DBT Bureau
Pune, 10 Oct 2024
Microsoft Corp. is unveiling several Microsoft Cloud for Healthcare innovations that connect care experiences, enhance team collaboration, empower healthcare workers, and unlock clinical and operational insights.
Through new healthcare AI models in Azure AI Studio, capabilities for healthcare data solutions in Microsoft Fabric, the healthcare agent service in Copilot Studio, and an AI-driven nursing workflow solution, Microsoft Cloud for Healthcare is supporting healthcare organizations on every step of their journey toward shaping a healthier future.
“We are at an inflection point where AI breakthroughs are fundamentally changing the way we work and live,” said Joe Petro, corporate vice president, Healthcare and Life Sciences Solutions and Platforms at Microsoft. “Across the broader healthcare and life sciences industry, these advancements are dramatically enhancing patient care and also rekindling the joy of practicing medicine for clinicians. Microsoft’s AI-powered solutions are helping lead these efforts by streamlining workflows, improving data integration, and utilizing AI to deliver better outcomes for healthcare professionals, researchers and scientists, payors, providers, medtech developers, and ultimately the patients they all serve.”
Expanding the reach of AI beyond text: healthcare AI models in Azure AI Studio
Microsoft is announcing the launch of healthcare AI models, a collection of cutting-edge multimodal medical imaging foundation models available in the Azure AI model catalog. Developed in collaboration with partners like Providence and Paige.ai, these models enable healthcare organizations to integrate and analyze diverse data types — ranging from medical imaging to genomics and clinical records. By using these advanced models as a foundation, healthcare organizations can rapidly build, fine-tune and deploy AI solutions tailored to their specific needs, all while minimizing the extensive compute and data requirements typically associated with building multimodal models from scratch.
“The development of foundational AI models in pathology and medical imaging is expected to drive significant advancements in cancer research and diagnostics,” said Carlo Bifulco, MD, chief medical officer of Providence Genomics and a co-author of the Prov-GigaPath study. “These models can complement human expertise by providing insights beyond traditional visual interpretation and, as we move toward a more integrated, multimodal approach, will reshape the future of medicine.”
Harnessing the power of healthcare data with Microsoft Fabric
Historically, healthcare data has been difficult to access due to its unstructured nature and the limitations of existing data management systems. These challenges have limited organizations’ ability to gain a comprehensive view of patient experiences and access valuable insights.
With the general availability of healthcare data solutions in Microsoft Fabric, healthcare organizations can overcome these barriers by reshaping how users access, manage and act on data with a single, unified AI-powered platform. Additionally, healthcare security application templates for Microsoft Purview, an innovative suite of features designed to help govern healthcare data, are available in public preview. We’re also launching new capabilities in public preview within healthcare data solutions in Microsoft Fabric including:
Conversational data integration: Send conversational data, such as patient conversations, from DAX Copilot to the Fabric platform. By sending DAX Copilot audio files, transcripts and draft clinical notes to Fabric, customers and partners can leverage various native tools in Azure and Fabric to analyze this data and/or combine it with other data to generate comprehensive insights.
Social determinants of health (SDOH) public dataset transformation: Ingest, persist, harmonize and consume SDOH national and international public datasets to enable healthcare organizations to identify risks and health-related social needs to help create equitable healthcare for all patients and communities.
Centers for Medicare & Medicaid Services (CMS) claim and claim line feed (CCLF) data ingestion: Streamline the ingestion of claims data and harmonize with clinical, imaging and SDOH data to unlock actionable insights on patients and populations.
Care management analytics: Leverage unified healthcare data and care management analytical templates to enhance patient care by identifying high-risk individuals, optimizing treatment plans and improving care coordination.
Data discovery and cohorting: Utilize an integrated workflow that allows healthcare organizations to create, manage, analyze and share patient cohorts.
Building a safe and responsible healthcare agent
Healthcare organizations face numerous challenges, including workforce shortages, rising costs and increasing patient care demands. Generative AI offers a potential solution to these challenges by automating administrative tasks, analyzing vast amounts of data for actionable insights and assisting healthcare professionals in decision-making.
To address this, Microsoft is announcing the public preview of healthcare agent service in Copilot Studio to build Copilot agents for appointment scheduling, clinical trial matching, patient triaging and more. Organizations can leverage the healthcare agent service to help create connected patient experiences, improve clinical workflows, and empower healthcare professionals while helping organizations meet industry expectations with Microsoft Copilot Studio. Early adopters, like Cleveland Clinic, which provided feedback to help optimize the solution for a healthcare setting, are already using these innovations to enhance patient experiences and improve operational efficiency.
Enhancing nursing workflows with AI: nursing early outcomes
With the World Health Organization (WHO)1 predicting a shortage of 4.5 million nurses by 2030, the urgency to deliver technology to support the nursing profession is felt more than ever.
Last month at Epic’s UGM, we announced the next focus area for our collaboration in Epic Workshop. Today, we’re sharing more about how we’re actively collaborating with several leading healthcare organizations — including Advocate Health, Baptist Health of Northeast Florida, Duke Health, Intermountain Health Saint Joseph Hospital, Mercy, Northwestern Medicine, Stanford Health Care, and Tampa General Hospital — to build an AI solution using ambient technology that addresses nursing documentation by drafting flowsheets for review, allowing nurses to focus less on paperwork and more on their patients. This innovation expands on the company’s long-standing strategic collaboration and joint development initiatives with Epic.
“AI is transforming nursing workflows by streamlining administrative tasks, allowing nurses to focus more on patient care,” said Corey Miller, vice president of R&D at Epic. “Together with Microsoft, we’re using AI-powered ambient voice technology to populate patient assessments. Nurses using the tool are already sharing positive feedback on how it enhances personalized patient interactions.”
“For nurses, the integration of AI-driven solutions into our workflows is a game changer,” said Terry McDonnell, DNP, ANCP-BC, senior vice president and chief nurse executive, Duke University Health System, vice dean for Clinical Affairs, Duke University School of Nursing, Duke Health. “It allows us to focus more on patient care rather than the administrative burden of documentation. By automating tedious tasks, Microsoft’s ambient AI solution helps alleviate burnout and gives us more time to connect with our patients at the bedside, where we truly make a difference.”
Empowering responsible AI practices across healthcare
In line with Microsoft’s dedication to responsible AI, these new solutions adhere to the company’s AI principles established in 2018 to help guide AI development and use. Microsoft remains committed to developing responsible AI by design, ensuring that these technologies positively impact both the healthcare ecosystem and broader society. In practice this means properly building, testing and monitoring systems to avoid undesirable behaviors, such as harmful content, bias, misuse and other unintended risks. Over the years, we have made significant investments in building out the necessary governance structure, policies, tools and processes to uphold these principles and build and deploy AI safely. At Microsoft, we are committed to sharing our learnings on this journey of upholding our Responsible AI principles with our customers. We use our own best practices and learnings to provide people and organizations with capabilities and tools to build AI applications that share the same high standards we strive for.
