Health Data Meets Artificial Intelligence And Machine Learning Posted on : Nov 21 - 2018

Data holds the key to future medical revolution. The more data we collect, the more we learn from it, and the closer we come to discovering revolutionary new treatments and cures.

The challenge has been speed. How quickly can we collect health data from various procedures and observations? How quickly can we analyze that data to extract new insights? How quickly can we learn as more new data reveals new understanding? How long will it take before all this is turned into meaningful medications and procedures that save lives?

And the answer has always been “not soon enough.” Until now.

Artificial Intelligence, Machine Learning And Cognitive Computing Join The Medical Team

Lots of data starts out offering incomplete value. As we collect more data, more answers are revealed. The problem is that this process of correlating and analyzing can take years before doctors and researchers can generate useful solutions from all the gathering data.

Machines learn faster.

At their most elemental level, all data sets are empirical in nature. They are what they are and are not open to interpretation. As such, they remain usefully objective and only rise in value as they are added to other forms of empirical data. It’s important to maintain the distinction between this unchanging data and the subjective nature of human opinions, interpretations and observations.

Effective health care requires the development of understanding based on two very different types of data. Structured data is found in very neat tables of columns and rows. Each column is another field of data, part of a more complete record. Each row in the table represents another record. This structure makes it easy for digital devices to ingest the data and process it.

What has been trickier has been all the unstructured data we encounter. CAT scans, MRIs and other types of diagnostic imaging are unstructured. There are no records containing precise fields. There are images that must be interpreted. The same is true of written information such as physician notes, diagnostic evaluations, medical research articles and much more.

While it's easy to imagine computers managing structured records and fields of data, most people couldn’t imagine a computer “reading” an MRI, an article or written notes. Even if they could scan and record the image and written content, they certainly couldn’t develop an understanding of what they were reading or evaluate the images. Right? View More