Breast Health

COVID-19

Cervical Health 

Contraception

Curbside Consults

Dermatology

Drug Pipeline News

Endometriosis

Genetic Testing

Gynecologic Oncology

Gynecology

Fetal Imaging

Abnormal Obstetrical Ultrasound

Ultrasound

Women's Imaging

Breast Imaging

Women's Ultrasound

Imaging

Infertility

LARC

Legally Speaking

Life Transitions

Malpractice

Menopause

Mental Health

Noninvasive Prenatal Testing

Obstetrics

Opinion

Osteoporosis

Pediatrics

Practice Management

Pregnancy and Birth

Sexual Health

Sexually Transmitted Infections

Surgery

Technology

Urology

Uterine Fibroids

Vulvovaginal Disease

Well Woman

About

News

Media

Podcasts

Insights

Investigator Perspectives

Medical World News

Peer Exchange

Peers & Perspectives

Videos

Conferences

Conference Coverage

Conference Listing

Publications

Contemporary OB/GYN® Journal

Digital Supplements

CME/CE

Resources

Physician Fact Sheets

Interactive Tools

Supplements and Featured Publications

Subscribe

Partnerships

Articles

She joined the MJH Life Sciences team in December 2019. She graduated from Youngstown State University in 2019 with a bachelor's degree in journalism and a minor in political science. Prior to graduating, Morgan worked as the editor-in-chief of her college newspaper. She went on to work as an assignment editor at a broadcast news station in Youngstown, Ohio, before joining 

 You can reach her at mebert@mjhlifesciences.com.

Experts urge a shift toward symptom-based menopause care, citing the high cost and limited clinical value of routine hormone panel testing.

Experts warn menopause hormone tests often unnecessary

Researchers have identified a distinctive CT imaging marker that increases the ability to predict severe postpartum bleeding.

CT scan pattern predicts risk of severe postpartum hemorrhage 

New research from Penn State reveals that endometriosis disrupts the autonomic nervous system, offering clues for earlier diagnosis.

Endometriosis found to influence blood pressure and stress response

A new study reveals that many women with polycystic ovary syndrome experience delayed diagnoses and inadequate care.

PCOS patients report feeling dismissed by health care providers

Advertise

Contact Us

Job Board

Terms of Use

Privacy Policy

Do Not Sell My Personal Information

Contemporary OB/GYN

Facebook

LinkedIn

RSS Feed

Spotlight

A Psychedelic to Treat Postpartum Depression?

CMV: In the Know

RSV Roundtable

STIs

Supplement: Closing the Gap in Cervical Cancer Screening

Vaginismus: Managing a Misunderstood and Underdiagnosed Condition

Why vNOTES Make Sense for My Patients

1rem

Authors

35th Annual Clinical Meeting of Advancing Minimally Invasive Gynecology Worldwide (AAGL)Las Vegas, NV - November 2006

Endometriosis and Pelvic Pain

What is your diagnosis of this placental lesion in a late second trimester pregnancy?

Clinical

Daily Dx: Placental Lesion

Saying "obstetrician-gynecologist" is a mouthful for most people, and it's probably the most abbreviated specialty in medicine, both spoken and written. However, there doesn't seem to be a consensus on how to pronounce OB-GYN. First, is it the two-syllable "O-B" or the monosyllabic "Ob"? Second, is it "gin" or "gyne" (like "Lyme")? I wonder if you have a preference. I know I do.

Almost nobody says "obstetrician-gynecologist" when speaking about these specialist physicians. But what's the "correct" way to pronounce OB/GYN?

Is It Ob-Gin or Ob-Gyne?

Artificial intelligence (AI) algorithms have shown high efficacy for identifying breast cancer on mammography images, according to a recent study published in 

These algorithms were submitted in the Radiological Society of North America’s (RSNA) AI Challenge, a crowdsourced competition with more than 1500 participating teams. Of submissions, the best 10 showed a performance close to that of the average screening radiologist in Europe and Australia.

“We were overwhelmed by the volume of contestants and the number of AI algorithms that were submitted as part of the Challenge,” said Yan Chen, PhD, professor in cancer screening at the University of Nottingham. “…We were also impressed by the performance of the algorithms given the relatively short window allowed for algorithm development.”

The challenge was conducted to evaluate the efficacy of algorithms submitted for breast cancer detection.

 The RSNA allowed submissions between November 2022 and February 2023, publicly announcing results in May 2023. There were 5415 breast screening cases included in the evaluation set, none of which were interval cancer cases.

Pathologic examination was used to identify cancer and benign lesions. Additional data collected included cancer laterality, patient age, invasive status, and whether a biopsy was performed. Breast density was also included when available.

AI algorithms were allowed to be developed using any architecture. However, they were run on the Kaggle server for assessment, making them limited by the server’s technical specifications. These algorithms provided breast-level prediction data, with some reporting outcomes as binary predictions and others on a continuous probability scale.

