A team of researchers from the University of Washington has developed DopFone, a smartphone-based system that accurately estimates fetal heart rate using only a standard smartphone’s speaker and microphone. The technology mimics the function of a traditional Doppler ultrasound by emitting a low-frequency tone and analyzing the subtle changes in its echo caused by the fetal heartbeat. The app works by placing the phone’s microphone against the user’s abdomen for one minute. It emits a subaudible 18-kilohertz tone—chosen because it can be detected by smartphone microphones and penetrates tissue effectively—while the fetus’s heartbeat creates tiny shifts in the returning sound waves. A machine learning model then processes the audio data, along with the patient’s demographic information, to estimate the fetal heart rate. In a clinical trial conducted at UW Medicine’s maternal-fetal medicine division, DopFone was tested on 23 pregnant women between 19 and 39 weeks of gestation. The system achieved an average error of just 2.1 beats per minute, well within the accepted clinical tolerance of ±8 bpm. While accuracy was slightly reduced for patients with higher body mass indexes, all readings remained within normal ranges. The app was not tested on patients with irregular heartbeats, as such conditions are considered medical emergencies requiring immediate professional attention. Traditional Doppler ultrasounds, the current clinical standard, are highly accurate but require expensive equipment and trained technicians, making them inaccessible in many low-resource settings. DopFone offers a low-cost, scalable alternative that could empower pregnant individuals to monitor fetal health at home, especially in areas with limited access to medical care. Lead author Poojita Garg, a doctoral student in the Paul G. Allen School of Computer Science & Engineering, emphasized the potential of the tool to shift from infrequent clinic visits to regular, at-home monitoring. “Eventually, DopFone could let people test fetal heart rate regularly, rather than relying on the intermittent tests at a doctor’s office, or not getting tested at all,” she said. “Patients might then send this data to doctors so they can better assess their health even when they’re not in a clinic.” The team plans to expand testing beyond the lab to collect more diverse data and further refine the model. Their ultimate goal is to release DopFone as a publicly available app, making fetal monitoring more accessible and equitable. “This women’s health space is often overlooked,” Garg said. “So I want to focus on accessible alternatives that can be available to people in low-resource areas, whether that’s here in the U.S. or in other countries. Because health belongs to everyone.”