Clinical obstetrics and gynecology最新文献

Artificial intelligence (AI) is rapidly reshaping gynecologic oncology across the continuum of care. This clinician-focused review synthesizes current evidence for AI-enabled prevention and screening (HPV-informed risk models, AI-assisted colposcopy), early detection and diagnosis (radiomics, liquid biopsy, and digital pathology), prognosis and risk prediction (multimodal models integrating clinical, imaging, histology, and genomics), and treatment guidance (surgical planning and response-predictive therapeutics). Across domains, deep learning and emerging multimodal models consistently match or surpass conventional approaches, offering gains in accuracy, speed, and reproducibility while enabling biologically informed decision support. We outline practical pathways for clinical integration, human-in-the-loop workflows, explainable outputs, and ethical and regulatory guardrails. Priority future directions include rigorous prospective trials, real-world performance tracking, and equity-centered deployment to ensure benefits generalize across diverse populations. Taken together, AI has the potential to enhance precision, consistency, and access in gynecologic cancer care, not by replacing clinicians, but by augmenting expertise at scale.

Artificial intelligence has emerged as a promising tool in fetal medicine, with applications in prenatal imaging, anomaly detection, and biometric analysis. Peer-reviewed studies have reported high accuracy for AI models in identifying congenital heart defects, segmenting brain structures, and predicting fetal growth patterns. Despite strong retrospective performance, most tools remain investigational due to limited external validation, lack of explainability, and poor integration with clinical workflows. This review synthesizes current evidence on AI applications in fetal diagnostics, highlights both capabilities and limitations, and outlines future directions needed for safe and effective clinical translation.

Artificial intelligence (AI) offers solutions to overcome limitations of fetal MRI, including motion, low signal-to-noise ratio, and slice misregistration. This review summarizes current AI applications in fetal MRI, focusing on image enhancement, automated segmentation, quantitative analysis, and emerging multimodal approaches. AI improves reconstruction, denoising, motion correction, and volumetric assessment, and supports tasks such as gestational-age estimation and anomaly detection. However, most studies rely on small, single-center data sets with limited external validation. Robust multicenter data, standardized protocols, and transparent evaluation frameworks are required before AI can be reliably integrated into routine prenatal imaging.

Artificial intelligence (AI) is increasingly used in reproductive endocrinology and infertility (REI), influencing nearly all aspects of assisted reproduction. Reported applications include ovarian stimulation, gamete and embryo assessment, endometrial evaluation, and prediction of IVF outcomes. These tools may reduce subjectivity, standardize grading, and provide individualized prognostic information. Predictive models for fertilization, implantation, miscarriage risk, and live birth have been developed, along with decision-support tools for embryo transfer and treatment continuation. However, most studies are retrospective and limited to intermediate outcomes. Concerns about generalizability, transparency, accountability, and equity remain. AI represents both hope and hype, pending rigorous, outcome-based validation.

The rapid evolution of generative artificial intelligence (AI) is poised to transform medicine and medical education. Large language models (LLMs) have begun to demonstrate capabilities in reasoning, diagnosis, documentation, and patient communication that can rival or exceed those of clinicians. In medical education, AI is reshaping how students learn and how faculty teach-offering individualized, context-sensitive guidance at scale. This article outlines the current state of AI integration in health care, examines how systems can responsibly implement it to enhance patient care and education, and raises critical questions about ethics and safety as we harness its transformative potential.

This study aimed to systematically evaluate the impact of hybrid antenatal care models (structured integration of in-person and remote visits) on adverse perinatal and maternal outcomes compared with traditional care. MEDLINE, CINAHL, Scopus, ClinicalTrials.gov, and the Cochrane Library were searched from inception to November 8, 2025. Studies comparing hybrid antenatal care with standard care were included. Primary outcome was stillbirth; secondary outcomes included small-for-gestational-age (SGA) at birth or fetal growth restriction (FGR), preterm birth (PTB) <37 weeks, cesarean delivery, preeclampsia with severe features, and neonatal intensive care unit (NICU) admission. Pooled odds ratios (ORs) were calculated using random-effects meta-analysis models with 95% CI and quantification of I2 statistics. Eight studies, encompassing 159.303 pregnancies, met the inclusion criteria. Of these, 60.987 (38.3%) received hybrid antenatal care, and 98.316 (61.7%) received traditional care. The incidence of stillbirth did not differ significantly between models (OR: 0.95; 95% CI: 0.76-1.19). Similarly, no differences were observed in SGA/FGR (OR: 0.99; 95% CI: 0.88-1.11), NICU admission (OR: 0.95; 95% CI: 0.86-1.05), PTB <37 weeks (OR: 1.01; 95% CI: 0.95-1.07), and preeclampsia with severe features (OR: 1.08; 95% CI: 0.94-1.23). A significant increase in cesarean delivery was observed among patients receiving hybrid care (OR: 1.08; 95% CI: 1.02-1.13). The latter achieves maternal and perinatal outcomes comparable to standard care models. Responsible implementation grounded in ethics, equity, and standardization might in the future reshape traditional maternity care.

Artificial intelligence is transforming obstetric practice through applications in diagnostic imaging, risk prediction, and clinical decision-making. Deep learning algorithms have achieved diagnostic accuracy comparable to that of experienced clinicians. However, gaps persist between algorithmic capability and clinical implementation. Critical challenges include limited external validation and algorithmic bias. This review examines current AI applications in obstetrics across multiple clinical domains: automated fetal biometry, structural anomaly detection, prediction of pregnancy complications, and intrapartum fetal surveillance. It highlights persistent technical, ethical, and implementation barriers. Key recommendations include multicenter validation across diverse populations, explainable AI approaches, and creating strong regulatory frameworks.

Congenital heart disease (CHD) is the most common major birth anomaly and a key cause of neonatal mortality. While early diagnosis improves outcomes, prenatal detection remains inconsistent. Artificial intelligence (AI) offers scalable solutions through automation of view acquisition, image interpretation, and functional assessment. AI has shown expert-level performance in view classification, CHD detection, and cardiac biometry. Tools like Fetal Intelligent Navigation Echocardiography, though not AI, enhance consistency and efficiency. Emerging AI modalities, including generative AI, self-supervised learning, and NLP-driven report automation, expand possibilities. Ongoing research is essential to ensure safe, equitable integration of AI into clinical workflows for improved CHD diagnosis worldwide.