iLEAD: Intelligent Learning For Explainable and acute decision-support
Although machine learning (ML) has greatly advanced how healthcare data is analyzed today, neither the state-of-the-art ML models nor the ML strategies are developed to address these healthcare-specific concerns. And, so far there is no well-known ML platform dedicated to addressing healthcare-specific problems, despite healthcare being one of the biggest data-generating industries. However, throughout the history of computational analysis, there is evidence that the availability of easy-to-use libraries, datasets, toolkits, etc. can cause a cascade of research resulting in the rapid evolution of specific analytical inter-disciplinary fields. The best examples are that of Computer Vision and Natural Language Processing (NLP). The availability and cumulative progress of ImageNet, a dataset with over 30000 labeled images, is one of the main breakthroughs in the recent growth of computer vision and AI. The availability of various corpus and toolkits that allow the easy creation of additional corpus, has allowed the development of context-aware and self-attention NLP models. We expect an ML platform dedicated to healthcare data analysis to have a similar impact on the emergent field of healthcare informatics.