Exploring Random Forest Machine Learning for Fetal Movement Detection Using Abdominal Acceleration and Angular Rate Data
Student Contest:
No
Affiliation Type:
Academia
Keywords:
wearable, IMU, features, maternal perception, PPV
Abstract:
Fetal movement is a commonly monitored indicator of fetal wellbeing with reductions in fetal movement being associated with poor perinatal outcomes. However, more informative datasets are required for improved clinical decision making. Wearable sensors coupled with ML methods could support accurate detection of fetal movement. Prior work has demonstrated the feasibility of accelerometer-based detection, but using angular rate data to train ML models has not been fully explored. The goal of this study was to train and validate ML models using acceleration and angular rate features for fetal movement detection. Ten pregnant participants wore four abdominal IMUs and one chest reference and used a handheld toggle to indicate perceived fetal movement. Three random forest classifiers were trained on acceleration features, angular rate features, and a combination of both. Performance was reported in terms of AUROC and standard metrics. All three models achieved good performance (AUROC = 0.70-0.77). The model combining acceleration and angular rate features achieved a notably higher PPV compared to the other models developed, indicating discriminative power over either feature set alone.
Track ID:
12
Track Name:
Technology for Women & Children’s Health/Equity and Access for Well-health