A Predictive Model of Live Birth Based on Obesity and Metabolic Parameters in Patients With PCOS Undergoing Frozen-Thawed Embryo Transfer

Contributing factors for pregnancy outcomes in women with PCOS after their first FET treatment: a retrospective cohort study

OBJECTIVE

We aim to explore the contributing factors of clinical pregnancy outcomes in PCOS patients undergoing their first FET treatment.

METHODS

A retrospective analysis was conducted on 574 PCOS patients undergoing their first FET treatment at a private fertility center from January 2018 to December 2021.

RESULTS

During the first FET cycle of PCOS patients, progesterone levels (aOR 0.109, 95% CI 0.018-0.670) and endometrial thickness (EMT) (aOR 1.126, 95% CI 1.043-1.419) on the hCG trigger day were associated with the clinical pregnancy rate. Similarly, progesterone levels (aOR 0.055, 95% CI 0.007-0.420) and EMT (aOR 1.179, 95% CI 1.011-1.376) on the hCG trigger day were associated with the live birth rate. In addition, AFC (aOR 1.179, 95% CI 1.011-1.376) was found to be a risk factor for preterm delivery.

CONCLUSIONS

In women with PCOS undergoing their first FET, lower progesterone levels and higher EMT on hCG trigger day were associated with clinical pregnancy and live birth, and AFC was a risk factor for preterm delivery. During FET treatment, paying attention to the patient's endocrine indicators and follicle status may have a positive effect on predicting and improving the pregnancy outcome of PCOS patients.

Predicting polycystic ovary syndrome with machine learning algorithms from electronic health records

Introduction

Predictive models have been used to aid early diagnosis of PCOS, though existing models are based on small sample sizes and limited to fertility clinic populations. We built a predictive model using machine learning algorithms based on an outpatient population at risk for PCOS to predict risk and facilitate earlier diagnosis, particularly among those who meet diagnostic criteria but have not received a diagnosis.

Methods

This is a retrospective cohort study from a SafetyNet hospital's electronic health records (EHR) from 2003-2016. The study population included 30,601 women aged 18-45 years without concurrent endocrinopathy who had any visit to Boston Medical Center for primary care, obstetrics and gynecology, endocrinology, family medicine, or general internal medicine. Four prediction outcomes were assessed for PCOS. The first outcome was PCOS ICD-9 diagnosis with additional model outcomes of algorithm-defined PCOS. The latter was based on Rotterdam criteria and merging laboratory values, radiographic imaging, and ICD data from the EHR to define irregular menstruation, hyperandrogenism, and polycystic ovarian morphology on ultrasound.

Results

We developed predictive models using four machine learning methods: logistic regression, supported vector machine, gradient boosted trees, and random forests. Hormone values (follicle-stimulating hormone, luteinizing hormone, estradiol, and sex hormone binding globulin) were combined to create a multilayer perceptron score using a neural network classifier. Prediction of PCOS prior to clinical diagnosis in an out-of-sample test set of patients achieved an average AUC of 85%, 81%, 80%, and 82%, respectively in Models I, II, III and IV. Significant positive predictors of PCOS diagnosis across models included hormone levels and obesity; negative predictors included gravidity and positive bHCG.

Conclusion

Machine learning algorithms were used to predict PCOS based on a large at-risk population. This approach may guide early detection of PCOS within EHR-interfaced populations to facilitate counseling and interventions that may reduce long-term health consequences. Our model illustrates the potential benefits of an artificial intelligence-enabled provider assistance tool that can be integrated into the EHR to reduce delays in diagnosis. However, model validation in other hospital-based populations is necessary.

Progress of the application clinical prediction model in polycystic ovary syndrome

Clinical prediction models play an important role in the field of medicine. These can help predict the probability of an individual suffering from disease, complications, and treatment outcomes by applying specific methodologies. Polycystic ovary syndrome (PCOS) is a common disease with a high incidence rate, huge heterogeneity, short- and long-term complications, and complex treatments. In this systematic review study, we reviewed the progress of clinical prediction models in PCOS patients, including diagnosis and prediction models for PCOS complications and treatment outcomes. We aimed to provide ideas for medical researchers and clues for the management of PCOS. In the future, models with poor accuracy can be greatly improved by adding well-known parameters and validations, which will further expand our understanding of PCOS in terms of precision medicine. By developing a series of predictive models, we can make the definition of PCOS more accurate, which can improve the diagnosis of PCOS and reduce the likelihood of false positives and false negatives. It will also help discover complications earlier and treatment outcomes being known earlier, which can result in better outcomes for women with PCOS.

