scholarly journals Data mining polycystic ovary morphology in electronic medical record ultrasound reports

2019 ◽  
Vol 5 (1) ◽  
Author(s):  
Jay Jojo Cheng ◽  
Shruthi Mahalingaiah
Keyword(s):  
Polycystic Ovary Syndrome ◽  
Large Scale ◽  
Polycystic Ovary ◽  
Medical Center ◽  
Ultrasound Images ◽  
Dominant Follicle ◽  
Ovary Syndrome ◽  
Test Set ◽  
Report Text

Abstract 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.

scholarly journals Data mining and classification of polycystic ovaries in pelvic ultrasound reports

2018 ◽  
Author(s):  
J. Jojo Cheng ◽  
Shruthi Mahalingaiah
Keyword(s):  
Polycystic Ovary ◽  
Medical Center ◽  
Ultrasound Images ◽  
Polycystic Ovaries ◽  
Pelvic Ultrasound ◽  
Tree Model ◽  
Test Set ◽  
Automatic Feature Extraction ◽  
Boosted Tree

AbstractObjectivesTo develop and evaluate the performance of a rules-based classifier and a gradient boosted tree model for automatic feature extraction and classification of polycystic ovary morphology (PCOM) in pelvic ultrasoundsMethodsPelvic 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 manually labeled for PCOM status as present, absent, or unidentifiable. Half of the labeled data was used as a training set, and the other half was used as a test set.ResultsOn the test set of 1000 random US reports, the accuracy of rules-based classifier (RBC) was 97.6% (95% CI: 96.5%, 98.5%) and 96.1% (94.7%, 97.2%) for the gradient boosted tree model (GBT). Both models were more adept at identifying non-PCOM ultrasounds than either unidentifiable or PCOM ultrasounds. The two classifiers estimated prevalence of PCOM within our population’s ultrasounds to be about 44%, unidentifiable 32%, and PCOM 24%.ConclusionsAlthough 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.

scholarly journals Association of CYP3A7*1C and Serum Dehydroepiandrosterone Sulfate Levels in Women with Polycystic Ovary Syndrome

2008 ◽  
Vol 93 (7) ◽  
pp. 2909-2912 ◽  
Author(s):  
Mark O. Goodarzi ◽  
Ning Xu ◽  
Ricardo Azziz
Keyword(s):  
Los Angeles ◽  
Polycystic Ovary Syndrome ◽  
White Women ◽  
Polycystic Ovary ◽  
Medical Center ◽  
Free Testosterone ◽  
Total Testosterone ◽  
Adrenal Androgen ◽  
Androgen Excess ◽  
Ovary Syndrome

Abstract Context: Adrenal androgen excess is common in polycystic ovary syndrome (PCOS) and appears to be heritable. CYP3A7 metabolizes dehydroepiandrosterone and its sulfate (DHEAS). A promoter variant, CYP3A7*1C, which results in persistent expression in adults, was associated with reduced DHEAS levels in a previous study, which led us to consider CYP3A7*1C as a modulator of adrenal androgen excess in patients with PCOS. Objective: The objective was to replicate the association between CYP3A7*1C and reduced DHEAS levels in PCOS patients and assess its possible role in modulating testosterone levels. Design: Women with and without PCOS were genotyped for CYP3A7*1C, and this variant was tested for association with DHEAS and total and free testosterone. Setting: Subjects were recruited from the reproductive endocrinology clinic at the University of Alabama at Birmingham; controls were recruited from the surrounding community. Genotyping took place at Cedars-Sinai Medical Center (Los Angeles, CA). Participants: A total of 287 white women with PCOS and 187 controls were studied. Main Measurements: CYP3A7*1C genotype, PCOS risk, and androgen levels were measured. Results: PCOS subjects who carried the CYP3A7*1C variant had lower levels of serum DHEAS and total testosterone (P = 0.0006 and 0.046, respectively). The variant was not associated with PCOS risk. Conclusion: This study replicated prior work of the association of CYP3A7*1C and decreased DHEAS in a different population of young PCOS women, providing further genetic evidence that CYP3A7 plays a potential role in modulation of DHEAS levels. Adult expression of CYP3A7 may modify the PCOS phenotype by ameliorating adrenal androgen excess.

