No abstract

The phenomenal growth in the healthcare data has inspired us in investigating robust and scalable models for data mining. For classification problems Information Gain(IG) based Decision Tree is one of the popular choices. However, depending upon the nature of the dataset, IG based Decision Tree may not always perform well as it prefers the attribute with more number of distinct values as the splitting attribute. Healthcare datasets generally have many attributes and each attribute generally has many distinct values. In this paper, we have tried to focus on this characteristics of the datasets while analysing the performance of our proposed approach which is a variant of Decision Tree model and uses the concept of Correlation Ratio(CR). Unlike IG based approach, this CR based approach has no biasness towards the attribute with more number of distinct values. We have applied our model on some benchmark healthcare datasets to show the effectiveness of the proposed technique.

Background: The SARS-CoV-2 pandemic has emerged as the most challenging global health problem of this century. The concomitant presence of co-morbidities like chronic kidney disease (CKD), diabetes, CHD, further complicates the problem. Aim: To assess the patterns of LFT abnormalities in patients of SARS-CoV-2 infection with and without CKD and evaluate the probable outcomes. Materials and Methods: A cross-sectional retrospective observational study done on 600 patient samples (Group 1: SARS-CoV-2 without CKD, Group 2: SARS-CoV-2 with CKD and Group 3: CKD uninfected with SARS-CoV-2) which were processed for LFT and KFT. Results: AST and ALT were significantly higher in all SARS-CoV-2 infected; Group 1 mean ± 2SD, (63.63 ± 42.89U/L & 50.25 ± 46.53U/L), group 2 (90.59 ± 62.51U/L & 72.09 ± 67.24 U/L) as compared to Group 3 (25.24 ± 7.47U/L & 24.93 ± 11.44U/L). A statistically significant elevation is seen in these two parameters in Group 2 as compared to Group 1. There was a negative significant correlation between eGFR and AST/ALT levels in Group 1 ( p < 0.05). In Group 2, a weak positive correlation was seen with ALT. Group 3, eGFR’s showed strong correlations with AST and ALT levels; reduction in kidney function correlated well with increase in serum ALP levels. Conclusions: This study establishes that SARS-CoV-2 infected, with CKD, show higher elevations in serum aminotransferase levels in comparison to those without CKD. In contrast, the CKD group not infected, shows a decline in serum aminotransferase levels. Serum ALT values in SARS-CoV-2 show significant correlation with eGFR. Also, elevated ALP values in CKD patients may be used as an indicator of declining kidney function.

No abstract

A woman in her 20s presented with chest pain, dyspnoea, arthralgia, muscle weakness and skin discolouration. She was diagnosed with dermatomyositis. During her admission, she developed pleuritic chest pain and shortness of breath accompanied by a significant troponin I rise. Her echocardiogram showed a hyperdynamic left ventricle with a trivial pericardial effusion; there were no regional wall motion abnormalities. Gadolinium-diethylenetriaminepantaacetic-enhanced cardiac MRI showed extensive myocarditis. She was started on corticosteroids and azathioprine which led to an improvement of symptoms and biochemical markers.