Stratification of Pediatric COVID-19 cases by inflammatory biomarker profiling and machine learning (preprint)

An objective method to identify imminent or current Multi-inflammatory Syndrome in Children (MIS-C) infected with SARS-CoV-2 is highly desirable. The aims were to define an algorithmically interpreted novel cytokine/chemokine assay panel providing such an objective classification. This study was conducted on 4 groups of patients seen at multiple sites of Texas Childrens Hospital, Houston, TX who consented to provide blood samples to our COVID-19 Biorepository. Standard laboratory markers of inflammation and a novel cytokine/chemokine array were measured in blood samples of all patients. Group 1 consisted of 72 COVID-19, 66 MIS-C and 63 uninfected control patients seen between May 2020 and January 2021 and predominantly infected with pre-alpha variants. Group 2 consisted of 29 COVID-19 and 43 MIS-C patients seen between January-May 2021 infected predominantly with the alpha variant. Group 3 consisted of 30 COVID-19 and 32 MIS-C patients seen between August-October 2021 infected with alpha and/or delta variants. Group 4 consisted of 20 COVID-19 and 46 MIS-C patients seen between October 2021- January 2022 infected with delta and/or omicron variants. Group 1 was used to train a L1-regularized logistic regression model which was validated using 5-fold cross validation, and then separately validated against the remaining naive groups. The area under receiver operating curve (AUROC) and F1-score were used to quantify the performance of the algorithmically interpreted cytokine/chemokine assay panel. Standard laboratory markers predict MIS-C with a 5-fold cross-validated AUROC of 0.86 {+/-} 0.05 and an F1 score of 0.78{+/-}0.07, while the cytokine/chemokine panel predicted MIS-C with a 5-fold cross-validated AUROC of 0.95 {+/-} 0.02 and an F1 score of 0.91 {+/-} 0.04, with only sixteen of the forty-five cytokines/chemokines sufficient to achieve this performance. Tested on Group 2 the cytokine/chemokine panel yielded AUROC =0.98, F1=0.93, on Group 3 it yielded AUROC=0.89 , F1 = 0.89, and on Group 4 AUROC= 0.99, F1= 0.97. Adding standard laboratory markers to the cytokine/chemokine panel did not improve performance. A top-10 subset of these 16 cytokines achieved equivalent performance on the validation data sets. Our findings demonstrate that a sixteen-cytokine/chemokine panel as well as the top ten subset provide a sensitive, specific method to identify MIS-C in patients infected with SARS-CoV-2 in all the major variants identified to date.

Population stratification enables modeling effects of reopening policies on mortality and hospitalization rates (preprint)

Objective: We study the influence of local reopening policies on the composition of the infectious population and their impact on future hospitalization and mortality rates. Materials and Methods: We collected datasets of daily reported hospitalization and cumulative morality of COVID 19 in Houston, Texas, from May 1, 2020 until June 29, 2020. These datasets are from multiple sources (USA FACTS, Southeast Texas Regional Advisory Council COVID 19 report, TMC daily news, and New York Times county level mortality reporting). Our model, risk stratified SIR HCD uses separate variables to model the dynamics of local contact (e.g., work from home) and high contact (e.g., work on site) subpopulations while sharing parameters to control their respective $R_0(t)$ over time. Results: We evaluated our models forecasting performance in Harris County, TX (the most populated county in the Greater Houston area) during the Phase I and Phase II reopening. Not only did our model outperform other competing models, it also supports counterfactual analysis to simulate the impact of future policies in a local setting, which is unique among existing approaches. Discussion: Local mortality and hospitalization are significantly impacted by quarantine and reopening policies. No existing model has directly accounted for the effect of these policies on local trends in infections, hospitalizations, and deaths in an explicit and explainable manner. Our work is an attempt to close this important technical gap to support decision making. Conclusion: Despite several limitations, we think it is a timely effort to rethink about how to best model the dynamics of pandemics under the influence of reopening policies.