Inductive database to support iterative data mining: Application to biomarker analysis on patient data in the Fight-HF project

Machine learning is now an essential part of any biomedical study but its integration into real effective Learning Health Systems, including the whole process of Knowledge Discovery from Data (KDD), is not yet realised. We propose an original extension of the KDD process model that involves an inductive database. We designed for the first time a generic model of Inductive Clinical DataBase (ICDB) aimed at hosting both patient data and learned models. We report experiments conducted on patient data in the frame of a project dedicated to fight heart failure. The results show how the ICDB approach allows to identify biomarker combinations, specific and predictive of heart fibrosis phenotype, that put forward hypotheses relative to underlying mechanisms. Two main scenarios were considered, a local-to-global KDD scenario and a trans-cohort alignment scenario. This promising proof of concept enables us to draw the contours of a next-generation Knowledge Discovery Environment (KDE).

Automated summary

Machine learning is an essential part of biomedical studies, but its integration into effective Learning Health Systems is still in progress. In this study, a model of an Inductive Clinical Database (ICDB) was proposed to host patient data and learned models. Experiments conducted on patient data in a heart failure project demonstrated the effectiveness of the ICDB approach in identifying biomarker combinations that are predictive of heart fibrosis phenotype and generating hypotheses about underlying mechanisms. This proof of concept paves the way for the development of a next-generation Knowledge Discovery Environment (KDE).