Advances in artificial intelligence (AI) have triggered interest in using intelligent systems to improve prenatal detection of fetal congenital heart defects (CHDs). Our aim is to systematically examine the current literature on diagnostic performance of AI-enabled prenatal cardiac ultrasound. This systematic review and meta-analysis was registered with PROSPERO (CRD42024549601). Embase, Medline, Cochrane Central Database of Controlled Trials, and CINAHL were searched from inception until February 2025. Studies evaluating AI performance in prenatal detection of fetal CHDs were eligible for inclusion, and studies focusing on the application of AI before 16 weeks of gestation, or using three- or four-dimensional ultrasound, were excluded. Pooled sensitivity and specificity were obtained using random-effect method, and pooled proportions using the Freeman-Tukey arcsine square root transformation. Heterogeneity was assessed with I² statistics. Risk of bias and adherence to reporting standards were assessed using QUADAS-2 and TRIPOD+AI, respectively. Risk of publication bias was assessed with Deek's test and certainty of evidence for outcomes with GRADE approach. Fifteen studies were included, of which fourteen developed and evaluated a model and one externally evaluated a previously trained model. Images and videos obtained during cardiac screening or fetal echocardiography of 30.121 fetuses were used for training, validation and testing. For the binary task of classifying heart as normal or abnormal, AI models achieved a pooled sensitivity of 0.89 (95% CI 0.83–0.93, I² = 77.92%) and specificity of 0.91 (95% CI 0.84–0.95, I² = 77.92%). The subgroup analysis showed that models tested on various CHDs exhibited lower sensitivity compared to those tested for a specific cardiac abnormality (0.85; 95% CI 0.75–0.91 vs 0.92; 95% CI 0.87–0.96), while specificity remained comparable (0.90; 95% CI 0.79–0.96 vs 0.91; 95% CI 0.81–0.97). Overall, AI models performed better than operators with lower expertise and were nearly comparable to experts; however, the human comparator group (median six clinicians, IQR 3–10) was usually small and non-blinded. Relevant sources of heterogeneity were the types of cardiac views collected, the prevalence of CHDs across different datasets, and the types of CHDs examined. The risk of bias was moderate-high and adherence to reporting standards low (>70% in 18/51 TRIPOD+AI items). The risk of publication bias was not statistically significant (Deek's test p = 0.474). These findings suggest that AI models perform better than clinicians with lower expertise, but this must be interpreted with caution due to the high risk of bias and sources of heterogeneity. This study was partly supported by the InnoHK-funded Hong Kong Centre for Cerebro-cardiovascular Health Engineering (COCHE) Project 2.1 (Cardiovascular risks in early life and fetal echocardiography). ATP and JAN are supported by the 10.13039/501100000272 National Institute for Health and Care Research (NIHR) 10.13039/501100013373 Oxford Biomedical Research Centre (BRC).

Introduction Congenital heart defect (CHD) is a significant, rapidly emerging global problem in child health and a leading cause of neonatal and childhood death. Prenatal detection of CHDs with the help of ultrasound allows better perinatal management of such pregnancies, leading to reduced neonatal mortality, morbidity and developmental complications. However, there is a wide variation in reported fetal heart problem detection rates from 34% to 85%, with some low- and middle-income countries detecting as low as 9.3% of cases before birth. Research has shown that deep learning-based or more general artificial intelligence (AI) models can support the detection of fetal CHDs more rapidly than humans performing ultrasound scan. Progress in this AI-based research depends on the availability of large, well-curated and diverse data of ultrasound images and videos of normal and abnormal fetal hearts. Currently, CHD detection based on AI models is not accurate enough for practical clinical use, in part due to the lack of ultrasound data available for machine learning as CHDs are rare and heterogeneous, the retrospective nature of published studies, the lack of multicentre and multidisciplinary collaboration, and utilisation of mostly standard planes still images of the fetal heart for AI models. Our aim is to develop AI models that could support clinicians in detecting fetal CHDs in real time, particularly in nonspecialist or low-resource settings where fetal echocardiography expertise is not readily available. Methods and analysis We have designed the Clinical Artificial Intelligence Fetal Echocardiography (CAIFE) study as an international multicentre multidisciplinary collaboration led by a clinical and an engineering team at the University of Oxford. This study involves five multicountry hospital sites for data collection (Oxford, UK (n=1), London, UK (n=3) and Southport, Australia (n=1)). We plan to curate 14 000 retrospective ultrasound scans of fetuses with normal hearts (n=13 000) and fetuses with CHDs (n=1000), as well as 2400 prospective ultrasound cardiac scans, including the proposed research-specific CAIFE 10 s video sweeps, from fetuses with normal hearts (n=2000) and fetuses diagnosed with major CHDs (n=400). This gives a total of 16 400 retrospective and prospective ultrasound scans from the participating hospital sites. We will build, train and validate computational models capable of differentiating between normal fetal hearts and those diagnosed with CHDs and recognise specific types of CHDs. Data will be analysed using statistical metrics, namely, sensitivity, specificity and accuracy, which include calculating positive and negative predictive values for each outcome, compared with manual assessment. Ethics and dissemination We will disseminate the findings through regional, national and international conferences and through peer-reviewed journals. The study was approved by the Health Research Authority, Care Research Wales and the Research Ethics Committee (Ref: 23/EM/0023; IRAS Project ID: 317510) on 8 March 2023. All collaborating hospitals have obtained the local trust research and development approvals.

