#HIMSS19: How Andrew Pecora, M.D. is combining the literature with social determinants of health and previous cases to inform clinical decision making at the point of care.
We’ve reached a tipping point in oncologic care, according to Andrew Pecora, M.D., chief innovation officer at Hackensack Meridian Health. One that requires highly specialized, highly intelligent tools.
Here’s the challenge: “Knowing exactly what to do — what’s the best care option to offer the patient in front of you – is rapidly becoming impossible,” Pecora, an oncologist by training, said before a room of several hundred attendees at HIMSS 2019 in Orlando, Florida.
LISTEN: Making the Most of Your HIMSS Experience
To Pecora’s point, the resources flowing into cancer research have grown drastically in recent decades. A quick PubMed search of the term “cancer” returns 70,438 published studies in the year 2000, 116,411 in 2010 and 178,078 in 2018. That breaks down to 192, 318 and 487 per day, respectively, and that’s only taking into account studies that can be found through a single publicly available database.
As if that were not enough, oncologists must also remain abreast of new therapies coming to market, plus all the distinct characteristics of individual patients including their social determinants of health, and how their physician peers are handling similar cases.
If those complex data points were to come together at the point of care in an intelligible way, it could inform clinical decision making and help health systems move towards a better answer for one of the most perplexing questions in the industry: How can we improve outcomes for patients while reducing the total cost of care at scale in a practical and clinically acceptable way?
Pecora set out to create such an artificial intelligence-driven point-of-care data aggregation tool with the help of IBM’s Watson for Oncology. The tool would simultaneously pull data from clinical trials and real-world results, present unique patient characteristics from the EHR, include each patient’s social determinants of health, and benchmark against patients with similar characteristics who had been previously treated. Then, that data would be combined to arrive at an AI-generated treatment suggestion.
“We thought we were geniuses,” Pecora said, describing the moment his idea became reality. “But the physicians said we had to show them data that the experts actually agreed with.”
Pecora tapped three leading breast cancer experts to suggest treatment approaches on 88 cases. Of the 223 responses, 78.5% agreed with the Watson for Oncology recommendation for the best possible treatment approach, 9.4% of recommendations were listed as clinically acceptable, and 12.1% of recommendations were listed as not recommended.
The next hurdle was to demonstrate that presentation of the data would result in changed clinical decision making at the point of care, Pecora said. He polled four solid tumor doctors and 6 hematologic malignancy doctors who didn’t typically take care of breast cancer on 339 breast cancer cases.
62% of the time, their choice agreed with Pecora’s results, 13% were clinically acceptable, and 24% of the time their choice was deemed by the system to be inappropriate care, he said, adding that their care pattern match was only 4%.
“So, if you show doctors at the point of care what experts think is appropriate and what the literature says might be best, the actually change their behavior,” Pecora said, adding that he believes he now has evidence to support moving forward with this cognitive computing point of care decision support system, supplemented by real-world data to improve treatment selection of complex disease such as breast cancer, especially when delivered in non-expert care settings.
“By using point of care solutions using expert opinion and the world literature combined with real-world evidence so that doctors can’t say ‘you’re not accounting for my kind of patients,’ you can demonstrate not just that there is selection of care that may not be optimal, but that you can change decision making before it happens at the point of care,” Pecora said. “You can improve outcomes for your patient, and if you do this at scale, reduce total cost of care for the population.”
Get the best insights in healthcare analytics directly to your inbox.
Weighing the Benefits and Challenges of Interoperability
Treating Healthcare IT's Interoperability Problem
HHS Issues Draft Strategy to Reduce Health IT Burden