Maayan Jaffe-Hoffman writes in the Jerusalem Journal that artificial intelligence (AI) is enabling medical technology to advance at an increasingly rapid pace. In Israel, Tel Aviv Sourasky Medical Center is leading this charge with a new center focused on developing models for leveraging AI – deep learning, machine learning, neural networks (biologically inspired programming paradigm that enables a computer to learn from observational data) and natural language processing – in the clinical workspace.
“We have been carefully collecting organized data on our patients for more than a decade,” said Dr. Ahuva Weiss-Meilik, head of the new AI Center. “Now, we are creating an ecosystem within the hospital to create the best models and formulas to inform and support our clinical staff.” Weiss-Meilik said that AI itself is not new. It has been informing other arenas from the automobile industry to the financial and banking sectors for the past decade. However, lack of quantity and quality data kept AI outside of the medical setting. Now, with the growth of clinical data, captured effectively by electronic health records, researchers, doctors and other clinical staff can take advantage of these new tools.
“We are constantly capturing data on our patients,” explained Weiss-Meilik. “We do clinical examinations, imaging, blood tests and more. All of this data is now accessible.”
But she said data can also be overwhelming for physicians.
“No doctor, no matter how good he is, would be able to look at this mass amount of data and gain immediate insight,” she said. “These new models allow doctors to see patterns or gain insights into a patient’s clinical results.”
And in real or rapid time.
According to Talma Hendler, professor of psychiatry and neuroscience at Tel Aviv University and the founding director of the Sagol Brain Institute at the hospital, with AI, a computation based on clinical data that might have taken a month in the past “can now be computed in an hour.”
These insights will improve patient care and outcomes.
“A predictive model might tell us that a sick person is likely to be readmitted to the hospital within a week because of this or that,” said Weiss-Meilik. “Or, let’s say a doctor is monitoring a fetus. He can easily see if the unborn baby’s heart rate has accelerated or decelerated, but he might not so readily see other, smaller changes that look normal to the doctor but to a predictive model might be known to be problematic.
“With predictive analytics, the formula can warn us that every time you see this pattern, there will be X or Y medical event,” she said.
Weiss-Meilik said that the team at Sourasky is already working on a new model that will help radiologists prioritize their scans.
Hendler said using increased AI will also allow for more personalized medical treatment and give doctors the ability to look at patients more holistically. If in the past a patient would have been labeled as diabetic or simply having heart disease, “machine learning will cluster a patient’s ailments and perhaps help us to develop new and more nuanced labels.”
Further, it might be able to tell doctors that all people between 40 and 60 with diabetes also have A, B or C, for example, which will enable doctors to monitor those patients for A, B or C and/or treat the symptoms.
“We could review a patient’s history to inform his or her care, or we could look at patients with similar profiles to inform care,” said Hendler. “Sometimes, doctors don’t really know and have to guess based on patient history or one or two medical tests. AI could be more accurate and especially predictive in terms of patients current and future state, respectively. Therefore it may strengthen the preventive arm of medical practice and could focus on health resilience and not only sickness vulnerability.”
She believes that just as today every patient who enters the emergency room is automatically given a blood test, in the future, some form of AI related testing and consideration will become standard practice. She called Sourasky “visionary” for making AI a priority.
“There have not been any major developments yet,” said Weiss-Meilik, “but development is enough.”
Sourasky is also working closely with medical technology companies that will be able to help leverage the work of the hospital’s researchers and staff to commercialize their models.
“If we develop these models and get them on the market, we could improve health worldwide,” Weiss-Meilik said.