The AI algorithm of an American entrepreneur from India can detect the healthiest sperm
To develop the sperm health test algorithm, the team at the California-based Oma Fertility Clinic scanned sperm from the ejaculates of more than 1,000 men.
New Delhi: An Indian-origin American entrepreneurial company is working on a new artificial intelligence (AI)-based algorithm that can identify the healthiest sperm, an advancement that could reduce the time and cost of in vitro fertilization (IVF) pregnancies.
To develop the sperm health test algorithm, the team at the California-based Oma Fertility Clinic scanned sperm from the ejaculates of more than 1,000 men, the Daily Mail reported.
The AI algorithm scans sperm cells for their shape and how fast they move to pick out the best ones for fertilizing an egg – a process the company believes will increase success rates with IVF and lower costs as couples spend less need rounds of treatment.
“As it stands, couples have to go through an average of three IVF cycles,” Dr Kiran Joshi, co-founder of Oma Robotics, told DailyMail.
“We want to reduce that number because that will reduce pain and financial burden and lead to greater success,” he said.
According to studies, about 40 percent of infertility cases are due to the male partner having a low sperm count.
The semen samples for the algorithm mostly came from men in their 30s and 40s, from all over the US and other countries. Some also ranged up to age 75.
The team of dr. Joshi extracted and analyzed a portion of semen from each sample — which contained up to 20,000 sperm cells, based on their shape and how well they swim — an exercise Dr. Joshi referred to as “like looking for a needle in a haystack”. report said.
A healthy sperm cell has a smooth and oval-shaped head and will also be able to swim quickly and in a straight line.
The sperm was assessed against these two aspects using standardized measurements and then a video of about 10 seconds of each was recorded, which was then fed into the AI to give it the ability to accurately estimate how healthy a certain sperm.
The AI algorithm delivers results within seconds. It draws a box around each sperm and then quickly assigns a color based on the sperm’s perceived health. The red boxes indicate unhealthy sperm, while green indicates healthy, the report said.
The findings, which show a “significant” difference between the two groups, will be published soon in an academic journal, the team said.