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
Double-level lengthening, bone transport, and bifocal compression-distraction are commonly undertaken using Ilizarov or other fixators. We performed double-level fixator-assisted nailing, mainly for the correction of deformity and lengthening in the same segment, using a straight intramedullary nail to reduce the time in a fixator. A total of 23 patients underwent this surgery, involving 27 segments (23 femora and four tibiae), over a period of ten years. The most common indication was polio in ten segments and rickets in eight; 20 nails were inserted retrograde and seven antegrade. A total of 15 lengthenings were performed in 11 femora and four tibiae, and 12 double-level corrections of deformity without lengthening were performed in the femur. The mean follow-up was 4.9 years (1.1 to 11.4). Four patients with polio had tibial lengthening with arthrodesis of the ankle. We compared the length of time in a fixator and the external fixation index (EFI) with a control group of 27 patients (27 segments) who had double-level procedures with external fixation. The groups were matched for the gain in length, age, and level of difficulty score.Aims
Patients and Methods
