Search

This paper develops a pedestrian potentially dangerous behaviour prediction method based on attention‐long‐short‐term memory (Attention‐LSTM) architecture to predict pedestrian trajectory and intention for the unexpected pedestrian crossing accident avoidance. To extract the road scene information for short periods of time, and improve the accuracy of subsequent intention inference and trajectory prediction, the panoramic segmentation is used to extrapolate pedestrian instances and segment areas of the environment. Next, an encoder–decoder framework based on Attention‐LSTM model is proposed to infer a pedestrian's intention to run or walk out into oncoming traffic straight and to predict the future trajectory. The proposed network involves two parts: temporal feature encoder and multi‐task decoder. The temporal feature encoder is mainly used to selectively emphasize the temporal features using attention mechanism, and then LSTM is employed for its encoding. In the multi‐task decoder, a multi‐head self‐attention mechanism and LSTM are used to forecast the pedestrians' intention and future trajectory, respectively. Extensive experiments on pedestrian intention estimation (PIE) datasets demonstrate that the authors' proposed approach surpasses prior studies in terms of prediction accuracy in trajectory and intention. This study can not only effectively avoid serious accidents caused by illegal road crossing but also achieve early warning for collision avoidance. [ABSTRACT FROM AUTHOR]

Introduction: Reducing neonatal deaths in premature infants in low- and middle-income countries is key to reducing global neonatal mortality. International neonatal networks, along with patient registries of premature infants, have contributed to improving the quality of neonatal care; however, the involvement of low-to-middle-income countries was limited. This project aims to form an international collaboration among neonatal networks in Asia (AsianNeo), including low-, middle- and high-income countries (or regions). Specifically, it aims to determine outcomes in sick newborn infants, especially very low birth weight (VLBW) infants or very preterm infants, with a view to improving the quality of care for such infants., Methods and Analysis: Currently, AsianNeo comprises nine neonatal networks from Indonesia, Japan, Malaysia, Philippines, Singapore, South Korea, Sri Lanka, Taiwan and Thailand. AsianNeo will undertake the following four studies: (1) institutional questionnaire surveys investigating neonatal intensive care unit resources and the clinical management of sick newborn infants, with a focus on VLBW infants (nine countries/regions); (2) a retrospective cohort study to describe and compare the outcomes of VLBW infants among Asian countries and regions (four countries/regions); (3) a prospective cohort study to develop the AsianNeo registry of VLBW infants (six countries/regions); and (4) implementation and evaluation of educational and quality improvement projects in AsianNeo countries and regions (nine countries/regions)., Ethics and Dissemination: The study protocol was approved by the Research Ethics Board of the National Center for Child Health and Development, Tokyo, Japan (reference number 2020-244, 2022-156). The study findings will be disseminated through educational programmes, quality improvement activities, conference presentations and medical journal publications., Competing Interests: Competing interests: None declared., (© Author(s) (or their employer(s)) 2024. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.)

Background: Though Aspirin and intravenous immunoglobulin (IVIG) remain the standard treatments for Kawasaki Disease (KD) to minimize coronary artery damage, the duration and dosage of aspirin are inconsistent across hospitals. However, the lack of multi-center randomized trials prevents definitive answers to the impact of high-dose aspirin., Methods: This clinical trial was structured as a prospective, evaluator-blinded, multi-center randomized controlled trial with two parallel arms, aiming to assess the effectiveness of IVIG as a standalone primary therapy of KD in comparison to the combination of IVIG with high-dose aspirin therapy. KD patients were enrolled between September, 2016 and August, 2019. A final cohort of 134 patients were randomly assigned to the standard and test groups with 69 and 65 patients, respectively. The Standard group received IVIG (2 g/kg) along with aspirin (80-100 mg/kg/day) until fever subsided for 48 hours. The test group received IVIG (2 g/kg) alone. Following the initial treatment, both groups received a daily aspirin dose (3-5 mg/kg) for six weeks. The primary outcome measure was the occurrence of coronary artery lesions (CAL) at the 6-8 weeks mark. The secondary outcome is IVIG resistance., Results: The overall rate of CAL in test group decreased from 10.8% at diagnosis to 1.5% and 3.1% at 6 weeks and 6 months, respectively. The CAL rate of standard group declined from 13.0% to 2.9% and 1.4%, with no statistically significant difference (P>0.1) in the frequency of CAL between the two groups. Furthermore, no statistically significant differences were found for treatment (P>0.1) and prevention (P>0.1) effect between the two groups., Conclusions: This marks the first prospective multi-center randomized controlled trial comparing the standard treatment of KD using IVIG plus high-dose aspirin against IVIG alone. Our analysis indicates that addition of high-dose aspirin during initial IVIG treatment is neither statistically significant nor clinically meaningful for CAL reduction., Registration: URL: http://www.clinicaltrials.gov ; identifier: NCT02951234., What Is New?: This study represents the first multi-center randomized controlled trial investigating the efficacy of high-dose aspirin or intravenous immunoglobulin (IVIG) during the acute stage of KD. This study assessed the impact of discontinuing high-dose aspirin (80-100 mg/kg/day) on the occurrence of CAL during the acute phase treatment of Kawasaki Disease.No significant differences were observed between high-dose aspirin plus IVIG treatment and IVIG alone treatment in terms of the frequency of abnormal coronary artery abnormalities. Additionally, our analysis revealed no statistically significant differences in either the treatment effect (the number of cases successfully treated) or prevention effect (the prevention of new cases) between these two treatments., What Are the Clinical Implications?: Comparison analysis indicated the non-inferiority between two groups with or without high-dose aspirin.Administering the standard 2 g/kg/day IVIG without high-dose aspirin (80-100 mg/kg/day) during the acute phase therapy for KD does not increase the risk of coronary artery lesions, which are a primary cause of morbidity and mortality in KD patients.Addition of high-dose aspirin during initial IVIG treatment is not statistically significant or clinically meaningful.

Objective: To compare the neurodevelopmental outcomes of preterm infants before and during the COVID-19 pandemic., Design: Premature infants born in 2018 were assigned to the pre-pandemic group, while those born in 2019 were assigned to the during-pandemic group., Setting: Nationwide cohort study., Patients: Very low birthweight premature infants registered in the Taiwan Premature Infant Follow-up Network database., Interventions: Anti-epidemic measures, including quarantine and isolation protocols, social distancing, the closure of public spaces and restrictions on travel and gatherings during COVID-19 pandemic., Main Outcome Measures: Outcomes were measured by Bayley Scales of Infant and Toddler Development Third Edition at corrected ages of 6, 12 and 24 months old. Generalised estimating equation (GEE) was applied to incorporate all measurements into a single model., Results: Among the 1939 premature infants who were enrolled, 985 developed before the pandemic, while 954 developed during the pandemic. Premature infants whose development occurred during the pandemic exhibited better cognitive composite at the corrected age of 6 months (beta=2.358; 95% CI, 1.07 to 3.65; p<0.001), and motor composite at corrected ages of 12 months (beta=1.680; 95% CI, 0.34 to 3.02; p=0.014). GEE analysis showed that infants who had grown during the pandemic achieved higher scores in cognitive composite (beta=1.416; 95% CI, 0.36 to 2.48; p=0.009)., Conclusion: Premature infants in Taiwan who developed during the pandemic showed better neurodevelopment compared with those born before the pandemic., Competing Interests: Competing interests: None declared., (© Author(s) (or their employer(s)) 2024. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.)

Background: Cryptogenic strokes related to a patent foramen ovale (PFO) in young patients have been reported. Percutaneous transcatheter occlusion is considered a safe and effective method for achieving PFO closure. Here, we present our experience of PFO closure in a series of young patients diagnosed with cryptogenic stroke., Methods: This was a retrospective study of 62 patients who were younger than 60 years of age and previously diagnosed with cryptogenic stroke. They underwent cardiac catheterization for the diagnosis of PFO and/or device closure. Bubble and echocardiography studies, the patients' characteristics, complications, and recurrence of stroke were recorded. The Risk of Paradoxical Embolism (RoPE) score index was also calculated., Results: Patients with a bubble study grade greater than grade I were likely to have PFO (odds ratio: 22.2 [95% confidence interval: 1.2-412.3]). The mean RoPE score in the PFO closure group was 7.18. Two patients (3.9%) developed atrial fibrillation during the procedure. Ischemic stroke recurred in two patients (3.3%)., Conclusions: Combining a bubble study with transcranial Doppler ultrasound or transthoracic echocardiography may increase the validity of PFO diagnosis. Because of the low recurrence rate of stroke and low complication rate, it is important to identify PFO patients with a bubble study grade greater than grade I. Closure of PFO may be a good strategy for preventing recurrent stroke among such patients.