Researchers develop AI-powered device to detect signs of ovulation

Researchers with the Brigham and Women’s Hospital (BWH) in Boston have developed a device that uses AI to automatically detect signs of ovulation in women, according to a recent study published in Lab on a Chip. The device could mean a more cost-effective and accurate resource for women looking to plan or prevent pregnancy.  

The device was extremely effective in predicting ovulation––99 percent accurate. It’s performance was evaluated by using artificial saliva and human saliva samples from six subjects. The device solves the problem of tricky interpretations of fern patterns––markers of ovulation.

“One of the biggest problems with saliva-based tests, we realized, was that users find it difficult to interpret the fern patterns,” Prudhvi Thirumalaraju, study co-author and senior research assistant at the Shafiee Lab, said in a statement. “We figured that advances in AI can be put to good use here, to help people get objective results on their smartphones.”

By using AI, a microfluidic device and a smartphone, researchers developed the device to automatically detect fern patterns by analyzing saliva samples. The AI algorithm for the device was trained using 1.4 million ImageNet images and retrained using more than 1,500 salivary ferning images until it was able to classify saliva samples into two categories: ovulating and non-ovulating samples.

To make the classification, saliva is collected onto a microfluidic device, smeared and left to air dry. The device and saliva sample is inserted into a 3D-printed optical attachment connected to a smartphone. The software then analyzes the fern patterns, determining if a woman is ovulating or not. Additionally, no physician is needed to perform the test since the device allows women to collect and test saliva samples on their own.

Several smartphone apps, like Dot and Flo, have had success using AI to help users plan and predict pregnancy and provide information about menstrual cycles. Other current methods for monitoring ovulation are typically costly or subjective, according to a press release. 

“One of the biggest advantages to this method is cost––whereas the cost of non-reusable urine stick tests can add up to $210 to $240 over the course of six months, our device represents the possibility of a one-time purchase,” study co-author Manoj Kumar Kanakasabapathy, senior research assistant in the Shafiee Lab, said in a statement. “Beyond human ovulation, there are applications here as well for animal breeding and even for dry eye disease, which can also produce fern-like patterns in samples from eye mucosa.”

Following the success of their device, researchers plan to do additional testing on a larger population and eventually seek FDA approval.

“Before we started this project, we weren’t aware that such a need existed. When we published last year on a technology for analyzing sperm to detect male infertility, we were approached by those who had read about our work and were wondering if we could develop a smart-phone based system to provide ovulation testing at home,” corresponding author Hadi Shafiee, PhD, principal investigator at the BWH Division of Engineering in Medicine and Renal Division of Medicine, said in a statement. “Our study indicates that an accurate, automated and low-cost test is indeed possible.”