< Back to Article

A modular deep learning architecture for interpretable disease prediction across tabular clinical and biometric datasets

Table 5

(a) Standalone model training configuration (MLP, CNN, FT-transformer). (b) Ensemble model training configuration (MLP + AE, CNN + AE, FT + AE).

doi: https://doi.org/10.1371/journal.pone.0348670.t005