CuraEx - Clinical Expert System Using Big-Data for Precision Medicine

Cancer is a complex non-communicable disease with many types and subtypes, where the same treatment does not work for all cancers. Moreover cancer drugs have tremendous side effects. Deciding a suitable line of treatment for cancer, demands complex analytics of diverse distributed numeric and categorical data. Suitable therapy depends on factors like tumor size, lymph node infection, metastasis, genetic patterns of the tumor and patient's clinical history. We present CuraEx, a Clinical Expert System (CES) that uses clinical and genomic marker of the patient combined with a knowledge-base created from distributed, dissimilar, diverse big-data. This system computes cancer staging based on constraints defined by the American Joint Committee on Cancer (AJCC). It predicts prognosis using a cancer registry compiled between 1997 to 2012 in the US. Semi-structured data mining on disease association data is used to determine the most appropriate approved drug for the cancer type. Additionally, suitable clinical trial information will be retrieved based on the patient's geographicals location and phenotype. We then integrate the genomic marker and clinical data of the patient which paves the way for precision medicine. Molecular information or genomics biomarkers of the patient helps in treatment selection, increases the likelihood of therapeutic efficacy and minimize the drug toxicity. Our clinical expert system is availabe at http://www.curaex.org/ for public use.