Women were aged 59 years when undergoing screening mammograms, with 2% of breasts having biopsy-proven cancer. Of noncancer cases, 3.2% were reported benign through biopsy. While 52% of breasts did not have density data available, 5.2% were A, 20% B, 20.1% C, and 2.6% D.

There were 1537 AI algorithms included in the final analysis, 1072 of which provided binary prediction and 465 provided a predicted probability. When ranking algorithms with a probabilistic F1 metric, a score of 0.555 was reported for the top algorithm.

A median recall rate of 1.7% was reported for the algorithms, alongside a median cancer detection rate of 0.54%. For the highest-ranked algorithm, these rates were 1.5% and 1%, respectively, vs 2.4% and 1.2% for the top 3, and 3.5% and 1.3% for the top 10.

The algorithms had a median positive predictive value (PPV) of 36.9% and a median negative predictive value (NPV) of 98.5%. For the top ranked algorithm, the top 3, and the top 10, PPVs were 64.6%, 49.2%, and 37.9%, respectively, while NPVs were 99%, 99.2%, and 99.4%.

The sensitivity and specificity of the algorithms were also reported, with medians of 27.6% and 98.7%, respectively. For the highest-ranked algorithm, these rates were 48.6% and 99.5%. Cancer type, acquisition site, and equipment manufacturer were all found to influence sensitivity.

Sensitivities of 56.7% and 29.7% were reported for invasive cancer cases and noninvasive cancer cases, respectively, for the top performing model. Additionally, a lower sensitivity was reported for site 1 vs site 2, and the use of Hologic equipment was linked to reduced sensitivity.

These results highlighted the efficacy of the submitted AI algorithms for detecting cancers on screening mammograms. Investigators concluded these algorithms could be used to increase sensitivity while maintaining clinically realistic recall rates.

“By releasing the algorithms and a comprehensive imaging dataset to the public, participants provide valuable resources that can drive further research and enable the benchmarking that is required for the effective and safe integration of AI into clinical practice,” said Chen.

RSNA AI challenge models can independently interpret mammograms. News release. Radiological Society of North America. August 12, 2025. Accessed August 14, 2025. https://www.eurekalert.org/news-releases/1093699

Chen Y, Partridge GJW, Vazirabad M, et al. Performance of algorithms submitted in the 2023 RSNA screening mammography breast cancer detection AI challenge. 

2025;316(2):e241447. doi:10.1148/radiol.241447

A major challenge study finds top-performing AI models can detect breast cancer on screening mammograms with accuracy comparable to experienced radiologists.

Top AI models show high accuracy in breast cancer screening

Attendance in prenatal care group visits increases the odds of women continuing with their care and experiencing better birth outcomes, according to a recent study published in 

Alongside better outcomes compared with women receiving one-on-one care, participants in a prenatal care group reported a preference for this care in future pregnancies. Investigators concluded these results may allow health providers in the United States to provide more effective and sustainable prenatal care.

“Bringing women together for group prenatal care allows them to form meaningful connections with peers and their midwife," said Crystal Patil, PhD, lead study author and professor of nursing at the University of Michigan. "They don’t just come to care and get a lecture about having a healthier pregnancy—instead, they collaboratively problem-solve."

The hybrid effectiveness-implementation trial was conducted to determine the impact of group prenatal care on outcomes in pregnant women.

 Participants were randomly assigned into a control arm of individual care vs group care, with the former group receiving standard antenatal care.

Standard care included meeting with a midwife for health assessments, with 8 visits offered to participants. In comparison, group care involved 7 antenatal sessions lasting 2 hours each and 1 session approximately 6 weeks after birth.

During these visits, 30 to 45 minutes were dedicated to socializing and health assessments. Additionally, participants underwent one-on-one sessions with the midwife in the group space. This included being able to have confidential discussions about personal concerns.

After the initial 30 to 45 minutes, the following 75 to 90 minutes were dedicated to group-wide interactive health promotion activities. Topics were discussed interactively, and group members participated in games, role plays, and the sharing of knowledge and experiences.

Participants included pregnant women presenting for their first antenatal visit and completing a baseline self-report survey. Those aged under 15 years or beyond 24-weeks’ gestation were excluded from the analysis.

Interventions were implemented through a 3-step model, robust training and mentoring program, support and interactive assistance, and minimizing the need for additional materials. The impact of group care was measured based on rates of low birth weight, with demographic and socioeconomic variables considered covariates.

Enhanced support and empowerment through group care

There were 1887 women included in the analysis, over 40% of whom were pregnant for the first time, nearly 60% aged 20 to 29 years, and over 90% married or in a relationship. Food insecurity within the prior year was reported in nearly 70%, and nearly 38% were anemic at baseline. These characteristics did not differ between care groups.

