The Paper FeedA feed of Bayesian network related papers, articles, books and research that we happen across and find of interest A comparison between discrete and continuous time Bayesian networks in learning from clinical time series data with irregularity2019
Background
Recently, mobile devices, such as smartphones, have been introduced into healthcare research to substitute paper diaries as datacollection tools in the home environment. Such devices support collecting patient data at different time points over a long period, resulting in clinical timeseries data with high temporal complexity, such as time irregularities. Analysis of such time series poses new challenges for machinelearning techniques. The clinical context for the research discussed in this paper is home monitoring in chronic obstructive pulmonary disease (COPD).
Objective
The goal of the present research is to find out which properties of temporal Bayesian network models allow to cope best with irregularly spaced multivariate clinical timeseries data.
Methods
Two mainstream temporal Bayesian network models of multivariate clinical time series are studied: dynamic Bayesian networks, where the system is described as a snapshot at discrete time points, and continuous time Bayesian networks, where transitions between states are modeled in continuous time. Their capability of learning from clinical time series that vary in nature are extensively studied. In order to compare the two temporal Bayesian network types for regularly and irregularly spaced timeseries data, three typical ways of observing timeseries data were investigated: (1) regularly spaced in time with a fixed rate; (2) irregularly spaced and missing completely at random at discrete time points; (3) irregularly spaced and missing at random at discrete time points. In addition, similar experiments were carried out using realworld COPD patient data where observations are unevenly spaced.
Results
For regularly spaced time series, the dynamic Bayesian network models outperform the continuous time Bayesian networks. Similarly, if the data is missing completely at random, discretetime models outperform continuous time models in most situations. For more realistic settings where data is not missing completely at random, the situation is more complicated. In simulation experiments, both models perform similarly if there is strong prior knowledge available about the missing data distribution. Otherwise, continuous time Bayesian networks perform better. In experiments with unevenly spaced realworld data, we surprisingly found that a dynamic Bayesian network where time is ignored performs similar to a continuous time Bayesian network.
Conclusion
The results confirm conventional wisdom that discretetime Bayesian networks are appropriate when learning from regularly spaced clinical time series. Similarly, we found that time series where the missingness occurs completely at random, dynamic Bayesian networks are an appropriate choice. However, for complex clinical timeseries data that motivated this research, the continuoustime models are at least competitive and sometimes better than their discretetime counterparts. Furthermore, continuoustime models provide additional benefits of being able to provide more finegrained predictions than discretetime models, which will be of practical relevance in clinical applications.
