hip replacements, from x-ray’s could revolutionise the investigation and management of patients who have failing total hip replacements.

 2. How could AI could be used in the next generation of orthopaedic diagnostics?

From a medical perspective, AI is now able to identify pathological changes in breast cancer and diabetic retinopathy. It is also being applied to predicting epileptic seizures from EEGs, diagnosing fractures, investigating sport performance, and in orthopaedics, predicting cartilage failure.

In 2005, Baldisserotto first proposed the use of AI to detect early failure of dental implants. Since then, however, there has been little progress in detecting failing orthopaedic implants. At present, patients with loose hip implants may have pain. The diagnosis can be confirmed by changes seen on serial radiographs; a process which can sometime take months or years because changes can be subtle. This is because, assessing minor temporal changes in position of a joint replacement using serial radiographs can be difficult. ML could achieve comparisons between one radiograph and another, taken at a different time point, with a high degree of accuracy and reliability. Quicker confirmation as to whether an implant is loose would also benefit the patient in this situation. Furthermore, a significant number of patients with pain following hip replacement have radiographs that fail to show a loose implant.

Early detection, or the ability to predict loosening, would benefit the rapid development of better designed hip replacements. Currently, the use of newly designed hip replacements needs to be followed up for 10 years.

3.Why is South West London Elective Orthopaedic Centre (SWLEOC) well placed to undertake research into Artificial Intelligence for osteoarthritis?

Scientific evidence is needed to confirm that AI does work and that it is safe, reliable and effective at making diagnosis.

 Our research centre at SWLEOC is world renowned for measuring outcomes following joint replacements and is the largest joint replacement centre in the UK. It undertakes 3,500 joint replacements annually and currently carrying out surveillance studies for several new hip replacement implants. SWLEOC is well positioned to provide a large volume of x-rays data for AI research projects.

SWLEOC currently boasts some of the most advanced imaging technology, software for data collection and patient outcome analysis. It is supported by a solid infrastructure of surgeons and dedicated research fellows and is a world leader in collaborative research. SWLEOC provides high quality, cost efficient, elective orthopaedic services and is ranked as one of the best in the world, and has been rated as Outstanding by the CQC. Our patients have excellent outcomes, low incidence of post-operative complications, and high patient satisfaction.

From a scientific perspective, the high volume of patients, robust scientific approach and emphasis on patient safety mean that SWLEOC is positioned as a centre of excellence for AI development.