Abstract: In this talk, we examine artificial intelligence approaches for extracting actionable insights from health care data in order to improve public health. Our goal is to simultaneously identify subpopulations with distinct health risks and health trajectories, and find the distinct risk factors or determinants associated each subpopulation. These determinants can then be used treatments, programs, and policies in order to reduce mortality and comorbidity and provide more efficient healthcare. We examine novel cadre machine learning approaches that combine predictive neural network modeling with more traditional statistical epidemiology methods for risk and survival analyses. We embed the cadre methods into a Semantically Targeted Analytics (Semantalytics) System that combines semantics, inference, automatic machine learning, and explainable AI. The AI system translate the public health questions to an analysis plan, prepares data, conducts analysis and reports results with visualization and text. We demonstrated these approach on public health care surveillance datasets and electronic medical records. The award winning “MortalityMinder” app examines the social determinants of “Deaths Despair” ( deaths from suicide and substance abuse) and other causes of mortality that are unexpectedly rising in the United States. Other applications include association of environment toxins associated with diseases, high needs patient management for a health management organization, and emergency department readmissions. We conclude with the discussion of the open challenges to create population health AI systems that can transform health care questions into data-driven actionable-insights on the fly.

Prof. Kristin P. Bennett is the Associate Director of the Institute for Data Exploration and Application and a Professor in the Mathematical Sciences and Computer Science Departments and at Rensselaer Polytechnic Institute. Her research focuses on extracting information from data using novel predictive or descriptive mathematical models and data visualizations, and the applications of these methods to support decision making and to accelerate discovery in science, engineering, public health and business. She has 30 years of experience and over 100 publications. As an active member of the machine learning, data mining, and operations research communities, she has served as a study section member for the NIH National Library of Medicine and as associate or guest editors for ACM Transactions on Knowledge Discovery from Data, SIAM Journal on Optimization, Naval Research Logistics, Machine Learning Journal, IEEE Transactions on Neural Networks, and Journal on Machine Learning Research. She served as program chair of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining and She has led many data-driven health-related projects based on machine learning and data mining. These include the award winning “MortaltyMinder app for understanding the social determinants of mortality, the NIH-sponsored “TB-Insight” project which uses bioinformatics to track and control tuberculosis, emergency department revisits for Albany Medical Center, and a project on high needs patient management for Capital District Physicians Health Plan, and the privacy preserving synthetic health data project for United Health Foundation, and subpopulation risk analysis method for IBM. She also led projects on sensor-based anomaly detection for industrial partners including GLOBALFOUNDRY and GE Renewables. She founded and directs the Data Interdisciplinary Challenges Intelligent Technology Exploration Laboratory (Data INCITE Lab.) which is pioneering highly effective new approaches for data analytics in undergraduate education with sponsorship from NIH, United Health Foundation, and industrial partners. In the Data INCITE Lab, undergraduate and graduate students tackle open applied data analytics problems contributed by industry, foundations, and researchers.

Abstract: While some experimental biologists view bioinformatics as a servant, I argue that it is rapidly turning into the queen of molecular biology. I will illustrate this view by showing how recent computational developments brought down biological dogmas that remained unchallenged for at least three decades. Specifically, I will discuss the N-end theory connecting the protein half-life with N-terminal Methionine Excision, the Master Alu Theory explaining repeat proliferation in the human genome, and Random Breakage Model of genome rearrangements. In the second part of the talk, I will discuss a century-old dogma about the traditional classroom and describe the recent efforts to repudiate it using Intelligent Tutoring Systems. I will describe a new educational technology called a Massive Adaptive Interactive Text (MAIT) that can prevent individual learning breakdowns and outperform a professor in a classroom. I will argue that computer science is a unique discipline where the transition to MAITs is about to happen and will describe a bioinformatics MAIT that has already outperformed me. In difference from existing Massive Online Open Courses (MOOCs), MAITs will capture digitized individual learning paths of all students and will transform educational psychology into a digital science. I will argue that the future MAIT revolution will profoundly affect the way we all teach and will generate large population-wide datasets containing individual learning paths through various MAITs.