Predicting polycystic ovary syndrome (PCOS) with machine learning algorithms from electronic health records

Introduction

Predictive models have been used to aid early diagnosis of PCOS, though existing models are based on small sample sizes and limited to fertility clinic populations. We built a predictive model using machine learning algorithms based on an outpatient population at risk for PCOS to predict risk and facilitate earlier diagnosis, particularly among those who meet diagnostic criteria but have not received a diagnosis.

Methods

This is a retrospective cohort study from a SafetyNet hospital's electronic health records (EHR) from 2003-2016. The study population included 30,601 women aged 18-45 years without concurrent endocrinopathy who had any visit to Boston Medical Center for primary care, obstetrics and gynecology, endocrinology, family medicine, or general internal medicine. Four prediction outcomes were assessed for PCOS. The first outcome was PCOS ICD-9 diagnosis with additional model outcomes of algorithm-defined PCOS. The latter was based on Rotterdam criteria and merging laboratory values, radiographic imaging, and ICD data from the EHR to define irregular menstruation, hyperandrogenism, and polycystic ovarian morphology on ultrasound.

Results

We developed predictive models using four machine learning methods: logistic regression, supported vector machine, gradient boosted trees, and random forests. Hormone values (follicle-stimulating hormone, luteinizing hormone, estradiol, and sex hormone binding globulin) were combined to create a multilayer perceptron score using a neural network classifier. Prediction of PCOS prior to clinical diagnosis in an out-of-sample test set of patients achieved AUC of 85%, 81%, 80%, and 82%, respectively in Models I, II, III and IV. Significant positive predictors of PCOS diagnosis across models included hormone levels and obesity; negative predictors included gravidity and positive bHCG.

Conclusions

Machine learning algorithms were used to predict PCOS based on a large at-risk population. This approach may guide early detection of PCOS within EHR-interfaced populations to facilitate counseling and interventions that may reduce long-term health consequences. Our model illustrates the potential benefits of an artificial intelligence-enabled provider assistance tool that can be integrated into the EHR to reduce delays in diagnosis. However, model validation in other hospital-based populations is necessary.

Association between Pre-Pregnancy Overweightness/Obesity and Pregnancy Outcomes in Women with Polycystic Ovary Syndrome: A Systematic Review and Meta-Analysis

Polycystic ovary syndrome (PCOS) is a common metabolic problem in women of reproductive age. Evidence suggests pregnant women with PCOS may have a higher risk of the development of adverse pregnancy outcomes; however, the relationship between pre-pregnancy overweight/obesity and pregnancy outcomes in women with PCOS remains uncertain. We try to clarify the relationship between pre-pregnancy overweight/obesity and subsequent pregnancy outcomes. Therefore, we conducted this systematic review and meta-analysis. We used the databases obtained from the PubMed, Embase, Web of Science, and Cochrane databases, plus hand-searching, to examine the association between pre-pregnancy overweightness/obesity and pregnancy outcomes in women with PCOS from inception to 4 February 2022. A total of 16 cohort studies, including 14 retrospective cohort studies (n = 10,496) and another two prospective cohort studies (n = 818), contributed to a total of 11,314 women for analysis. The meta-analysis showed significantly increased odds of miscarriage rate in PCOS women whose pre-pregnancy body mass index (BMI) is above overweight (OR 1.71 [95% CI 1.38–2.11]) or obese (OR 2.00 [95% CI 1.38–2.90]) under a random effect model. The tests for subgroup difference indicated the increased risk was consistent, regardless which body mass index cut-off for overweight (24 or 25 kg/m²) or obesity (28 and 30 kg/m²) was used. With the same strategies, we found that pregnant women in the control group significantly increased live birth rate compared with those pregnant women with PCOS as well as pre-pregnancy overweight/obesity (OR 0.79 [95% CI 0.71–0.89], OR 0.78 [95% CI 0.67–0.91]). By contrast, we did not find any association between PCOS women with pre-pregnancy overweight/obesity and preterm birth. Based on the aforementioned findings, the main critical factor contributing to a worse pregnancy outcome may be an early fetal loss in these PCOS women with pre-pregnancy overweight/obesity. Since PCOS women with pre-pregnancy overweightness/obesity were associated with worse pregnancy outcomes, we supposed that weight reduction before attempting pregnancy in the PCOS women with pre-pregnancy overweightness/obesity may improve the subsequent pregnancy outcomes.