Optimal Stopping for Medical Treatment with Predictive Information

48 Pages Posted: 13 Jun 2019 Last revised: 13 Jan 2020

See all articles by Guang Cheng

Guang Cheng

School of Management, University of Science and Technology of China

Jingui Xie

School of Management, University of Science and Technology of China

Zhichao Zheng

Singapore Management University - Lee Kong Chian School of Business

Date Written: June 1, 2019

Abstract

Data availability and advancement in machine learning techniques make accurate prediction of the future a foreseeable reality. How to efficiently utilize the predictive information in a multistage medical decision-making environment, however, remains understudied. In this paper, we develop a discrete-time, finite-horizon Markov decision process model, incorporating perfect predictive information, to support decisions on medical treatment continuation. We extend our framework to a situation with prediction errors, using a partially observable Markov decision process. We characterize the structure of the optimal policies under both settings and show that knowing predictive information can lead to significantly different decision protocols. We calibrate and test our models with an extubation problem in an intensive care unit (ICU). Using a patient-level data set, we compare the performance of different extubation policies and demonstrate that incorporating predictive information can decrease extubation failure rate and reduce ICU length-of-stay of ventilated patients, especially for patients with poor initial conditions.

Keywords: Medical Decision Making; Optimal Stopping; Predictive Information; Partially Observable Markov Decision Process; Intensive Care Unit

Suggested Citation

Cheng, Guang and Xie, Jingui and Zheng, Zhichao, Optimal Stopping for Medical Treatment with Predictive Information (June 1, 2019). Available at SSRN: https://ssrn.com/abstract=3397530 or http://dx.doi.org/10.2139/ssrn.3397530

Guang Cheng

School of Management, University of Science and Technology of China ( email )

No. 96 Jinzhai Road
Hefei, Anhui 230026
China

Jingui Xie

School of Management, University of Science and Technology of China ( email )

Jinzhai Road No. 96
HEFEI, Anhui 230026
China
86(551)63606983 (Phone)

Zhichao Zheng (Contact Author)

Singapore Management University - Lee Kong Chian School of Business ( email )

50 Stamford Road
Singapore, 178899
Singapore
(65) 6808 5474 (Phone)
(65) 6828 0777 (Fax)

HOME PAGE: http://www.zhengzhichao.com

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
86
Abstract Views
572
rank
315,062
PlumX Metrics