Participants receiving group care showed greater supportive relationships and peer connectedness than those receiving individual care, with a point estimate of 1.43. These patients also had higher pregnancy-related empowerment scale (PRES) scores, with a point estimate of 2.14. Higher PRES scores were also reported in multiparous women.

Wait time, satisfaction with care, care attendance, and preference for future group care were also positively impacted by group care. A 3.26-fold increased chance of reduced wait time was reported in the group care arm, and the point estimate for satisfaction vs the individual care arm was 1.21.

Group care was linked to more diverse diets in late pregnancy, higher healthy pregnancy knowledge, and increased partner communication scores vs individual care. While no association with low birth weight was reported, lower mental distress scores were noted in the group care arm, with a point estimate of -0.61.

Most clinical outcomes did not differ based on group vs individual care. However, the results highlighted the efficacy of group prenatal care toward providing important health promotion topics.

“While most women do know what supports a healthy pregnancy, group visits help them turn that knowledge into action—by sharing strategies, building confidence, and finding practical ways to eat well and prepare for childbirth,” said Patil.

Sherburne M. 'Care groups' keep women coming back for prenatal visits. News release. University of Michigan. July 31, 2025. Accessed August 14, 2025. https://www.eurekalert.org/news-releases/1093284

Patil CL, Norr KF, Kapito E, et al. Group antenatal care positively transforms the care experience: results of an effectiveness trial in Malawi. 

2025;20(6):e0317171. doi:10.1371/journal.pone.0317171

A new study reveals that group prenatal care leads to higher care attendance and better mental health during pregnancy compared with traditional one-on-one visits.

Group prenatal care boosts attendance and health outcomes

Women living in US counties with persistently low cervical cancer screening rates experience nearly twice the rate of cervical cancer diagnoses, particularly of late-stage disease, and mortality compared with those in high-screening counties, according to a new analysis from researchers at the MUSC Hollings Cancer Center.

, builds on prior work showing that cervical cancer incidence and death rates are higher in low-income and rural counties. “We know that higher screening uptake prevents disease and subsequent mortality,” said lead author Trisha Amboree, PhD. “In the previous papers, we didn't have any individual-level screening data. This paper helps to contextualize our previous findings to say what we're seeing is at least probably partially a result of repeatedly low screening.”

Using data from the Surveillance, Epidemiology, and End Results (SEER)–22 database, investigators identified cervical cancer cases among women aged 20 years and older, along with corresponding mortality data from the National Center for Health Statistics. Screening coverage estimates were obtained from SEER’s small area estimates for 1086 counties.

Counties were classified as “repeatedly low screening” if coverage was below 70% from 2011 to 2016 and at least one earlier time period (2004–2007 or 2008–2010). “Repeatedly high screening” counties had coverage of 80% or greater during those periods. Nationally, the cervical cancer screening goal is 79.2%.

Of the counties studied, 70 were classified as repeatedly low screening, 141 as repeatedly high screening, and 875 as intermediate. Most low-screening counties were rural (87.1%) and had median household incomes below $75,000. Nearly half were located in Texas, with others in Idaho and New Mexico.

From 2016 to 2021 (excluding 2020), age-adjusted cervical cancer incidence was 83% higher in low-screening counties compared with high-screening counties (rate ratio [RR], 1.83; 95% CI, 1.67–2.00). Localized-stage incidence was 75% higher, regional-stage incidence 87% higher, and distant-stage incidence 84% higher.

Cervical cancer mortality was nearly doubled in low-screening counties, with a 96% higher death rate compared with high-screening counties (RR, 1.96; 95% CI, 1.66–2.30).

The analysis found that nearly all repeatedly low-screening counties were rural and low-income, reflecting structural barriers to preventive care. In South Carolina, where the state’s data were not part of the national database, access issues remain significant. Fourteen counties have no obstetrician-gynecologists, and several others have only a handful or a single family physician providing screening.

Timely screening, such as Pap smears or HPV testing, can detect precancerous lesions or early-stage cancer, improving the chances of successful treatment. Current US Preventive Services Task Force guidelines recommend Pap testing every 3 years for women aged 21 to 65 years, or HPV testing (alone or with a Pap) every 5 years for those aged 30 to 65 years.

“This latest analysis reinforces the need for improved access to screening and treatment, particularly in rural and low-income counties,” the authors wrote. Hollings Cancer Center addresses these gaps in South Carolina through its Mobile Health Unit, which provides cervical cancer screening in underserved areas.

While the study’s cross-sectional design precludes causal conclusions and results may be influenced by socioeconomic factors and self-reported screening data, the findings underscore a clear association between low screening coverage and worse outcomes.

