DiagnoseNET is designed as a modular framework that enables the deep learning application-workflow management and expressivity to build and finetune the neural architecture, while its runtime abstracts the distributed orchestration of portability and scalability from a GPU workstation to multi-nodes computational platforms. It automatizes in one expression API the neural architecture definition, the hyperparameter search, the data locality and batching, while the runtime coordinate the parameters between the devices according to the execution modes, which enables the workers selection through synchronous or asynchronous coordination gradient computations with gRPC or MPI communication protocols, tested on x86 and arm architectures.

DiagnoseNET is oriented to design a green intelligence medical workflow for deploying medical diagnostic tools with minimal infrastructure requirements and low power consumption. The first application built was to automate the unsupervised patient phenotype representation workflow trained on a mini-cluster of Nvidia Jetson TX2. This workflow was divided into three stages:

1. The first stage mining electronic health records for patient feature extraction and serialised each patient record in a clinical document architecture schema to create a binary patient representation.
2. The second stage embedding the patient’s binary matrix via an unsupervised learning to obtain a new latent space and identify the patient’s phenotypic representations.
3. The last stage focuses on supervised learning using the patient's features (binary or latent representation) as an input for machine learning algorithms or as an initialiser for deep neural networks.