Predictive probabilistic models for treatment planning in paediatric cardiology
Niels B. Peek · Utrecht University Repository (Utrecht University) · 1998
The planning of clinical treatment actions for children with congenital heart disease requires a subtle trade-off between their immediate and long-term consequences, where most of these consequences cannot be predicted with certainty. It is described how this problem can be cast as a finite-horizon, partially observable Markov decision process. The complexity of the resulting model is reduced by using a graphical representation of state space and transition probabilities; it is shown that such a representation yields a significant decrease in the number of model parameters that have to be assessed. 1. INTRODUCTION A significant problem for the paediatric cardiologist in the management of patients with a cardiac anomaly is to decide if and when a patient has to be submitted to surgical treatment. In the management of these patients, there is always a trade-off between the benefits gained by waiting before surgical intervention in the hope that the patient's condition will improve, and ...