Anatomical factors associated with progression of hallux valgus

Development of Hallux Valgus Classification Using Digital Foot Images with Machine Learning

Hallux valgus, a frequently seen foot deformity, requires early detection to prevent it from becoming more severe. It is a medical economic problem, so a means of quickly distinguishing it would be helpful. We designed and investigated the accuracy of an early version of a tool for screening hallux valgus using machine learning. The tool would ascertain whether patients had hallux valgus by analyzing pictures of their feet. In this study, 507 images of feet were used for machine learning. Image preprocessing was conducted using the comparatively simple pattern A (rescaling, angle adjustment, and trimming) and slightly more complicated pattern B (same, plus vertical flip, binary formatting, and edge emphasis). This study used the VGG16 convolutional neural network. Pattern B machine learning was more accurate than pattern A. In our early model, Pattern A achieved 0.62 for accuracy, 0.56 for precision, 0.94 for recall, and 0.71 for F1 score. As for Pattern B, the scores were 0.79, 0.77, 0.96, and 0.86, respectively. Machine learning was sufficiently accurate to distinguish foot images between feet with hallux valgus and normal feet. With further refinement, this tool could be used for the easy screening of hallux valgus.

Symmetry of bilateral hallux valgus deformity: A radiographic study

Hallux valgus (HV) is a common anatomical deformity leading to pain and difficulty with footwear and mobility. Bilateral HV deformity is much more common than unilateral although it remains unclear whether the severity of deformity is equal between feet. The objective was to investigate the severity and symmetry of HV in patients with bilateral symptomatic deformity presenting for surgery. Weight-bearing radiographs of patients presenting with symptomatic bilateral HV were reviewed. The hallux valgus angle (HVA) and intermetatarsal angle (IMA) were measured and classified as mild, moderate, or severe. Left-to-right comparison was undertaken to assess whether the degree of deformity was similar for each foot. The relationship between age, HVA, and IMA was also assessed. Between July 2014 and June 2020, 322 ft (161 patients with bilateral deformity) underwent corrective HV surgery. Of those, 6.8%, 64.6%, and 28.4% were classified as mild, moderate, and severe, respectively on the left side, and on the right 6.2%, 67.7%, and 26.1% were classified as mild, moderate, and severe respectively. There was no statistically significant difference between feet for either IMA (p = 0.06) or HVA (p = 0.85). There was a moderate correlation (R = 0.41, p ≤ 0.001) between HVA and IMA. There was only a 'weak' or 'very weak' correlation between age and HVA or IMA. Patients presenting for surgery with symptomatic bilateral HV have symmetrical moderate radiographic deformity at the time they present for consideration of surgical intervention.