How providers can make AI, machine learning work

Chris Nerney
Chris Nerney, Contributing Writer |
How providers can make AI, machine learning work

Artificial intelligence (AI) has the potential to transform healthcare in a number of ways, from enabling personalized medicine to accelerating medical discoveries.
For example, Mayo Clinic and IBM Watson Health are using AI to help identify patients for enrollment in breast cancer clinical trials, which increases participation in clinical trials, thus making promising new treatments available to more patients while giving clinicians and researchers more data faster. And it is data that fuels AI and machine learning.
“If you have enough data, you can build a model,” David Parish, a healthcare AI leader for Google Cloud, said at HIMSS18 in Las Vegas. “If the data is consistent and accurate enough, that model will work very well.”
Parish, however, adds an important caveat. “The model is not going to be smarter or more accurate than the examples I give it,” he said.
Thus it’s the quality and quantity of data that determines how far AI will take an organization. And that’s where the problems can begin.
“In many organizations, the data isn’t in a single place or in a useable format, or it contains biases that can lead to bad decisions,” InterSystems writes over at Healthcare IT News.
What healthcare organizations must do to ensure quality AI is to assess existing data flows, invest in areas where data is siloed or flawed, and develop an overall data management process that can support AI-enabled clinical care and medical research.
“It is essential for companies to spend time understanding the data flows into AI and machine learning systems in real time, what the quality of that data looks like, and how it can be stored, augmented and used for future training,” according to InterSystems.
This might mean upgrading networking and infrastructure equipment to handle collect, process, and transmit vasts amounts of data in real time, as well as rethinking data quality measures and data flow.
“Once organizations put the right technologies, teams and process analysis pieces in place, AI and machine learning programs will be poised to achieve the kinds of success expected of such hyped technology," concludes InterSystems.