Analysis of Big Data of HCV Patients

: The present study aimed to analyze big data posted on Kaggle about HCV infection and to find correlations between demographic variables and clinical variables related to HCV infection. The data posted on Kaggle is a large data consisting of 1385 patients. Data included some variables such as age, gender and Body Mass Index (BMI). Clinical manifestations were also included such as fever, jaundice, headache, nausea and vomiting. Variables including laboratory findings including white blood cells, red blood cells, platelets and hemoglobin were also included. Various statistical models were included such as descriptive statistics such as frequencies, percentages, means, and standard deviations. The correlations between study variable were assed using Pearson correlation. Significance was considered at α # 0.05. Study findings showed that clinical manifestations were reported by about 50% of patients. The results reported some correlations between study variables including positively significant correlations between HB and BMI, nausea and vomiting. Also, there were some negatively significant correlation between jaundice and BMI and diarrhea and hemoglobin. Taken together, we recommend future studies to investigate the importance of such correlations.