Robust Policies For Proactive ICU Transfers
Participer
INFORMATIONS SYSTEMS ET OPERATIONS MANAGEMENT
Intervenant : Julien Grand Clement
Ph.D. Candidate from the Industrial Engineering and Operations Research (IEOR) department at
Columbia University
Abstract :
Patients whose transfer to the Intensive Care Unit (ICU) is unplanned are prone to higher mortality rates than those who were admitted directly to the ICU. Recent advances in machine learning to predict patient deterioration have introduced the possibility of \emph{proactive transfer} from the ward to the ICU. In this work, we study the problem of finding \emph{robust} patient transfer policies which account for uncertainty in statistical estimates due to data limitations when optimizing to improve overall patient care. We propose a Markov Decision Process model to capture the evolution of patient health, where the states represent a measure of patient severity. Under fairly general assumptions, we show that an optimal transfer policy has a threshold structure, i.e., that it transfers all patients above a certain severity level to the ICU (subject to available capacity).
As model parameters are typically determined based on statistical estimations from real-world data, they are inherently subject to misspecification and estimation errors. We account for this parameter uncertainty by deriving a robust policy that optimizes the worst-case reward across all plausible values of the model parameters. We show that the robust policy also has a threshold structure under fairly general assumptions. Moreover, it is more aggressive in transferring patients than the optimal nominal policy, which does not take into account parameter uncertainty. We present computational experiments using a dataset of hospitalizations at 21 KNPC hospitals, and present empirical evidence of the sensitivity of various hospital metrics (mortality, length-of-stay, average ICU occupancy) to small changes in the parameters. Our work provides useful insights into the impact of parameter uncertainty on deriving simple policies for proactive ICU transfer that have strong empirical performance and theoretical guarantees.
Pdf: https://arxiv.org/pdf/2002.06247.pdf
Bio :
“My research focuses on risk-aware data-driven decisions to positively impact healthcare practice. In recent years, the increasing availability of healthcare data has led to fast-growing data-driven approaches in both healthcare decisions and operations. However, while data is abundant, healthcare decision-making faces a few specific challenges, most significant among them, the asymmetric risk of beneficial versus detrimental decisions that potentially increase mortality, the high-dimensionality of the representation space for patients’ health condition, and the sparsity and noisiness of the data. Addressing these challenges requires new risk-aware decision tools that can enable tractable and robust data-driven healthcare decisions”