Microsoft on Wednesday announced the inclusion of text analytics capabilities within its Azure Cognitive Services product.
According to the software giant, the Text Analytics for health feature can process a wide variety of data types and tasks, including extracting more than 100 types of personally identifiable information (including protected health information) from unstructured text.
The new preview feature can also associate words or phrases in text with semantic entities – such as illness symptoms; diagnosis; medication name and class; and dosage – and identify connections between concepts.
“Trained on a diverse range of medical data – covering various formats of clinical notes, clinical trials protocols, and more – the health feature is capable of processing a broad range of data types and tasks, without the need for time-intensive, manual development of custom models to extract insights from the data,” said Hadas Bitran, Microsoft Healthcare group manager, in a blog post accompanying the announcement.
WHY IT MATTERS
According to Microsoft, Text Analytics for health can help providers, companies and researchers construct insights and connections from unstructured English-language medical data. The software also supports the detection of modifiers like negation – such as when notes mention that a patient has not been diagnosed with something.
“Text Analytics for health enables researchers, data analysts, medical professionals and [independent software vendors] in the healthcare and biomedical space to unlock a wide range of scenarios – like producing analytics on historical medical data and creating prediction models, matching patients to clinical trials, or assisting in clinical quality reviews,” said Bitran.
As one example, Bitran noted, Microsoft used Text Analytics along with the company’s Cognitive Search to develop the COVID-19 search engine. The tool allows researchers to search more than 47,000 scholarly articles for relevant information amidst the sometimes overwhelming amount of content regarding the novel coronavirus.
Liam Cavanagh, Azure Cognitive Search team principal program manager, explained in an accompanying video, “We took a set of open data sets provided by the Semantic Scholar,” part of the Allen Institute for AI providing up-to-date research papers.
TA for health, Cavanagh continued, “allows us to extract out all the important medical entities … that are discussed within that content and then tag it.”
“We wanted to make it so that you could really find what you’re looking for,” Cavanagh said. “So that even if you search for a very specific term, we wanted to use some AI capabilities … based on what we know of that content, here are some other terms you could consider using to find more relevant information.”
THE LARGER TREND
Other major software companies have pinpointed the advantages of using artificial intelligence to extract information from unstructured text, especially where healthcare data is concerned.
In late 2018, Amazon Web Services announced the launch of its Amazon Comprehend Medical, a HIPAA-eligible tool to help process unstructured data and identify patient information.
“The process of developing clinical trials and connecting them with the right patients requires research teams to sift through and label mountains of unstructured medical record data,” said Fred Hutchinson Cancer Research Center Chief Information Officer Matthew Trunnell.
Meanwhile, earlier this year, SAS released its own COVID-19 search tool, which can extract text and numerical data from more than 50,000 research articles and allow users quick access to relevant information.
ON THE RECORD
“The healthcare industry is overwhelmed with data. Much of this healthcare data is in the form of unstructured text, such as doctor’s notes, medical publications, electronic health records, clinical trials protocols, medical encounter transcripts and more,” said Bitran.
“Healthcare organizations, providers, researchers, pharmaceutical companies, and others face an incredible challenge in trying to identify and draw insights from all that information. Unlocking insights from this data has massive potential for improving healthcare services and patient outcomes,” Bitran continued.
Kat Jercich is senior editor of Healthcare IT News.
Twitter: @kjercich
Healthcare IT News is a HIMSS Media publication.
Source: Read Full Article