health care

AI is being embraced by the health care profession, with almost six out of ten health care providers in the U.S. integrating it into their business processes in the last year, according to a recent study commissioned by the global intelligent automation company ABBYY, and carried out by Sapio Research.

The study also revealed that half of the respondents reported improved efficiency and increased productivity. Forty-three percent reported reduced employee stress, and 37% reported better work-life balance.

Additionally, 60% reported that employees were carrying out more interesting and valuable work. One of the biggest benefits of AI is that it can take over tedious, time-consuming and cumbersome paperwork to free up valuable time so that workers can concentrate on the essential elements of their jobs. In the health care profession, that means more face-to-face time with patients.

Experts on the nexus of AI and health care say the industry will reap huge benefits from the technology, not just in doing the tedious paperwork, but with diagnosis and preventative care. Some providers are already using AI in that area and it has saved lives.

In a recent podcast session hosted by the American Medical Association, guest speaker Dr. Vincent Liu, a senior research scientist and regional medical director of Augmented Clinical Intelligence at Kaiser Permanente, spoke of AI’s impact, with regard to the medical group’s Advanced Alert Monitor (AAM) program. AAM is designed to identify high-risk patients who are in the hospital, in stable condition, but at risk of falling into critical condition or dying.

“So, over the past several years, we’ve used millions – hundreds of millions of data points from our hospitalized patients and granular EHR (Electronic Health Record) data, things like lab values, vital signs, other key clinical data to develop a machine learning algorithm that worked with good accuracy to predict patients at risk for deterioration in the next 12 hours, so early enough to actually intervene and hopefully prevent,” Dr. Liu said. He added that the algorithms should be paired with a “robust workflow” that can maximize the information that is given by AI. “So, we worked with extraordinary clinicians and teams across our 21 hospitals here in Northern California to develop workflows that made sense in response to an AAM alert.”

“Our results were published a couple of years ago in the New England Journal of Medicine, which showed that the implementation of AAM within this entire program, working closely with clinicians, reduced mortality, reduced the rate of ICU transfers and is estimated to save as much as 500 lives per year across our hospitals. So that was a really exciting object lesson for us in how we could leverage AI and machine learning to improve the care of our patients. But again, making sure that it was closely tied with what made sense for our clinicians and patients.”

Computer vision algorithms is another area that AI could potentially have a huge impact on, in terms of accuracy of diagnosis. Dr. Liu said, “there’s the potential to increase the identification of patients who may be at risk for breast cancer from 20% using traditional approaches to as much as 60 to 70% using, again, this computer vision augmentation.”

ABBYY’S Senior Director of AI Strategy, Max Vermeir, said in an interview with Techstrong AI, that the sector is still very much in the starting phase of digitization and automation, but such technologies can be accelerated, to access more information so that a patient’s medical history is comprehensive and at the fingertips of medical professionals caring for the patient. Mr. Vermeir added that in the health care sector, it is crucial that the process has quality control.

“In health care there are so many steps, which is good, right, because we are talking about people lives, you don’t want to make mistakes, you don’t want to have the wrong kind of input coming from any kind of platform, whether its AI or something simple…within this sector there are so many different steps with quality assurance, documentation and everything else that has to happen. I do think we are on that path.”

“Vendors like us, we are preparing ourselves much more to provide all those assurances to these organizations. I do think we are on the path to seeing it more and more in all different shapes and sizes, going from having an assistant at a kiosk that is virtual, that will help you go through the entire outboarding process, to actually doctors using the archived data to the point they will get notifications, and I would even say suggestions as to what could be the next possible best step, because there have already been studies that the combination of Ai and the doctor yields the best results, this is a perfect example that AI is not here to replace us, it is here to help us.”

Ms. Oishi Banerjee, a PhD student in Computer Science at Harvard University, who is doing research with the Rajpurkar Lab in the Department of Biomedical Informatics at Harvard Medical School, said in an interview with Techstrong AI that she optimistic about AI elevating patient care, particularly in the area of radiology.

“Like what we’re seeing with paperwork, AI can potentially boost efficiency in medical imaging,” she said. “For instance, AI tools can already sort through medical images and identify the really concerning ones, to help doctors respond to time-sensitive cases more quickly. AI tools can also look at images and suggest diagnoses, which can help doctors interpret those images more efficiently. Looking forward, generative AI tools will assist doctors with the writing process, which can also really speed up reporting.”

She added, that with regard to accuracy, “AI tools can help doctors interpret images more accurately. For example, there are AI tools that highlight small problem areas on an image, catching subtle findings that the human eye might have missed. AI tools can also improve accuracy indirectly just by making doctors’ workloads more reasonable, because a well-rested doctor tends to make fewer mistakes.”