Background
Post‐COVID multisystem hyperinflammatory syndrome in children (MISC) has clinical and laboratory similarities with Kawasaki disease (KD). Inflammatory markers like C‐reactive protein (CRP), interleukin 6 (IL6) as well as N‐terminal probrain natriuretic peptide (NT‐proBNP) are elevated in both. This study attempts a comparative analysis of the 3 markers in an attempt at early differentiation for planning appropriate management.
Methodology
This analytical study conducted at the Institute of Child Health, Kolkata, India compared the levels of the above 3 markers at admission between 72 patients with KD, 30% of whom had coronary artery lesions (CALs) collected over a period of 18 months (Jan 2017‐June 2018), with 71 MISC patients over a period of 6 months (July 2020‐December 2020). The non‐parametric Mann‐Whitney
U
test was used to test for similarity in distributions of the samples of CRP, NT‐proBNP and IL6 in KD and MISC patients using correction factor for similar ranks. The 3 parameters were compared using receiver operating characteristic (ROC) curve analysis.
Results
Mean IL6 value in KD was 83.22 pg/mL and in MISC 199.91 pg/mL, which was not found to be statistically significant (
P
= .322 > .05).However mean NT‐proBNP (914.91 pg/mL) with CRP level (96.32 mg/L) in KD was significantly lower (
P
< .05 for both cases) than that in MISC (9141.16 pg/mL and 145.66 mg/L respectively). ROC analysis showed NT‐proBNP has the best sensitivity and specificity in predicting MISC.
Conclusion
NT‐proBNP and CRP are significantly higher among MISC patients; ROC analysis shows levels >935.7 pg/mL and >99.55 mg/L respectively might act as a guide to differentiate between them.
With the proliferation of unstructured data, text classification or text categorization has found many applications in topic classification, sentiment analysis, authorship identification, spam detection, and so on. There are many classification algorithms available. Naïve Bayes remains one of the oldest and most popular classifiers. On one hand, implementation of naïve Bayes is simple and, on the other hand, this also requires fewer amounts of training data. From the literature review, it is found that naïve Bayes performs poorly compared to other classifiers in text classification. As a result, this makes the naïve Bayes classifier unusable in spite of the simplicity and intuitiveness of the model. In this paper, we propose a two-step feature selection method based on firstly a univariate feature selection and then feature clustering, where we use the univariate feature selection method to reduce the search space and then apply clustering to select relatively independent feature sets. We demonstrate the effectiveness of our method by a thorough evaluation and comparison over 13 datasets. The performance improvement thus achieved makes naïve Bayes comparable or superior to other classifiers. The proposed algorithm is shown to outperform other traditional methods like greedy search based wrapper or CFS.
This study comparing the different parameters of children suffering from multisystem inflammatory syndrome in children (MIS-C) in Kolkata, India, during the two waves (July, 2020–January, 2021 and April–July, 2021) showed that the second wave had a higher propensity of Kawasaki disease (KD)-like presentation, cardiac affection and pediatric intensive care unit admission, and increased incidence of use of steroids for treatment.
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.