Sepsis is a potentially life-threatening inflammatory response to infection or severe tissue damage. It has a highly variable clinical course, requiring constant monitoring of the patient’s state to guide the management of intravenous fluids and vasopressors, among other interventions. Despite decades of research, there’s still debate among experts on optimal treatment. Here, we combine for the first time, distributional deep reinforcement learning with mechanistic physiological models to find personalized sepsis treatment strategies. Our method handles partial observability by leveraging known cardiovascular physiology, introducing a novel physiology-driven recurrent autoencoder, and quantifies the uncertainty of its own results. Moreover, we introduce a framework for uncertainty-aware decision support with humans in the loop. We show that our method learns physiologically explainable, robust policies, that are consistent with clinical knowledge. Further our method consistently identifies high-risk states that lead to death, which could potentially benefit from more frequent vasopressor administration, providing valuable guidance for future research.

Debt collection is a massive industry, within the USA alone more than $50 billion recovered each year. However the information available is often limited and incomplete, and predicting whether a given debtor would repay is inherently a challenging task. This has amplified research on debt recovery classification and prediction models of late. This report considers three main mathematical, data mining and statistical models in debt recovery classification, in logistic regression, artificial neural networks and affinity analysis. It also compares the effectiveness of the above-mentioned tools in evaluating whether a debt is likely to be repaid. The construction and analysis of the models were based on a fairly large unbalanced data sample provided by a debt collection agency. We have shown that all three models could classify the debt repayments with a considerable accuracy, if the assumptions of the models are satisfied.

No abstract

There has been considerable interest in leveraging RL and stochastic control methods to learn optimal treatment strategies for critically ill patients, directly from observational data. However, there is significant ambiguity on the control objective and on the best reward choice for the standard RL objective. In this work, we propose a clinically motivated control objective for critically ill patients, for which the value functions have a simple medical interpretation. Further, we present theoretical results and adapt our method to a practical Deep RL algorithm, which can be used alongside any value based Deep RL method. We experiment on a large sepsis cohort and show that our method produces results consistent with clinical knowledge.