Paper Title
Neutrophil Count Prediction For Personalized Drug Dosing In Childhood Cancer Patients Receiving 6-Mercaptopurine Chemotherapy Treatment

Abstract
Acute Lymphoblastic Leukaemia (ALL) is a common form of blood cancer that usually affects children under 15 years of age. Chemotherapy treatment for ALL is delivered in three phases viz. induction, intensification, and maintenance. The maintenance phase involves oral administration of the chemotherapy drug 6-Mercaptopurine (6-MP) in varying doses to destroy any remaining abnormal cells and prevent reoccurrence. A key side effect of the treatment is a reduction in neutrophil counts which can lead to a condition known as neutropenia. This carries a risk of secondary infection and has been linked to 60% ALL fatalities. Current practice aims to control neutrophil counts by varying 6-MP dosages on a weekly basis and is based upon clinical judgment and experience of the medical professionals involved. Conceived as a decision support aid for clinicians then, presented are the results of a machine learning technique that predicts neutrophil counts one or more weeks ahead using data from ALL blood test resultsand 6-MP dosing.In this work, a model is trained and validated using data from a single female ALL patient�s maintenance phase.The prediction error is found to be typically within +/-290/microL at one week and within +/- 820/microL fora 14 day prediction. Index Terms�Leukaemia, Neutrophils,Artificial Neural Networks,Time Series Prediction.