Butterfly iQ helps midwives perform ultrasound on the same level as trained sonographers, says study. (Picture courtesy of Butterfly Network)
Butterfly iQ puts midwives on par with trained sonographers, says study
April 19, 2022
by John R. Fischer, Senior Reporter
Butterfly Network’s handheld, whole-body ultrasounds can help midwives perform ultrasound at the same level as trained sonographers, according to a new study.
Butterfly iQ is a transducer that uses semiconductor technology to perform “whole-body imaging” with a single handheld probe. It leverages AI to generate quality images and connects to a mobile phone or tablet, and is powered by Butterfly’s proprietary Ultrasound-on-Chip technology. The company launched the solution in 2018 and a follow-up solution, Butterfly IQ+ in 2020.
Researchers at the University of North Carolina say the technology could help democratize and create greater access to obstetric ultrasound in rural settings and low-resource countries, which are strained by the high costs of equipment and a limited number of qualified sonographers.
“Armed with a pocket-sized Butterfly probe and a smartphone, a Zambian midwife with no prior training in sonography can assess gestational age as accurately as a certified sonographer using an expensive machine. This has the potential to revolutionize the delivery of obstetric care in settings like Zambia,” said Dr. Joni Price, an assistant professor of obstetrics and gynecology for UNC who lives full-time in Zambia, in a statement.
Price and her colleagues had 4,695 pregnant women in North Carolina and Zambia undergo blind ultrasound sweeps along with standard fetal measurements with a commercial ultrasound machine and Butterfly iQ. A trained neural network was used to estimate the gestational age from the sweeps.
The researchers assessed the AI model and biometry against previously established gestational age. The mean absolute error was 3.9 ±0.12 days for the model versus 4.7 ±0.15 days for biometry. Similar results were found in North Carolina and Zambia and the findings were supported in the test set of women who conceived by in vitro fertilization and in those from whom sweeps were carried out by untrained users with low-cost, battery-powered devices.
Due to the AI model’s accuracy and use among untrained providers, the findings indicate that Butterfly iQ could be used in low-resource settings like Zambia by untrained personnel like midwives. “The results of this study offer hope to millions of mothers when it comes to determining risk and sequencing care. The findings also reinforce our belief that mid-level practitioners, when armed with the right tools, can meaningfully improve outcomes and advance the standard of care,” said Dr. John Martin, chief medical officer at Butterfly Network.
The findings were published in NEJM Evidence.
Butterfly iQ is a transducer that uses semiconductor technology to perform “whole-body imaging” with a single handheld probe. It leverages AI to generate quality images and connects to a mobile phone or tablet, and is powered by Butterfly’s proprietary Ultrasound-on-Chip technology. The company launched the solution in 2018 and a follow-up solution, Butterfly IQ+ in 2020.
Researchers at the University of North Carolina say the technology could help democratize and create greater access to obstetric ultrasound in rural settings and low-resource countries, which are strained by the high costs of equipment and a limited number of qualified sonographers.
“Armed with a pocket-sized Butterfly probe and a smartphone, a Zambian midwife with no prior training in sonography can assess gestational age as accurately as a certified sonographer using an expensive machine. This has the potential to revolutionize the delivery of obstetric care in settings like Zambia,” said Dr. Joni Price, an assistant professor of obstetrics and gynecology for UNC who lives full-time in Zambia, in a statement.
Price and her colleagues had 4,695 pregnant women in North Carolina and Zambia undergo blind ultrasound sweeps along with standard fetal measurements with a commercial ultrasound machine and Butterfly iQ. A trained neural network was used to estimate the gestational age from the sweeps.
The researchers assessed the AI model and biometry against previously established gestational age. The mean absolute error was 3.9 ±0.12 days for the model versus 4.7 ±0.15 days for biometry. Similar results were found in North Carolina and Zambia and the findings were supported in the test set of women who conceived by in vitro fertilization and in those from whom sweeps were carried out by untrained users with low-cost, battery-powered devices.
Due to the AI model’s accuracy and use among untrained providers, the findings indicate that Butterfly iQ could be used in low-resource settings like Zambia by untrained personnel like midwives. “The results of this study offer hope to millions of mothers when it comes to determining risk and sequencing care. The findings also reinforce our belief that mid-level practitioners, when armed with the right tools, can meaningfully improve outcomes and advance the standard of care,” said Dr. John Martin, chief medical officer at Butterfly Network.
The findings were published in NEJM Evidence.