USA – Google Health is enhancing the capabilities of its clinician-facing search tool by incorporating artificial intelligence to add context to physicians’ clinical notes.
Paul Muret, vice president and general manager of Care Studio at Google Health, announced new features of the company’s clinical software that harmonizes healthcare data from various sources and helps organize patient data at the ViVE 2022 conference.
Natural language processing (NLP) is used in the new Conditions feature to provide physicians with a dynamic list of conditions pulled from the patient record, as well as related information such as medications, labs, vitals, and notes.
“Our North Star is really improving outcomes, and we also care deeply about the clinician experience,” Muret said during an on-stage interview.
“Providing information in the right moment is so critical. We need to be also using our capabilities to extract meaning out of that data.”
Google is leveraging its expertise in search tools to create software that provides clinicians with a longitudinal view of patient records as well as the ability to search through those records quickly using a single secure tool.
Care Studio arose from Google’s collaboration with Ascension to test an electronic health record search tool that pulls patient electronic health records into an interface to help clinicians find useful information more easily.
In 2019, the tech giant and Ascension were chastised after it was revealed that the two organizations had formed a health data partnership, raising privacy concerns.
Former Google Health CEO David Feinberg, M.D., quickly took to the web at the time to directly address the controversy surrounding Google’s data deal with Ascension.
Beth Israel Deaconess Medical Center also agreed to pilot the clinical search tool, which has since been renamed Care Studio, in February 2021.
Google Health used artificial intelligence in this latest feature to understand medical concepts from notes that may be written in incomplete sentences, shorthand, or with misspelled words.
According to Muret, using NLP, the technology can add context to a condition that is mentioned and map these concepts to a vocabulary of tens of thousands of medical conditions.
As an example, one clinician might write “multiple sclerosis exacerbation” while another might document the same problem as “MS flare.”
Care Studio is able to recognize that these different terms are linked to the same condition and supported by the same evidence, he said.
When a clinician clicks on a condition, such as diabetes, they will see blood sugar levels, insulin administrations, endocrinology consult notes, and retinopathy screening studies, according to Muret.
In addition, if important information is missing, Google’s tool will highlight its absence from the chart.
If standard labs for a diabetic patient, such as hemoglobin A1c results, are missing, the technology will alert the user.
He explained that with these resources, a clinician can quickly understand a new patient’s medical history or easily review an existing patient’s insulin regimen before their appointment.
According to Muret, conditions are organized by acuity so that a clinician can quickly determine whether a patient’s condition is acute or chronic.
Liked this article? Sign up to receive our regular email newsletters, focused on Africa and World’s healthcare industry, directly into your inbox. SUBSCRIBE HERE