Entropy and Compression Capture Different Complexity Features: The Case of Fetal Heart Rate

Abstract

Entropy and compression have been used to distinguish fetuses at risk of hypoxia from their healthy counterparts through the analysis of Fetal Heart Rate (FHR). Low correlation that was observed between these two approaches suggests that they capture different complexity features. This study aims at characterizing the complexity of FHR features captured by entropy and compression, using as reference international guidelines. Single and multi-scale approaches were considered in the computation of entropy and compression. The following physiologic-based features were considered: FHR baseline; percentage of abnormal long (%abLTV) and short (%abSTV) term variability; average short term variability; and, number of acceleration and decelerations. All of the features were computed on a set of 68 intrapartum FHR tracings, divided as normal, mildly, and moderately-severely acidemic born fetuses. The correlation between entropy/compression features and the physiologic-based features was assessed. There were correlations between compressions and accelerations and decelerations, but neither accelerations nor decelerations were significantly correlated with entropies. The %abSTV was significantly correlated with entropies (ranging between −0.54 and −0.62), and to a higher extent with compression (ranging between −0.80 and −0.94). Distinction between groups was clearer in the lower scales using entropy and in the higher scales using compression. Entropy and compression are complementary complexity measures.

Complexity of Cardiotocographic Signals as A Predictor of Labor

“…In our study, Gzip_FHR has a Spearman’s correlation coefficient of −0.524 and 0.5 with abSTV and avSTV’s variabilities, respectively. These results contrast with a previous study [ 41 ] where correlation values were much higher in absolute value (−0.851 and 0.774). Some different characteristics of the datasets used in each study can explain these differences.…”

“…The information captured by compression relates to the information comprised of other physiological features, such as short and long term variabilities [ 41 ]. In our study, Gzip_FHR has a Spearman’s correlation coefficient of −0.524 and 0.5 with abSTV and avSTV’s variabilities, respectively.…”

Non-linear Methods Predominant in Fetal Heart Rate Analysis: A Systematic Review

“…Moreover, some authors also include in the definition the value of the base excess or base deficit (127). Some authors defined as "at risk of acidemia" when pH < 7.20 (33,47,(128)(129)(130)(131)(132)(133)(134)(135)(136) or pH < 7.15 (30,121,(137)(138)(139)(140)(141)(142)(143); others define when pH < 7.1 (43,126,(144)(145)(146) or even when pH < 7.05 (38,44,48,78,(147)(148)(149)(150)(151)(152)(153)(154)(155)(156)(157)(158)(159)(160)(161)(162)(163)(164)(165)…”

Imputation Method for Fetal Heart Rate Signal Evaluation Based on Optimal Transport Theory

“…In the FHR analysis, we need to extract as much feature patterns as possible. In addition to the time-domain characteristics of STV and LTV, entropy measurement plays a vital role in the nonlinear analysis of FHR [9,29]. In [30], the approximate entropy analysis revealed several similar patterns in FHR signals.…”

“…MAE, RMSE, and W 2 imputation metrics are defined as Different methods of imputation performance were compared in four standard FHR features: the Approximate Entropy (ApEn) [29], Short-Term Variability (STV) [7], Long-Term Variability (LTV), and Δ (Delta) [8]. The formula is defined as follows:…”