Developing machine learning classifiers for carbapenem resistance prediction in Klebsiella pneumoniae using Google's teachable machine.

We developed neural network models trained with images from Klebsiella pneumoniae genomes, encoded via Chaos Game Representation, to predict carbapenem resistance. Both real (n = 168) and synthetic AI-generated (n = 200) images were used. The best-performing model, among the 72 developed, achieved up to 87.5 % accuracy on generalization datasets.