Plenary Talks
Venue, Hotels and Social
Paper Submission

Invited talks and Tutorials

Invited talks have always been an important way to add value to the conference, not only for the presentations but also because of the interactions during the event.

Invited talks

Dr. Eva Lee

Director of Center for Operations Research in Medicine and HealthCare
H. Milton Stewart School of Industrial and Systems Engineering
Georgia Institute of Technology

Outcome-Driven Personalized Treatment Design

Diabetes affects 422 million people globally, costing over $825 billion per year. In the United States, about 30.3 million live with the illness. Current diabetes management focuses on close monitoring of a patient’s blood glucose level, while the clinician experiments with dosing strategy based on clinical guidelines and his (her) own experience. In this talk we describe a model for designing a personalized treatment plan tailored specifically to the patient’s unique dose-effect characteristics. Such a plan is more effective and efficient—for both treatment outcome and treatment cost—than current trial-and-error approaches. Our approach incorporates two key mathematical innovations. First, we develop a predictive dose-effect model that uses fluid dynamics, a compartmental model of partial differential equations, constrained least-square optimization, and statistical smoothing. The model leverages a patient’s routine self-monitoring of blood glucose and prescribed medication to establish a direct relationship between drug dosage and drug effect. This answers a fundamental century-long puzzle on how to predict dose effect without using invasive procedures to measure drug concentration in the body. Second, a multi-objective mixed-integer programming model incorporates this personalized dose-effect knowledge along with clinical constraints, and produces optimized plans that provide better glycemic control while using less drug. This is an added benefit because diabetes is costly to treat as it progresses, and requires continuous intervention. Implemented at Grady Memorial Hospital, our system reduces the hospital cost by $39,500 per patient for pregnancy cases where a mother suffers from gestational diabetes. This is a decrease of more than fourfold in the overall hospital costs for such cases. For type 2 diabetes, which accounts for about 90 to 95% of all diagnosed cases of diabetes in adults, our approach leads to improved blood glucose control using less medication, resulting in about 39% savings ($40,880 per patient) in medical costs for these patients. Our mathematical model is the first that (1) characterizes personalized dose response for oral anti-diabetic drugs; and (2) optimizes outcome and dosing strategy through mathematical programming.

Dr. Mario Guarracino

researcher at High Performance Computing and Networking
Institute of the Italian National Research Council

What can we learn from metabolic networks?

Networks represent a convenient model for many scientific and technological problems. From power grids to biological processes and functions, from financial networks to chemical compounds, the representation of case studies with graphs enables the possibility to highlight both topological and qualitative characteristics. In this talk, we report recent developments in supervised classification of data in form of networks. Given two or more classes whose members are networks, we build a mathematical model to classify them. We focus on networks with labeled nodes and weighted edges, defining distances between networks and building a supervised classification model. We detail the graphical model selection process and provide empirical results on datasets of biological interest.

Dr. Parisa Rashidi

Assistant Professor
Department of Biomedical Engineering
University of Florida

Intelligent Patient Monitoring Systems

In recent years, we have witnessed a rapid surge in building intelligent health systems. Artificial intelligence and machine learning techniques are central to all these systems and constitute a major step towards developing more intelligent healthcare solutions. These techniques not only make it possible to process and transform data into actionable knowledge, but also facilitate decision making and reasoning. This talk will discuss the rise of intelligent health systems in patient monitoring and will explore the challenges and opportunities in this area.

Dr. Azra Bihorac

R. Glenn Davis Professor of Medicine, Surgery and Anesthesiology
Division of Nephrology, Hypertension, & Renal Transplantation
Department of Medicine

Next generation intelligent decision support for augmented decision making

The average American can expect to undergo 7 surgical operations during her lifetime. Each year 150,000 patients die and 1.5 million develop a major complication within 30 days after surgery. Perioperative medicine accounts for 40% of the national health budget. Timely identification of patients at risk is of utmost importance. Digitalization of electronic health records provide new resources for the use of advance machine learning and artificial intelligence for augmenting decision making foe health care providers. We will discuss development and implementation of next-generation clinical decision support in surgical practice at University of Florida.