CDANs: Temporal Causal Discovery from Autocorrelated and Non-Stationary Time Series Data

TL;DR

This paper introduces CDANs, a novel causal discovery method for autocorrelated and non-stationary time series data, effectively identifying lagged and contemporaneous causal relationships and changing modules, especially in healthcare datasets.

Contribution

The paper presents a new constraint-based causal discovery approach that handles high dimensionality, lagged causal relationships, and changing modules in non-stationary time series data.

Findings

Effective detection of causal relationships in synthetic and real-world datasets.

Outperforms baseline methods in identifying changing modules.

Accurately captures lagged and contemporaneous causal links.

Abstract

Time series data are found in many areas of healthcare such as medical time series, electronic health records (EHR), measurements of vitals, and wearable devices. Causal discovery, which involves estimating causal relationships from observational data, holds the potential to play a significant role in extracting actionable insights about human health. In this study, we present a novel constraint-based causal discovery approach for autocorrelated and non-stationary time series data (CDANs). Our proposed method addresses several limitations of existing causal discovery methods for autocorrelated and non-stationary time series data, such as high dimensionality, the inability to identify lagged causal relationships, and overlooking changing modules. Our approach identifies lagged and instantaneous/contemporaneous causal relationships along with changing modules that vary over time. The method optimizes the conditioning sets in a constraint-based search by considering lagged parents instead of conditioning on the entire past that addresses high dimensionality. The changing modules are detected by considering both contemporaneous and lagged parents. The approach first detects the lagged adjacencies, then identifies the changing modules and contemporaneous adjacencies, and finally determines the causal direction. We extensively evaluated our proposed method on synthetic and real-world clinical datasets, and compared its performance with several baseline approaches. The experimental results demonstrate the effectiveness of the proposed method in detecting causal relationships and changing modules for autocorrelated and non-stationary time series data.