Early Pregnancy

EARLY-PREG is an open-cohort clinical study with a preconception, longitudinal, bidirectional and counterfactual design. The aim of this cohort is to investigate the proteomic signatures of maternal-embryonic communication by interrogating a growing biorepository of maternal fluids and tissues collected during the first two weeks after fertilisation. Participants in the EARLY-PREG cohort consist of healthy couples seeking pregnancy, as well as women who are not seeking to conceive. The three main outcomes in the cohort are defined according to menstrual cycles in which conception is achieved and those in which conception is not achieved. Their clinical definitions are as follows: * Pregnancy with a full-term live birth refers to the cycle in which the ovum is fertilised, leading to pregnancy, with beta-hCG levels above the clinical threshold for a positive pregnancy test. * Early pregnancy loss refers to a miscarriage up to 12 6/7 weeks. * Non-pregnancy refers to a menstrual cycle in which conception does not occur, confirmed by a clinically negative beta-hCG test. When referring to the same individual, this is, by definition, considered the counterfactual to the corresponding conception cycle.

This study seeks to determine pregnant patients in the Philadelphia area can be recruited to a conversational AI texting platform. The trial will be considered feasible if recruitment goals are met in proportion to delivery volume at the hospital.

This is a multicentre, parallel-group, open-label, pragmatic, randomised-control trial of early lifestyle intervention versus routine prenatal care by random allocation (1:1) in women with early abnormal glucose metabolism (EAGM) to compare the incidence of large-gestational age and preterm birth between two groups. The investigators aim to assess the effectiveness of early lifestyle interventions and to provide evidence for the optimal standard management for Chinese women with EAGM.

This research integrates artificial intelligence to enhance early pregnancy ultrasonography quality control, focusing on specific fetal sections. In collaboration with prominent medical institutions, the investigators have amassed extensive fetal ultrasound data. The investigators aim to develop a deep learning model that can accurately identify essential anatomical areas in ultrasound images and evaluate their quality. This tool is expected to significantly decrease misdiagnoses of conditions like Down Syndrome and neural system deformities by ensuring real-time image quality assessment.