Machine learning algorithms enhance decision-making efficiency by leveraging available data. However, as data evolves over time, it becomes crucial to adapt machine learning (ML) systems incrementally to accommodate new data patterns. This adaptation is achieved through online learning or continuous ML technologies. Although deep learning technologies have demonstrated outstanding performance on predefined datasets, their application to online, streaming, and continuous learning scenarios has been limited. DeepRiver is a Python package for deep learning on data streams. Built on top of River (Montiel et al., 2021) and PyTorch (Paszke et al., 2017), it offers a unified API for both supervised and unsupervised learning. Additionally, it provides a suite of tools for preprocessing data streams and evaluating deep learning models.

The Nonlinear Grey Bernoulli Model NGBM(1, 1) is a recently developed grey model which has various applications in different fields, mainly due to its accuracy in handling small time-series datasets with nonlinear variations. In this paper, to fully improve the accuracy of this model, a novel model is proposed, namely Rolling Optimized Nonlinear Grey Bernoulli Model RONGBM(1, 1). This model combines the rolling mechanism with the simultaneous optimization of all model parameters (exponential, background value and initial condition). The accuracy of this new model has significantly been proven through forecasting Vietnam’s GDP from 2013 to 2018, before it is applied to predict the total COVID-19 infected cases globally by day.

BackgroundCryptococcus gattii is a primary fungal pathogen capable of causing severe central nervous system infections in apparently immunocompetent hosts. C. gattii meningitis in non-human immunodeficiency virus hosts often presents diagnostic dilemmas, higher rates of neurological complications, and unpredictable therapeutic outcomes. Data regarding clinical trajectories and management outcomes in non-immunocompromised patients remain limited in Asia.Cases presentationsWe describe a case series of eight immunocompetent middle-aged patients diagnosed with culture-confirmed C.gattii meningitis. All patients presented with headaches and low-grade fevers, prompting early lumbar puncture upon admission. Antifungal therapy was promptly initiated following positive cerebrospinal fluid India ink examinations. Despite aggressive induction treatment consisting of amphotericin B combined with either fluconazole or voriconazole, alongside therapeutic daily lumbar punctures for intracranial pressure control, clinical responses varied markedly. Six patients achieved clinical stabilization; however, two experienced progressive deterioration of consciousness, ultimately culminating in irreversible coma.ConclusionC.gattii meningitis poses a substantial clinical challenge in immunocompetent individuals and may carry poor outcomes despite prompt diagnosis and guideline-directed antifungal and decompression therapy. This case series underscores the pressing need for larger prospective studies to identify early prognostic markers, evaluate host immune-inflammatory interactions, and standardize induction and salvage antifungal regimens for this population.

Summary: Introduction: Measles outbreaks increased worldwide during the period of 2017-2019. Similarly, Vietnam experienced one of the largest measles outbreaks in recent decades, with various paediatric patients presenting severe complications. In this study, we aim to identify factors associated with death and severity among children with measles admitted to Vietnam National Children’s Hospital (VNCH) in Hanoi, Vietnam between 2017 and 2019. Method: This single-center retrospective cohort study included 2, 072 patients with measles admitted to VNCH from 1/1/2017 to 31/12/2019. Data on epidemiological, clinical characteristics, vaccine status, and outcomes were collected and summarised. We conducted both univariable and multivariable logistic regression analyses to examine the correlations between various characteristics of hospitalized children and mortality. Findings: In total, there were 2, 072 patients, including 1, 297 (62.6%) males and 775 (37.4%) females. The median age was 9 months (interquartile range 7 − 17). 87.3% of cases had not received any measles-containing vaccine (MCV). 30 (1.4%) patients died, with 40% aged less than 9 months. Only 3 among 30 (10%) who died had received at least 1 dose of MCV. Bronchopneumonia was the most common complication, occurring in 1, 413 (68.2%) patients. The following characteristics were significantly associated with mortality in the multivariable analysis: age under 9 months and age from 9 months to 5 years, residing 20 to 200 kilometres from VNCH, and having co-infection with adenovirus or other hospital acquired infections. Age group was also significantly associated with severity in the multivariable analysis. Interpretation: Vietnam continues to face the threat of future measles epidemics, given the burden of hospitalization and the high rate of complications observed in hospitalized patients. This highlights the critical need to maintain high measles vaccine coverage, particularly by targeting the unvaccinated population. To prevent future outbreaks and lower measles incidence, routine immunization needs to be strengthened, and earlier scheduling of MCV1 needs to be further evaluated. The comprehensive analysis of the 2017-19 measles outbreak presented in this study will contribute to informed decision-making regarding appropriate measures to counteract future resurgences of measles in Vietnam. Funding: No specific grant from funding agencies in the public, commercial or not-for-profit sectors supported the submission and publication of this manuscript.