Intrapartum cardiotocogram monitoring between obstetricians and computer analysis

Computer Vision for Identification of Increased Fetal Heart Variability in Cardiotocogram

INTRODUCTION

Increased fetal heart rate variability (IFHRV), defined as fetal heart rate (FHR) baseline amplitude changes of >25 beats per minute with a duration of ≥1 min, is an early sign of intrapartum fetal hypoxia. This study evaluated the level of agreement of machine learning (ML) algorithms-based recognition of IFHRV patterns with expert analysis.

METHODS

Cardiotocographic recordings and cardiotocograms from 4,988 singleton term childbirths were evaluated independently by two expert obstetricians blinded to the outcomes. Continuous FHR monitoring with computer vision analysis was compared with visual analysis by the expert obstetricians. FHR signals were graphically processed and measured by the computer vision model labeled SALKA.

RESULTS

In visual analysis, IFHRV pattern occurred in 582 cardiotocograms (11.7%). Compared with visual analysis, SALKA recognized IFHRV patterns with an average Cohen's kappa coefficient of 0.981 (95% CI: 0.972-0.993). The sensitivity of SALKA was 0.981, the positive predictive rate was 0.822 (95% CI: 0.774-0.903), and the false-negative rate was 0.01 (95% CI: 0.00-0.02). The agreement between visual analysis and SALKA in identification of IFHRV was almost perfect (0.993) in cases (N = 146) with neonatal acidemia (i.e., umbilical artery pH <7.10).

CONCLUSIONS

Computer vision analysis by SALKA is a novel ML technique that, with high sensitivity and specificity, identifies IFHRV features in intrapartum cardiotocograms. SALKA recognizes potential early signs of fetal distress close to those of expert obstetricians, particularly in cases of neonatal acidemia.

Evaluation of fetal acidemia during delivery using the conventional 5-tier classification and Rainbow systems

The association between prepartum time-series fetal heart rate pattern changes and cord blood gas data at delivery was examined using the conventional 5-tier classification and the Rainbow system for 229 female patients who delivered vaginally. They were classified into three groups based on the results of umbilical cord blood gas analysis at delivery. The fetal heart rate pattern classifications were based on analysis of measurement taken at 10-min intervals, beginning at 120 min pre-delivery. The relationship between fetal heart rate pattern classification and cord blood pH at delivery changed over time. The 5-tier classification at each interval increased before delivery in the Mild and Severe groups compared with the Normal group. No significant differences were observed between acidemia groups. The Rainbow classification showed a significant differences between the acidemia groups at each interval, particularly during the prepartum period. A relationship between classification and outcome was evident before delivery for both the 5-tier classification and Rainbow system.

Analysis of antepartum cardiotocography based on S/k proportions and probability in 20 minutes

Abstract Objectives: although mortality and perinatal asphyxia in newborns have been considerably reduced, there are still deficiencies in screening and diagnosis methods for intrapartum fetal well being that aim to detect its early alterations. Therefore, the purpose of this research was to apply a methodology based on probability and entropy and confirm its capacity to detect normal and abnormal fetal cardiac dynamics from 20-minute cardiotocographic tracings. Methods: 80 cardiotocographic tracings of pregnant women in the last trimester were collected, of which the minimum and maximum fetal heart rate were evaluated every 10 seconds, as well as its repetitions along with their probability and the diagnostic S/k ratio. Finally, the statistical analysis was carried out to establish the diagnostic capacity of the method concerning the clinical evaluation and interpretation of the cardiotocographic tracing, taken as the Gold Standard. Results: it was confirmed that S/k ratio values differentiated normal from abnormal fetal cardiac dynamics with sensitivity and specificity values of 100% and a Kappa coefficient of 1. Conclusion: the applicability of a diagnostic mathematical method of cardiotocography was confirmed, which suggests its implementation in the clinical context to detect alterations in fetal well-being in 20 minutes.