What is unstructured data?

Unstructured data is anything that does not have a schema or other form of data model. An easy way to think about it is that unstructured data is anything that cannot be broken down to fit into a spreadsheet, database, or other tabular data store. This makes unstructured data unusable for computing applications without some form of data processing.

Data Types

In medicine you can find unstructured data at every turn. Most people will point to doctor’s notes as being the primary source and when it comes to data stored in EHRs that is true. However, doctor’s notes are only the tip of the unstructured data iceburg. The enormity of the problem becomes clear when you consider PDF documents, scanned copies of patient surveys, emails, chat transcripts, faxed documents, and printed copies of patient records.

The Value of Unstructured Data

All of this data has tremendous value in helping to provide efficient care and treatment to patients. Unlocking it for easy use and helping to deal with the staggering amount of unstructured data used daily in healthcare will be a substantial part of driving efficiencies and lowering costs for the healthcare system as a whole.