Microsoft empowers health organizations with generative AI and actionable data insights

October 21, 2023

This post was co-authored by Naveen Valluri, General Manager, Health Data & AI, Microsoft Health & Life Sciences.

In the past year, AI has transformed what we thought was possible and opened up new avenues for groundbreaking transformations. From creating personalized treatment plans to extracting insights from XRAYs and MRIs, generative AI has made the concept of artificial intelligence real—and accessible, such as with Azure AI Health Bot. For the healthcare industry, this might mean the beginning of a transformative era that changes how healthcare is delivered and accessed—making precision medicine truly individualized, speeding up groundbreaking research for life threatening diseases, and finding new and innovative ways to improve patient care.

Making AI and machine learning real and actionable starts with the data being analytics ready. Healthcare data has been growing at an exponential rate and most healthcare organizations don’t know where to start with organizing that data. It is usually on-premises, siloed, and hard to navigate. The very first step would be to make this data accessible and normalize it in a way that makes it ready for analytics and AI in the cloud. Industry-specific solutions in Microsoft Fabric provide relevant solutions that unify data and insights for healthcare organizations through one common architecture and experience. Now available in preview, healthcare data solutions in Microsoft Fabric eliminate the costly, time-consuming process of stitching together a complex set of disconnected, multi-modal health data sources—text, images, video, and more—and provide a secure and governed way for organizations to access, analyze, and visualize data-driven insights across their organization.

We’re making several exciting announcements about new data and AI capabilities that will be introduced across the Microsoft Cloud for Healthcare to help health organizations improve patient experience, gain new insights with machine learning and AI, and handle health information securely. Features like de-identification service and getting insights from unstructured text will also be available soon in Fabric. We’re pleased to announce:

  • General availability of multi-language support in Text Analytics for health, an Azure AI Language service. Healthcare organizations worldwide can use the Text Analytics for health service to extract meaningful insights in six languages in addition to English—Spanish, French, German, Italian, Portuguese, and Hebrew—making this technology more accessible to health organizations worldwide and improving health equity on a global scale.
  • De-identification service (in preview) in Microsoft Fabric and Azure Health Data Services so organizations can de-identify medical data such that the resulting data retains its clinical relevance and distribution while also adhering to the HIPAA privacy rule. Our service supports unstructured text and will soon cover various other data types (structured, imaging, and MedTech). The service uses state-of-the-art machine learning models to automatically extract, redact, or surrogate over 30 entities—including HIPAA’s 18 protected health information (PHI) identifiers—from unstructured text such as clinical notes, messages, or clinical trial studies.
  • Expansion of our Azure AI Health Bot in preview to allow healthcare organizations to build copilots for their healthcare professionals to further manage administrative and clinical workloads as well as improve patient experiences. Azure AI Health Bot is designed to help healthcare organizations create specialized chatbot experiences which are now powered by generative AI, enabling high-value conversational scenarios for the health and life sciences industry.
  • Adding three new built-in models in preview to Azure AI Health Insights. These built-in models create actionable, chronological patient timelines based on clinical data and evidence, provide simplified, patient-friendly versions of clinical notes and reports, and surface radiology insights from radiology reports to help radiologists improve their workflow.

Building a healthcare ecosystem with a partner network 

In addition to our exciting product announcements, Wolters Kluwer also announced that its Health Language Platform, a Fast Healthcare Interoperability Resources (FHIR®) terminology server, will work with Microsoft Azure and Azure Health Data Services to help customers enrich and standardize their healthcare data with medical ontologies on Microsoft Azure.  

Customers onboarding to Azure will be able to access Wolters Kluwer’s Health Language Platform via Azure Marketplace to validate and translate their FHIR data so that it is ready for future analysis. Organizations can achieve semantic interoperability across multi-modal data sources to propel a range of use cases across healthcare. 

Working with our partner ecosystem, Microsoft is committed to continuing to develop healthcare technology that helps our customers use Microsoft Cloud to derive insights from their data and responsibly use AI. By connecting our customers with the right partners in our ecosystem and giving them access to Azure Marketplace, we want to ensure they have access to the right building blocks for their organizations use case.  

Real-world innovation in healthcare

By combining Microsoft Cloud for Healthcare services and tools, health organizations are coming up with new and innovative solutions to meet their unique needs.

For example, let’s say a researcher is working on a new drug for Alzheimer’s disease and needs to find suitable patients with specific symptoms and diagnoses to work on a hypothesis. First, they would de-identify their raw data so that they can use it for their research. If we look at this from the perspective of the clinician, they may want to look at a specific set of patients to see if there are any similarities and patterns that may help them with treatment plans for specific patients. Once they have established this, they can then gather from clinical notes they may have missed to ensure they have the full picture. When writing out their report and prescriptions for the patient, the clinician can opt to simplify their note using AI, making the note much easier for the patient to read as it will exchange complicated terminology for something easier to understand.

Next, a patient who has been diagnosed with Alzheimer’s disease takes the leading role. They are interested in finding more information about their prescription medications in the report which they were able to understand much more easily than before due to the lack of medical jargon. They find that their hospital website has a chatbot and are easily able to interact with them to get answers about their medications and set up appointments if they want.

And that’s just one possibility. Whether it’s finding new treatments, enhancing patient engagement, or optimizing workflows, Microsoft Cloud for Healthcare can help healthcare organizations achieve more.

Helping solve healthcare’s biggest problems

At Microsoft, we want to empower you in solving the challenges you face on a day-to-day basis—whether it be reducing clinician burnout or delighting your patients with personalized care—and to do these—allowing you to gain insights from your data and develop and deploy AI at scale.

With the help of Dataside, a Microsoft partner in Brazil, Oncoclínicas is using Microsoft’s Azure AI text analytics for health to extract data from non-structured fields like medical notes, anatomic pathology, genomic, and imaging reports like MRI. This data was then used by Dataside for various use cases such as clinical trial feasibility, a better understanding of the scenarios for pharmacoeconomics, and gaining a deeper understanding of group epidemiology and outcomes of interest.

“Text Analytics for health was a turning point for Grupo Oncoclínicas to scale our processes and to structure our clinical notes, exam reports and field analysis, which previously only depended on manual curation. Having a solution that works in Portuguese is key—most global solutions tend to only cater to English, thereby neglecting other languages. Accuracy in the native Portuguese allowed us to maintain a high level of accuracy while analyzing the unstructured text.”—Marcio Guimaraes Souza, Head of Data and AI at Grupo Oncoclínicas.

“We are excited to be collaborating with Microsoft to explore the potential of generative AI through the Azure AI Health Bot. This partnership aims to enhance healthcare content utilization at Ramsay Healthcare, offering a transformative way for healthcare professionals to engage with the vast clinical knowledge base. Our innovative solution facilitates seamless and efficient interactions, providing healthcare teams with quick access to answers, recommendations, and inventive troubleshooting solutions, all delivered through an intuitive chat interface. We are confident that it holds the promise to play a pivotal role in our daily operations, reducing time to find relevant content, and potentially revolutionizing the way we provide patient care.”—Towa Jexmark, Head of Innovation and Strategic Partnerships at Ramsay Santé.

Do more with your data with Microsoft Cloud for Healthcare

With Microsoft Cloud for Healthcare, organizations can transform their patient experience, discover new insights with the power of machine learning and AI, and manage PHI data with confidence. Enable your data for the future of healthcare innovation with Microsoft Cloud for Healthcare.

We look forward to working with you as you build the future of health.


FHIR® is the registered trademark of HL7 and is used with the permission of HL7.

The post Microsoft empowers health organizations with generative AI and actionable data insights appeared first on Azure Blog.