Automatic fetal movement recognition from multi-channel accelerometry data

A wearable fetal movement detection system for pregnant women

A wearable device-based fetal movement detection system for pregnant women is proposed to resolve the problems of low accuracy of fetal movement detection by fetal heart monitor, difficulties of fetal movement monitoring by pregnant women in person, and inability to monitor for long periods of time by ultrasonic Doppler imaging device. The overall software design flow of the system is proposed after determining the overall structure of the system based on symmetric sensor. The application circuit of the three-axis acceleration sensor MC3672 and its supporting sensor data collection program are designed, and the application circuit of the main control chip NRF52840 with Cortex-M4 core is analyzed. The function of data collection and algorithm recognition result transfer to a smartphone is realized through the fetal movement recognition and algorithm design and Bluetooth communication design. Finally, the system test scheme is introduced, which involves performing functional tests on four healthy pregnant volunteers and analyzing the results. The experimental results show that the average recognition rate and correct rate of this system to recognize fetal movement is 89.74% when using the real fetal movement actively perceived by pregnant women as the standard, achieving a domestic and wearable design of fetal movement monitoring device for pregnant women that can be used to analyze and predict the fetal health condition.

Clinical Assessment of Fetal Well-Being and Fetal Safety Indicators

Delivering safe clinical trials of novel therapeutics is central to enable pregnant women and their babies to access medicines for better outcomes. This review describes clinical monitoring of fetal well‐being and safety. Current pregnancy surveillance includes regular antenatal checks of blood pressure and urine for signs of gestational hypertension. Fetal and placental development is assessed routinely using the first‐trimester “dating” and mid‐trimester “anomaly” ultrasound scans, but the detection of fetal anomalies can continue throughout pregnancy using targeted sonography or magnetic resonance imaging (MRI). Serial sonography can be used to assess fetal size, well‐being, and placental function. Carefully defined reproducible imaging parameters, such as the head circumference (HC), abdominal circumference (AC), and femur length (FL), are combined to calculate an estimate of the fetal weight. Doppler analysis of maternal uterine blood flow predicts placental insufficiency, which is associated with poor fetal growth. Fetal doppler analysis can indicate circulatory decompensation and fetal hypoxia, requiring delivery to be expedited. Novel ways to assess fetal well‐being and placental function using MRI, computerized cardiotocography (CTG), serum circulating fetoplacental proteins, and mRNA may improve the assessment of the safety and efficacy of maternal and fetal interventions. Progress has been made in how to define and grade clinical trial safety in pregnant women, the fetus, and neonate. A new system for improved safety monitoring for clinical trials in pregnancy, Maternal and Fetal Adverse Event Terminology (MFAET), describes 12 maternal and 18 fetal adverse event (AE) definitions and severity grading criteria developed through an international modified Delphi consensus process. This fills a vital gap in maternal and fetal translational medicine research.

Improving Development of Drug Treatments for Pregnant Women and the Fetus

The exclusion of pregnant populations, women of reproductive age, and the fetus from clinical trials of therapeutics is a major global public health issue. It is also a problem of inequity in medicines development, as pregnancy is a protected characteristic. The current regulatory requirements for drugs in pregnancy are being analyzed by a number of agencies worldwide. There has been considerable investment in developing expertise in pregnancy clinical trials (for the pregnant person and the fetus) such as the Obstetric-Fetal Pharmacology Research Centers funded by the National Institute of Child Health and Human Development. Progress has also been made in how to define and grade clinical trial safety in pregnant women, the fetus, and neonate. Innovative methods to model human pregnancy physiology and pharmacology using computer simulations are also gaining interest. Novel ways to assess fetal well-being and placental function using magnetic resonance imaging, computerized cardiotocography, serum circulating fetoplacental proteins, and mRNA may permit better assessment of the safety and efficacy of interventions in the mother and fetus. The core outcomes in women’s and newborn health initiative is facilitating the consistent reporting of data from pregnancy trials. Electronic medical records integrated with pharmacy services should improve the strength of pharmacoepidemiologic and pharmacovigilance studies. Incentives such as investigational plans and orphan disease designation have been taken up for obstetric, fetal, and neonatal diseases. This review describes the progress that is being made to better understand the extent of the problem and to develop applicable solutions.

Passive Fetal Movement Recognition Approaches Using Hyperparameter Tuned LightGBM Model and Bayesian Optimization

Fetal movement is an important clinical indicator to assess fetus growth and development status in the uterus. In recent years, a noninvasive intelligent sensing fetal movement detection system that can monitor high-risk pregnancies at home has received a lot of attention in the field of wearable health monitoring. However, recovering fetal movement signals from a continuous low-amplitude background that is heavily contaminated with noise and recognizing real fetal movements is a challenging task. In this paper, fetal movement can be efficiently recognized by combining the strength of Kalman filtering, time and frequency domain and wavelet domain feature extraction, and hyperparameter tuned Light Gradient Boosting Machine (LightGBM) model. Firstly, the Kalman filtering (KF) algorithm is used to recover the fetal movement signal in a continuous low-amplitude background contaminated by noise. Secondly, the time domain, frequency domain, and wavelet domain (TFWD) features of the preprocessed fetal movement signal are extracted. Finally, the Bayesian Optimization algorithm (BOA) is used to optimize the LightGBM model to obtain the optimal hyperparameters. Through this, the accurate prediction and recognition of fetal movement are successfully achieved. In the performance analysis of the Zenodo fetal movement dataset, the proposed KF + TFWD + BOA-LGBM approach's recognition accuracy and F1-Score reached 94.06% and 96.85%, respectively. Compared with 8 existing advanced methods for fetal movement signal recognition, the proposed method has better accuracy and robustness, indicating its potential medical application in wearable smart sensing systems for fetal prenatal health monitoring.