Polycystic ovary syndrome (PCOS) is the most common hormonal problem that usually affects women between the ages of 15 and 45, and it can be effectively treated using artificial intelligence (AI) and machine learning (ML). It can be detected and diagnosed, a recent national laboratory claims. Health (NIH) Research.
Researchers thoroughly reviewed published scientific papers that utilize AI/ML to diagnose and classify PCOS and found that such programs are effective in doing so.
“Given the high burden of underdiagnosis and misdiagnosis of PCOS in the community and its potentially severe outcomes, we wanted to confirm the utility of AI/ML in identifying patients who may be at risk for PCOS. ” said Janet Hall. She is an MD, senior investigator and endocrinologist at the National Institute of Environmental Health Sciences (NIEHS), part of the NIH, and a co-author of the study. “The effectiveness of AI and machine learning in detecting PCOS was even more impressive than we thought.”
Diagnosis challenges for PCOS
PCOS is characterized by inadequate ovarian function and is often accompanied by high testosterone levels. This disease can cause irregular menstrual cycles, acne, excess facial hair, or hair loss.
Type 2 diabetes, sleep problems, psychological problems, heart disease, and reproductive issues such as uterine cancer and infertility are all common risks for women with PCOS.
“PCOS can be difficult to diagnose given its overlap with other symptoms,” said Sukand Shekhar, MD, lead author of the study and associate investigator and endocrinologist at NIEHS. Ta. “These data reflect the untapped potential of incorporating her AI/ML into electronic medical records and other clinical settings to improve the diagnosis and care of women with PCOS.”
To find sensitive diagnostic biomarkers to help diagnose PCOS, the study authors advised combining large population-based studies with electronic health datasets and considering standard clinical tests.
PCOS diagnostic criteria and the role of AI/ML
Diagnosis is made using standardized criteria that have been developed over time and are generally recognized.
These criteria typically include clinical signs and symptoms (such as acne, excessive hair growth, and irregular periods) as well as laboratory and radiological findings (such as multiple small cysts on an ovarian ultrasound or an enlarged ovary). ) It is included. +
Artificial intelligence (AI) is the use of computer-based tools or systems that simulate human intelligence and support prediction and decision-making. ML is a branch of AI that focuses on using knowledge from the past to inform decisions in the present.
AI is the perfect tool to help identify hard-to-diagnose conditions like PCOS because it can process vast amounts of diverse data, including data collected from electronic medical records.
Review the findings
Over the past 25 years (1997-2022), all peer-reviewed studies that used AI/ML to identify PCOS were systematically examined by researchers.
The researchers identified eligible prospective studies with the help of specialized NIH librarians. They screened a total of 135 studies, of which 31 were used for this paper.
Each observational study evaluated how AI/ML technology is being used to diagnose patients. About half of the studies included ultrasound images. The average age of study participants was 29 years.
Accuracy in detecting PCOS ranged from 80 to 90% across 10 studies that used standardized diagnostic criteria to make the diagnosis.
“We obtained very high performance of AI/ML in detecting PCOS across a variety of diagnostic and classification techniques, which is the most important outcome of our study,” said Shekhar.
The authors conclude that AI/ML-based programs could significantly improve the ability to detect PCOS in women early, potentially leading to economic savings and reducing the burden of PCOS on patients and healthcare systems. I’m pointing it out.
Seamless integration of AI/ML for chronic health disorders is enabled by follow-up studies with strong validation and testing procedures.