JMIR Publications

ABSTRACT

Background:

Primary intracranial germ cell tumors(iGCTs) are highly malignant brain tumors that predominantly occur in children and adolescents, with an incidence rate ranking third among primary brain tumors in East Asia(8-15%). Due to their insidious onset and impact on critical functional areas of the brain, these tumors often result in irreversible abnormalities in growth and development, as well as cognitive and motor impairments in affected children. Therefore, early diagnosis is vital for improving patient outcomes and quality of life.

Objective:

This study investigates the application of facial recognition technology in the early detection of intracranial germ cell tumors (iGCTs) in children and adolescents. Early diagnosis through advanced screening techniques is vital for improving patient outcomes and quality of life.

Methods:

The study comprised the collection and division of datasets into training (n=574, iGCTs=358, control=189) and validation (n=142, iGCTs=79, control=63), with an additional independent test dataset (n=236, iGCTs=130, control=106) sourced from four medical institutions. A regression model using clinically relevant, statistically significant data was developed and combined with GVisageNet outputs to create a hybrid model. This integration sought to assess the incremental value of clinical data. The model's predictive mechanisms were explored through correlation analyses with endocrine indicators and stratified evaluations based on the degree of hypothalamic-pituitary-target (HPT) axis damage. Performance metrics included area under the curve (AUC), accuracy, sensitivity, and specificity.

Results:

The independent test set showed GVisageNet achieving an AUC of 0.739, superior to the regression model alone (AUC=0.632, P<.001) but less than the hybrid model (AUC=0.789, P=.04). Significant correlations were found between the model's outputs and nine endocrine indicators. Performance varied with HPT axis damage, indicating a further understanding of the working mechanism of GVisageNet.

Conclusions:

GVisageNet offers a promising approach for the early detection of iGCTs, emphasizing the importance of combining deep learning with clinical data for personalized healthcare.