Machine learning prediction for COVID-19 disease severity at hospital admission.

IMPORTANCE: Early prognostication of patients hospitalized with COVID-19 who may require mechanical ventilation and have worse outcomes within 30 days of admission is useful for delivering appropriate clinical care and optimizing resource allocation. OBJECTIVE: To develop machine learning models to predict COVID-19 severity at the time of the hospital admission based on a single institution data. DESIGN, SETTING, AND PARTICIPANTS: We established a retrospective cohort of patients with COVID-19 from University of Texas Southwestern Medical Center from May 2020 to March 2022. Easily accessible objective markers including basic laboratory variables and initial respiratory status were assessed using Random Forest's feature importance score to create a predictive risk score. Twenty-five significant variables were identified to be used in classification models. The best predictive models were selected with repeated tenfold cross-validation methods. MAIN OUTCOMES AND MEASURES: Among patients with COVID-19 admitted to the hospital, severity was defined by 30-day mortality (30DM) rates and need for mechanical ventilation. RESULTS: This was a large, single institution COVID-19 cohort including total of 1795 patients. The average age was 59.7 years old with diverse heterogeneity. 236 (13%) required mechanical ventilation and 156 patients (8.6%) died within 30 days of hospitalization. Predictive accuracy of each predictive model was validated with the 10-CV method. Random Forest classifier for 30DM model had 192 sub-trees, and obtained 0.72 sensitivity and 0.78 specificity, and 0.82 AUC. The model used to predict MV has 64 sub-trees and returned obtained 0.75 sensitivity and 0.75 specificity, and 0.81 AUC. Our scoring tool can be accessed at https://faculty.tamuc.edu/mmete/covid-risk.html . CONCLUSIONS AND RELEVANCE: In this study, we developed a risk score based on objective variables of COVID-19 patients within six hours of admission to the hospital, therefore helping predict a patient's risk of developing critical illness secondary to COVID-19.

Immature Platelet Fraction as a Biomarker for Disease Severity in Pediatric Respiratory Coronavirus Disease 2019.

In this retrospective single-institution cohort study of 113 hospitalized pediatric patients with respiratory coronavirus disease 2019, those admitted to the intensive care unit or requiring mechanical ventilation had significantly higher immature platelet fractions than those who did not require intensive care unit-level care or ventilation. Immature platelet fraction may be an accessible biomarker for disease severity in pediatric respiratory coronavirus disease 2019.

Poly (methyl vinyl ether-co-maleic acid) - Pectin based hydrogel-forming systems: Gel, film, and microneedles.

Cross-linking of natural and synthetic polymers is widely explored to achieve the desired material properties (mechanical strength, drug loading capacity, swelling and erosion rates). However, the potential of polymers produced by crosslinking poly (methyl vinyl ether-co-maleic acid) (PMVE/MA) and pectin (PE) in pharmaceutics is mainly unexplored so far. We have investigated the effect of various esterification conditions and pectin content on the physicochemical properties. Materials have been characterized by fourier transform infrared, differential scanning calorimetry and scanning electron microscopy. In addition, swelling and bioadhesive features of PMVE/MA-PE hydrogel systems were investigated. A band shift for the carbonyl group from 1706 to 1776cm-1, and glass transition (Tg) increased from 55.4±0.9°C to 119.5±0.3°C confirmed the formation of esterification reaction within the cross-linked films. Cross-linked PMVE/MA:PE films with a ratio of 5 demonstrated a superior mass increase when compared to 2.5, 3.125, 3.75, 6.25, and 7.5 ratios of the same hydrogel film. Formulations containing PMVE/MA and pectin with a ratio of 3.75 showed superior bioadhesive features. For the first time, we engineered three-dimensional printing based swell-able microneedle arrays made out of cross-linked PMVE/MA-PE. Microneedle arrays height and aspect ratio were ranged from 702.5±11.9µm to 726±23.3µm and 3.12±0.20 to 3.29±0.21, respectively. Cross-linked PMVE/MA-PE Microneedle arrays (10-2, 24h) indicated the least height loss, 22.33±4.15%, during axial compression test; whilst, transverse failure of cross-linked PMVE/MA-PE Microneedle arrays was varied from 0.15±0.05 to 0.25±0.04N/needle. In conclusion, we obtained a novel cross-linked polymer system with promising features of drug delivery and bio-analytical applications.

Global kinetic analysis of seeded BSA aggregation.

Accelerated aggregation studies were conducted around the melting temperature (Tm) to elucidate the kinetics of seeded BSA aggregation. Aggregation was tracked by SEC-HPLC and intrinsic fluorescence spectroscopy. Time evolution of monomer, dimer and soluble aggregate concentrations were globally analysed to reliably deduce mechanistic details pertinent to the process. Results showed that BSA aggregated irreversibly through both sequential monomer addition and aggregate-aggregate interactions. Sequential monomer addition proceeded only via non-native monomers, starting to occur only by 1-2°C below the Tm. Aggregate-aggregate interactions were the dominant mechanism below the Tm due to an initial presence of small aggregates that acted as seeds. Aggregate-aggregate interactions were significant also above the Tm, particularly at later stages of aggregation when sequential monomer addition seemed to cease, leading in some cases to insoluble aggregate formation. The adherence (or non-thereof) of the mechanisms to Arrhenius kinetics were discussed alongside possible implications of seeding for biopharmaceutical shelf-life and spectroscopic data interpretation, the latter of which was found to often be overlooked in BSA aggregation studies.

Novel use of pectin as a microneedle base.

Hydrocolloid pectin formulation was utilized as a novel base for fabricating biodegradable micro-needle (MN) arrays. The pectin MNs were, on average, found to be 897.71 ± 3.48 µm in height and 234.31 ± 2.27 µm in base width, with an inter base spacing of 498.66 ± 1.60 µm, and corresponding to an aspect ratio of 3.83 ± 0.04. Bovine serum albumin (BSA) and pectin gel interaction was found to be dependent on the loaded protein amount. By contrast, regardless of the amount of BSA incorporated, pectin MNs competed with BSA to form a complex with Cu(2+) ions in a bicinchoninic acid (BCA) kit. The glass transition of the pectin MN base was found to be 145.15 ± 12.09, with a delta Cp of 2.60 ± 0.02 J g(-1) K(-1). Because pectin MNs are skin friendly and naturally occurring, with biodegradable and hydrocolloidal features, they are promising vehicle for the controlled release of macromolecules.