AI is increasingly expected to perform no shortage of “clinical miracles,” but providers need to get the basics in order first perform expecting too much of new AI technology.

So wrote Dr. Lonny Reisman, former Aetna chief medical officer and now founder and CEO of HealthReveal, an AI solutions developer, in a recent column aimed at laying out an effective, methodical path for providers to take toward AI implementation.

First, Reisman says, providers should focus on applying AI tools to primarily structured data, leaving for the future the countless reams of unstructured data many stakeholders are itching to tackle.  The goal, Reisman points out, is to avoid misleading conclusions.

“Parsing doctors’ notes is a tricky undertaking,” he observes. “Extracting lab values or physiological parameters is invaluable, but in many instances natural language processing may miss context. Was it you, for example, or your mother, who has a history of heart failure?”

Next, he says, validate the data.

“The adage ‘garbage in, garbage out’ is true. Claims data are intended to facilitate reimbursement, not necessarily reflect underlying clinical reality. . . . Check and cross-check for validation of claims veracity, looking for repeated diagnoses or the use of certain interventions or drugs associated with a ‘true’ diagnosis.”

Third, begin with the evidence.

“Conclusions drawn from well-conducted clinical trials may serve as a better foundation for artificial intelligence and machine learning than raw statistical inference. By first starting with established, efficacious interventions (e.g., anticoagulation for stroke reduction in high risk atrial fibrillation patients), we may then deploy AI to personalize interventions for individual patients.”

Finally, show results.

“AI is making significant advances in imaging interpretation,” Reisman recognizes, “with encouraging results in areas like diabetic retinopathy. As we extend to the domain of highly complex and nuanced clinical decision making, let’s ensure similar proof of benefits (or flaws). Evidence and credibility are essential as we endeavor to augment the skills of practicing clinicians.”

In the end, there’s no doubt Reisman shares the high hopes of many others for the potential of AI in healthcare.  All he’s suggesting is a little caution along the way.

“With ever-expanding patient data and the sheer power of AI, novel approaches to clinical decision making will naturally emerge,” he predicts, but “a rigorous focus on data-driven and evidence-based approaches is paramount. This will instill confidence in the medical community and ensure we keep patients’ best interest at heart.”