Automated Software Analysis of Fetal Movement Recorded during a Pregnant Woman's Sleep at Home

Made to move: A review of measurement strategies to characterize heterogeneity in normal fetal movement

Fetal movement is a crucial indicator of fetal well-being. Characteristics of fetal movement vary across gestation, posing challenges for researchers to determine the most suitable assessment of fetal movement for their study. We summarize the current measurement strategies used to assess fetal movement and conduct a comprehensive review of studies utilizing these methods. We critically evaluate various measurement approaches including subjective maternal perception, ultrasound, Doppler ultrasound, wearable technology, magnetocardiograms, and magnetic resonance imaging, highlighting their strengths and weaknesses. We discuss the challenges of accurately capturing fetal movement, which is influenced by factors such as differences in recording times, gestational ages, sample sizes, environmental conditions, subjective perceptions, and characterization across studies. We also highlight the clinical implications of heterogeneity in fetal movement assessment for monitoring fetal behavior, predicting adverse outcomes, and improving maternal attachment to the fetus. Lastly, we propose potential areas of future research to overcome the current gaps and challenges in measuring and characterizing abnormal fetal movement. Our review contributes to the growing body of literature on fetal movement assessment and provides insights into the methodological considerations and potential applications for research.

Effect of ritodrine hydrochloride infusion on fetal movement with the use of a fetal movement acceleration measurement recorder (FMAM recorder)

AIM

To investigate the effect of ritodrine hydrochloride infusion on fetal movement.

METHOD

We gathered 20 pregnant women who received ritodrine hydrochloride infusion as the treated group, and 147 pregnant women who did not as the control group. All women recorded gross fetal movement with the fetal movement acceleration measurement recorder after 28 gestational weeks. The record was divided into epochs of 10 s, and the ratio of movement-positive epochs to all epochs was calculated as the fetal movement index. Furthermore, the mean duration and the mean number per hour of no-fetal movement period, where the fetus did not move for 5 min or more, were calculated as the indexes of no-fetal movement. All indexes were compared between the two groups at 28-31 and 32-35 gestational weeks.

RESULTS

The fetal movement indexes (%) were 17.29 ± 7.46 (mean ± SD) in the control group and 13.65 ± 7.13 in the treated group at 28-31 weeks (p = 0.139). At 32-35 weeks, they were 14.55 ± 6.43 and 18.50 ± 5.33, respectively (p = 0.03). Similarly, the no-fetal movement indexes (min, times/h) were 15.03 ± 10.99 and 1.61 ± 0.88, and 18.70 ± 15.80 and 1.75 ± 0.96 (p = 0.824, and 0.673) at 28-31 weeks. At 32-35 weeks, they were 18.13 ± 10.88 and 1.95 ± 0.97, and 9.20 ± 5.51 and 1.14 ± 0.71, respectively (p = 0.003, and 0.003).

CONCLUSION

Ritodrine hydrochloride infusion increased the fetal movement and decreased the no-fetal movement period at 32-35 weeks.

Passive Fetal Movement Signal Detection System Based on Intelligent Sensing Technology

Fetal movement (FM) is an essential physiological parameter to determine the health status of the fetus. To address the problems of harrowing FM signal extraction and the low recognition rate of traditional machine learning classifiers in FM signal detection, this paper develops a passive FM signal detection system based on intelligent sensing technology. FM signals are obtained from the abdomen of the pregnant woman by using accelerometers. The FM signals are extracted and identified according to the clinical nature of the features hidden in the amplitude and waveform of the FM signals that fluctuate in duration. The system consists of four main stages: (i) FM signal preprocessing, (ii) maternal artifact signal preidentification, (iii) FM signal identification, and (iv) FM classification. Firstly, Kalman filtering is used to reconstruct the FM signal in a continuous low-amplitude noise background. Secondly, the maternal artifact signal is identified using an amplitude threshold algorithm. Then, an innovative dictionary learning algorithm is used to construct a dictionary of FM features, and orthogonal matching pursuit and adaptive filtering algorithms are used to identify the FM signals, respectively. Finally, mask fusion classification is performed based on the multiaxis recognition results. Experiments are conducted to evaluate the performance of the proposed FM detection system using publicly available and self-built accelerated FM datasets. The classification results showed that the orthogonal matching pursuit algorithm was more effective than the adaptive filtering algorithm in identifying FM signals, with a positive prediction value of 89.74%. The proposed FM detection system has great potential and promise for wearable FM health monitoring.

