Development of a multimodal magnetic resonance imaging-based machine learning prediction model for flight cadets

In the realm of civil aviation, the existing methods for selecting and training flight cadets have limitations, such as long evaluation cycles and susceptibility to subjective factors. This study integrated multimodal magnetic resonance imaging (MRI) data, including structural MRI (sMRI), diffusion tensor imaging (DTI), and functional MRI (fMRI), with machine learning techniques. The aim was to construct prediction models capable of accurately differentiating flight cadets from ground cadets. Data were collected from 39 flight cadets with extensive flight training and 37 ground cadets. Representative features were meticulously extracted from each modality and fused at the feature level. Four machine learning classification algorithms, namely logistic regression (LR), random forest support vector machine and Gaussian naive Bayes were employed for model construction. Rigorous five-fold cross-validation and permutation tests were conducted to ensure model reliability. The results revealed that the multimodal fusion model (sMRI + DTI + fMRI + LR) exhibited the optimal performance, achieving an accuracy of 0.838, an area under the receiver operating characteristic curve (AUC) of 0.942, a sensitivity of 0.835, and a specificity of 0.834. Through SHapley Additive exPlanations analysis, features with high contributions to the classification were identified, which were closely associated with advanced cognitive functions, visual processing, and attention allocation. This research not only offers a novel approach for the selection and training evaluation of flight cadets but also demonstrates the potential of multimodal MRI-based machine learning models in exploring the neural mechanisms underlying flight-related skills.