Dataset Information

Polycystic ovary morphology: age-based ultrasound criteria.

ABSTRACT: To determine age-based criteria for polycystic ovary morphology.Cross-sectional, case-control design.Outpatient setting.Women with polycystic ovary syndrome (PCOS) defined by hyperandrogenism and irregular menses (n = 544) and controls with regular menses and no evidence of hyperandrogenism (n = 666) participated. Parameters were tested in a second cohort of women with PCOS (n = 105) and controls (n = 32) meeting the same criteria.Subjects underwent a pelvic ultrasound documenting ovarian volume and maximum follicle number in a single plane.A receiver operating characteristic curve was constructed to determine the ovarian volume and follicle number with the best sensitivity and specificity to define PCOS for age groups at approximately 5-year intervals from age 18 to >44 years.The best sensitivity and specificity were obtained using a threshold volume of 12 mL and 13 follicles for ages ?24 years, 10 mL and 14 follicles for ages 25-29 years, 9 mL and 10 follicles for ages 30-34 years, 8 mL and 10 follicles for ages 35-39 years, 10 mL and 9 follicles for ages 40-44 years, and 6 mL and 7 follicles for ages >44 years. Data from a second cohort confirmed the need to decrease volume and follicle number with increasing age to diagnose PCOS. Polycystic ovary morphology was most accurate at predicting the PCOS diagnosis for women ages 30-39 years.The ovarian volume and follicle number threshold to define polycystic ovary morphology should be lowered starting at age 30.

SUBMITTER: Kim HJ

PROVIDER: S-EPMC5657450 | biostudies-literature | 2017 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Polycystic ovary morphology: age-based ultrasound criteria.

Kim Hyun-Jun HJ Adams Judith M JM Gudmundsson Jens A JA Arason Gudmundur G Pau Cindy T CT Welt Corrine K CK

Fertility and sterility 20170812 3

<h4>Objective</h4>To determine age-based criteria for polycystic ovary morphology.<h4>Design</h4>Cross-sectional, case-control design.<h4>Setting</h4>Outpatient setting.<h4>Subject(s)</h4>Women with polycystic ovary syndrome (PCOS) defined by hyperandrogenism and irregular menses (n = 544) and controls with regular menses and no evidence of hyperandrogenism (n = 666) participated. Parameters were tested in a second cohort of women with PCOS (n = 105) and controls (n = 32) meeting the same criter ...[more]

PMID: 28807396

Similar Datasets

Project description:Background:Polycystic ovary syndrome (PCOS) is characterized by hyperandrogenemia, oligo-anovulation, and numerous ovarian cysts. Hospital electronic medical records provide an avenue for investigating polycystic ovary morphology commonly seen in PCOS at a large scale. The purpose of this study was to develop and evaluate the performance of two machine learning text algorithms, for classification of polycystic ovary morphology (PCOM) in pelvic ultrasounds. Methods:Pelvic ultrasound reports from patients at Boston Medical Center between October 1, 2003 and December 12, 2016 were included for analysis, which resulted in 39,093 ultrasound reports from 25,535 unique women. Following the 2003 Rotterdam Consensus Criteria for polycystic ovary syndrome, 2000 randomly selected ultrasounds were expert labeled for PCOM status as present, absent, or unidentifiable (not able to be determined from text alone). An ovary was marked as having PCOM if there was mention of numerous peripheral follicles or if the volume was greater than 10?ml in the absence of a dominant follicle or other confounding pathology. Half of the labeled data was used to develop and refine the algorithms, and the other half was used as a test set for evaluating its accuracy. Results:On the evaluation set of 1000 random US reports, the accuracy of the classifiers were 97.6% (95% CI: 96.5, 98.5%) and 96.1% (94.7, 97.2%). Both models were more adept at identifying PCOM-absent ultrasounds than either PCOM-unidentifiable or PCOM-present ultrasounds. The two classifiers estimated prevalence of PCOM within the whole set of 39,093 ultrasounds to be 44% PCOM-absent, 32% PCOM-unidentifiable, and 24% PCOM-present. Conclusions:Although accuracy measured on the test set and inter-rater agreement between the two classifiers (Cohen's Kappa?=?0.988) was high, a major limitation of our approach is that it uses the ultrasound report text as a proxy and does not directly count follicles from the ultrasound images themselves.

Dataset Information

Polycystic ovary morphology: age-based ultrasound criteria.

Publications

Polycystic ovary morphology: age-based ultrasound criteria.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets