Search

The advancement of artificial intelligence (AI) demands significant data and computational resources that have an adverse impact on the environment. To address this issue, a novel computing architecture that is both energy efficient and eco-friendly is urgently required. Edge computing has emerged as an increasingly popular solution to this problem. In this study, we explore the development history of edge computing and AI and analyze the potential of model quantization to link AI and edge computing. Our comparative analysis demonstrates that the quantization approach can effectively reduce the model's size and accelerate model inference while maintaining its functionality, thereby enabling its deployment on edge devices. This research serves as a valuable guide and reference for future advancements in edge AI. [ABSTRACT FROM AUTHOR]

Background: Endoscopic ultrasound-guided pancreatic duct (PD) drainage (EUS-PDD) is being increasingly performed as an alternative method to surgical drainage to achieve PD decompression after failed endoscopic retrograde pancreatography (ERP). However, no directly study has compared EUS-PDD with surgical PD drainage after failed ERP in patients with chronic pancreatitis. Methods: Consecutive patients who underwent EUS-PDD or longitudinal pancreaticojejunostomy after failed ERP were retrospectively identified from our endoscopy and medical information systems. The primary end point was the Izbicki pain score. The secondary end points were pain relief at the end of follow-up, procedure outcomes, adverse events, readmission, and reintervention. Results: A total of 21 patients (11 EUS-PDD, 10 surgical drainages) were analyzed. There were no significant differences in mean Izbicki pain score (EUS-PDD, 13.6 ± 10.1 vs. surgical drainage 10.7 ± 7.9, p = 0.483) or complete/partial pain relief (60%/30% vs. 70%/30%, p = 0.752) at the end of follow-up of the two groups. The rates of overall adverse events (27.3% vs. 30.0%, p = 0.893) and readmission (63.6% vs. 40.0%, p = 0.290) were similar in the two treatment groups, while patients in EUS-PDD group required more reinterventions (45.5% vs. 0%, p = 0.039) compared with patients in the surgery group. Conclusion: EUS-PDD showed comparable pain relief and safety to surgical PD drainage after failed ERP, with a higher rate of reintervention. The selection of EUS-PDD or surgical drainage may be appropriate based on an individualized strategy. [ABSTRACT FROM AUTHOR]

Objective This study investigated the clinical outcome of monochorionic diamniotic (MCDA) twins with selective intrauterine growth restriction (sIUGR). Study Design International Peace Maternal and Child Health Hospital of Shanghai ultrasound database was investigated to identify all MCDA delivered from January 2013 to December 2017. After identifying 43 pairs of MCDA twins with sIUGR and 282 pairs of normal MCDA twins, we compared clinical outcomes between the two groups. Results Compared with normal twins, sIUGR fetuses had significantly shorter gestational age at delivery, smaller average birth weight of both twins, more significant intertwin difference in birth weight, lower Apgar scores, and higher intrauterine fetal demise (IUFD) rate, and smaller placental weight. The rate of abnormal umbilical cord insertions and abnormal blood flow in the ductus venosus (DV) and middle cerebral artery (MCA) is significantly higher in the sIUGR group. In addition, the subtype analysis of sIUGR groups indicated the poorest outcomes in type II with no significant difference between type I and III. Conclusion MCDA twins with sIUGR generally exhibited limited clinical outcomes than normal MCDA twins. These limitations are mainly associated with abnormal umbilical cord insertions and blood flow in the DV and MCA. Clinical outcomes differed among the three types of sIUGR, with type II having the worst prognosis and the highest IUFD rate. Key points sIUGR generally exhibited limited clinical outcomes than normal MCDA twins. These limitations are mainly associated with blood flow of the DV and MCA. sIUGR with type II has the worst prognosis and the highest IUFD rate. [ABSTRACT FROM AUTHOR]

Background: Plasmapheresis is widely used for severe hypertriglyceridemia-associated acute pancreatitis (HTG-AP) to remove excessive triglycerides from plasma. This study aimed to evaluate whether plasmapheresis could improve the duration of organ failure in HTG-AP patients. Methods: We analyzed a cohort of patients from a multicenter, prospective, long-running registry (the PERFORM) collecting HTG-AP patients admitted to the study sites within 72 h from the onset of symptoms. This study was based on data collected from November 2020 to March 2023. Patients who had organ failure at enrollment were involved in the analyses. The primary outcome was time to organ failure resolution within 14 days. Multivariable Cox regression model was used to evaluate the association between plasmapheresis and time to organ failure resolution. Directed acyclic graph (DAG) was used to identify potential confounders. Results: A total of 122 HTG-AP patients were included (median [IQR] sequential organ failure assessment (SOFA) score at enrollment, 3.00 [2.00–4.00]). Among the study patients, 46 underwent plasmapheresis, and 76 received medical treatment. The DAG revealed that baseline serum triglyceride, APACHE II score, respiratory failure, cardiovascular failure, and renal failure were potential confounders. After adjusting for the selected confounders, there was no significant difference in time to organ failure resolution between patients undergoing plasmapheresis and those receiving exclusive medical treatment (HR = 1.07; 95%CI 0.68–1.68; P = 0.777). Moreover, the use of plasmapheresis was associated with higher ICU requirements (97.8% [45/46] vs. 65.8% [50/76]; OR, 19.33; 95%CI 2.20 to 169.81; P = 0.008). Conclusions: In HTG-AP patients with early organ failure, plasmapheresis was not associated with accelerated organ failure resolution compared to medical treatment but may be associated with more ICU admissions. Trial registration: The PERFORM study was registered in the Chinese Clinical Trial Registry (ChiCTR2000039541). Registered 30 October 2020. [ABSTRACT FROM AUTHOR]