The data science industry – irrespective of domain & business – spends significant effort (> 90%) on the preparation, access, approval and provisioning of data to build “analytics-ready” data. A simple rule-of-thumb is: “If the input data is garbage then AI/ML outcomes are garbage as well (garbage-in then garbage-out)”. My previous and current projects are about building analytics-ready data infrastructures and platforms using “Semantic Technologies”, essentially making data FAIR (findable, accessible, interoperable and reusable) and improving “Intend to Insight” data pipelines. I am passionate about connecting variety of data (graph, images, key-value, stream , table, text, tree) and retrieve such interconnected data in a manner that:
I am interested in developing technologies that can ease the access of interconnected healthcare (phenotype) and genomics (genotype) data which will ultimately bring precision medicine into the clinical use. I approach towards the precision medicine from a data (computational) perspective. I have always believed that the human health and disease is one area which can immensely benefit from connecting the vast pools of data ecosystems (electronic health records, clinical trials reports, genetic discoveries, climate and environmental changes).
Specialties: Electronic Health Records (EHRs), Clinical Trial Databases, Cancer Genomics, Linked & FAIR Data, Ontology, Knowledge Graph & Data Analytics.
SIFEM - Global initiative on Combating Hearing Loss