An AI-driven method for total knee arthroplasty (TKA) is showing promise for patients with naturally bowed legs. Early results indicate better alignment and greater satisfaction compared to traditional methods.
The functionally aligned knee-replacement surgery technique leverages AI and robotic assistance to tailor implant positioning to each patient’s native anatomy.
In a study published in the Journal of Arthroplasty, lead author Associate Professor Simon Young from Waipapa Taumata Rau at the University of Auckland stated, ‘The results are positive for patients whose legs are naturally bowed.’
Young, an orthopaedic surgeon at Health New Zealand Te Whatu Ora Waitematā, performs surgeries at the Elective Surgery Centre on the Auckland North Shore Hospital campus.
Since 2017, the centre has employed robotic systems in knee surgeries to enhance precision, establishing the groundwork for the current innovation.
Traditional knee-replacement surgery often assumes a straight-legged alignment, which doesn’t reflect the anatomical reality for a significant subset of patients.
Young noted: ‘Around 30% of the population have bowed legs either naturally or because of conditions such as arthritis. If you look around on a football field, you will see many people who are young, fit, and healthy, who naturally have bowed legs. If, when they get older, they get arthritis and you put the new knee in straight, it will be in a position it has never been in their lives. For these people, knee replacements that assume the leg is straight may not work as well as ones that are functionally aligned.’
Young’s team created an AI algorithm that integrates with robotic surgery tools to address this mismatch.
The system analyses thousands of potential positions – between 20,000 and 25,000 – for the knee implant, based on preoperative imaging and intraoperative data, including soft tissue tension.
Young explained: ‘When we are in the operating room, we're virtually positioning the components. Then, we consider the patient’s native alignment and also their soft tissue tension. The computer model goes through and analyses the options and ranks them according to what would be optimal for that patient. We then choose what we think is the best option.’
Half of the patients underwent conventional mechanical alignment in a randomised trial involving 244 participants; one group received conventional mechanical alignment, while the other group received the AI-assisted, functionally aligned procedure. Radiographs and patient-reported outcomes were used to monitor the patients for two years.
Both groups demonstrated encouraging results, but patients with more significant natural bowing reported greater satisfaction with the functionally aligned technique.
Given the findings, Young recommends that surgeons consider a patient’s native leg shape when planning TKA. He has also developed an app for surgeons in New Zealand, Australia, and Asia to implement functional alignment in their practice. Further research is underway to refine and expand the tool.
Young said: ‘This is about personalising knee replacement to better match the individual, rather than applying a one-size-fits-all approach.’