Prof. Pavel Pevzner is Ronald R. Taylor Professor of Computer Science and Engineering and Director of the NIH Center for Computational Mass Spectrometry at University of California, San Diego. He holds Ph.D. from Moscow Institute of Physics and Technology, Russia. He was named Howard Hughes Medical Institute Professor in 2006. He was elected the Association for Computing Machinery Fellow in 2010, the International Society for Computational Biology Fellow in 2012, the European Academy of Sciences member (Academia Europaea) in 2016, and the American Association for Advancement in Science (AAAI) Fellow in 2018. He was awarded a Honoris Causa (2011) from Simon Fraser University in Vancouver, the Senior Scientist Award (2017) by the International Society for Computational Biology, and the Kanellakis Theory and Practice Award from the Association for Computing Machinery. Dr. Pevzner authored textbooks "Computational Molecular Biology: An Algorithmic Approach", "Introduction to Bioinformatics Algorithms" (with Neal Jones) and “Bioinformatics Algorithms: an Active Learning Approach” (with Phillip Compeau). He co-developed the Bioinformatics and Data Structure and Algorithms online specializations on Coursera as well as the Algorithms and Data Structures MicroMaster Program at edX.

Abstract: In this talk, I will present some of our recent discoveries made through mining and modeling omic data of tens of thousands of samples of cancer tissues and inflammatory diseases. We have demonstrated: cancer cells of at least 16 most prevalent cancer types all harbor Fenton Reactions: Fe2+ + H2O2 -> Fe3+ + ∙OH + OH- in their cytosols and mitochondria. A consequence of the cytosolic Fenton reactions is that they continuously produce OH- at rates that can gradually overwhelm the intracellular pH buffer, which will drive the pH go up and ultimately kill the cells if not neutralized. As response, all these cancer cells alter increasingly more metabolisms, commonly referred to as metabolic reprogramming. We have studied ~40 such reprogrammed metabolisms and found that they have one thing in common: they each produce more H+ than their original metabolisms, presumably to neutralize the OH-. Among them, a most significant one is the Warburg effect, the basis for cancer detection using PET/CT. I will present data to show that the Warburg effect so induced can drive cell division. In addition, I will present preliminary data to show that two lesser known metabolic reprogramming: over-productions of sialic acids and gangliosides of specific types, both of which produce more protons. In addition, their deployment in plasma membrane create increasingly stronger cell-cell repulsion because of their negative charges, which may gradually result in substantial deformation of the affected cells, leading to the activation of a mechanical stress response program, which coordinates a series of counterbalancing activities to the cell deformation, including cell protrusion and contraction, ultimately giving rise to cell migration. I will also present a few computational challenges we must overcome to fully develop this model, including (1) deconvolution of tissue-based gene-expression data; (2) accurate prediction of intracellular pH of cancer cells; (3) reliable estimation of kinetic parameters of large-scale ODE-based kinetic reaction systems for modeling intracellular pH homeostasis among others.

Prof. Ying Xu has been the "Regents and Georgia Research Alliance Eminent Scholar" Chair of bioinformatics and computational biology and Professor in Biochemistry and Molecular Biology Department since 2003, and was the Founding Director of the Institute of Bioinformatics, the University of Georgia (UGA). He also holds a part-time Chair Professor position at Jilin University of China. He received his Ph.D. degree in theoretical computer science from the University of Colorado at Boulder in 1991. He started his bioinformatics career in 1993 when he joined Oak Ridge National Lab. His current research interests are in cancer bioinformatics and systems biology. He has over 300 publications, including five books, with total citations more than 12,000 and H-Index = 58; and has given over 250 invited/contributed talks at conferences, research organizations and universities.