“Our study findings underscore the urgent need to improve cervical cancer screening in rural and lower-income counties,” the authors concluded. “Particularly, counties where screening coverage is repeatedly low should be targeted.”

Amboree TL, Montealegre JR, Damgacioglu H, et al. County-level cervical cancer screening coverage and differences in incidence and mortality. 

. 2025;8(8):e2526709. doi:10.1001/jamanetworkopen.2025.26709

Medical University of South Carolina. Counties with low rates of cervical cancer screening see higher rates of incidence and death. EurekAlert! August 13, 2025. Accessed August 14, 2025. https://www.eurekalert.org/news-releases/1094428


Counties with persistently low cervical cancer screening rates have nearly double the rates of late-stage diagnoses and mortality, study finds.

Lower cervical cancer screening rates linked to higher late-stage diagnoses and mortality

A new artificial intelligence (AI) platform developed by Ultrasound AI has demonstrated high accuracy in predicting delivery timing from standard obstetric ultrasound images, according to findings from the Perinatal Artificial Intelligence in Ultrasound (PAIR) study published in 

The Journal of Maternal-Fetal & Neonatal Medicine

. The study, conducted with researchers at the University of Kentucky, suggests the technology could improve risk assessment for preterm birth (PTB) and enhance maternal-fetal care, particularly in resource-limited settings.

“This is a major milestone for the field of maternal-fetal medicine and for Ultrasound AI,” said Robert Bunn, founder and president of Ultrasound AI. “Our AI’s ability to accurately predict delivery timing—and learn and improve over time—has profound implications for both clinical practice and public health, especially in settings where early risk identification is critical and access to specialist care is limited.”

The retrospective cohort study analyzed deidentified ultrasound images from 5714 pregnant patients who delivered at the University of Kentucky between 2017 and 2021. A total of 19,940 unique ultrasound exams and 877,141 images were used for initial AI training. Of these, 79% were allocated to a training set and 21% to an independent validation set.

The AI used deep learning algorithms, including convolutional neural networks and transformers, to process still ultrasound images without input from clinical measurements, maternal history, or operator annotations. Predictions focused on the number of days until delivery and whether the birth would be preterm (<37 weeks’ gestation). The model underwent multiple retraining iterations, incorporating more than 2 million ultrasound images by the final version (V4).

In the initial model (V1), the AI achieved an R² of 0.90 for term births and 0.85 for all births combined when predicting days to delivery. For spontaneous PTB, the R² was 0.48. Retraining improved performance substantially: in V4, R² reached 0.95 for term births, 0.92 for all births, and 0.72 for spontaneous PTB.

The model’s PTB prediction sensitivity was initially 39%, with a specificity of 93% and an area under the receiver operating characteristic curve (AUC) of 0.757. After retraining, sensitivity increased to 40% and specificity to 95%, with AUC rising to 0.825. For births occurring within 30 days, AUC improved from 0.842 to 0.900.

Performance was consistent across trimesters, with mean absolute error ranging from approximately 12 to 15 days. The AI maintained accuracy across patient demographics, including variations in age, body mass index, and race or ethnicity.

PTB remains the leading cause of neonatal mortality worldwide, and accurate prediction is a persistent challenge. Traditional PTB risk assessment methods rely on clinical history, biomarker testing, and cervical length measurements, which can be limited by interobserver variability and access to specialized care.

Ultrasound AI’s platform offers a noninvasive, operator-independent tool that can be integrated into standard imaging workflows without additional testing. “AI is reaching into the womb and helping us forecast the timing of birth, which we believe will lead to better prediction[s] to help mothers across the world,” said John M. O’Brien, MD, division director of maternal-fetal medicine at the University of Kentucky.

The authors noted that continuous learning capabilities and the ability to process large imaging datasets enable the model to improve over time. The system could potentially be enhanced by integrating serial ultrasound exams, biochemical biomarkers, and Doppler or fetal movement data.

The PAIR study demonstrates that AI can predict delivery timing with high accuracy using only ultrasound images and can improve the prediction of PTB with iterative retraining. Further validation in diverse populations and integration into clinical workflows could advance personalized obstetric care, potentially improving maternal and neonatal outcomes.

Hiltzik Strategies. Ultrasound AI publishes landmark study demonstrating breakthrough in predicting delivery timing using AI and ultrasound images. EurekAlert! August 13, 2025. Accessed August 14, 2025. https://www.eurekalert.org/news-releases/1094602

Patel N, O’Brien J, Bunn R, Schanbacher B, Bauer J, Lam GK. Perinatal artificial intelligence in ultrasound (PAIR) study: predicting delivery timing. 

. 2025;38(1):2532099. doi:10.1080/14767058.2025.2532099

AI model predicts delivery timing from ultrasound images with high accuracy, offering a potential tool for preterm birth risk assessment.

Andrew S. Cook, MD

Articles

Latest Updated Articles