The association of race, ethnicity, and socioeconomic status on the severity of menopause symptoms: a study of 68,864 women.

OBJECTIVE: This study aimed to evaluate if and how race, ethnicity, and socioeconomic status (SES) are associated with the severity of menopause symptoms in a large, diverse sample of women. METHODS: For this cross-sectional study conducted between March 24, 2019, and January 13, 2023, a total of 68,864 women were enrolled from the Evernow online telehealth platform. Participants underwent a clinical intake survey, which encompassed demographic information, detailed medical questionnaires, and a modified Menopause Rating Scale. The modified scale was adapted for ease of use online and is available in the supplementary material along with the full intake. Symptom severity was evaluated using a multivariate binomial generalized linear model, accounting for factors such as race, ethnicity, age, body mass index, smoking status, bilateral oophorectomy status, and SES. Odds ratios (OR) and CIs were calculated based on the linear regression coefficients. RESULTS: Of the participants, 67,867 (98.6%) were included in the analysis after excluding outliers and those with unknown oophorectomy status. The majority of respondents identified as White (77.4%), followed by Hispanic (9.0%), Black (6.7%), two or more races/ethnicities (4.4%), Asian (1.2%), Indigenous/First Nations (0.8%), Middle Eastern (0.3%), and South Asian (0.2%). Notably, individuals identifying as Black (hot flashes OR, 1.91; 97.5% CI, 1.75-2.09; P < 0.001), Hispanic (skin/hair changes OR, 1.58; 97.5% CI, 1.45-1.71; P < 0.001), Indigenous/First Nations (painful sex OR, 1.39; 97.5% CI, 1.19-2.75; P = 0.007), Middle Eastern (weight changes OR, 2.22; 97.5% CI, 1.25-4.37; P = 0.01), or with two or more races/ethnicities (skin/hair changes OR, 1.41; 97.5% CI, 1.26-1.58; P < 0.001) reported higher levels of symptom severity compared with their White counterparts. Conversely, Asian and South Asian participants reported lower symptom severity. Even after incorporating SES into the linear model, racial and ethnic groups with lower SES (Black, Hispanic, Indigenous, and multiple ethnicities) exhibited slight shifts in OR while maintaining high statistical significance (Black [hot flashes OR, 1.87; 97.5% CI, 1.72-2.04; P < 0.001], Hispanic [skin/hair changes OR, 1.54; 97.5% CI, 1.42-1.68; P < 0.001], Indigenous/First Nations [painful sex OR, 1.74; 97.5% CI, 1.17-2.70; P = 0.009], multiple ethnicities [skin/hair changes OR, 1.41; 97.5% CI, 1.26-1.58; P < 0.001]). CONCLUSIONS: Our study suggests that the relationship between race and ethnicity and the severity of menopause symptoms is not solely explained by differences in SES but is itself an independent factor. Understanding and addressing social, cultural, and economic factors are crucial to reduce disparities in menopausal symptoms.

Current applications of artificial intelligence in assisted reproductive technologies through the perspective of a patient's journey.

PURPOSE OF REVIEW: This review highlights the timely relevance of artificial intelligence in enhancing assisted reproductive technologies (ARTs), particularly in-vitro fertilization (IVF). It underscores artificial intelligence's potential in revolutionizing patient outcomes and operational efficiency by addressing challenges in fertility diagnoses and procedures. RECENT FINDINGS: Recent advancements in artificial intelligence, including machine learning and predictive modeling, are making significant strides in optimizing IVF processes such as medication dosing, scheduling, and embryological assessments. Innovations include artificial intelligence augmented diagnostic testing, predictive modeling for treatment outcomes, scheduling optimization, dosing and protocol selection, follicular and hormone monitoring, trigger timing, and improved embryo selection. These developments promise to refine treatment approaches, enhance patient engagement, and increase the accuracy and scalability of fertility treatments. SUMMARY: The integration of artificial intelligence into reproductive medicine offers profound implications for clinical practice and research. By facilitating personalized treatment plans, standardizing procedures, and improving the efficiency of fertility clinics, artificial intelligence technologies pave the way for value-based, accessible, and efficient fertility services. Despite the promise, the full potential of artificial intelligence in ART will require ongoing validation and ethical considerations to ensure equitable and effective implementation.

The Role of Artificial Intelligence and Machine Learning in Assisted Reproductive Technologies.

