Machine learning-aided algorithm design for prediction of severity from clinical, demographic, biochemical and immunological parameters: Our COVID-19 experience from the pandemic.

Background: The severity of laboratory and imaging finding was found to be inconsistent with clinical symptoms in COVID-19 patients, thereby increasing casualties. As compared to conventional biomarkers, machine learning algorithms can learn nonlinear and complex interactions and thus improve prediction accuracy. This study aimed at evaluating role of biochemical and immunological parameters-based machine learning algorithms for severity indexing in COVID-19.

Accuracy of contrast-enhanced CT in liver neoplasms in children under 2 years age.

Background: Multiple differentials exist for pediatric liver tumors under 2 years. Accurate imaging diagnosis may obviate the need for tissue sampling in most cases.

Objective: To evaluate the imaging features and diagnostic accuracy of computed tomography (CT) in liver tumors in children under 2 years.

Intracranial extraosseous dural-based Ewing's sarcoma with fluid-haematocrit levels: imaging findings of a rare tumour.

Extraosseous dural-based primary Ewing's sarcoma of the central nervous system is a rare tumour posing a diagnostic challenge. On cross-sectional radiological imaging, the lesion has an extra-axial location with heterogeneous appearance. These lesions are usually multicystic with internal haemorrhage causing fluid-haematocrit levels.

Machine learning predictive models of LDL-C in the population of eastern India and its comparison with directly measured and calculated LDL-C.

Background: LDL-C is a strong risk factor for cardiovascular disorders. The formulas used to calculate LDL-C showed varying performance in different populations. Machine learning models can study complex interactions between the variables and can be used to predict outcomes more accurately.