How can cry acoustics associate newborns' distress levels with neurophysiological and behavioral signals?

Abstract

Introduction: Even though infant crying is a common phenomenon in humans' early life, it is still a challenge for researchers to properly understand it as a reflection of complex neurophysiological functions. Our study aims to determine the association between neonatal cry acoustics with neurophysiological signals and behavioral features according to different cry distress levels of newborns.

Methods: Multimodal data from 25 healthy term newborns were collected simultaneously recording infant cry vocalizations, electroencephalography (EEG), near-infrared spectroscopy (NIRS) and videos of facial expressions and body movements. Statistical analysis was conducted on this dataset to identify correlations among variables during three different infant conditions (i.e., resting, cry, and distress). A Deep Learning (DL) algorithm was used to objectively and automatically evaluate the level of cry distress in infants.

Results: We found correlations between most of the features extracted from the signals depending on the infant's arousal state, among them: fundamental frequency (F0), brain activity (delta, theta, and alpha frequency bands), cerebral and body oxygenation, heart rate, facial tension, and body rigidity. Additionally, these associations reinforce that what is occurring at an acoustic level can be characterized by behavioral and neurophysiological patterns. Finally, the DL audio model developed was able to classify the different levels of distress achieving 93% accuracy.

Conclusion: Our findings strengthen the potential of crying as a biomarker evidencing the physical, emotional and health status of the infant becoming a crucial tool for caregivers and clinicians.

Keywords: EEG; NIRS; body language; cry acoustic; distress; newborns.

Figure 1

Paradigm, data acquisition, and analysis pipeline. (A) Audio was recorded and segmented in cry episodes and cry units depending on the distress levels of the cry. Then, time and frequency features were extracted with Praat and noise/outliers were removed with a band-pass filter. (B) Video was recorded for each session and the newborn’s facial expressions and body movements were assessed through the COMFORT scale. (C) EEG data were collected for the whole session; a preprocessing step as shown here was then applied to ensure high data quality. Lastly, clean EEG data were segmented according to the audio segmentation and the power spectrum was computed. (D) NIRS data were acquired for the whole session and a pre-processing pipeline as shown in this panel was followed. As for the EEG, NIRS data were segmented with the audio segmentation procedure. Consent was obtained from the family to publish the newborn’s face in the figure for publication.

Figure 2

Deep Learning (DL) and Machine Learning (ML) Models. (A) Classification procedure for both Machine and Deep Learning models. (B) Accuracy for both models, specificity, and sensitivity are also indicated.

Figure 3

Differences in power spectrum for resting, cry, and distress conditions (n = 295 segments, for both conditions, n was balanced using random sampling), were obtained by applying a Kruskal-Wallis test with Dunn’s test (for post-hoc comparisons). (A) Topographic EEG maps of relative power distribution for delta (ẟ), theta (θ), and alpha (α) bands. The upper portion of each map shows the nose (frontal area) and the lower side shows the occipital side. (B) Percentage of relative power changes across frequency bands and electrodes for each condition. Specifically, for Figure 3, * and the line below represents a statistically highly significant difference p < 0.001 from pairwise comparisons. * and the bracket indicates a statistically highly significant difference p < 0.001 for all the pairwise comparisons.

Figure 4

Pairwise comparisons between cry, distress, and resting in relative power. (A) Differences between cry and resting (n = 295 segments, for both conditions, n was balanced using random sampling) were obtained by the Mann–Whitney test. (B) Differences between distress and resting (n = 180 segments, for both conditions–n was balanced using random sampling) were obtained by the Mann–Whitney test. (C) Differences between cry and distress (n = 180 segments, for both conditions, n was balanced using random sampling) were obtained by the Mann–Whitney test. The color bar is displayed as a family-wise corrected significance level of 1–value of p: the blue darker color depicts a higher statistically significant difference between pairwise comparisons and the red color the opposite.

Figure 5

Comparisons in rSO2, SpO2, and PR-bpm among the three conditions. (A) rSO2 differences among resting (n = 441 segments), cry (n = 272 segments), and distress conditions (n = 140 segments). (B) SpO₂ differences among resting (n = 361 segments), cry (n = 295 segments), and distress conditions (n = 150 segments). (C) PR-bpm differences among resting (n = 421 segments), cry (n = 295 segments), and distress conditions (n = 153 segments). ANOVA and Tukey–Kramer tests were applied for post hoc comparisons and the bootstrapping procedure repeated 10,000 times was applied to correct for normality and unbalanced categories. Resting is displayed as a black circle, cry as a purple square, and distress condition as a red triangle. The dotted line for each variable represents the mean value for the resting condition. *** indicates p < 0.001 and * indicates p < 0.05. Data are presented as mean ± standard error mean.

Figure 6

Comparisons of the COMFORT scale scores among conditions (resting: n = 24 segments, cry: n = 67 segments, and distress: n = 25). (A) Alertness, Agitation, Cry, Body Movement, Muscular Tone, Facial Tension scores and (B) Total scores are reported. The Kruskal-Wallis test along with Dunn’s test (for post-hoc comparisons) were used. The dotted line for each variable represents the mean value for the resting condition. *** indicates p < 0.001 and * indicates p < 0.05. Data are presented as mean ± standard error mean.

Figure 7

Correlation Matrix. Spearman Correlation coefficients (rho) among acoustic features, EEG relative power frequency bands, NIRS, and COMFORT scale. The colormap represents the rho values. The darker purple color indicates positive correlations and the blue light color the negative ones. Circle size indicates the statistical significance level (1-value of p), thus, a bigger circle size represents higher statistically significant levels and a smaller size indicates the opposite. Feature group labels: light blue is used for cry temporal features; darker blue for cry frequency features; light purple for EEG relative power frequency bands; light red for NIRS features; and light green for the COMFORT scale scores.

Figure 8

Concordance Analysis. Kendall coefficients (W) between acoustic features and EEG, NIRS, and COMFORT scale for cry (purple) and distress (red) conditions. * indicates W coefficients greater than 0.5. W coefficients greater than 0.7 are framed with a rectangle. To group the variables within each feature (EEG, NIRS, and COMFORT scale), different colors were set in the figure (light purple for EEG, light red for NIRS, and light green for the COMFORT scale).