arXiv subjects

Subhro Das

Publications and source records attributed to Subhro Das.

39 records · Page 3Linked to original sources

arXiv2019

Learning Patient Engagement in Care Management: Performance vs. Interpretability

The health outcomes of high-need patients can be substantially influenced by the degree of patient engagement in their own care. The role of care managers includes that of enrolling patients into care programs and keeping them sufficiently engaged in the program, so that patients can attain various goals. The attainment of these goals is expected to improve the patients' health outcomes. In this paper, we present a real world data-driven method and the behavioral engagement scoring pipeline for scoring the engagement level of a patient in two regards: (1) Their interest in enrolling into a relevant care program, and (2) their interest and commitment to program goals. We use this score to predict a patient's propensity to respond (i.e., to a call for enrollment into a program, or to an assigned program goal). Using real-world care management data, we show that our scoring method successfully predicts patient engagement. We also show that we are able to provide interpretable insights to care managers, using prototypical patients as a point of reference, without sacrificing prediction performance.

cs.LG↗

arXiv2017

Distributed Estimation of Dynamic Fields over Multi-agent Networks

This work presents distributed algorithms for estimation of time-varying random fields over multi-agent/sensor networks. A network of sensors makes sparse and noisy local measurements of the dynamic field. Each sensor aims to obtain unbiased distributed estimates of the entire field with bounded mean-squared error (MSE) based on its own local observations and its neighbors' estimates. This work develops three novel distributed estimators: Pseudo-Innovations Kalman Filter (PIKF), Distributed Information Kalman Filter (DIKF) and Consensus+Innovations Kalman Filter (CIKF). We design the gain matrices such that the estimators achieve unbiased estimates with bounded MSE under minimal assumptions on the local observation and network communication models. This work establishes trade-offs between these three distributed estimators and demonstrates how they outperform existing solutions. We validate our results through extensive numerical evaluations.

cs.IT↗

arXiv2016

Consensus+Innovations Distributed Kalman Filter with Optimized Gains

In this paper, we address the distributed filtering and prediction of time-varying random fields represented by linear time-invariant (LTI) dynamical systems. The field is observed by a sparsely connected network of agents/sensors collaborating among themselves. We develop a Kalman filter type consensus+innovations distributed linear estimator of the dynamic field termed as Consensus+Innovations Kalman Filter. We analyze the convergence properties of this distributed estimator. We prove that the mean-squared error of the estimator asymptotically converges if the degree of instability of the field dynamics is within a pre-specified threshold defined as tracking capacity of the estimator. The tracking capacity is a function of the local observation models and the agent communication network. We design the optimal consensus and innovation gain matrices yielding distributed estimates with minimized mean-squared error. Through numerical evaluations, we show that, the distributed estimator with optimal gains converges faster and with approximately 3dB better mean-squared error performance than previous distributed estimators.

cs.IT↗