A systematic scoping review to identify the design and assess the performance of devices for antenatal continuous fetal monitoring

BACKGROUND

Antepartum fetal monitoring aims to assess fetal development and wellbeing throughout pregnancy. Current methods utilised in clinical practice are intermittent and only provide a 'snapshot' of fetal wellbeing, thus key signs of fetal demise could be missed. Continuous fetal monitoring (CFM) offers the potential to alleviate these issues by providing an objective and longitudinal overview of fetal status. Various CFM devices exist within literature; this review planned to provide a systematic overview of these devices, and specifically aimed to map the devices' design, performance and factors which affect this, whilst determining any gaps in development.

METHODS

A systematic search was conducted using MEDLINE, EMBASE, CINAHL, EMCARE, BNI, Cochrane Library, Web of Science and Pubmed databases. Following the deletion of duplicates, the articles' titles and abstracts were screened and suitable papers underwent a full-text assessment prior to inclusion in the review by two independent assessors.

RESULTS

The literature searches generated 4,885 hits from which 43 studies were included in the review. Twenty-four different devices were identified utilising four suitable CFM technologies: fetal electrocardiography, fetal phonocardiography, accelerometry and fetal vectorcardiography. The devices adopted various designs and signal processing methods. There was no common means of device performance assessment between different devices, which limited comparison. The device performance of fetal electrocardiography was reduced between 28 to 36 weeks' gestation and during high levels of maternal movement, and increased during night-time rest. Other factors, including maternal body mass index, fetal position, recording location, uterine activity, amniotic fluid index, number of fetuses and smoking status, as well as factors which affected alternative technologies had equivocal effects and require further investigation.

CONCLUSIONS

A variety of CFM devices have been developed, however no specific approach or design appears to be advantageous due to high levels of inter-device and intra-device variability.

Correlation between newborn size and gross fetal movement as counted by a fetal movement acceleration measurement recorder

The development of the fetal movement acceleration measurement (FMAM) recorder has enabled the accurate counting of gross fetal movements. The aim of the study was to investigate whether gross fetal movement is related to a newborn's size. A total of 90 pregnant women who delivered singleton infant at term were recruited. Gross fetal movements were counted using an FMAM recorder during maternal sleep. The ratio of movement positive 10-s epochs to all epochs during one night was calculated as an index of fetal movement. Independent explanatory variables for the fetal movement index were selected from eight possibilities, that is, maternal age, gestational week, and the six physical measures of the newborn (height, weight, head circumference, chest circumference, Kaup index, and the ratio of head to chest circumference) with the stepwise regression procedure. The selected physical variables and the fetal movement index were analyzed using multiple regression analysis. A total of 2812.95 h from 423 night records were available. Gestational weeks and weight of the newborn were selected as the significant independent variables. Multiple regression analysis revealed that newborn weight had a positive correlation with the fetal movement index (p < 0.0001). The multiple regression equation was "The fetal movement index (%) = 34.9989-0.9088 × gestational weeks + 0.0033 × newborn weight (g)." A person's physical ability and lifetime activity level may originate from fetal health. This study may provide a new way of looking at the Developmental Origins of Health and Disease theory.

Counting fetal movements of small-for-gestational infants using a fetal movement acceleration measurement recorder

Background: Our purpose was to clarify whether small-for-gestational (SGA) infants is associated with a decrease in fetal movements (FMs) even in the absence of hypoxia. We used a fetal movement acceleration measurement (FMAM) recorder, which enabled counting gross FMs for hours at a time.Methods: (1) Parameters of FMs for 13 women who delivered SGA infants were plotted over normal reference value curves made from 64 normal pregnant women in another study. (2) Linear regression analysis was conducted for the women with SGA infants and the normal pregnant women.Results: Thirty-eight data recordings were available in the SGA group. (1) For the ratio of movement positive 10-s epoch, 14 recordings (36.8%) were below 10% of the normal values. For an average number of movements, 13 (34.2%) were below 10%. Regarding average number, average duration, and longest duration of non-movement period, 12 (31.6%), 13 (34.2%), and 15 records (39.4%) were above 90% of the normal values, respectively. (2) SGA was a factor that decreased the positive epoch ratio and the average movements number, and increased the average number and duration, and the longest duration of non-movement period.Conclusions: SGA is associated with decreased movements even in the absence of hypoxia.

