Application of Machine Learning and Artificial Intelligence in the Diagnosis and Classification of Polycystic Ovarian Syndrome - A Systematic Review

Aug 5, 2026

Upload by Anda

Polycystic Ovarian Syndrome (PCOS) is the most common endocrinopathy in women of reproductive age and remains widely underdiagnosed, contributing to substantial morbidity. This systematic review evaluates the utility of artificial intelligence and machine learning for PCOS diagnosis or classification, synthesizing evidence from databases including MEDLINE, Embase, the Cochrane Central Register of Controlled Trials, Web of Science, and IEEE Xplore through January 1, 2022. Results summarize study counts, data sources, employed algorithms, and diagnostic performance metrics to clarify clinical potential and methodological needs for standardized criteria and improved reporting.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Introduction

Methods

Results

Diagnostic performance and algorithms

Conclusion

TYPE Systematic Review PUBLISHED 18 September 2023 DOI 10.3389/fendo.2023.1106625 OPEN ACCESS EDITED BY Masoud Afnan, Qingdao United Family Hospital, China REVIEWED BY Noraishikin Zulkarnain, Universiti Kebangsaan Malaysia, Malaysia Saubhagya Jena, All India Institute of Medical Sciences Bhubaneswar, India *CORRESPONDENCE Skand Shekhar [skand.shekhar@nih.gov](skand.shekhar@nih.gov) RECEIVED 24 November 2022 ACCEPTED 04 August 2023 PUBLISHED 18 September 2023 CITATION Barrera FJ, Brown EDL, Rojo A, Obeso J, Plata H, Lincango EP, Terry N, RodrguezGutie´rrez R, Hall JE and Shekhar S (2023) Application of machine learning andartiﬁcial intelligence in the diagnosis and classiﬁcation of polycystic ovarian syndrome: a systematic review. Front. Endocrinol. 14:1106625 . doi: 10.3389/fendo.2023.1106625 COPYRIGHT © 2023 Barrera, Brown, Rojo, Obeso, Plata, Lincango, Terry, Rodrguez-Gutie´rrez, Halland Shekhar. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Application of machine learning and artiﬁcial intelligence in the diagnosis and classiﬁcation of polycystic ovarian syndrome: a systematic review Francisco J. Barrera 1,2, Ethan D. L. Brown 3, Amanda Rojo 2, Javier Obeso 2, Hiram Plata 2, Eddy P. Lincango 4, Nancy Terry5, Ren´e Rodr ´ıguez-Guti´errez 2,4,6, Janet E. Hall 3 and Skand Shekhar 3* 1 Department of Epidemiology, Harvard TH Chan School of Public Health, Boston, MA, United States, 2 Plataforma INVEST Medicina, Universidad Autónoma de Nuevo León-Knowledge Education Research (UANL-KER), Unit Mayo Clinic (KER Unit Mexico), Universidad Autónoma de Nuevo León, Monterrey, Mexico, 3 Reproductive Physiology and Pathophysiology Group, Clinical Research Branch, National Institute of Environmental Health Sciences, National Institutes of Health, Research Triangle Park, NC, United States, 4 Knowledge and Evaluation Research Unit-Endocrinology (KER-Endo), Mayo Clinic, Rochester, MN, United States, 5 Division of Library Services, Ofﬁce of Research Services, National Institutes of Health, Bethesda, MD, United States, 6 Endocrinology Division, Department of Internal Medicine, University Hospital “Dr. Jose´ E. Gonz´alez”, Universidad Autonoma de Nuevo Leon, Monterrey, Mexico Introduction: Polycystic Ovarian Syndrome (PCOS) is the most common endocri no pathy in women of reproductive age and remains widely underdiagnosed leading to signiﬁcant morbidity. Artiﬁcial intelligence (AI) and machine learning (ML) hold promise in improving diagnostics. Thus, we performed a systematic review of literature to identify the utility of AI/ML in the diagnosis or classiﬁcation of PCOS. Methods: We applied a search strategy using the following databases MEDLINE, Embase, the Cochrane Central Register of Controlled Trials, the Web of Science, and the IEEE Xplore Digital Library using relevant keywords. Eligible studies were identiﬁed, and results were extracted for their synthesis from inception until January 1, 2022 . Results: 135 studies were screened and ultimately, 31 studies were included in this study. Data sources used by the AI/ML interventions included clinical data, electronic health records, and genetic and proteomic data. Ten studies (32%) employed standardized criteria (NIH, Rotterdam, or Revised International PCOS classiﬁcation), while 17 (55%) used clinical information with/without imaging. The most common AI techniques employed were support vector machine (42% studies), K-nearest neighbor (26%), and regression models (23%) were the commonest AI/ML. Receiver operating curves (ROC) were employed to comp

FAQs

What problem does the review address about PCOS?

The review addresses that PCOS is common yet frequently underdiagnosed, leading to significant morbidity. It evaluates whether AI/ML can improve diagnostic and classification performance.

How were eligible studies identified in the review?

Eligible studies were retrieved using search strategies across MEDLINE, Embase, the Cochrane Central Register of Controlled Trials, Web of Science, and IEEE Xplore with relevant keywords. Evidence was synthesized from inception to January 1, 2022.

Which AI/ML approaches and data sources were most commonly used?

AI/ML interventions used clinical data, electronic health records, and genetic/proteomic data. Support vector machines were among the most common techniques, along with K-nearest neighbor and regression models.

Aug 5, 2026

Upload by Anda