I credit my concept of a Data Mural to Rahul Bhavgava with MIT and Doctors for Global Health (DGH), an all-volunteer organization that cares deeply about health disparities and works to rectify them around the globe. He brought together doctors, public health professionals, community health workers, and artists to create a collaborative mural of a DGH project using project data to tell a compelling story. This idea is a perfect representation of the kind of “Data Mural” we want to create – a map of the geographic extent of the occurrence of infectious disease and a way to explore together the factors that may impact it’s course and cause.

Epinome1

Data Mural provides public health with a tool that gathers near real-time POC data to understand the contemporary geographical distribution of infectious disease through real time mapping, indexing and Big Data analytics tools.

This will allow public health care workers, policy and decision makers to improve their ability to triage spatially, manage infectious disease outbreak alerts and effectively teach – and reach – the most successful treatments down to the individual patient level.

In general Big Data applications rely on hospital records to gather data about disease incidence. Using POC sensors that are used in the field by health care workers has significant challenges.

Screen Shot 2015-03-11 at 11.33.49 PM

Data Mural is designed to be used by field health care workers that are involved in using POC sensors to screen or diagnose infectious diseases at the point they are occurring, not just in hospitals or clinics.

Providing near-real time data quickly to health care professionals in the field will be a critical tool for managing infectious disease outbreaks in the future, for example to triage family testing or treatment through mapping home visits and POC results on the ground.

There are a lot of mapping and GIS visualization tools already in the market and already used to map diseases. What makes Data Mural different is near-real time data from Point of Care (POC) diagnostic sensors is dynamic and doesn’t lend itself to a traditional data warehouse.

The VDW approach is a unique competitive advantage that allows Data Mural to integrate near-real time POC sensor data, index it alongside with all of the possibly relevant information (or metadata), and dynamically develop and test hypothesis. 

The Data Mural VDW approach also allows users to set up the Data Analytics program in a matter of days rather than months – we’re just now seeing Ebola maps when the crisis has been declared “won”- what might have changed if the Big Data Analytics been done in a day or two?

Data Mural leverages the already available visualization tools that provide really nice GIS visualizations of large data sets. However the current data correlations they provide are, for the most part, “flat”; that is two-dimensional rather than multidimensional (i.e., comparing lots of the available (index or meta-data over a specific geographic region).

Data Mural provides a unique set of Data Analytics tools that allow users to use and interact with Data Mural in new and unique ways. This is critical because we’ve all learned that great visualization tools are great if you know what metadata to use, but you first have to develop your own hypothesis and then build the query, etc…

cg

Our Data Analytics tools, Epinome and Epicanvas work within and along with the index allow exploration and rapid hypothesis discovery needed to integrate heterogeneous data and produce insight.

Data Mural provides a full complement of unique tools that allow users to still utilize all of the tools they currently use for mapping and visualization of data in a rapidly deployable, scaleable, and very low cost Virtual Data Warehouse. We complement this offering with a set of new Data Analytics called Epinome and Epicanvas that allow users to dynamically interface and use data in new and creative ways.