Correlation between umbilical cord length and gross fetal movement as counted by a fetal movement acceleration measurement recorder

Introduction

The fetal movement acceleration measurement (FMAM) recorder has made it possible to count gross fetal movements over many hours. Our purpose was to examine the relationship between umbilical cord length and fetal movements as counted by the FMAM recorder.

Methods

Sixty-two pregnant women recorded fetal movements weekly from 28 weeks to term. The ratio of 10-s periods in which movement occurred to total time was calculated as a movement index. Umbilical cord length was measured at delivery. (1) Multiple linear regression analyses were conducted with six explanatory variables (primipara / multipara, anterior / posterior located placenta, placental weight, the mean movement index of 28-31, 32-35, and 36-39 week) and a response valuable (umbilical cord length). (2) All women were divided into groups of shorter, middle, and longer cord length, specifically less than 50 cm, between 50 and 60 cm, and more than 60 cm. The movement index was compared among the three groups at 28-31, 32-35, and 36-39 weeks.

Results

A total of 2355.6 h from 368 night records were available. (1) There were no relationships between the cord length and the movement index of 28-31, 32-35, and 36-39 weeks (p = 0.090, 0.235, 0.129, respectively). (2) There were no differences in the movement index among the three groups at 28-31 and 32-35 gestational weeks (p = 0.096, and 0.465, respectively); however, the longer cord group had a greater movement index than the other two groups at 36-39 weeks (p = 0.0008).

Discussion

This study suggested that fetal movement near term is an important factor in determining whether cord length becomes relatively longer in normal pregnancies.

Reference values for a fetal movement acceleration measurement recorder to count fetal movements

BackgroundA newly developed fetal movement acceleration measurement recorder has made it possible to count gross movements for hours. The purpose of this study was to determine the normal reference values for such movements.MethodsOne hundred and six pregnant women recorded fetal movements by themselves when they slept at home weekly from 28 weeks to term. The normal reference values were determined based on the data that could be recorded for more than 4 h per night.ResultsA total of 2,458 h of data from 385 recordings from 64 women was available. The median ratio of 10-s periods in which fetal movements occurred to the total time interval was 17% at 28 gestational weeks, decreasing to ∼6% at term. The number of fetal movements was 74 times/h, decreasing to 29 times at term. The number, the mean, and the longest durations of periods with no fetal movement, meaning no fetal movements were found for more than 5 min, were 1.56 times/h, 7.95 and 14.25 min, respectively, at 28 weeks, and increasing to 2.54 times, and 9.63 and 19.67 min, respectively, at term.ConclusionsThis study provides normal reference values for gross fetal movement count using the fetal movement acceleration measurement recorder.

Detection of fetal kicks using body-worn accelerometers during pregnancy: Trade-offs between sensors number and positioning

Monitoring fetal wellbeing is key in modern obstetrics. While fetal movement is routinely used as a proxy to fetal wellbeing, accurate, noninvasive, long-term monitoring of fetal movement is challenging. A few accelerometer-based systems have been developed in the past few years, to tackle common issues in ultrasound measurement and enable remote, self-administrated monitoring of fetal movement during pregnancy. However, many questions remain unanswered to date on the optimal setup in terms of body-worn accelerometers as well as signal processing and machine learning techniques used to detect fetal movement. In this paper, we systematically analyze the trade-offs between sensor number and positioning, the presence of reference accelerometers outside of the abdominal area and provide guidelines on dealing with class imbalance. Using a dataset of 15 measurements collected employing 6 three-axial accelerometers we show that including a reference accelerometer on the back of the participant consistently improves fetal movement detection performance regardless of the number of sensors utilized. We also show that two accelerometers plus a reference accelerometer are sufficient for optimal results.