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
To assess if older symptomatic children with club foot deformity differ in perceived disability and foot function during gait, depending on initial treatment with Ponseti or surgery, compared to a control group. Second aim was to investigate correlations between foot function during gait and perceived disability in this population. In all, 73 children with idiopathic club foot were included: 31 children treated with the Ponseti method (mean age 8.3 years; 24 male; 20 bilaterally affected, 13 left and 18 right sides analyzed), and 42 treated with primary surgical correction (mean age 11.6 years; 28 male; 23 bilaterally affected, 18 left and 24 right sides analyzed). Foot function data was collected during walking gait and included Oxford Foot Model kinematics (Foot Profile Score and the range of movement and average position of each part of the foot) and plantar pressure (peak pressure in five areas of the foot). Oxford Ankle Foot Questionnaire, Disease Specific Index for club foot, Paediatric Quality of Life Inventory 4.0 were also collected. The gait data were compared between the two club foot groups and compared to control data. The gait data were also correlated with the data extracted from the questionnaires.Aims
Methods
