# Biomechanical comparison of two surgical methods for Hallux Valgus deformity: Exploring the use of artificial neural networks as a decision-making tool for orthopedists

## TL;DR

This study explores using artificial neural networks to help orthopedists choose the best surgical method for Hallux Valgus deformity based on gait parameters.

## Contribution

The study introduces a novel use of artificial neural networks to classify and recommend surgical approaches for Hallux Valgus.

## Key findings

- Neural networks achieved 100% accuracy in classifying patients based on their surgical method.
- Mismatch cases were identified between surgeon decisions and neural network recommendations.
- Postoperative gait parameters strongly correlate with the type of surgery performed.

## Abstract

Hallux Valgus foot deformity affects gait performance. Common treatment options include distal oblique metatarsal osteotomy and chevron osteotomy. Nonetheless, the current process of selecting the appropriate osteotomy method poses potential biases and risks, due to its reliance on subjective human judgment and interpretation. The inherent variability among clinicians, the potential influence of individual clinical experiences, or inherent measurement limitations may contribute to inconsistent evaluations. To address this, incorporating objective tools like neural networks, renowned for effective classification and decision-making support, holds promise in identifying optimal surgical approaches. The objective of this cross-sectional study was twofold. Firstly, it aimed to investigate the feasibility of classifying patients based on the type of surgery. Secondly, it sought to explore the development of a decision-making tool to assist orthopedists in selecting the optimal surgical approach. To achieve this, gait parameters of twenty-three women with moderate to severe Hallux Valgus were analyzed. These patients underwent either distal oblique metatarsal osteotomy or chevron osteotomy. The parameters exhibiting differences in preoperative and postoperative values were identified through various statistical tests such as normalization, Shapiro-Wilk, non-parametric Wilcoxon, Student t, and paired difference tests. Two artificial neural networks were constructed for patient classification based on the type of surgery and to simulate an optimal surgery type considering postoperative walking speed. The results of the analysis demonstrated a strong correlation between surgery type and postoperative gait parameters, with the first neural network achieving a remarkable 100% accuracy in classification. Additionally, cases were identified where there was a mismatch with the surgeon’s decision. Our findings highlight the potential of artificial neural networks as a complementary tool for surgeons in making informed decisions. Addressing the study’s limitations, future research may investigate a wider range of orthopedic procedures, examine additional gait parameters and use more diverse and extensive datasets to enhance statistical robustness.