Artificial intelligence (AI) and machine learning, the form most commonly used in medicine, offer powerful tools utilizing the strengths of large data sets and intelligent algorithms. These systems can help to revolutionize delivery of treatments, access to medical care, and improvement of outcomes, particularly in the realm of reproductive medicine. Whether that is more robust oocyte and embryo grading or more accurate follicular measurement, AI will be able to aid clinicians, and most importantly patients, in providing the best possible and individualized care. However, despite all of the potential strengths of AI, algorithms are not immune to bias and are vulnerable to the many socioeconomic and demographic biases that current healthcare systems suffer from. Wrong diagnoses as well is furthering of healthcare discrimination are real possibilities if both the capabilities and limitations of AI are not well understood. Armed with appropriate knowledge of how AI can most appropriately operate within medicine, and specifically reproductive medicine, will enable clinicians to both create and utilize machine learning-based innovations for the furthering of reproductive medicine and ultimately achieving the goal of building of healthy families.

Meeting the demand for fertility services: the present and future of reproductive endocrinology and infertility in the United States.

The field of reproductive endocrinology and infertility (REI) is at a crossroads; there is a mismatch between demand for reproductive endocrinology, infertility and assisted reproductive technology (ART) services, and availability of care. This document's focus is to provide data justifying the critical need for increased provision of fertility services in the United States now and into the future, offer approaches to rectify the developing physician shortage problem, and suggest a framework for the discussion on how to meet that increase in demand. The Society of REI recommend the following: 1. Our field should aggressively explore and implement courses of action to increase the number of qualified, highly trained REI physicians trained annually. We recommend efforts to increase the number of REI fellowships and the size complement of existing fellowships be prioritized where possible. These courses of action include: a. Increase the number of REI fellowship training programs. b. Increase the number of fellows trained at current REI fellowship programs. c. The pros and cons of a 2-year focused clinical fellowship track for fellows interested primarily in ART practice were extensively explored. We do not recommend shortening the REI fellowship to 2 years at this time, because efforts should be focused on increasing the number of fellowship training slots (1a and b). 2. It is recommended that the field aggressively implements courses of action to increase the number of and appropriate usage of non-REI providers to increase clinical efficiency under appropriate board-certified REI physician supervision. 3. Automating processes through technologic improvements can free providers at all levels to practice at the top of their license.

Applications of artificial intelligence in ovarian stimulation: a tool for improving efficiency and outcomes.

Because of the birth of the first baby after in vitro fertilization (IVF), the field of assisted reproductive technologies (ARTs) has seen significant advancements in the past 40 years. Over the last decade, the healthcare industry has increasingly adopted machine learning algorithms to improve patient care and operational efficiency. Artificial intelligence (AI) in ovarian stimulation is a burgeoning niche that is currently benefiting from increased research and investment from both the scientific and technology communities, leading to cutting-edge advancements with promise for rapid clinical integration. AI-assisted IVF is a rapidly growing area of research that can improve ovarian stimulation outcomes and efficiency by optimizing the dosage and timing of medications, streamlining the IVF process, and ultimately leading to increased standardization and better clinical outcomes. This review article aims to shed light on the latest breakthroughs in this area, discuss the role of validation and potential limitations of the technology, and examine the potential of these technologies to transform the field of assisted reproductive technologies. Integrating AI responsibly into IVF stimulation will result in higher-value clinical care with the goal of having a meaningful impact on enhancing access to more successful and efficient fertility treatments.

Evaluating the utility of a global webinar for mentoring medical students and OBGYN residents in REI.

BACKGROUND: In medical school and residency, clinical experiences influence trainee's decisions on what medical specialty they choose. Most trainees have limited access to opportunities to engage in the field of reproductive endocrinology and infertility (REI). Due to the COVID-19 pandemic and the shutdown of away electives, exposure to REI was especially limited. This study aims to evaluate the effectiveness of a live Q and A webinar on improving trainees' access to mentorship and knowledge of the path to becoming a reproductive endocrinology and infertility (REI) physician. MATERIALS AND METHODS: This study is a prospective paired cohort study. Medical students and OBGYN residents participated in a global Q and A webinar featuring REI physicians and fellows. 70 pre- and post-webinar surveys were included in the analysis. Paired nonparametric tests (Wilcoxon signed-rank test) were performed to assess whether post-webinar knowledge was significantly different from pre-webinar knowledge. RESULTS: Of the 268 registrants, 162 (60%) attended the live webinar. A majority of the respondents who completed both surveys were female (90%) and allopathic medical students (80%). Seventy-seven percent reported receiving only minimal advice about an REI career from their medical school or residency program, while 22% reported receiving some advice, and 1% extensive advice. Thirty-four percent had previously shadowed an REI physician and 23% had rotated in an REI office. Post-webinar significantly more trainees had a better understanding of the REI field, the path required to become an REI physician, opportunities to find mentors in the field, opportunities that are conducive to learning more about REI, and applying for rotations in the REI field (p = <.00001). Eighty-two percent agreed that their interest in REI increased due to this webinar. CONCLUSIONS: A webinar featuring REI physicians and fellows was effective in providing mentorship and career advisement for prospective REI trainees who otherwise expressed having limited access to the field.

