AI and machine learning could diagnose polycystic ovary syndrome, study shows

AI and machine learning could effectively detect and diagnose polycystic ovary syndrome (PCOS), a new study by the National Institutes of Health has found.

Researchers have systematically reviewed published scientific studies that used AI/ML to analyse data to diagnose and classify PCOS and found that AI/ML based programmes were able to successfully detect the condition which affects one in 10 women globally.

PCOS, the most common hormone disorder among women, affects the way the ovaries work and happens due to hormone imbalance in the pituitary gland and the ovaries. In many cases, it is accompanied by elevated levels of testosterone.

The disorder can cause irregular periods, acne, extra facial hair, or hair loss from the head. Women with PCOS are often at an increased risk for developing type two diabetes, as well as sleep, psychological, cardiovascular, and other reproductive disorders such as uterine cancer and infertility.

Diagnosis is based on widely accepted standardised criteria that have evolved over the years, but typically includes clinical features accompanied by laboratory and radiological findings.

However, because some of the features of PCOS can co-occur with other disorders such as obesity, diabetes, and cardiometabolic disorders, it frequently goes unrecognised.

Scientists suggested integrating large population-based studies with electronic health datasets and analysing common laboratory tests to identify sensitive diagnostic biomarkers that can facilitate the diagnosis of PCOS.

“Given the large burden of under- and mis-diagnosed PCOS in the community and its potentially serious outcomes, we wanted to identify the utility of AI/ML in the identification of patients that may be at risk for PCOS,” explained Janet Hall, senior investigator and endocrinologist at the National Institute of Environmental Health Sciences (NIEHS), part of NIH, and a study co-author.

“The effectiveness of AI and machine learning in detecting PCOS was even more impressive than we had thought.”

The researchers conducted a systematic review of all peer-reviewed studies published on this topic for the past 25 years (1997-2022) that used  AI/ML to detect PCOS.

With the help of an NIH librarian, the researchers identified potentially eligible studies. In total, they screened 135 studies and included 31 in this paper.

All studies were observational and assessed the use of AI/ML technologies on patient diagnosis. Ultrasound images were included in about  half the studies. The average age of the participants in the studies was 29.

Among the 10 studies that used standardised diagnostic criteria to diagnose PCOS, the accuracy of detection ranged from 80-90 per cent.

Skand Shekhar, senior author of the study and assistant research physician and endocrinologist at the NIEHS, said: “These data reflect the untapped potential of incorporating AI/ML in electronic health records and other clinical settings to improve the diagnosis and care of women with PCOS.

“Across a range of diagnostic and classification modalities, there was an extremely high performance of AI/ML in detecting PCOS, which is the most important takeaway of our study.”

The authors noted that AI/ML based programmes have the potential to significantly enhance our capability to identify women with PCOS early, with associated cost savings and a reduced burden of PCOS on patients and on the health system.

Follow-up studies with robust validation and testing practices will allow for the smooth integration of AI/ML for chronic health conditions, they added.