Large-Scale Nonlinear Machine Learning: AI Meets Health

Machine learning is accelerating the translation of biological and biomedical data to advance the detection, diagnosis, treatment, and prevention of diseases. However, the unprecedented scale and complexity of large-scale biomedical data have presented critical computational bottlenecks requiring new concepts and enabling tools. To address the challenging problems in the emerging biomedical and health applications, we proposed multiple novel nonlinear machine learning models with theoretical foundations for scalable nonlinear association study, interactive feature detection, multi-dimensional data integration, longitudinal feature learning, etc. Meanwhile, to deal with the big data computations, we proposed new asynchronous distributed stochastic gradient and coordinate descent methods for efficiently solving convex and non-convex problems, and also parallelized the deep learning optimization algorithms with layer-wise model parallelism and the first theoretical convergence guarantee.

We applied our new large-scale nonlinear machine learning models to analyze the multi-modal and longitudinal neuroimaging and genome-wide array data in Imaging Genetics and discover the phenotypic and genotypic biomarkers to characterize the neurodegenerative process in the progression of Alzheimer’s disease and other complex brain disorders. We also utilized our new machine learning models to analyze the Electronic Medical Records (EMR) for predicting the heart failure patients’ readmission and drug side effects, identify the histopathological image markers and the multi-dimensional cancer genomic biomarkers in The Cancer Genome Atlas (TCGA) for precision medicine, and guide design of nanoparticle synthesis in Materials Genome research, and detect the DTI and fMRI based brain circuitry patterns in Human Connectome.