The use of technology to assess balance and alignment during total knee surgery can provide an overload of numerical data to the surgeon. Meanwhile, this quantification holds the potential to clarify and guide the surgeon through the surgical decision process when selecting the appropriate bone recut or soft tissue adjustment when balancing a total knee. Therefore, this paper evaluates the potential of deploying supervised machine learning (ML) models to select a surgical correction based on patient-specific intra-operative assessments. Based on a clinical series of 479 primary total knees and 1,305 associated surgical decisions, various ML models were developed. These models identified the indicated surgical decision based on available, intra-operative alignment, and tibiofemoral load data.Aims
Methods
Surgeons need to be able to measure angles and distances in three dimensions in the planning and assessment of knee replacement. Computed tomography (CT) offers the accuracy needed but involves greater radiation exposure to patients than traditional long-leg standing radiographs, which give very little information outside the plane of the image. There is considerable variation in CT radiation doses between research centres, scanning protocols and individual scanners, and ethics committees are rightly demanding more consistency in this area. By refining the CT scanning protocol we have reduced the effective radiation dose received by the patient down to the equivalent of one long-leg standing radiograph. Because of this, it will be more acceptable to obtain the three-dimensional data set produced by CT scanning. Surgeons will be able to document the impact of implant position on outcome with greater precision.