Echogenic fetal bowel (EB) is a prenatal ultrasound finding (0.2%-1.4% of all pregnancies) defined as bowel of similar or greater echogenicity than surrounding bone. In fact, the ultrasound assessment is strongly subjective with inter-observer variability. The pathophysiology depends on the underlying condition, apparently related with meconium stasis and hypercellularity. It is often an isolated finding, with possible association with other structural anomalies. About the origin, it was observed in fetuses with cystic fibrosis, congenital infections, thalassemia, intraamniotic bleeding, fetal growth restriction. Fetuses with EB are at increased risk of adverse perinatal outcome, such as intrauterine growth restriction, placental dysfunction and perinatal death, highlighting the need for a thorough antenatal management and post-natal follow-up. It seems to be associated with a plenty of conditions, such as a poor fetal outcome, fetal growth restriction and placental dysfunction. Therefore management requires a multidisciplinary approach with different specialties' involvement and the prognosis is influenced by the underlying pathophysiology. In this complex scenario, the present review aims to define the clinical pathway which should be offered to pregnant women in case of finding of fetal EB ultrasound marker, to rule out any suspected pathological cause.

Background: Treatment of breast cancer (BC) includes locoregional and systemic therapies depending on tumor and patient’s characteristics. Inositol hexaphosphate (IP6) is known as a strong antioxidant agent, able to improve local (i.e., breast region) side effects, functional status and quality-of-life. We investigated some potential beneficial effects, including hematological and local, of the combined therapy with oral myo-inositol administration and topical IP6 application in patients undergoing surgery for BC and eligible to adjuvant chemotherapy. Methods: We considered BC patients randomly assigned to the Inositol Group (oral myo-inositol + IP6 local application for the entire neoadjuvant treatment period) and to the Control Group (standard of care). The EORTC QLQ-BR23 and QLQ-C30 questionnaires were administered to both groups and blood parameters were assessed as per clinical routine practice at baseline (before starting adjuvant chemotherapy), T1 (after the first two doses of epirubicin-cyclophosphamide regimen), T2 (at the end of epirubicin-cyclophosphamide regimen), T3 (after the first six doses of paclitaxel regimen), and T4 (at the end of the paclitaxel treatment). Results: A total of 36 BC patients were considered, 18 in the Inositol Group and 18 in the Control Group. The Inositol Group showed a lower decrease in red blood cells, hemoglobin levels and white blood cells with respect to controls (p ≤ 0.02), as well as amelioration in scores related to breast and arm local symptoms (p ≤ 0.02), body image (p = 0.04) and quality-of-life related symptoms (p ≤ 0.04). Conclusions: In our cohort of BC patients, a combined treatment with oral myo-inositol + IP6 local application was able to improve local symptoms and quality-of-life related symptoms which represent clinically relevant aspects associated with patient’s prognosis.

Background: Congenital heart diseases (CHDs) are often associated with significant neurocognitive impairment and neurological delay. This study aims to elucidate the correlation between type of CHD and Doppler velocimetry and to investigate the possible presence of fetal brain abnormalities identified by magnetic resonance imaging (MRI). Methods: From July 2010 to July 2020, we carried out a cross-sectional study of 63 singleton pregnancies with a diagnosis of different types of complex CHD: LSOL (left-sided obstructive lesions; RSOL (right-sided obstructive lesions) and MTC (mixed type of CHD). All patients underwent fetal echocardiography, ultrasound evaluation, a magnetic resonance of the fetal brain, and genetic counseling. Results: The analysis of 63 fetuses shows statistically significant results in Doppler velocimetry among the different CHD groups. The RSOL group leads to higher umbilical artery (UA-PI) pressure indexes values, whereas the LSOL group correlates with significantly lower values of the middle cerebral artery (MCA-PI) compared to the other subgroups (p = 0.036), whereas the RSOL group shows a tendency to higher pulsatility indexes in the umbilical artery (UA-PI). A significant correlation has been found between a reduced head circumference (HC) and the presence of brain injury at MRI (p = 0.003). Conclusions: Congenital left- and right-sided cardiac obstructive lesions are responsible for fetal hemodynamic changes and brain growth impairment. The correct evaluation of the central nervous system (CNS) in fetuses affected by CHD could be essential as prenatal screening and the prediction of postnatal abnormalities.

Objectives: To assess the efficacy of remote blood pressure monitoring to prevent readmission due to complications of hypertensive disorders of pregnancy. Methods: The search was conducted using MEDLINE, EMBASE, Web-of-Sciences, Scopus, ClinicalTrial.gov, OVID and Cochrane-Library as electronic databases from the inception of each database to November 2023. Selection criteria included randomized controlled trials of postpartum individuals randomized to remote blood pressure monitoring or telehealth strategies vs. routine-care. The primary outcome was postpartum readmission, defined as postpartum hospital admission after discharge. Secondary maternal outcomes included stroke, eclampsia, ICU-admission, maternal death, emergency department visit, ascertainment of a blood pressure measurement within 7–10 days after delivery, attendance of the 4–6-week postpartum visit. The summary measures were reported as relative risk (RR) or as mean difference (MD) with 95 % confidence intervals (CI). Results: Four RCTs including 714 individuals randomized to either telematic reporting of blood pressure measurements (n=356, 49.8 %) or standard postpartum care (n=358, 50.1 %). There were no significant differences in the rate of hospital readmission due to hypertensive related causes (5.3 % vs. 11.8 %). However, emergency department visit rate differed significantly among the two groups (9.0 % vs. 4.4 %). With regards to postpartum follow up, blood pressure assessment at 10 days postpartum and 4–6-week postpartum visit attendance rate were similar. No included RCT provided data on maternal secondary outcome like pulmonary edema, stroke, maternal death, and ICU admission. Conclusions: Remote blood pressure monitoring is not superior to standard care to prevent hypertensive related readmission and increases emergency department visits.