OBJECTIVES: Light sedation is recommended over deep sedation for invasive mechanical ventilation to improve clinical outcome but may increase the risk of agitation. This study aimed to develop and prospectively validate an ensemble machine learning model for the prediction of agitation on a daily basis. DESIGN: Variables collected in the early morning were used to develop an ensemble model by aggregating four machine learning algorithms including support vector machines, C5.0, adaptive boosting with classification trees, and extreme gradient boosting with classification trees, to predict the occurrence of agitation in the subsequent 24 hours. SETTING: The training dataset was prospectively collected in 95 ICUs from 80 Chinese hospitals on May 11, 2016, and the validation dataset was collected in 20 out of these 95 ICUs on December 16, 2019. PATIENTS: Invasive mechanical ventilation patients who were maintained under light sedation for 24 hours prior to the study day and who were to be maintained at the same sedation level for the next 24 hours. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: A total of 578 invasive mechanical ventilation patients from 95 ICUs in 80 Chinese hospitals, including 459 in the training dataset and 119 in the validation dataset, were enrolled. Agitation was observed in 36% (270/578) of the invasive mechanical ventilation patients. The stepwise regression model showed that higher body temperature (odds ratio for 1°C increase: 5.29; 95% CI, 3.70–7.84; p < 0.001), greater minute ventilation (odds ratio for 1 L/min increase: 1.15; 95% CI, 1.02–1.30; p = 0.019), higher Richmond Agitation-Sedation Scale (odds ratio for 1-point increase: 2.43; 95% CI, 1.92–3.16; p < 0.001), and days on invasive mechanical ventilation (odds ratio for 1-d increase: 0.95; 95% CI, 0.93–0.98; p = 0.001) were independently associated with agitation in the subsequent 24 hours. In the validation dataset, the ensemble model showed good discrimination (area under the receiver operating characteristic curve, 0.918; 95% CI, 0.866–0.969) and calibration (Hosmer-Lemeshow test p = 0.459) in predicting the occurrence of agitation within 24 hours. CONCLUSIONS: This study developed an ensemble model for the prediction of agitation in invasive mechanical ventilation patients under light sedation. The model showed good calibration and discrimination in an independent dataset.
Background: The role of sodium bicarbonate therapy (SBT) remains controversial. This study aimed to investigate whether hemodynamic status before SBT contributed to the heterogeneous outcomes associated with SBT in acute critically ill patients.Methods: We obtained data from patients with metabolic acidosis from the Medical Information Mart for Intensive Care (MIMIC)-III database. Propensity score matching (PSM) was applied to match the SBT group with the control group. Logistic regression and Cox regression were used to analyze a composite of newly “developed or exacerbated organ dysfunction” (d/eOD) within 7 days of ICU admission and 28-day mortality associated with SBT for metabolic acidosis.Results: A total of 1,765 patients with metabolic acidosis were enrolled, and 332 pairs obtained by PSM were applied to the final analyses in the study. An increased incidence of newly d/eOD was observed in the SB group compared with the control group (54.8 vs. 44.6%, p < 0.01). Multivariable logistic regression indicated that the adjusted OR of SBT for this composite outcome was no longer significant [OR (95% CI): 1.39 (0.9, 1.85); p = 0.164]. This effect of SBT did not change with the quintiles stratified by pH. Interestingly, SBT was associated with an increased risk of the composite of newly d/eOD in the subgroup of patients with worsening hemodynamics before SBT [adjusted OR (95% CI): 3.6 (1.84, 7.22), p < 0.001]. Moreover, the risk potential for this composite of outcomes was significantly increased in patients characterized by both worsening [adjusted OR (95% CI): 2.91 (1.54, 5.47), p < 0.001] and unchanged hemodynamics [adjusted OR (95% CI): 1.94 (1.01, 3.72), p = 0.046] compared to patients with improved hemodynamics before SBT. Our study failed to demonstrate an association between SBT and 28-day mortality in acute critically ill patients with metabolic acidosis.Conclusions: Our findings did not demonstrate an association between SBT and outcomes in critically ill patients with metabolic acidosis. However, patients with either worsening or unchanged hemodynamic status in initial resuscitation had a significantly higher risk potential of newly d/eOD subsequent to SBT.
