ViVE 2022: Google Health expands AI capabilities of Care Studio to organize patient data

MIAMI—Google Health is expanding the capabilities of its clinician-facing search tool using artificial intelligence to bring context to physicians' clinical notes.

Speaking at the ViVE 2022 conference, 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 different sources and helps organize patient data.

The new Conditions feature uses natural language processing (NLP) to provide physicians with a dynamic list of conditions pulled from the patient record plus related information including 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."

Getting a holistic summary of a patient's medical history can be challenging, as key clinical insights are often buried in unstructured notes and data silos. With the new Conditions feature, Google uses its deep understanding of data to provide a quick and concise summary of a patient’s medical conditions along with critical context from clinical notes, Muret wrote in a blog post.

Care Studio was born out of Google's partnership with Ascension to pilot an electronic health record search tool that pulls patient electronic health records into an interface to help clinicians more easily find useful information.

The tech giant and Ascension faced criticism in 2019 when news broke about a health data partnership between the two organizations, sparking potential privacy concerns. David Feinberg, M.D., the former head of Google Health, quickly took to the web at the time to directly address controversy swirling around Google's data deal with Ascension.

In a blog post and video, Feinberg, a physician and healthcare executive, clarified how the tech giant is using Ascension's data to build "an intelligent suite of tools for clinicians, including a tool that aims to make health records more useful, more accessible and more searchable by pulling them into a single, easy-to-use interface for doctors."

In February 2021, Beth Israel Deaconess Medical Center also signed on to pilot the clinical search tool, since named Care Studio.

Google is using its expertise with search tools to design software that offers clinicians a longitudinal view of patient records and the ability to quickly search through those records using a single secure tool.

Healthcare data are structured in numerous ways, making them difficult to organize. Clinician notes also differ based on whether content is meant for clinical decision making, billing or regulatory uses, Muret said in the blog post. When it comes to writing notes, clinicians use different abbreviations or acronyms depending on their personal preference, what health system they’re a part of, their region and other factors. 

With this latest feature, Google Health applied artificial intelligence to understand medical concepts from notes that may be written in incomplete sentences, shorthand or with misspelled words. Using NLP, the technology can add context for a condition that is mentioned and map these concepts to a vocabulary of tens of thousands of medical conditions, according to Muret.

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.

If a clinician clicks on a condition like diabetes, they may see blood sugar levels, insulin administrations, endocrinology consult notes and retinopathy screening studies, Muret explained. And, if critical information is missing, Google's tool will highlight its absence from the chart.

The technology will flag if standard labs for a patient with diabetes are missing, like hemoglobin A1c results. 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, he said.

Conditions are organized by acuity, so a clinician can quickly determine whether a patient’s condition is acute or chronic, according to Muret in the blog post.