Predictive hemoglobin response model development for effective anemia management

点击翻译按钮获取中文摘要

Renal disease patients with anemia are generally treated by the administration of recombinant human erythropoietin (rHuEPO) to adjust the hemoglobin (Hb) level. It has been recognized by the clinical community that an unstable Hb levels can lead to increased risk of mortality for the patients suffering from anemia. Conventional methods for guiding rHuEPO dosing are generally based on clinician's experiences and imprecise. Cybernius Medical Ltd. aims to develop an automatic decision support system to achieve effective anemia management. In this project, the objective is to develop a predictive model that would predict a patient's hemoglobin level response to rHuEPO dosing with an acceptable level of accuracy. The model will be used in future to develop an automatic decision making support system for anemia management using model based control technique. First-principle and data-driven methods will both be investigated to develop a model that is able to provide accurate Hb level predictions based on rHuEPO dosing. The large amount of renal disease patients suffering from anemia will benefit from the research with reduced risk of high Hb level variability. The research can also lead to reduced use of rHuEPO and the economic burden of patient, and reduce the clinician's time spent on anemia management.