Towards better reliability in fetal heart rate variability using time domain and spectral domain analyses. A new method for assessing fetal neurological state?

Advanced Predictive Analytics for Fetal Heart Rate Variability Using Digital Twin Integration

Fetal heart rate variability (FHRV) is a critical indicator of fetal well-being and autonomic nervous system development during labor. Traditional monitoring methods often provide limited insights, potentially leading to delayed interventions and suboptimal outcomes. This study proposes an advanced predictive analytics approach by integrating approximate entropy analysis with a hidden Markov model (HMM) within a digital twin framework to enhance real-time fetal monitoring. We utilized a dataset of 469 fetal electrocardiogram (ECG) recordings, each exceeding one hour in duration, to ensure sufficient temporal information for reliable modeling. The FHRV data were preprocessed and partitioned into parasympathetic and sympathetic components based on downward and non-downward beat detection. Approximate entropy was calculated to quantify the complexity of FHRV patterns, revealing significant correlations with umbilical cord blood gas parameters, particularly pH levels. The HMM was developed with four hidden states representing discrete pH levels and eight observed states derived from FHRV data. By employing the Baum-Welch and Viterbi algorithms for training and decoding, respectively, the model effectively captured temporal dependencies and provided early predictions of the fetal acid-base status. Experimental results demonstrated that the model achieved 85% training and 79% testing accuracy on the balanced dataset distribution, improving from 78% and 71% on the imbalanced dataset. The integration of this predictive model into a digital twin framework offers significant benefits for timely clinical interventions, potentially improving prenatal outcomes.

Methods for analyzing infant heart rate variability: A preliminary study

Heart rate (HR) and heart rate variability (HRV) reflect autonomic development in infants. To better understand the autonomic response in infants, reliable HRV recordings are vital, yet no protocol exists. The purpose of this paper is to present reliability of a common procedure for analysis from two different file types. In the procedure, continuous electrocardiograph recordings of 5-10 min are obtained at rest in infants at 1 month of age by using a Hexoskin Shirt-Junior's (Carre Technologies Inc., Montreal, QC, Canada). Electrocardiograph (ECG; .wav) and R-R interval (RRi; .csv) files are extracted. The RRi of the ECG signal is generated by VivoSense (Great Lakes NeuroTechnologies, Independence, OH). Two MATLAB (The MathWorks, Inc., Natick, MA) scripts converted files for analysis with Kubios HRV Premium (Kubios Oy, Kuopio, Finland). A comparison was made between RRi and ECG files for HR and HRV parameters, and then tested with t tests and correlations via SPSS. There are significant differences in root mean squared successive differences between recording types, with only HR and low-frequency measures significantly correlated together. Recording with Hexoskin and analysis with MATLAB and Kubios enable infant HRV analysis. Differences in outcomes exist between procedures, and standard methodology for infant HR analysis is needed.

Growth-restricted human fetuses have preserved respiratory sinus arrhythmia but reduced heart rate variability estimates of vagal activity during quiescence

The aim was to assess the association between fetal growth restriction (FGR) and fetal heart rate variability (FHRV) in relation to fetal movements. A prospective observational cohort study was performed. Non-invasive fetal electrocardiography (NI-FECG) allowed beat-to-beat assessments with <5% corrections of RR intervals. FHRV analyses included: Root mean square of successive RR interval differences (RMSSD), high frequency power (HF power), and low frequency power (LF power). Fetal movements were categorized by continuous ultrasound scanning. We enrolled 36 singleton pregnant women expecting a small fetus (< the 2.3 percentile of mean weight for gestational age) diagnosed by ultrasound, of whom 25 presented with a birthweight < the 2.3 percentile. Among these, 11 were excluded due to low quality NI-FECG recordings, leaving 14 women with 28 recordings eligible for inclusion in the analyses. The control group consisted of 22 healthy fetuses with birthweights between the 10th and the 90th percentile (average for gestational age [AGA]). In FGR fetuses the HRV response to respiratory activity was comparable to that of AGA fetuses. RMSSD (Ratio 1.54 [95% CI: 1.33; 1.79]) and HF power (Ratio 2.88 [95% CI: 2.12; 3.91]) increased, whereas LF/HF power (Ratio: 0.44 [95% CI: 0.31;0.63]) decreased. However, during fetal quiescence, FGR fetuses differed significantly from AGA fetuses. Compared to AGA fetuses, FGR fetuses displayed lower RMSSD (Ratio 0.77 (95% CI: 0.58; 1.02)) and HF power (Ratio 0.56 (95% CI:0.32; 0.98)). This reduction was associated with the severity of the FGR. In conclusion, FGR fetuses displayed a respiratory sinus arrhythmia (RSA) comparable to AGA fetuses; however, more important, parameters representing cardiac vagal activity were impaired in FGR fetuses during quiescence. RSA may constitute an intrinsic function of the cardiovascular system, which is unaffected by fetal compromise. However, the basic cardiac outflow assessed during fetal quiescence indicates a suppressed cardiac vagal activity in the FGR fetuses.

Increased variability of fetal heart rate during labour: a review of preclinical and clinical studies

Increased fetal heart rate variability (FHRV) in intrapartum cardiotocographic recording has been variably defined and poorly understood, limiting its clinical utility. Both preclinical (animal) and clinical (human) evidence support that increased FHRV is observed in the early stage of intrapartum fetal hypoxaemia but can also be observed in a subset of fetuses during the preterminal stage of repeated hypoxaemia. This review of available evidence provides data and expert opinion on the pathophysiology of increased FHRV, its clinical significance and a stepwise approach regarding the management of this pattern, and propose recommendations for standardisation of related terminology.

Fetal respiratory movements improve reliability of heart rate variability and suggest a coupling between fetal respiratory arrhythmia and vagal activity

Fetal heart rate variability (FHRV) reflects autonomic cardiac regulation. The autonomic nervous system constantly adjusts the heart rate to maintain homeostasis. By providing insight into the fetal autonomic state, FHRV has the potential to become an investigational and clinical instrument. However, the method needs standardization and the influence of fetal movements, including fetal respiratory movements, is not well explored. Therefore, in a highly standardized setting, the aim was to evaluate the association between fetal movements and fetal heart rate variability (FHRV) including their impact on reliability. Fetal heart rate was obtained by noninvasive fetal electrocardiography (NI-FECG) and fetal movements by simultaneous ultrasound scanning in 30 healthy singleton pregnant women on two occasions with a maximum interval of 7 days. The standard deviation of normal-to-normal RR-intervals (SDNN), root mean square of successive RR-interval differences (RMDDS), high-frequency power (HF-power), low-frequency power (LF-power), and LF/HF were measured. A multivariate mixed model was used and reliability was defined as acceptable by a coefficient of variance (CV) ≤15% and an intraclass correlation coefficient (ICC) ≥0.80. During time periods with fetal respiratory movements, the highest reliability was achieved. Intra- and inter-observer reliability measurements were very high (CV: 0-9%; ICC ≧ 0.86). Within the same recording, SDNN and RMSSD achieved acceptable reliability (CV: 14-15%; ICC ≧ 0.80). However, day-to-day reliability displayed high CV's. In time periods with fetal respiratory movements, as compared to periods with quiescence RMSSD and HF-power were higher (Ratio: 1.33-2.03) and LF/HF power lower (Ratio: 0.54). In periods with fetal body movements SDNN, RMSSD and HF-power were higher (Ratio: 1.27-1.65). In conclusion, time periods with fetal respiratory movements were associated with high reliability of FHRV analyses and the highest values of parameters supposed to represent vagal activity.