Background Considering the widespread of coronavirus disease 2019 (COVID-19) pandemic in the world, it is important to understand the spatiotemporal development of the pandemic. In this study, we aimed to visualize time-associated alterations of COVID-19 in the context of continents and countries. Methods Using COVID-19 case and death data from February to December 2020 offered by Johns Hopkins University, we generated time-associated balloon charts with multiple epidemiological indicators including crude case fatality rate (CFR), morbidity, mortality and the total number of cases, to compare the progression of the pandemic within a specific period across regions and countries, integrating seven related dimensions together. The area chart is used to supplement the display of the balloon chart in daily new COVID-19 case changes in UN geographic regions over time. Javascript and Vega-Lite were chosen for programming and mapping COVID-19 data in browsers for visualization. Results From February 1st to December 20th 2020, the COVID-19 pandemic spread across UN subregions in the chronological order. It was first reported in East Asia, and then became noticeable in Europe (South, West and North), North America, East Europe and West Asia, Central and South America, Southern Africa, Caribbean, South Asia, North Africa, Southeast Asia and Oceania, causing several waves of epidemics in different regions. Since October, the balloons of Europe, North America and West Asia have been rising rapidly, reaching a dramatically high morbidity level ranging from 200 to 500/10 000 by December, suggesting an emerging winter wave of COVID-19 which was much bigger than the previous ones. By late December 2020, some European and American countries displayed a leading mortality as high as or over 100/100 000, represented by Belgium, Czechia, Spain, France, Italy, UK, Hungary, Bulgaria, Peru, USA, Argentina, Brazil, Chile and Mexico. The mortality of Iran was the highest in Asia (over 60/100 000), and that of South Africa topped in Africa (40/100 000). In the last 15 days, the CFRs of most countries were at low levels of less than 5%, while Mexico had exceptional high CFR close to 10%. Conclusions We creatively used visualization integrating 7-dimensional epidemiologic and spatiotemporal indicators to assess the progression of COVID-19 pandemic in terms of transmissibility and severity. Such methodology allows public health workers and policy makers to understand the epidemics comparatively and flexibly.
Vertisols are clayey soils with a high potential for improving production. Therefore, understanding the impact of tillage and fertilization on soil physicochemical properties and microbial community is essential for improving the vertisols with a high montmorillonite and smectite clay content. A 3-year field experiment was conducted to compare the effects of different tillage and fertilization practices at three depths of the vertisol under the wheat–maize cropping system in the North China Plain. The experimental treatments included rotary tillage without fertilization (R-CK), rotary tillage with chemical nitrogen (N), phosphorus (P), and potassium (K) fertilization (R-NPK), R-NPK plus biochar (R-NPKB), deep tillage without fertilization (D-CK), deep tillage with chemical N, P, and K fertilization (D-NPK), and D-NPK plus biochar (D-NPKB). The results showed that D-NPKB significantly improved winter wheat and summer maize yields by 14.4 and 3.8%, respectively, compared with R-NPK. The nitrate (NO3––N) content of the deeper soil layer in D-NPKB was significantly higher than that in D-NPK. Meanwhile, biochar application increased the pH in the three layers. Compared with R-NPK, D-NPKB significantly increased the average content of available phosphorus (AP), soil organic carbon (SOC), and total nitrogen (TN) by 73.7, 18.5, and 19.0%, respectively. Meanwhile, Gaiellale, Sphingomonadaceae, and Nocardioidaceae were the predominant bacteria at the family level across all treatments, with a total relative proportion ranging from 14.1 to 23.6%. In addition, the abundance of Bacillaceae in deep tillage was 9.4% higher in the 20–30-cm soil layer than that in rotary tillage. Furthermore, the correlation analysis revealed a significant positive correlation between crop yield and chemical factors such as NO3––N and the abundances of Gaiellalea, Sphingomonadaceae, and Nocardioidaceae. The findings collectively indicated that deep tillage combined with biochar application could increase the soil nutrients and modify the bacterial structure in the deeper soil layer and therefore will be beneficial for improving the productivity of the vertisols.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.