Modelling of cancer treatment with activity-meter records using linear and binary logistic regressions

Cancer is a term for diseases in which cells grow abnormally without control and can attack surrounding tissue. In the recent years, cancer has become the leading cause of death in the world. The most commonly used cancer treatment is chemotherapy with a series of 5-Fluorouracil (5-FU) based therapies. This study aims to determine the factors which influence the success of chemotherapy. The statistical method used in this study is lineaar regression analysis and binary logistic regression. The results of linear regression revealed that that the dose of 5-FU 1 compound and the patient's body mass index had a significant effect on the level change of White Blood Cells (WBC) with a significant level of 5%, while the dose of Irinotecan compounds had a significant effect at a significance level of 20%. The change in the percentage of neutrophil of patients is affected by the age of the patient. Moreover, the average hours of deep sleep is affected by the age of the patient and the dose of compound P (Panumumab). The logistic regression analysis showed that the patient's age, the average number of patient's footsteps and the dose of 5 FU-1 given during chemotherapy had a significant effect on WBC changes after chemotherapy with a significance level of 10%. The logistic regression model is able to correctly predict the WBC change with 75.44% AUC.