COVID-19: Data-Driven optimal allocation of ventilator supply under uncertainty and risk.

This study presents a new risk-averse multi-stage stochastic epidemics-ventilator-logistics compartmental model to address the resource allocation challenges of mitigating COVID-19. This epidemiological logistics model involves the uncertainty of untested asymptomatic infections and incorporates short-term human migration. Disease transmission is also forecasted through a new formulation of transmission rates that evolve over space and time with respect to various non-pharmaceutical interventions, such as wearing masks, social distancing, and lockdown. The proposed multi-stage stochastic model overviews different scenarios on the number of asymptomatic individuals while optimizing the distribution of resources, such as ventilators, to minimize the total expected number of newly infected and deceased people. The Conditional Value at Risk (CVaR) is also incorporated into the multi-stage mean-risk model to allow for a trade-off between the weighted expected loss due to the outbreak and the expected risks associated with experiencing disastrous pandemic scenarios. We apply our multi-stage mean-risk epidemics-ventilator-logistics model to the case of controlling COVID-19 in highly-impacted counties of New York and New Jersey. We calibrate, validate, and test our model using actual infection, population, and migration data. We also define a new region-based sub-problem and bounds on the problem and then show their computational benefits in terms of the optimality and relaxation gaps. The computational results indicate that short-term migration influences the transmission of the disease significantly. The optimal number of ventilators allocated to each region depends on various factors, including the number of initial infections, disease transmission rates, initial ICU capacity, the population of a geographical location, and the availability of ventilator supply. Our data-driven modeling framework can be adapted to study the disease transmission dynamics and logistics of other similar epidemics and pandemics.

A simulation-deep reinforcement learning (SiRL) approach for epidemic control optimization.

In this paper, we address the controversies of epidemic control planning by developing a novel Simulation-Deep Reinforcement Learning (SiRL) model. COVID-19 reminded constituents over the world that government decision-making could change their lives. During the COVID-19 pandemic, governments were concerned with reducing fatalities as the virus spread but at the same time also maintaining a flowing economy. In this paper, we address epidemic decision-making regarding the interventions necessary given of the epidemic based on the purpose of the decision-maker. Further, we intend to compare different vaccination strategies, such as age-based and random vaccination, to shine a light on who should get priority in the vaccination process. To address these issues, we propose a simulation-deep reinforcement learning (DRL) framework. This framework is composed of an agent-based simulation model and a governor DRL agent that can enforce interventions in the agent-based simulation environment. Computational results show that our DRL agent can learn effective strategies and suggest optimal actions given a specific epidemic situation based on a multi-objective reward structure. We compare our DRL agent's decisions to government interventions at different periods of time during the COVID-19 pandemic. Our results suggest that more could have been done to control the epidemic. In addition, if a random vaccination strategy that allows super-spreaders to get vaccinated early were used, infections would have been reduced by 32% at the expense of 4% more deaths. We also show that a behavioral change of fully quarantining 10% of the risky individuals and using a random vaccination strategy leads to a reduction of the death toll by 14% and 27% compared to the age-based vaccination strategy that was implemented and the New Jersey reported data, respectively. We have also demonstrated the flexibility of our approach to be applied to other locations by validating and applying our model to the COVID-19 case in the state of Kansas.

Optimizing multi-modal cancer treatment under 3D spatio-temporal tumor growth.

In this paper we introduce a new mixed-integer linear programming (MIP) model that explicitly integrates the spread of cancer cells into a spatio-temporal reaction-diffusion (RD) model of cancer growth, while taking into account treatment effects. This linear but non-convex model appears to be the first of its kind by determining the optimal sequence of the typically prescribed cancer treatment methods-surgery (S), chemotherapy (C), and radiotherapy (R)-while minimizing the newly generated tumor cells for early-stage breast cancer in a unique three-dimensional (3D) spatio-temporal system. The quadratically-constrained cancer growth dynamics and treatment impact formulations are linearized by using linearization as well as approximation techniques. Under the supervision of medical oncologists and utilizing several literature resources for the parameter values, the effectiveness of treatment combinations for breast cancer specified with different sequences (i.e., SRC, SCR, CR, RC) are compared by tracking the number of cancer cells at the end of each treatment modality. Our results provide the optimal dosages for chemotherapy and radiation treatments, while minimizing the growth of new cancer cells.

Manipulating the steady state of metabolic pathways.

Metabolic pathways show the complex interactions among enzymes that transform chemical compounds. The state of a metabolic pathway can be expressed as a vector, which denotes the yield of the compounds or the flux in that pathway at a given time. The steady state is a state that remains unchanged over time. Altering the state of the metabolism is very important for many applications such as biomedicine, biofuels, food industry, and cosmetics. The goal of the enzymatic target identification problem is to identify the set of enzymes whose knockouts lead the metabolism to a state that is close to a given goal state. Given that the size of the search space is exponential in the number of enzymes, the target identification problem is very computationally intensive. We develop efficient algorithms to solve the enzymatic target identification problem in this paper. Unlike existing algorithms, our method works for a broad set of metabolic network models. We measure the effect of the knockouts of a set of enzymes as a function of the deviation of the steady state of the pathway after their knockouts from the goal state. We develop two algorithms to find the enzyme set with minimal deviation from the goal state. The first one is a traversal approach that explores possible solutions in a systematic way using a branch and bound method. The second one uses genetic algorithms to derive good solutions from a set of alternative solutions iteratively. Unlike the former one, this one can run for very large pathways. Our experiments show that our algorithms' results follow those obtained in vitro in the literature from a number of applications. They also show that the traversal method is a good approximation of the exhaustive search algorithm and it is up to 11 times faster than the exhaustive one. This algorithm runs efficiently for pathways with up to 30 enzymes. For large pathways, our genetic algorithm can find good solutions in less than 10 minutes.