Incidence and risk factors of intrauterine adhesions after myomectomy.

Objective: To determine the incidence and risk factors for intrauterine adhesions (IUAs) after minimally invasive and open myomectomy and hysteroscopic myomectomy (HM). Design: Retrospective cohort study. Setting: University-affiliated fertility center. Patients: Patients aged ≥18 years undergoing robotic-assisted or conventional laparoscopic minimally invasive myomectomy, abdominal myomectomy, or HM between January 2007 and January 2017. Only patients who underwent uterine cavity evaluation within 12 months of surgery via hysteroscopy or hysterosalpingography were included. Patients were excluded if they had a history of IUA before myomectomy. Interventions: Not applicable. Main Outcome Measures: The primary outcomes of this study were the presence and severity of IUA. The secondary outcomes were the identification of risk factors for IUA formation. The severity of IUAs was scored by 2 investigators using a previously published grading system by March et al. Results: Of 1,315 patients who underwent myomectomy, 173 (13.2%) met the inclusion criteria. Intrauterine adhesions were identified in 9.3% of all patients, 75.0% of which were classified as minimal. The incidence of IUA did not vary by modality: 8.6%, minimally invasive myomectomy; 7.8%, abdominal myomectomy; and 11.8%, HM. There were no differences in incidence of IUA by the number or size of fibroids removed. Of patients with IUA, 87.5% had submucosal fibroids resected compared with 58.6% without IUA. Conclusions: The incidence of postoperative IUA in women undergoing myomectomy of any modality is relatively low (9.3%) and does not vary by modality alone. Most IUAs are of minimal degree. The presence of submucosal fibroids is associated with an increased risk of IUA in all modalities.

An interpretable machine learning model for individualized gonadotrophin starting dose selection during ovarian stimulation.

RESEARCH QUESTION: Can we develop an interpretable machine learning model that optimizes starting gonadotrophin dose selection in terms of mature oocytes (metaphase II [MII]), fertilized oocytes (2 pronuclear [2PN]) and usable blastocysts? DESIGN: This was a retrospective study of patients undergoing autologous IVF cycles from 2014 to 2020 (n = 18,591) in three assisted reproductive technology centres in the USA. For each patient cycle, an individual dose-response curve was generated from the 100 most similar patients identified using a K-nearest neighbours model. Patients were labelled as dose-responsive if their dose-response curve showed a region that maximized MII oocytes, and flat-responsive otherwise. RESULTS: Analysis of the dose-response curves showed that 30% of cycles were dose-responsive and 64% were flat-responsive. After propensity score matching, patients in the dose-responsive group who received an optimal starting dose of FSH had on average 1.5 more MII oocytes, 1.2 more 2PN embryos and 0.6 more usable blastocysts using 10 IU less of starting FSH and 195 IU less of total FSH compared with patients given non-optimal doses. In the flat-responsive group, patients who received a low starting dose of FSH had on average 0.3 more MII oocytes, 0.3 more 2PN embryos and 0.2 more usable blastocysts using 149 IU less of starting FSH and 1375 IU less of total FSH compared with patients with a high starting dose. CONCLUSIONS: This study demonstrates retrospectively that using a machine learning model for selecting starting FSH can achieve optimal laboratory outcomes while reducing the amount of starting and total FSH used.

An interpretable machine learning model for predicting the optimal day of trigger during ovarian stimulation.