Classification of polycystic ovary syndrome into three types according to response to human corticotropin-releasing hormone

1999 ◽  
Vol 72 (1) ◽  
pp. 15-20 ◽  
Author(s):  
Yoshihito Kondoh ◽  
Tsuguo Uemura ◽  
Masahiko Ishikawa ◽  
Natsuko Yokoi ◽  
Fumiki Hirahara
Keyword(s):  
Polycystic Ovary Syndrome ◽  
Polycystic Ovary ◽  
Corticotropin Releasing Hormone ◽  
Ovary Syndrome ◽  
Releasing Hormone

scholarly journals Sex Modifies the Effect of Genetic Risk Scores for Polycystic Ovary Syndrome on Metabolic Phenotypes

2021 ◽  
Author(s):  
Ky'Era V. Actkins ◽  
Genevieve Jean-Pierre ◽  
Melinda C. Aldrich ◽  
Digna R. Velez Edwards ◽  
Lea K. Davis
Keyword(s):  
Polycystic Ovary Syndrome ◽  
Genetic Risk ◽  
Polycystic Ovary ◽  
Medical Center ◽  
Genetic Risk Score ◽  
Risk Scores ◽  
Ovary Syndrome ◽  
Biological Variables ◽  
Increased Risk ◽  
The Relationship

Females with polycystic ovary syndrome (PCOS), the most common endocrine disorder in women, have an increased risk of developing metabolic disorders such as insulin resistance, obesity, and type 2 diabetes (T2D). Furthermore, while only diagnosable in females, males with a family history of PCOS can also exhibit a poor cardiometabolic profile. Therefore, we aimed to elucidate the role of sex in the relationship between PCOS and its comorbidities by conducting bidirectional genetic risk score analyses in both sexes. We conducted a phenome-wide association study (PheWAS) using PCOS polygenic risk scores (PCOSPRS) to understand the pleiotropic effects of PCOS genetic liability across 1,380 medical conditions in females and males recorded in the Vanderbilt University Medical Center electronic health record (EHR) database. After adjusting for age and genetic ancestry, we found that European descent males with higher PCOSPRS were significantly more likely to develop cardiovascular diseases than females at the same level of genetic risk, while females had a higher odds of developing T2D. Based on observed significant associations, we tested the relationship between PRS for comorbid conditions (e.g., T2D, body mass index, hypertension, etc.) and found that only PRS generated for BMI and T2D were associated with a PCOS diagnosis. We then further decomposed the T2DPRS association with PCOS by adjusting the model for measured BMI and BMIresidual (enriched for the environmental contribution to BMI). Results demonstrated that genetically regulated BMI primarily accounted for the relationship between T2DPRS and PCOS. This was further supported in a mediation analysis, which only revealed clinical BMI measurements, but not BMIresidual, as a strong mediator for both sexes. Overall, our findings show that the genetic architecture of PCOS has distinct metabolic sex differences, but these associations are only apparent when PCOSPRS is explicitly modeled. It is possible that these pathways are less explained by the direct genetic risk of metabolic traits than they are by the risk factors shared between them, which can be influenced by biological variables such as sex.

Evaluation of a Center of Research Excellence in Polycystic Ovary Syndrome as a Large-Scale Collaborative Research Translation Initiative, Including Evaluating Translation of Guideline Impact

2018 ◽  
Vol 36 (01) ◽  
pp. 042-049
Author(s):  
Samantha Kozica-Olenski ◽  
Helena Teede ◽  
Rhonda Garad
Keyword(s):  
Polycystic Ovary Syndrome ◽  
Large Scale ◽  
Best Practice ◽  
Polycystic Ovary ◽  
Research Translation ◽  
Ovary Syndrome ◽  
Practice Approach ◽  
Research Benefit ◽  
Research Excellence ◽  
Evidence Based Guideline

AbstractResearch translation and evaluation are often underconsidered in research design and implementation thus limiting research benefit to the end user. In this article, we first describe a best practice approach to evaluation, for a center of research excellence in polycystic ovary syndrome. Within this, we outline a comprehensive research translation program with inbuilt evaluation of the first International Evidence-based Guideline for the Assessment and Management of Polycystic Ovary Syndrome (2018). We seek to provide a real-world example of comprehensive approaches to evaluation and research translation.

Sign in / Sign up

Export Citation Format

Share Document