Related Experiment Video
Updated: Apr 18, 2026
09:24
Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable
Published on: May 17, 2024
2.4K
Smartphone Detection of Fetal Movements Using Artificial Intelligence.
Kenneth Moise1, Kelly Gaither, Anna Madden-Rusnak
1Department of Women's Health, Dell Medical School at the University of Texas at Austin, the Comprehensive Fetal Care Center at Dell Children's Medical Center, and the Texas Advanced Computing Center at the University of Texas at Austin; Austin, Texas.
Obstetrics and Gynecology
|April 16, 2026
Summary
Smartphone audio recordings can accurately detect fetal movements, including breathing and hiccups, surpassing maternal perception. This innovative method offers a reliable way to monitor fetal well-being non-invasively.
Area of Science:
- Biomedical Engineering
- Maternal-Fetal Medicine
- Signal Processing
Background:
- Fetal movement monitoring is crucial for assessing fetal well-being.
- Maternal perception of fetal movements is subjective and often inaccurate.
- Novel, objective methods for fetal movement detection are needed.
Purpose of the Study:
- To evaluate the efficacy of machine learning algorithms using smartphone audio recordings for detecting fetal movements.
- To compare the accuracy of smartphone-based detection with maternal perception and ultrasound.
Main Methods:
- A prospective study simultaneously recorded fetal movements via ultrasound and smartphone audio.
- Audio signals were processed to extract Mel-frequency cepstral coefficients (MFCCs).
- Machine learning models were trained to detect fetal movements, with ultrasound as the gold standard.
Main Results:
- The machine learning model demonstrated high accuracy in detecting fetal movements (AUROC 0.886).
- Detection accuracy for gross fetal movements was 64.0%, significantly higher than maternal perception (18.0%).
- Accurate detection of fetal breathing (93.0%) and hiccups (73.0%) was achieved, outperforming maternal perception.
Conclusions:
- Smartphone-based audio analysis is a reliable method for detecting various fetal movements.
- This technology offers a superior alternative to maternal perception for monitoring fetal activity.
- The findings support the potential of using smartphones for non-invasive fetal well-being assessments.
