At the American Association of Clinical Endocrinology’s annual conference, Skand Shekhar MD, an assistant research physician and endocrinologist at the National Institute of Environmental Health believe that artificial intelligence and machine learning may be useful for detecting and classifying polycystic ovary syndrome (PCOS). His conclusion was supported by the data from a systematic review and meta-analysis of 31 observational studies from nine to 2000 participants.
The studies used clinical data and imaging, with AI/machine learning techniques such as support vector machine (42%), K-nearest neighbor (26%) and regression models (23%) to evaluate the performance of AI in the detection of PCOS. Results indicated extremely high performance for AI and machine learning models, with area under the receiver operating characteristic curves varying between 73% and 100%. Diagnostic accuracy, sensitivity, specificity, positive predictive value, and negative predictive value were also very high.
These findings suggest that AI and machine learning may be highly useful tool, together with standardized criteria of diagnosing PCOS in order to reduce diagnostic delays and to possibly help reduce the number of people suffering from PCOS without a proper diagnosis.
Skand Shekhar encourages future studies to use AI and machine learning within electronic health records and to involve more clinician input. Shekhar further believes that this could open up an exciting new pathway to help improve the health and wellbeing of countless PCOS patients all over the world.
The National Institute of Environmental Health Sciences (NIH) is a part of the United States Department of Health and Human Services. The mission of the NIH is to seek fundamental knowledge about the nature and behavior of living systems, and the application of that knowledge to enhance health, lengthen life, and reduce illness and disability. Skand Shekhar is an assistant research physician and endocrinologist at the NIH with expertise in the fields of diabetes, agrometeorology, and air pollution and the environment. His passions are to research and identify new resources for healthcare and promote ways to prevent and manage chronic conditions by advancing personalized medicine.
