University of Washington researchers developed DopFone, an AI system using smartphone hardware to estimate fetal heart rate accurately.
Key Details
- 1DopFone utilizes an off-the-shelf smartphone's speaker and microphone to mimic Doppler ultrasound.
- 2A machine learning model analyzes echoes to estimate fetal heart rate.
- 3Clinical test on 23 pregnant women showed average error of 2 bpm, well within the accepted 8 bpm clinical threshold.
- 4Accuracy was slightly reduced in patients with higher BMI, but remained within safe limits.
- 5Published in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (Dec 2025).
- 6The goal is to make the app publicly available, particularly improving access in low-resource settings.
Why It Matters
DopFone represents a low-cost, accessible alternative to traditional Doppler ultrasound technology—a significant advancement for fetal monitoring, especially in regions lacking medical equipment or staff. Its successful clinical validation highlights AI's expanding role in democratizing access to essential imaging-driven health information.
Source
EurekAlert
Related News
•EurekAlert
NIH-Backed AI Model Predicts Cancer Survival Using Single-Cell Data
Researchers have developed scSurvival, a machine learning tool that uses single-cell tumor data to accurately predict cancer patient survival and identify high-risk cell populations.
•EurekAlert
Deep Learning Pathomics Platform Improves Immunotherapy Prediction in Lung Cancer
A deep learning pathomics platform accurately predicts immunotherapy response in metastatic NSCLC using routine pathology slides.
•EurekAlert
AI Pathology Model Outperforms PD-L1 in Predicting NSCLC Immunotherapy Response
MD Anderson's Path-IO machine learning platform accurately predicts immunotherapy responses in metastatic non-small cell lung cancer, surpassing current biomarker standards.