Refine
Has Fulltext
- no (3)
Document Type
- Article (3)
Language
- English (3)
Is part of the Bibliography
- yes (3)
Keywords
- COVID-19 (1)
- Dependent light scattering (1)
- EHR (1)
- Multiple light scattering (1)
- Particle sizing (1)
- Percus-Yevick model (1)
- Photon Density Wave spectroscopy (1)
- Polymer dispersions (1)
- TRIPOD (1)
- Yukawa model (1)
- adiponectin (1)
- arabinoxylan (1)
- clinical (1)
- cohort (1)
- dietary fibre (1)
- electronic health record (1)
- hospital (1)
- informatics (1)
- leptin (1)
- machine learning (1)
- mortality (1)
- performance (1)
- prediction (1)
- resistin (1)
The consumption of arabinoxylan, a soluble fibre fraction, has been shown to improve glycemic control in type 2 diabetic subjects. Soluble dietary fibre may modulate gastrointestinal or adipose tissue hormones regulating food intake. The present study investigated the effects of arabinoxylan consumption on serum glucose, insulin, lipids, leptin, adiponectin and resistin in subjects with impaired glucose tolerance. In a randomized, single-blind, controlled, crossover intervention trial, 11 adults consumed white bread rolls as either placebo or supplemented with 15g arabinoxylan for 6 weeks with a 6-week washout period. Fasting serum glucose, insulin, triglycerides, unesterified fatty acids, apolipoprotein A1 and B, adiponectin, resistin and leptin were assessed before and after intervention. Fasting serum glucose, serum triglycerides and apolipoprotein A-1 were significantly lower during arabinoxylan consumption compared to placebo (p = 0.029, p = 0.047; p = 0.029, respectively). No effects of arabinoxylan were observed for insulin, adiponectin, leptin and resistin as well as for apolipoprotein B, and unesterified fatty acids. In conclusion, the consumption of AX in subjects with impaired glucose tolerance improved fasting serum glucose, and triglycerides. However, this beneficial effect was not accompanied by changes in fasting adipokine concentrations.
Photon Density Wave (PDW) spectroscopy is presented as a fascinating technology for the independent determination of scattering (mu(s)’ and absorption (ita) properties of highly turbid liquid dispersions. The theory is reviewed introducing new expressions for the PDW coefficients k(I) and k(Phi). Furthermore, two models for dependent scattering, namely the hard sphere model in the Percus-Yevick Approximation (HSPYA) and the Yukawa model in the Mean Spherical Approximation (YMSA), are experimentally examined. On the basis of the HSPYA particle sizing is feasible in dispersions of high ionic strength. It is furthermore shown that in dialyzed dispersions or in technical copolymers with high particle charge only the YMSA allows for correct dilution-free particle sizing. (C) 2013 Elsevier Ltd. All rights reserved.
Background:
COVID-19 has infected millions of people worldwide and is responsible for several hundred thousand fatalities. The COVID-19 pandemic has necessitated thoughtful resource allocation and early identification of high-risk patients. However, effective methods to meet these needs are lacking.
Objective:
The aims of this study were to analyze the electronic health records (EHRs) of patients who tested positive for COVID-19 and were admitted to hospitals in the Mount Sinai Health System in New York City; to develop machine learning models for making predictions about the hospital course of the patients over clinically meaningful time horizons based on patient characteristics at admission; and to assess the performance of these models at multiple hospitals and time points.
Methods:
We used Extreme Gradient Boosting (XGBoost) and baseline comparator models to predict in-hospital mortality and critical events at time windows of 3, 5, 7, and 10 days from admission. Our study population included harmonized EHR data from five hospitals in New York City for 4098 COVID-19-positive patients admitted from March 15 to May 22, 2020. The models were first trained on patients from a single hospital (n=1514) before or on May 1, externally validated on patients from four other hospitals (n=2201) before or on May 1, and prospectively validated on all patients after May 1 (n=383). Finally, we established model interpretability to identify and rank variables that drive model predictions.
Results:
Upon cross-validation, the XGBoost classifier outperformed baseline models, with an area under the receiver operating characteristic curve (AUC-ROC) for mortality of 0.89 at 3 days, 0.85 at 5 and 7 days, and 0.84 at 10 days. XGBoost also performed well for critical event prediction, with an AUC-ROC of 0.80 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. In external validation, XGBoost achieved an AUC-ROC of 0.88 at 3 days, 0.86 at 5 days, 0.86 at 7 days, and 0.84 at 10 days for mortality prediction. Similarly, the unimputed XGBoost model achieved an AUC-ROC of 0.78 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. Trends in performance on prospective validation sets were similar. At 7 days, acute kidney injury on admission, elevated LDH, tachypnea, and hyperglycemia were the strongest drivers of critical event prediction, while higher age, anion gap, and C-reactive protein were the strongest drivers of mortality prediction.
Conclusions:
We externally and prospectively trained and validated machine learning models for mortality and critical events for patients with COVID-19 at different time horizons. These models identified at-risk patients and uncovered underlying relationships that predicted outcomes.