Women will soon be able to monitor the progress of their pregnancy thanks to groundbreaking wearable ultrasound technology.
Scientists at the University of California San Diego have developed a dime-sized patch that captures continuous live images deep inside the body for up to 24 hours.
As it stands, the technology was developed to monitor patients with heart disease and look for early warning signs of strokes and heart attacks.
But the team, led by Professor Sheng Xu, told DailyMail.com they are working on a version that can be used on pregnant women.
The wearable device is a small sticker that can remain on the skin for up to 24 hours, even during strenuous exercise. This is the first time that ultrasound technology can be used during sports
The sticker transmits and receives the ultrasound waves used to generate a constant stream of images of the four heart chambers in real time
The ultrasonic sticker must be physically attached to a computer, but the UC San Diego team is creating a wireless circuit for the patch.
That would be a big breakthrough on how healthcare workers can prevent and monitor chronic diseases.
Scaling up artificial intelligence machine learning technology to monitor the health of a fetus in the womb would be a huge boon to pregnant women in the US, who are more vulnerable to pregnancy-related death than women in the other wealthiest countries of the world. the world. world, such as France and Canada.
Most pregnancies are carried to term without any problems, but the number of complications is increasing. Between 2014 and 2018, pregnancy complications increased more than 16 percent, while childbirth complications increased more than 14 percent, according to Blue Cross Blue Shield.
The latest technology emerging from Dr. Xu is a big step towards making cumbersome and expensive ultrasounds more accessible.
It could be especially useful for pregnant women living in hard-to-reach areas with few gynaecologists/obstetricians willing to monitor their baby’s growth.
The device, which can be worn for 24 hours at a time, is currently only suitable for monitoring heart health and the risk of cardiovascular disease.
The postage stamp-sized patch takes continuous images of the heart’s four chambers at different angles to measure how much blood the heart is pumping, a sign of heart disease risk.
Dr. Xu said, “The technology enables anyone to use ultrasound on the go.”
“The increasing risk of heart disease calls for more sophisticated and inclusive monitoring procedures,” he added.
By providing patients and physicians with more granular details, continuous and real-time cardiac imaging monitoring is poised to fundamentally optimize and reshape the cardiac diagnosis paradigm.”
The wearable patch, which researchers say is softer than human skin, sends and receives ultrasound waves that then generate a constant stream of real-time images of the heart.
Machine learning technology analyzes scans using an AI algorithm that takes into account all functions of a healthy heart: stroke volume (the volume of blood the heart pumps out each beat), ejection fraction (the percentage of blood pumped out of the heart’s left ventricle each beat) and cardiac output (the amount of blood the heart pumps out each minute).
Too little blood flow means not enough oxygenated blood is being pumped through the heart, usually due to a partial or complete blockage of your heart’s coronary arteries.
Ruixiang Qi, a master’s student in the Xu group at UC San Diego, said, “We use this machine learning model to calculate cardiac volume based on the shape and area of the left ventricle segmentation. The deep learning model with image segmentation is the first to be functionalized in portable ultrasound devices.
How would the AI sticker work?
Scientists at UC San Diego have created an ultrasound device that can assess both the structure and function of the human heart.
Once applied to a person’s skin, the wearable heart monitor provides real-time, automated insights into the heart’s hard-to-record blood pumping activity.
It even works when a person is training to analyze the amount of blood the heart is pumping, the first time this has ever been done.
A unique algorithm designed by the researchers is based on a machine learning model that can spit out numbers that reflect blood flow.
It can be worn for up to 24 hours.
The current iteration of the patch is wired to a computer that automatically downloads the data while the patch is still active.
The team developed a wireless circuit for the patch. This development will be reported.
“This allows the device to provide accurate and continuous waveforms of key cardiac indices in various physical states, including static and post-exercise, which has never been achieved before.”
AI is increasingly being used to diagnose serious health problems such as breast and colon cancer. And heart disease is a leading cause of death among Americans. Every 34 seconds, a person dies from cardiovascular disease in the US.
The Covid-era lockdowns that caused economies to grind to a halt also increased deaths from heart disease.
In 2020, about 697,000 people in the US died of heart disease, meaning one in five deaths can be attributed to it. ‘
The UC San Diego team isn’t alone in its search for wearable diagnostic technology.
A team of physician-scientists at the Smidt Heart Institute at Cedars-Sinai in Los Angeles has created an AI tool that can effectively identify and differentiate two life-threatening heart conditions, hypertrophic cardiomyopathy and cardiac amyloidosis, that are difficult for cardiologists to understand. place.
The team’s new algorithm relied on more than 34,000 cardiac ultrasound videos from the echocardiography laboratories of Cedars-Sinai and Stanford Healthcare to identify features related to the thickness of heart walls and the size of heart chambers to identify patients as potentially suffering from heart disease. .
Researchers at the Massachusetts Institute of Technology (MIT) have created a similar little sticker that can capture live continuous images of what’s happening deep inside the body for up to 48 hours