OBJECTIVE: To develop an interpretable machine learning model for optimizing the day of trigger in terms of mature oocytes (MII), fertilized oocytes (2PNs), and usable blastocysts. DESIGN: Retrospective study. SETTING: A group of three assisted reproductive technology centers in the United States. PATIENT(S): Patients undergoing autologous in vitro fertilization cycles from 2014 to 2020 (n = 30,278). INTERVENTION(S): None. MAIN OUTCOME MEASURE(S): Average number of MII oocytes, 2PNs, and usable blastocysts. RESULT(S): A set of interpretable machine learning models were developed using linear regression with follicle counts and estradiol levels. When using the model to make day-by-day predictions of trigger or continuing stimulation, possible early and late triggers were identified in 48.7% and 13.8% of cycles, respectively. After propensity score matching, patients with early triggers had on average 2.3 fewer MII oocytes, 1.8 fewer 2PNs, and 1.0 fewer usable blastocysts compared with matched patients with on-time triggers, and patients with late triggers had on average 2.7 fewer MII oocytes, 2.0 fewer 2PNs, and 0.7 fewer usable blastocysts compared with matched patients with on-time triggers. CONCLUSION(S): This study demonstrates that it is possible to develop an interpretable machine learning model for optimizing the day of trigger. Using our model has the potential to improve outcomes for many in vitro fertilization patients.

Early pregnancy anxiety during the COVID-19 pandemic: preliminary findings from the UCSF ASPIRE study.

BACKGROUND: Antenatal anxiety has been linked to adverse obstetric outcomes, including miscarriage and preterm birth. However, most studies investigating anxiety during pregnancy, particularly during the COVID-19 pandemic, have focused on symptoms during the second and third trimester. This study aims to describe the prevalence of anxiety symptoms early in pregnancy and identify predictors of early pregnancy anxiety during the COVID-19 pandemic. METHODS: We assessed baseline moderate-to-severe anxiety symptoms after enrollment in the UCSF ASPIRE (Assessing the Safety of Pregnancy in the Coronavirus Pandemic) Prospective Cohort from May 2020 through February 2021. Pregnant persons < 10 weeks' gestation completed questions regarding sociodemographic characteristics, obstetric/medical history, and pandemic-related experiences. Univariate and multivariate hierarchical logistic regression analyses determined predictors of moderate or severe anxiety symptoms (Generalized Anxiety Disorder-7 questionnaire score ≥ 10). All analyses performed with Statistical Analysis Software (SAS®) version 9.4. RESULTS: A total of 4,303 persons completed the questionnaire. The mean age of this nationwide sample was 33 years of age and 25.7% of participants received care through a fertility clinic. Over twelve percent of pregnant persons reported moderate-to-severe anxiety symptoms. In univariate analysis, less than a college education (p < 0.0001), a pre-existing history of anxiety (p < 0.0001), and a history of prior miscarriage (p = 0.0143) were strong predictors of moderate-to-severe anxiety symptoms. Conversely, having received care at a fertility center was protective (26.6% vs. 25.7%, p = 0.0009). COVID-19 related stressors including job loss, reduced work hours during the pandemic, inability to pay rent, very or extreme worry about COVID-19, and perceived stress were strongly predictive of anxiety in pregnancy (p < 0.0001). In the hierarchical logistic regression model, pre-existing history of anxiety remained associated with anxiety during pregnancy, while the significance of the effect of education was attenuated. CONCLUSION(S): Pre-existing history of anxiety and socioeconomic factors likely exacerbated the impact of pandemic-related stressors on early pregnancy anxiety symptoms during the COVID-19 pandemic. Despite on-going limitations for in-person prenatal care administration, continued emotional health support should remain an important focus for providers, particularly when caring for less privileged pregnant persons or those with a pre-existing history of anxiety.

Assessing efficacy of intravenous acetaminophen for perioperative pain control for oocyte retrieval: a randomized, double-blind, placebo-controlled trial.

