The global outbreak of the new Coronavirus brought to our attention an inconvenient truth about influenza: The seasonal flu kills between 291,000 to 645,000 people worldwide each year. Still, a December 2019 survey found that 37% of US adults did not intend to get a flu shot.
Not getting a flu shot could turn out to be an unfortunate decision for people who don’t know—and their doctors don’t know—that they are at high risk for developing flu-related complications. But applying AI algorithms to patient data and identifying unvaccinated high-risk individuals, could “prevent deaths and hospitalization,” says Dr. Jeremy Orr.
Orr is the CEO of Medial EarlySign, an Israeli startup that has developed algorithms that assist healthcare providers with the early detection of a number of life-threatening conditions, including lower GI disorders, prediabetes progression to diabetes, and colorectal cancer. Medial EarlySign’s data sets cover more than 20 million patient lives and 150 million patient years and it has tested its algorithms in studies conducted in 13 clinical sites worldwide.
“When the doctor does a test and tells you everything is in the ‘normal range,’ nothing to worry about, there is a lot of information there that they are not seeing that could suggest that you are at risk for certain clinical conditions,” explains Orr. “The traditional way to interpret lab tests—‘normal ranges’—is totally broken and has been for some time. With machine learning we can see that there are patterns in normal-appearing labs that suggest that the patient has high risk for or already having colorectal cancer, for example.”
This is the promise of “personalized medicine” or “precision medicine,” finding the hidden clues of potential risks and telling data patterns, what Orr calls “the non-intuitive relationships,” in a person’s medical record or test results. And Medial EarlySign’s algorithms alert healthcare providers to a serious disease at a stage where there is a better chance for a successful intervention.
Orr sees Medial EarlySign’s competitive differentiation in the high quality and expertise of its data science team, the work they have done to clean messy healthcare data, and their seamless integration with the existing workflow of the healthcare systems they partner with. In addition, “We don’t go to a health system and say give us all your data,” says Orr. “We give them something they can implement behind their firewall in a secure cloud location. We are giving them the benefit of AI without all the heavy training stage.”
Getting doctors to adopt a new approach is not an easy task and Medial relies on the papers reporting on the results of its clinical studies for convincing evidence of the efficacy of its algorithms. In addition, they overcome AI’s “black box” challenge by offering with their solution a “but why?” feature, explaining to the doctors some of the reasons their patient is considered high-risk. “They can see the value of the machine in picking the subtle things they are likely to miss and they can have a more informed conversation with the patient,” says Orr. And he adds: “AI is not going to replace doctors. They do some really important communications with patients and we want to augment that.”
Medial EarlySign’s currently works with Maccabi Healthcare Services in Israel and Geisinger Health, SLUCare, and Kaiser Permanente Northwest in the US. Orr’s vision for the future is to “get AI insights beyond just healthcare providers.” This means partnering with labs, diagnostics companies, and technology platforms “that can put the insights in different parts of the ecosystem faster.”
Medial EarlySign may become the “AI Inside” for companies supplying products and services to the healthcare industry.
* * *
Click here to read the original Forbes article on Medial EarlySign.