Impact of the COVID-19 pandemic on congenital diaphragmatic hernia patients: a single-center retrospective study.

PURPOSE: To investigate the impact of COVID-19 on the treatment of children with congenital diaphragmatic hernia (CDH). METHODS: We retrospectively collected and compared the data of patients with CDH admitted between January 1, 2020 and December 31, 2021(study group) with the CDH patients admitted before the pandemic between January 1, 2018 and December 31, 2019 (control group). RESULTS: During the pandemic, 41 patients with CDH diagnosed prenatally were transferred to our hospital, and 40 underwent surgical repair. The number of patients treated in our hospital increased by 24.2% compared with the 33 patients before the pandemic. During the pandemic, the overall survival rate, postoperative survival rate and recurrence rate were 85.4%, 87.5% and 7.3%, respectively, and there were no significant differences compared with the control group (75.8%, 83.3% and 9.1%, respectively). The average length of hospital stay in patients admitted during the pandemic was longer than that in the control group (31 days vs. 16 days, P < 0.001), and the incidence of nosocomial infection was higher than that in the control group (19.5% vs. 3%, P = 0.037). CONCLUSIONS: CDH patients confirmed to be SARS-CoV-2 infection-free can receive routine treatment. Our data indicate that the implementation of protective measures during the COVID-19 pandemic, along with appropriate screening and case evaluation, do not have a negative impact on the prognosis of children.

A generalized AI system for human embryo selection covering the entire IVF cycle via multi-modal contrastive learning.

In vitro fertilization (IVF) has revolutionized infertility treatment, benefiting millions of couples worldwide. However, current clinical practices for embryo selection rely heavily on visual inspection of morphology, which is highly variable and experience dependent. Here, we propose a comprehensive artificial intelligence (AI) system that can interpret embryo-developmental knowledge encoded in vast unlabeled multi-modal datasets and provide personalized embryo selection. This AI platform consists of a transformer-based network backbone named IVFormer and a self-supervised learning framework, VTCLR (visual-temporal contrastive learning of representations), for training multi-modal embryo representations pre-trained on large and unlabeled data. When evaluated on clinical scenarios covering the entire IVF cycle, our pre-trained AI model demonstrates accurate and reliable performance on euploidy ranking and live-birth occurrence prediction. For AI vs. physician for euploidy ranking, our model achieved superior performance across all score categories. The results demonstrate the potential of the AI system as a non-invasive, efficient, and cost-effective tool to improve embryo selection and IVF outcomes.

Recommendations for perinatal and neonatal surgical management during the COVID-19 pandemic.

Coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 has spread rapidly around the world and is a significant threat to global health. Patients in the Neonatal Surgery Department have rapidly progressing diseases and immature immunity, which makes them vulnerable to pulmonary infection and a relatively higher mortality. This means that these patients require multidisciplinary treatment including early diagnosis, timely transport, emergency surgery and intensive critical care. The COVID-19 pandemic poses a threat to carrying out these treatments. To provide support for the health protection requirements of the medical services in the Neonatal Surgery Department, we developed recommendations focusing on patient transport, surgery selection and protection requirements with the aim of improving treatment strategies for patients and preventing infection in medical staff during the current COVID-19 pandemic.