METEROther pregnant women have grown accustomed to seeing their baby for the first time through a blurry black-and-white ultrasound, an image that can be shown to friends and family. But it remains a luxury in many parts of the world. Now artificial intelligence is being used to develop technology that can bring the long-awaited milestone of pregnancy closer to the women who most need medical monitoring of their baby’s health through ultrasound.
A pilot project in Uganda is using artificial intelligence software to power ultrasound imaging not only to scan fetuses but also to encourage women to attend health services earlier in their pregnancies, helping to reduce stillbirths and complications.
Low- and middle-income countries tend to have Very few Specialists trained to carry out the scans and the equipment are concentrated in urban hospitals, which can mean a long and expensive trip from the homes of rural women.
But seeing women in the early stages of pregnancy can be a matter of life or death, says Dr. Daniel Lukakamwa, an obstetrician and gynecologist at Kawempe National Referral Hospital in Uganda’s capital, Kampala, where they are helping to develop the artificial intelligence software.
“This has sparked a lot of interest among pregnant women to undergo ultrasounds,” says Lukakamwa. “People are very willing to participate in the study without any apprehension. We seem to be overwhelmed.”
Late presentation is a major problem for maternity services, says Lukakamwa. “The first trimester is very important in terms of abnormalities and perhaps later fevers leading to stillbirth,” she says.
AI-based ScanNav FetalCheck SoftwareThe software, developed by Intelligent Ultrasound, will allow gestational age to be determined accurately without the need for specialized sonographers to take measurements of the fetus in the womb to determine the progress of the pregnancy. The software has been trained with a database of millions of images to “recognize” the gestation of a pregnancy.
Is One of several AI programs that assess pregnancy. which are in different stages of testing and the first results are encouraging, according to the developers.
The technology also allows midwives or nurses to perform ultrasound scans, who simply have to pass a probe over the woman’s abdomen for the software to provide the data. It can also be combined with portable devices, making it possible to provide care for women at home.
At Kawempe Hospital, the aim of the trial is to create a tool to predict which pregnancies are at highest risk of stillbirth, but staff say it is already helping them engage with women earlier.
Radiologist Joness Biira says: “Mothers who have given birth have recommended that we take part in the study. They talk to them and more and more mothers are joining the research programme. They really like it and trust our results.”
The main challenge facing staff, he says, is “perhaps power cuts.”
For Sarah Kyolaba, 30, who lives in Kikoni village, technology has made her feel more in control of her second pregnancy.
“I can see how the baby moves,” she says, “how its internal organs are developing, and I can see everything while I’m having the ultrasound. It makes me happy to see my baby move.”
When she was pregnant with her son, now five, she found out at the last minute that he was too big and she would have to have a Caesarean section. “They told me I had to have a Caesarean section, but I wasn’t ready for that.”
AI is also being used in The largest study ever conducted A study on the use of aspirin to prevent preeclampsia is to be carried out in Kenya, Ghana and South Africa. It will compare the effects of two different doses of the drug in women at high risk of developing the disease.
After the newsletter promotion
The exact gestational age is vital for the trial. The risk of preeclampsia changes as pregnancy progresses and the prophylactic effect of aspirin depends on its early administration.
Dr Angela Koech, an obstetrician working in rural Kenya and a research scientist at Aga Khan University in Nairobi, said accurate dating was vital.
“The biggest challenge I face is when I have a mother, usually late in pregnancy, who has developed a complication and I need to make a decision about her,” says Koech, who has Led the research that guided the development of AI ultrasound programs.
“For example, if a woman has preeclampsia or hypertension during pregnancy and comes to me late in pregnancy, I can say, ‘Let’s deliver this baby now because her hypertension is severe.’
“But I need to know if this baby will survive. If this woman is 30 weeks, 32, 34, 36 or 38, the decision she makes will be very different.”
It would not be safe, she says, to deliver a very premature baby in a rural facility that does not have a neonatal unit. “When the mother tells me what her gestational age is based on her last period, which she is not sure of – and I cannot really trust it – then that decision becomes very difficult.”
According to Koech, many rural Kenyan women do not seek medical attention until they are well into their pregnancy. In some places it is considered “inappropriate to disclose a pregnancy before it is apparent,” while a visit to an antenatal clinic can cost money in travel costs and take many hours.
Dr Aris Papageorghiou, co-founder of Intelligent Ultrasound and director of clinical research at the Oxford Institute of Maternal and Perinatal Health, is aware of concerns that the technology could be seen as an inferior service for women in poorer countries.
“The right thing to do is to build capacity in those environments, to build the right equipment, to provide training, to have all the things that we have in high-income countries. But the reality is that over the last few decades, that just hasn’t happened. So I think that a stopgap solution, and it may just be a stopgap solution, is a good solution,” he said.