By
Artificial intelligence (AI) and machine studying (ML) have proven high efficacy in detecting and diagnosing Polycystic Ovary Syndrome (PCOS), a prevalent hormone dysfunction in women, in accordance with a research by the National Institutes of Health.
NIH research critiques 25 years of knowledge and finds AI/ML can detect frequent hormone dysfunction.
Artificial intelligence (AI) and machine studying (ML) can successfully detect and diagnose Polycystic Ovary Syndrome (PCOS), which is the most typical hormone dysfunction amongst women, sometimes between ages 15 and 45, in accordance with a brand new research by the National Institutes of Health (NIH). Researchers systematically reviewed revealed scientific research that used AI/ML to research knowledge to diagnose and classify PCOS and located that AI/ML primarily based packages had been in a position to efficiently detect 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,” mentioned Janet Hall, M.D., senior investigator and endocrinologist on the National Institute of Environmental Health Sciences (NIEHS), a part of NIH, and a research co-author. “The effectiveness of AI and machine learning in detecting PCOS was even more impressive than we had thought.”
Challenges of Diagnosing PCOS
PCOS happens when the ovaries don’t work correctly, and in lots of instances, is accompanied by elevated ranges of testosterone. The dysfunction may cause irregular durations, pimples, additional facial hair, or hair loss from the top. Women with PCOS are sometimes at an elevated threat for growing kind 2 diabetes, in addition to sleep, psychological, cardiovascular, and different reproductive issues equivalent to uterine most cancers and infertility.
“PCOS can be challenging to diagnose given its overlap with other conditions,” mentioned Skand Shekhar, M.D., senior creator of the research and assistant analysis doctor and endocrinologist on the NIEHS. “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.”
Study authors steered integrating massive population-based research with digital health datasets and analyzing frequent laboratory assessments to establish delicate diagnostic biomarkers that may facilitate the analysis of PCOS.
PCOS Diagnostic Criteria and Role of AI/ML
Diagnosis relies on widely-accepted standardized standards which have developed through the years, however sometimes contains medical options (e.g., pimples, extra hair progress, and irregular durations) accompanied by laboratory (e.g., high blood testosterone) and radiological findings (e.g., a number of small cysts and elevated ovarian quantity on ovarian ultrasound). However, as a result of a few of the options of PCOS can co-occur with different issues equivalent to weight problems, diabetes, and cardiometabolic issues, it frequently goes unrecognized.
AI refers to using computer-based methods or instruments to imitate human intelligence and to assist make choices or predictions. ML is a subdivision of AI targeted on studying from earlier occasions and making use of this information to future decision-making. AI can course of large quantities of distinct knowledge, equivalent to that derived from digital health data, making it a great help within the analysis of difficult-to-diagnose issues like PCOS.
Review Findings
The researchers performed a scientific assessment of all peer-reviewed research revealed on this subject for the previous 25 years (1997-2022) that used AI/ML to detect PCOS. With the assistance of an skilled NIH librarian, the researchers recognized doubtlessly eligible research. In complete, they screened 135 research and included 31 on this paper. All research had been observational and assessed using AI/ML applied sciences on affected person analysis. Ultrasound photos had been included in about half the research. The common age of the contributors within the research was 29.
Among the 10 research that used standardized diagnostic standards to diagnose PCOS, the accuracy of detection ranged from 80-90%.
“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,” mentioned Shekhar.
The authors notice that AI/ML-based packages have the potential to considerably improve {our capability} to establish women with PCOS early, with related value financial savings and a diminished burden of PCOS on sufferers and on the health system.
Follow-up research with sturdy validation and testing practices will enable for the sleek integration of AI/ML for persistent health circumstances.
Reference: “Application of machine learning and artificial intelligence in the diagnosis and classification of polycystic ovarian syndrome: a systematic review” by Francisco J. Barrera, Ethan D.L. Brown, Amanda Rojo, Javier Obeso, Hiram Plata, Eddy P. Lincango, Nancy Terry, René Rodríguez-Gutiérrez, Janet E. Hall and Skand Shekhar, 18 September 2023, Frontiers in Endocrinology.
DOI: 10.3389/fendo.2023.1106625
This work was supported by the Intramural Research Program of the NIH/National Institute of Environmental Health Sciences (ZIDES102465 and ZIDES103323).
