Dataset Information

Assessment of anovulation in eumenorrheic women: comparison of ovulation detection algorithms.

ABSTRACT:

Objective

To compare previously used algorithms to identify anovulatory menstrual cycles in women self-reporting regular menses.

Design

Prospective cohort study.

Setting

Western New York.

Patient(s)

Two hundred fifty-nine healthy, regularly menstruating women followed for one (n=9) or two (n=250) menstrual cycles (2005-2007).

Intervention(s)

None.

Main outcome measure(s)

Prevalence of sporadic anovulatory cycles identified using 11 previously defined algorithms that use E2, P, and LH concentrations.

Result(s)

Algorithms based on serum LH, E2, and P levels detected a prevalence of anovulation across the study period of 5.5%-12.8% (concordant classification for 91.7%-97.4% of cycles). The prevalence of anovulatory cycles varied from 3.4% to 18.6% using algorithms based on urinary LH alone or with the primary E2 metabolite, estrone-3-glucuronide, levels.

Conclusion(s)

The prevalence of anovulatory cycles among healthy women varied by algorithm. Mid-cycle LH surge urine-based algorithms used in over-the-counter fertility monitors tended to classify a higher proportion of anovulatory cycles compared with luteal-phase P serum-based algorithms. Our study demonstrates that algorithms based on the LH surge, or in conjunction with estrone-3-glucuronide, potentially estimate a higher percentage of anovulatory episodes. Addition of measurements of postovulatory serum P or urine pregnanediol may aid in detecting ovulation.

SUBMITTER: Lynch KE

PROVIDER: S-EPMC4119548 | biostudies-literature | 2014 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Assessment of anovulation in eumenorrheic women: comparison of ovulation detection algorithms.

Lynch Kristine E KE Mumford Sunni L SL Schliep Karen C KC Whitcomb Brian W BW Zarek Shvetha M SM Pollack Anna Z AZ Bertone-Johnson Elizabeth R ER Danaher Michelle M Wactawski-Wende Jean J Gaskins Audrey J AJ Schisterman Enrique F EF

Fertility and sterility 20140527 2

<h4>Objective</h4>To compare previously used algorithms to identify anovulatory menstrual cycles in women self-reporting regular menses.<h4>Design</h4>Prospective cohort study.<h4>Setting</h4>Western New York.<h4>Patient(s)</h4>Two hundred fifty-nine healthy, regularly menstruating women followed for one (n=9) or two (n=250) menstrual cycles (2005-2007).<h4>Intervention(s)</h4>None.<h4>Main outcome measure(s)</h4>Prevalence of sporadic anovulatory cycles identified using 11 previously defined al ...[more]

PMID: 24875398

Similar Datasets

Project description:BackgroundAttaining pregnancy is conditional upon a series of complex processes, including adequately timed intercourse, ovulation, fertilisation, and implantation. Anovulation is a first-line treatment target for couples with difficulty conceiving and is frequently examined in studies of fecundability.ObjectivesTo identify whether sporadic anovulation is an important determinant of cumulative pregnancy rates and time to pregnancy among fertile women with regular menstrual cycles.MethodsWe simulated cumulative pregnancy rates and time to pregnancy for 12 consecutive menstrual cycles among 100 000 women based on data-driven probabilities of implantation, fertilisation, ovulation, and intercourse occurring in the fertile window. We assumed anovulation probabilities of 1%, 8%, or 14.5% and intercourse averaging once per week, every other day, or daily. The model incorporated reductions in implantation and fertilisation rates for successive cycles of non-pregnancy.ResultsAfter 12 cycles, a reduction in the per cycle incidence of anovulation from 14.5% to 1% resulted in a 4.0% higher cumulative pregnancy rate (86.7% vs 90.7%) and similar time to pregnancy (1-cycle median difference). In contrast, increasing mean unscheduled sexual intercourse frequency from weekly to every other day was associated with a 5-cycle median reduction in time to pregnancy (weekly: 7 cycles; every other day or daily: 2 cycles) and a 28.9% increase in the cumulative pregnancy rate (weekly: 59.9%, every other day: 88.8%; daily: 91.6%).ConclusionsIn presumed fertile women with regular menstrual cycles, routine investigation of anovulation may not be an informative outcome in studies of fecundability, and routine testing to ensure ovulation and treatment of anovulation are unlikely to be medically necessary. While biomarkers or cervical fluid may help time intercourse to the fertile window, time to pregnancy can also be improved through increasing the frequency of unscheduled intercourse. These findings need corroboration in large preconception time to pregnancy studies.

Project description:ImportanceApplication of deep learning algorithms to whole-slide pathology images can potentially improve diagnostic accuracy and efficiency.ObjectiveAssess the performance of automated deep learning algorithms at detecting metastases in hematoxylin and eosin-stained tissue sections of lymph nodes of women with breast cancer and compare it with pathologists' diagnoses in a diagnostic setting.Design, setting, and participantsResearcher challenge competition (CAMELYON16) to develop automated solutions for detecting lymph node metastases (November 2015-November 2016). A training data set of whole-slide images from 2 centers in the Netherlands with (n = 110) and without (n = 160) nodal metastases verified by immunohistochemical staining were provided to challenge participants to build algorithms. Algorithm performance was evaluated in an independent test set of 129 whole-slide images (49 with and 80 without metastases). The same test set of corresponding glass slides was also evaluated by a panel of 11 pathologists with time constraint (WTC) from the Netherlands to ascertain likelihood of nodal metastases for each slide in a flexible 2-hour session, simulating routine pathology workflow, and by 1 pathologist without time constraint (WOTC).ExposuresDeep learning algorithms submitted as part of a challenge competition or pathologist interpretation.Main outcomes and measuresThe presence of specific metastatic foci and the absence vs presence of lymph node metastasis in a slide or image using receiver operating characteristic curve analysis. The 11 pathologists participating in the simulation exercise rated their diagnostic confidence as definitely normal, probably normal, equivocal, probably tumor, or definitely tumor.ResultsThe area under the receiver operating characteristic curve (AUC) for the algorithms ranged from 0.556 to 0.994. The top-performing algorithm achieved a lesion-level, true-positive fraction comparable with that of the pathologist WOTC (72.4% [95% CI, 64.3%-80.4%]) at a mean of 0.0125 false-positives per normal whole-slide image. For the whole-slide image classification task, the best algorithm (AUC, 0.994 [95% CI, 0.983-0.999]) performed significantly better than the pathologists WTC in a diagnostic simulation (mean AUC, 0.810 [range, 0.738-0.884]; P < .001). The top 5 algorithms had a mean AUC that was comparable with the pathologist interpreting the slides in the absence of time constraints (mean AUC, 0.960 [range, 0.923-0.994] for the top 5 algorithms vs 0.966 [95% CI, 0.927-0.998] for the pathologist WOTC).Conclusions and relevanceIn the setting of a challenge competition, some deep learning algorithms achieved better diagnostic performance than a panel of 11 pathologists participating in a simulation exercise designed to mimic routine pathology workflow; algorithm performance was comparable with an expert pathologist interpreting whole-slide images without time constraints. Whether this approach has clinical utility will require evaluation in a clinical setting.

Dataset Information

Assessment of anovulation in eumenorrheic women: comparison of ovulation detection algorithms.

Objective

Design

Setting

Patient(s)

Intervention(s)

Main outcome measure(s)

Result(s)

Conclusion(s)

Publications

Assessment of anovulation in eumenorrheic women: comparison of ovulation detection algorithms.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets