Blinded, randomized trial of sonographer versus AI cardiac function assessment.

Artificial intelligence (AI) has been developed for echocardiography1-3, although it has not yet been tested with blinding and randomization. Here we designed a blinded, randomized non-inferiority clinical trial (ClinicalTrials.gov ID: NCT05140642; no outside funding) of AI versus sonographer initial assessment of left ventricular ejection fraction (LVEF) to evaluate the impact of AI in the interpretation workflow. The primary end point was the change in the LVEF between initial AI or sonographer assessment and final cardiologist assessment, evaluated by the proportion of studies with substantial change (more than 5% change). From 3,769 echocardiographic studies screened, 274 studies were excluded owing to poor image quality. The proportion of studies substantially changed was 16.8% in the AI group and 27.2% in the sonographer group (difference of -10.4%, 95% confidence interval: -13.2% to -7.7%, P < 0.001 for non-inferiority, P < 0.001 for superiority). The mean absolute difference between final cardiologist assessment and independent previous cardiologist assessment was 6.29% in the AI group and 7.23% in the sonographer group (difference of -0.96%, 95% confidence interval: -1.34% to -0.54%, P < 0.001 for superiority). The AI-guided workflow saved time for both sonographers and cardiologists, and cardiologists were not able to distinguish between the initial assessments by AI versus the sonographer (blinding index of 0.088). For patients undergoing echocardiographic quantification of cardiac function, initial assessment of LVEF by AI was non-inferior to assessment by sonographers.

Video-based AI for beat-to-beat assessment of cardiac function.

Accurate assessment of cardiac function is crucial for the diagnosis of cardiovascular disease1, screening for cardiotoxicity2 and decisions regarding the clinical management of patients with a critical illness3. However, human assessment of cardiac function focuses on a limited sampling of cardiac cycles and has considerable inter-observer variability despite years of training4,5. Here, to overcome this challenge, we present a video-based deep learning algorithm-EchoNet-Dynamic-that surpasses the performance of human experts in the critical tasks of segmenting the left ventricle, estimating ejection fraction and assessing cardiomyopathy. Trained on echocardiogram videos, our model accurately segments the left ventricle with a Dice similarity coefficient of 0.92, predicts ejection fraction with a mean absolute error of 4.1% and reliably classifies heart failure with reduced ejection fraction (area under the curve of 0.97). In an external dataset from another healthcare system, EchoNet-Dynamic predicts the ejection fraction with a mean absolute error of 6.0% and classifies heart failure with reduced ejection fraction with an area under the curve of 0.96. Prospective evaluation with repeated human measurements confirms that the model has variance that is comparable to or less than that of human experts. By leveraging information across multiple cardiac cycles, our model can rapidly identify subtle changes in ejection fraction, is more reproducible than human evaluation and lays the foundation for precise diagnosis of cardiovascular disease in real time. As a resource to promote further innovation, we also make publicly available a large dataset of 10,030 annotated echocardiogram videos.

Deep learning to detect left ventricular structural abnormalities in chest X-rays.

BACKGROUND AND AIMS: Early identification of cardiac structural abnormalities indicative of heart failure is crucial to improving patient outcomes. Chest X-rays (CXRs) are routinely conducted on a broad population of patients, presenting an opportunity to build scalable screening tools for structural abnormalities indicative of Stage B or worse heart failure with deep learning methods. In this study, a model was developed to identify severe left ventricular hypertrophy (SLVH) and dilated left ventricle (DLV) using CXRs. METHODS: A total of 71 589 unique CXRs from 24 689 different patients completed within 1 year of echocardiograms were identified. Labels for SLVH, DLV, and a composite label indicating the presence of either were extracted from echocardiograms. A deep learning model was developed and evaluated using area under the receiver operating characteristic curve (AUROC). Performance was additionally validated on 8003 CXRs from an external site and compared against visual assessment by 15 board-certified radiologists. RESULTS: The model yielded an AUROC of 0.79 (0.76-0.81) for SLVH, 0.80 (0.77-0.84) for DLV, and 0.80 (0.78-0.83) for the composite label, with similar performance on an external data set. The model outperformed all 15 individual radiologists for predicting the composite label and achieved a sensitivity of 71% vs. 66% against the consensus vote across all radiologists at a fixed specificity of 73%. CONCLUSIONS: Deep learning analysis of CXRs can accurately detect the presence of certain structural abnormalities and may be useful in early identification of patients with LV hypertrophy and dilation. As a resource to promote further innovation, 71 589 CXRs with adjoining echocardiographic labels have been made publicly available.

Detection of Left Ventricular Systolic Dysfunction From Electrocardiographic Images.

BACKGROUND: Left ventricular (LV) systolic dysfunction is associated with a >8-fold increased risk of heart failure and a 2-fold risk of premature death. The use of ECG signals in screening for LV systolic dysfunction is limited by their availability to clinicians. We developed a novel deep learning-based approach that can use ECG images for the screening of LV systolic dysfunction. METHODS: Using 12-lead ECGs plotted in multiple different formats, and corresponding echocardiographic data recorded within 15 days from the Yale New Haven Hospital between 2015 and 2021, we developed a convolutional neural network algorithm to detect an LV ejection fraction <40%. The model was validated within clinical settings at Yale New Haven Hospital and externally on ECG images from Cedars Sinai Medical Center in Los Angeles, CA; Lake Regional Hospital in Osage Beach, MO; Memorial Hermann Southeast Hospital in Houston, TX; and Methodist Cardiology Clinic of San Antonio, TX. In addition, it was validated in the prospective Brazilian Longitudinal Study of Adult Health. Gradient-weighted class activation mapping was used to localize class-discriminating signals on ECG images. RESULTS: Overall, 385 601 ECGs with paired echocardiograms were used for model development. The model demonstrated high discrimination across various ECG image formats and calibrations in internal validation (area under receiving operation characteristics [AUROCs], 0.91; area under precision-recall curve [AUPRC], 0.55); and external sets of ECG images from Cedars Sinai (AUROC, 0.90 and AUPRC, 0.53), outpatient Yale New Haven Hospital clinics (AUROC, 0.94 and AUPRC, 0.77), Lake Regional Hospital (AUROC, 0.90 and AUPRC, 0.88), Memorial Hermann Southeast Hospital (AUROC, 0.91 and AUPRC 0.88), Methodist Cardiology Clinic (AUROC, 0.90 and AUPRC, 0.74), and Brazilian Longitudinal Study of Adult Health cohort (AUROC, 0.95 and AUPRC, 0.45). An ECG suggestive of LV systolic dysfunction portended >27-fold higher odds of LV systolic dysfunction on transthoracic echocardiogram (odds ratio, 27.5 [95% CI, 22.3-33.9] in the held-out set). Class-discriminative patterns localized to the anterior and anteroseptal leads (V2 and V3), corresponding to the left ventricle regardless of the ECG layout. A positive ECG screen in individuals with an LV ejection fraction ≥40% at the time of initial assessment was associated with a 3.9-fold increased risk of developing incident LV systolic dysfunction in the future (hazard ratio, 3.9 [95% CI, 3.3-4.7]; median follow-up, 3.2 years). CONCLUSIONS: We developed and externally validated a deep learning model that identifies LV systolic dysfunction from ECG images. This approach represents an automated and accessible screening strategy for LV systolic dysfunction, particularly in low-resource settings.

Sex Differences in Myocardial and Vascular Aging.

It is well known that cardiovascular disease manifests differently in women and men. The underlying causes of these differences during the aging lifespan are less well understood. Sex differences in cardiac and vascular phenotypes are seen in childhood and tend to track along distinct trajectories related to dimorphism in genetic factors as well as response to risk exposures and hormonal changes during the life course. These differences underlie sex-specific variation in cardiovascular events later in life, including myocardial infarction, heart failure, ischemic stroke, and peripheral vascular disease. With respect to cardiac phenotypes, females have intrinsically smaller body size-adjusted cardiac volumes and they tend to experience greater age-related wall thickening and myocardial stiffening with aging. With respect to vascular phenotypes, sexual dimorphism in both physiology and pathophysiology are also seen, including overt differences in blood pressure trajectories. The majority of sex differences in myocardial and vascular alterations that manifest with aging seem to follow relatively consistent trajectories from the very early to the very later stages of life. This review aims to synthesize recent cardiovascular aging-related research to highlight clinically relevant studies in diverse female and male populations that can inform approaches to improving the diagnosis, management, and prognosis of cardiovascular disease risks in the aging population at large.

Severe aortic stenosis detection by deep learning applied to echocardiography.

BACKGROUND AND AIMS: Early diagnosis of aortic stenosis (AS) is critical to prevent morbidity and mortality but requires skilled examination with Doppler imaging. This study reports the development and validation of a novel deep learning model that relies on two-dimensional (2D) parasternal long axis videos from transthoracic echocardiography without Doppler imaging to identify severe AS, suitable for point-of-care ultrasonography. METHODS AND RESULTS: In a training set of 5257 studies (17 570 videos) from 2016 to 2020 [Yale-New Haven Hospital (YNHH), Connecticut], an ensemble of three-dimensional convolutional neural networks was developed to detect severe AS, leveraging self-supervised contrastive pretraining for label-efficient model development. This deep learning model was validated in a temporally distinct set of 2040 consecutive studies from 2021 from YNHH as well as two geographically distinct cohorts of 4226 and 3072 studies, from California and other hospitals in New England, respectively. The deep learning model achieved an area under the receiver operating characteristic curve (AUROC) of 0.978 (95% CI: 0.966, 0.988) for detecting severe AS in the temporally distinct test set, maintaining its diagnostic performance in geographically distinct cohorts [0.952 AUROC (95% CI: 0.941, 0.963) in California and 0.942 AUROC (95% CI: 0.909, 0.966) in New England]. The model was interpretable with saliency maps identifying the aortic valve, mitral annulus, and left atrium as the predictive regions. Among non-severe AS cases, predicted probabilities were associated with worse quantitative metrics of AS suggesting an association with various stages of AS severity. CONCLUSION: This study developed and externally validated an automated approach for severe AS detection using single-view 2D echocardiography, with potential utility for point-of-care screening.

AI-ENABLED ASSESSMENT OF CARDIAC FUNCTION AND VIDEO QUALITY IN EMERGENCY DEPARTMENT POINT-OF-CARE ECHOCARDIOGRAMS.

BACKGROUND: The adoption of point-of-care ultrasound (POCUS) has greatly improved the ability to rapidly evaluate unstable emergency department (ED) patients at the bedside. One major use of POCUS is to obtain echocardiograms to assess cardiac function. OBJECTIVES: We developed EchoNet-POCUS, a novel deep learning system, to aid emergency physicians (EPs) in interpreting POCUS echocardiograms and to reduce operator-to-operator variability. METHODS: We collected a new dataset of POCUS echocardiogram videos obtained in the ED by EPs and annotated the cardiac function and quality of each video. Using this dataset, we train EchoNet-POCUS to evaluate both cardiac function and video quality in POCUS echocardiograms. RESULTS: EchoNet-POCUS achieves an area under the receiver operating characteristic curve (AUROC) of 0.92 (0.89-0.94) for predicting whether cardiac function is abnormal and an AUROC of 0.81 (0.78-0.85) for predicting video quality. CONCLUSIONS: EchoNet-POCUS can be applied to bedside echocardiogram videos in real time using commodity hardware, as we demonstrate in a prospective pilot study.

Association of sickle cell trait with adverse pregnancy outcomes in a population-based cohort.

INTRODUCTION: Sickle cell trait (SCT) is common in African descendants. Its association with several adverse pregnancy outcomes (APOs) has been reported but remains inconsistent. The objectives of this study are to test associations of SCT with APOs in non-Hispanic Black women, including (1) validate the associations of SCT with previously reported APOs, (2) test novel associations of SCT with broad spectrum of APOs, and (3) estimate the attributable risk of SCT for implicated APOs. MATERIAL AND METHODS: This is a retrospective analysis of a prospectively designed population-based cohort. Women/participants were self-reported non-Hispanic Black women from the UK Biobank (UKB). SCT status was determined based on heterozygous Glu6Val in the HBB gene. Several APOs were studied, including four previously reported SCT-associated APOs (preeclampsia, bacteriuria, pregnancy loss, and preterm delivery), and broad conditions related to pregnancy, childbirth, and the puerperium. APOs were curated by experts' peer review and consensus processes. Associations of SCT with APOs were tested by estimating its relative risk and 95% confidence interval (95% CI), adjusting for number of live births and age at first birth. Attributable risk proportion (ARP) and population attributable risk proportion (PARP) of SCT to APOs were estimated. RESULTS: Among the 4057 self-reported non-Hispanic Black women with pregnancy records in the UKB, 581 (14.32%) were SCT carriers. For four previously reported SCT-associated APOs, two were confirmed at a nominal P < 0.05; relative risk (RR) was 2.39 (95% CI 1.09-5.23) for preeclampsia, and 4.85 (95% CI 1.77-13.27) for bacteriuria. SCT contributed substantially to these two APOs among SCT carriers, with attributable risk proportion estimated at 61.00% and 68.96% for preeclampsia and bacteriuria, respectively. SCT also contributed substantially to these two APOs in the population (self-reported Black UK women), with population attributable risk proportion estimated at 18.30% and 24.14% for preeclampsia and bacteriuria, respectively. In addition, novel associations were found for seven other APOs (nominal P < 0.05). CONCLUSIONS: SCT is significantly associated with APOs in this study and contributes substantially to APOs among self-reported Black women in the UK. Confirmation of these findings in independent study populations is required.

Current and Future Applications of Artificial Intelligence in Cardiac CT.

PURPOSE OF REVIEW: In this review, we aim to summarize state-of-the-art artificial intelligence (AI) approaches applied to cardiovascular CT and their future implications. RECENT FINDINGS: Recent studies have shown that deep learning networks can be applied for rapid automated segmentation of coronary plaque from coronary CT angiography, with AI-enabled measurement of total plaque volume predicting future heart attack. AI has also been applied to automate assessment of coronary artery calcium on cardiac and ungated chest CT and to automate the measurement of epicardial fat. Additionally, AI-based prediction models integrating clinical and imaging parameters have been shown to improve prediction of cardiac events compared to traditional risk scores. Artificial intelligence applications have been applied in all aspects of cardiovascular CT - in image acquisition, reconstruction and denoising, segmentation and quantitative analysis, diagnosis and decision assistance and to integrate prognostic risk from clinical data and images. Further incorporation of artificial intelligence in cardiovascular imaging holds important promise to enhance cardiovascular CT as a precision medicine tool.

The Association between Maternal Body Mass Index and the Risk of Perinatal Depression.

OBJECTIVE: The aim of this study was to evaluate whether the risk of perinatal depression is associated with body mass index (BMI) category. STUDY DESIGN: We performed a retrospective cohort study of women who completed an Edinburgh Postnatal Depression Scale (EPDS) questionnaire during the antepartum period at an integrated health system from January 2003 to May 2018. Risk of perinatal depression was defined as a score of ≥10 on the EPDS or an affirmative response to thoughts of self-harm. Risk of perinatal depression was compared by first trimester BMI category, defined as underweight (BMI: <18.5 kg/m2), normal weight (BMI: 18.5-24.9 kg/m2), overweight (BMI: 25.0-29.9 kg/m2), or obese (BMI: ≥30.0 kg/m2). Univariable analyses were performed using χ 2, Fisher's exact test, analysis of variance, Kruskal-Wallis, and Wilcoxon rank-sum tests as appropriate to evaluate the association between maternal BMI category, demographic and clinical characteristics, and risk of perinatal depression. Logistic multivariable regression models were performed to adjust for potential confounders identified as variables with p < 0.10 in univariable analysis. RESULTS: Our analysis included 3,420 obese women, 3,839 overweight women, 5,949 normal weight women, and 1,203 underweight women. The overall median gestational age at EPDS administration was 27 weeks (interquartile range: 23-29). Overweight and obese women were more likely to be non-Hispanic Black, Hispanic, multiparous, to have public insurance, prepregnancy diabetes, and chronic hypertension as compared with normal or underweight women (p < 0.001). In univariable analysis, the risk of perinatal depression was not significantly different among underweight (10.8%, odds ratio [OR]: 0.86, 95% confidence interval [CI]: 0.79-1.18) or overweight women (12%, OR: 0.96, 95% CI: 0.79-1.18); however, the risk was higher among obese women (14.7%, 95% CI: 1.21-1.55) compared with normal weight women (11.2%). In multivariable analysis, obesity remained associated with an increased risk of perinatal depression (adjusted OR: 1.19, 95% CI: 1.04-1.35). CONCLUSION: Obesity is associated with an increased risk of perinatal depression as compared with women of normal weight. KEY POINTS: · Maternal obesity is associated with an increased risk of perinatal depression.. · Maternal BMI is associated with increased risk of perinatal depression.. · Maternal obesity is an independent risk factor for perinatal depression..

Cardiac microstructural alterations in immune-inflammatory myocardial disease: a retrospective case-control study.

BACKGROUND: Immune-inflammatory myocardial disease contributes to multiple chronic cardiac processes, but access to non-invasive screening is limited. We have previously developed a method of echocardiographic texture analysis, called the high-spectrum signal intensity coefficient (HS-SIC) which assesses myocardial microstructure and previously associated with myocardial fibrosis. We aimed to determine whether this echocardiographic texture analysis of cardiac microstructure can identify inflammatory cardiac disease in the clinical setting. METHODS: We conducted a retrospective case-control study of 318 patients with distinct clinical myocardial pathologies and 20 healthy controls. Populations included myocarditis, atypical chest pain/palpitations, STEMI, severe aortic stenosis, acute COVID infection, amyloidosis, and cardiac transplantation with acute rejection, without current rejection but with prior rejection, and with no history of rejection. We assessed the HS-SIC's ability to differentiate between a broader diversity of clinical groups and healthy controls. We used Kruskal-Wallis tests to compare HS-SIC values measured in each of the clinical populations with those in the healthy control group and compared HS-SIC values between the subgroups of cardiac transplantation rejection status. RESULTS: For the total sample of N = 338, the mean age was 49.6 ± 20.9 years and 50% were women. The mean ± standard error of the mean of HS-SIC were: 0.668 ± 0.074 for controls, 0.552 ± 0.049 for atypical chest pain/palpitations, 0.425 ± 0.058 for myocarditis, 0.881 ± 0.129 for STEMI, 1.116 ± 0.196 for severe aortic stenosis, 0.904 ± 0.116 for acute COVID, and 0.698 ± 0.103 for amyloidosis. Among cardiac transplant recipients, HS-SIC values were 0.478 ± 0.999 for active rejection, 0.594 ± 0.091 for prior rejection, and 1.191 ± 0.442 for never rejection. We observed significant differences in HS-SIC between controls and myocarditis (P = 0.0014), active rejection (P = 0.0076), and atypical chest pain or palpitations (P = 0.0014); as well as between transplant patients with active rejection and those without current or prior rejection (P = 0.031). CONCLUSIONS: An echocardiographic method can be used to characterize tissue signatures of microstructural changes across a spectrum of cardiac disease including immune-inflammatory conditions.

Gender Differences in Authorship of Critical Care Literature.

Rationale: Gender gaps exist in academic leadership positions in critical care. Peer-reviewed publications are crucial to career advancement, and yet little is known regarding gender differences in authorship of critical care research.Objectives: To evaluate gender differences in authorship of critical care literature.Methods: We used a validated database of author gender to analyze authorship of critical care articles indexed in PubMed between 2008 and 2018 in 40 frequently cited journals. High-impact journals were defined as those in the top 5% of all journals. We used mixed-effects logistic regression to evaluate the association of senior author gender with first and middle author gender, as well as association of first author gender with journal impact factor.Measurements and Main Results: Among 18,483 studies, 30.8% had female first authors, and 19.5% had female senior authors. Female authorship rose slightly over the last decade (average annual increases of 0.44% [P < 0.01] and 0.51% [P < 0.01] for female first and senior authors, respectively). When the senior author was female, the odds of female coauthorship rose substantially (first author adjusted odds ratio [aOR], 1.93; 95% confidence interval [CI], 1.71-2.17; middle author aOR, 1.48; 95% CI, 1.29-1.69). Female first authors had higher odds than men of publishing in lower-impact journals (aOR, 1.30; 95% CI, 1.16-1.45).Conclusions: Women comprise less than one-third of first authors and one-fourth of senior authors of critical care research, with minimal increase over the past decade. When the senior author was female, the odds of female coauthorship rose substantially. However, female first authors tend to publish in lower-impact journals. These findings may help explain the underrepresentation of women in critical care academic leadership positions and identify targets for improvement.

Recurrent Non Immune Fetal Hydrops Associated With IPEX Syndrome.

Immune dysregulation, polyendocrinopathy, enteropathy, X-linked (IPEX) is a clinical syndrome associated with mutations in FOXP3 and consequent abnormalities of T regulatory cells. Affected males typically die in infancy or early childhood from a variety of autoimmune conditions. Reports of recurrent pregnancy loss of male fetuses in these families have been accompanied by descriptions of nonimmune fetal hydrops, with or without additional fetal anomalies. Here, we report an additional family affected by IPEX with a novel mutation leading to recurrent second trimester fetal hydrops and intrauterine fetal demise with associated fetal anomalies. This report underscores how careful genetic and pathologic analysis of even midtrimester fetuses can provide important information impacting an entire family. It also further substantiates the use of broad, symptom-targeted genetic screening panels in cases of recurrent pregnancy loss even in the absence of a remarkable pedigree.

Gender Trends in Authorship of Foot and Ankle Academic Literature Over 24 Years.

Underrepresentation of females in surgery is reflected in research productivity across academic medicine, with male faculty being more likely to publish research than their female counterparts. In this study, we aimed to describe the representation and longevity of female investigators among the authors of articles in 3 foot and ankle research journals from 1993 to 2017. In this retrospective bibliometric analysis, authors from 3 prominent foot and ankle research journals (Foot and Ankle International, The Journal of Foot and Ankle Surgery, and Foot and Ankle Clinics) were identified. The proportion of female authors who were first, middle, and senior authors and the total publication count per author were determined. From 1993 to 2017, 8132 original articles were published and a total of 6597 (81.1%) had an accessible author list. This allowed us to identify 25,329 total authors, of whom 22,961 (90.7%) were successfully matched to a gender. A total of 9273 unique authors were identified (females, 19.2%). Female representation increased for first and senior authors over the years from 6.5% and 5.9% (1993 to 1997) to 16.9% and 13.1% (2013 to 2017, p < .001), respectively. However, compared with male authors, female authors published fewer articles (mean: 1.7 versus 2.4, p < .001). Of the 2691 authors who first published during 2006 to 2011, 369 authors (13%), consisting of 8.1% females and 15% males (p < .001), continued to publish 5 years after their initial publication. Female representation in academic foot and ankle research has increased >2-fold over the past 2 decades. But despite these advances, compared to male authors, female authors are less likely to continue publishing 5 years after initial publication, and on average publish fewer articles.

Perinatal and obstetric outcomes of dichorionic vs trichorionic triplet pregnancies.

BACKGROUND: Clinical management and outcome of multiple gestation can be affected by chorionicity. In triplet pregnancies, fetal death has been associated with dichorionic (DC) and monochorionic placentation. Studies evaluating triplet pregnancy outcomes in relation to chorionicity have been few and may not reflect contemporary antenatal and neonatal care. OBJECTIVE: The objective of this study was to compare obstetric and perinatal outcomes in DC and trichorionic (TC) triplet pregnancies. STUDY DESIGN: We performed a retrospective cohort study of triplet pregnancies that delivered at ≥20 weeks' gestation at 2 Chicago area hospitals from January 1999 through December 2010. Chorionicity was determined by pathology specimen. Maternal and infant charts were reviewed for obstetric and perinatal outcomes. RESULTS: The study population included 159 pregnancies (477 neonates) of which 108 were TC (67.9%) and 51 were DC (32.1%). Over 94% of mothers in this study had all 3 infants survive to discharge regardless of chorionicity. No difference was found in perinatal mortality rate between DC and TC triplets (3.3% vs 4.6%; P = .3). DC triplets were significantly more likely to be very low birthweight (41.8% vs 22.2%; odds ratio, 2.2; 95% confidence interval, 1.2-4.2; P = .02) and to deliver at <30 weeks (25.5% vs 8.3%; odds ratio, 6.1; 95% confidence interval, 1.9-19.4; P = .002) compared to TC triplets. Criteria for twin-twin transfusion syndrome (TTTS) were present in 3 DC triplet pregnancies (5.9%). Neonates in pregnancies complicated by TTTS were less likely to survive 28 days as compared to neonates from DC pregnancies that were not affected by TTTS (P = .02) or TC neonates (P = .02) Neonatal survival was similar in DC pregnancies not affected by TTTS and TC pregnancies (98.6% and 96.6%; P = .7). CONCLUSION: Although perinatal mortality did not correlate with chorionicity, DC pregnancies were more likely to deliver <30 weeks' gestational age and have very low birthweight neonates. Neonatal mortality appears to be mediated by the presence or absence of TTTS as 28-day survival was worse in DC pregnancies complicated by TTTS, but similar between DC pregnancies not affected by TTTS and TC pregnancies.

Implications of sleep-disordered breathing in pregnancy.

OBJECTIVE: The objective of the study was to examine the relationship between sleep-disordered breathing (SDB) and adverse pregnancy outcomes in a high-risk cohort. STUDY DESIGN: This was a planned analysis of a prospective cohort designed to estimate the prevalence and trends of SDB in high-risk pregnant women. We recruited women with a body mass index of 30 kg/m(2) or greater, chronic hypertension, pregestational diabetes, prior preeclampsia, and/or a twin gestation. Objective assessment of SDB was completed between 6 and 20 weeks and again in the third trimester. SDB was defined as an apnea hypopnea index of 5 or greater and further grouped into severity categories: mild SDB (5-14.9), moderate SDB (15-29.9), and severe SDB (≥30). Pregnancy outcomes (preeclampsia, gestational diabetes, preterm birth, infant weight) were abstracted by physicians blinded to the SDB results. RESULTS: Of the 188 women with a valid early pregnancy sleep study, 182 had complete delivery records. There was no relationship demonstrated between SDB exposure in early or late pregnancy and preeclampsia, preterm birth less than 34 weeks, and small-for-gestational-age (<5%), or large-for-gestational-age (>95%) neonates. Conversely, SDB severity in early pregnancy was associated with the risk of developing gestational diabetes (no SDB, 25%; mild SDB, 43%; moderate/severe SDB, 63%; P = .03). The adjusted odds ratio for developing gestational diabetes for moderate/severe SDB was 3.6 (0.6, 21.8). CONCLUSION: This study suggests a dose-dependent relationship between SDB in early pregnancy and the subsequent development of gestational diabetes. In contrast, no relationships between SDB during pregnancy and preeclampsia, preterm birth, and extremes of birthweight were demonstrated.

Clinical implementation of noninvasive prenatal testing among maternal fetal medicine specialists.

OBJECTIVE: To assess the clinical implementation of non-invasive prenatal testing (NIPT) among maternal-fetal medicine (MFM) specialists. METHOD: Practicing MFMs were invited by email to complete questionnaires via SurveyMonkey©. RESULTS: Of 278 respondents, 56% were male, 48% practiced in academic centers, and 94% currently offer NIPT. NIPT is most often being offered 'to specific patients meeting certain criteria' (59.2%), for indications of advanced maternal age (87.5%), abnormal screen results (94.9%), abnormal ultrasound findings (90.2%), and 'when a high-risk patient declines invasive diagnostic testing' (73.7%). Thirteen percent indicated NIPT is being offered as a diagnostic test. Regardless of whether NIPT was presented as a diagnostic or screening test, 65.3% of MFMs estimate 'some' of their patients have undergone invasive testing for confirmation. Responses were mixed concerning appropriate populations and diagnostic capabilities of NIPT, but MFMs generally agree NIPT should be confirmed with invasive testing and will replace conventional screening procedures. CONCLUSION: Assessment indicates NIPT is being adopted by MFMs, largely in accord with recently published American College of Obstetricians and Gynecologists and the Society for MFM guidelines. Cost and test performance remain factors for not adopting NIPT. Further research on clinical management based on NIPT results and patient understanding of NIPT results is suggested.

Sleep disordered breathing in a high-risk cohort prevalence and severity across pregnancy.

OBJECTIVE: The objective of this study was to determine the prevalence and incidence of sleep disordered breathing (SDB) in pregnancy among high-risk women. STUDY DESIGN: This was a prospective, observational study. We recruited women with a body mass index (BMI) ≥ 30 kg/m(2), chronic hypertension, pregestational diabetes, history of preeclampsia, and/or a twin gestation. Objective assessment of SDB was completed between 6 and 20 weeks and again in the third trimester. SDB was defined as an apnea-hypopnea index (AHI) ≥5, and further grouped into severity categories: mild (5-14.9), moderate (15-29.9) and severe (≥30). Subjects who had a normal AHI at the baseline (AHI < 5), but an abnormal study in the third trimester (AHI ≥5) were classified as having "new-onset" SDB. RESULTS: A total of 128 women were recruited. In early pregnancy 21, 6 and 3% had mild, moderate, or severe SDB, respectively. These frequencies increased to 35, 7, and 5% in the third trimester (p < 0.001). About 27% (n = 34) experienced a worsening of SDB during pregnancy; 26 were cases of new-onset SDB, while the other 8 had SDB in early pregnancy that worsened in severity. The incidence of new-onset SDB was 20%. The majority of these new-onset cases were mild. CONCLUSIONS: SDB in early pregnancy is common in high-risk women and new-onset SDB occurs in 20% of these women.

Leveraging 3D Echocardiograms to Evaluate AI Model Performance in Predicting Cardiac Function on Out-of-Distribution Data.

Advancements in medical imaging and artificial intelligence (AI) have revolutionized the field of cardiac diagnostics, providing accurate and efficient tools for assessing cardiac function. AI diagnostics claims to improve upon the human-to-human variation that is known to be significant. However, when put in practice, for cardiac ultrasound, AI models are being run on images acquired by human sonographers whose quality and consistency may vary. With more variation than other medical imaging modalities, variation in image acquisition may lead to out-of-distribution (OOD) data and unpredictable performance of the AI tools. Recent advances in ultrasound technology has allowed the acquisition of both 3D as well as 2D data, however 3D has more limited temporal and spatial resolution and is still not routinely acquired. Because the training datasets used when developing AI algorithms are mostly developed using 2D images, it is difficult to determine the impact of human variation on the performance of AI tools in the real world. The objective of this project is to leverage 3D echos to simulate realistic human variation of image acquisition and better understand the OOD performance of a previously validated AI model. In doing so, we develop tools for interpreting 3D echo data and quantifiably recreating common variation in image acquisition between sonographers. We also developed a technique for finding good standard 2D views in 3D echo volumes. We found the performance of the AI model we evaluated to be as expected when the view is good, but variations in acquisition position degraded AI model performance. Performance on far from ideal views was poor, but still better than random, suggesting that there is some information being used that permeates the whole volume, not just a quality view. Additionally, we found that variations in foreshortening didn't result in the same errors that a human would make.