Deep transfer learning and data augmentation improve glucose levels prediction in type 2 diabetes patients
Deng Y, Lu L, Aponte L, Angelidi A, Novak V, Karniadakis G, Mantzoros C. Deep transfer learning and data augmentation improve glucose levels prediction in type 2 diabetes patients. Npj Digital Medicine 2021, 4: 109. PMID: 34262114, PMCID: PMC8280162, DOI: 10.1038/s41746-021-00480-x.Peer-Reviewed Original ResearchData augmentationTransfer learningNetwork architectureData augmentation techniquesNeural network architectureTransfer-learning strategyDeep-learning methodsDeep learning modelsDeep transfer learningTransfer-learning methodsSame network architectureDifferent loss functionsFuture glucose levelsAccurate predictive modelsH prediction horizonPublic datasetsGenerative modelGlucose level predictionAugmentation techniquesLoss functionPrediction accuracyDatasetLevel predictionPrediction horizonArchitecture