OBJECTIVE: To compare the effect of preoperative intravenous (IV) acetaminophen versus oral (PO) acetaminophen or placebo on postoperative pain scores and the time to discharge in women undergoing oocyte retrieval. DESIGN: Randomized, double-blind, placebo-controlled trial. SETTING: Single academic fertility center. PATIENT(S): Women aged 18-43 years undergoing oocyte retrieval. INTERVENTION(S): Randomization to preoperative 1,000 mg IV acetaminophen and PO placebo (group A), IV placebo and 1,000 mg PO acetaminophen (group B), or IV and PO placebo (group C) MAIN OUTCOME MEASURE(S): Difference in patient-reported postoperative visual analog scale pain scores from baseline and the time to discharge. RESULT(S): Of the 159 women who completed the study, there were no differences in the mean postoperative pain score differences or the time to discharge. Although not statistically significant, the mean postoperative opioid dose requirement in group A was lower than that in groups B and C (0.24 vs. 0.59 vs. 0.58 mg IV morphine equivalents, respectively) due to fewer women in group A requiring rescue pain medication (8% vs. 19% vs. 15%, respectively). Group A also reported less constipation when compared with groups B and C (19% vs. 33% vs. 40%, respectively). The rates of postoperative nausea were similar, and there were no differences in embryology or early pregnancy outcomes between the study groups. CONCLUSION(S): Preoperative IV acetaminophen for women undergoing oocyte retrieval did not reduce postoperative pain scores or shorten the time to discharge when compared with PO acetaminophen or placebo and, thus, cannot currently be recommended routinely in this patient population. CLINICAL TRIAL REGISTRATION NUMBER: NCT03073980.

Prevalence and characteristics of patients declined from pursuing in vitro fertilization with autologous oocytes.

PURPOSE: To determine the frequency of and factors associated with a patient being declined from pursuing a cycle of in vitro fertilization with autologous oocytes (IVF-AO). METHODS: A cross-sectional study using a nationwide cohort of female respondents aged 35 or over, who visited a US fertility clinic from 1/2015 to 3/2020, responded to the online FertilityIQ questionnaire ( http://www.fertilityiq.com ). All respondents were asked if they were previously declined from pursuing a cycle of IVF-AO. Examined demographic and clinical predictors included age, race/ethnicity, education, income, clinic type, care received in a mandated state, insurance coverage for fertility treatment, and self-reported infertility diagnosis. Logistic regression was used to calculate the adjusted odds ratios for factors associated with being declined from pursuing IVF-AO. RESULTS: Of 8660 women who met inclusion criteria, 418 (4.8%) reported previously being declined a cycle of IVF-AO. In the multivariate analysis, predictors of being declined from pursuing IVF-AO included increasing age, income of less than $50,000, and diagnoses of poor oocyte quality and diminished ovarian reserve. Predictors of being less likely to report decline included some college or college degree and diagnoses of male factor, unexplained or tubal infertility. Notably, diagnosis of PCOS or residence in a state with mandated fertility coverage was not predictive of patients being declined from pursuing IVF-AO. CONCLUSION: Nearly 5% of patients who pursued IVF reported being declined from pursuing IVF-AO. Further studies are needed to confirm our findings and explore whether patients being declined treatment meet the criteria for futile or very poor prognosis.

A machine learning algorithm can optimize the day of trigger to improve in vitro fertilization outcomes.

OBJECTIVE: To determine whether a machine learning causal inference model can optimize trigger injection timing to maximize the yield of fertilized oocytes (2PNs) and total usable blastocysts for a given cohort of stimulated follicles. DESIGN: Descriptive and comparative study of new technology. SETTING: Tertiary academic medical center. PATIENT(S): Patients undergoing IVF with intracytoplasmic sperm injection from 2008 to 2019 (n = 7,866). INTERVENTION(S): Causal inference was performed with the use of a T-learner. Bagged decision trees were used to perform inference. The decision was framed as either triggering on that day or waiting another day. All patient characteristics and stimulation parameters on a given day were used to determine the recommendation. MAIN OUTCOME MEASURE(S): Average outcome improvement in total 2PNs and usable blastocysts compared with the physician's decision. RESULT(S): For evaluation of average outcome improvement on 2PNs, the benefit of following the model's recommendation was 3.015 (95% CI 2.626, 3.371) more 2PNs. For total usable blastocysts, the benefit was 1.515 (95% CI 1.134, 1.871) more usable blastocysts. Given that the physicians-model agreement was 52.57% and 61.89%, respectively, algorithm-assisted trigger decisions yield, on average, 1.430 more 2PNs and 0.577 more total usable blastocysts per stimulation. The most important features weighted in the model's decision were the number of follicles 16-20 mm in diameter, the number of follicles 11-15 mm in diameter, and estradiol level, in that order. CONCLUSION(S): The use of this machine learning algorithm to optimize trigger injection timing may lead to a significant increase in the number of 2PNs and total usable blastocysts obtained from an IVF stimulation cycle when compared with physician decisions. Future research is required to confirm these findings prospectively.