At the HIMSS24 event, Google Cloud announced several new solutions to help healthcare and life sciences organizations enable interoperability, build better data foundations for businesses, and deploy generative AI (gen AI) tools for improving patient outcomes.
Both healthcare administrative costs and physician burnout have been increasing substantially. There is also a shortage of over 10 million nurses worldwide. This creates a major opportunity for healthcare providers, payers, electronic health records (EHR) companies, and life science companies to build gen AI solutions that enable healthcare workers and other employees to work more efficiently and effectively.
Google Cloud’s Vertex AI Search for Healthcare – which launched today – helps developers build better assistive technology for clinicians and other health system workers to alleviate administrative burdens. And it enables medically-tuned and gen AI search on a broad spectrum of data such as FHIR data and clinical notes. These search and question-answering features now integrate with MedLM, Healthcare Data Engine (HDE), and Cloud Healthcare FHIR APIs. This makes it easier for healthcare and life science organizations to build the data analytics and AI solutions needed for next-era health systems.
The key Vertex AI Search for Healthcare includes these features:
1.) Medically-tuned search — By providing medically-tuned search on electronic health record (EHR) data, scanned documents, and other clinical data, healthcare applications can now surface the most relevant information for clinicians and others engaged in the decision-making and processing without having to click through hundreds of pages of notes or toggle between different screens and applications.
2.) Configurable cloud APIs—Healthcare application developers can utilize configurable cloud APIs to directly integrate the medically tuned search into the clinician workflow tools.
3.) Question-answering—Clinicians can now use the service to answer questions like “Does the patient have a history of cancer?” This typically involves understanding medical terminology related to cancers and the nuances of language in medical notes and scanned documents.
4.) Factuality – Since the results are based in the healthcare organizations’ real data, Vertex AI Search for Healthcare can cite and link to specific data points that generated the answers, providing transparency to users, increasing confidence in the responses, and helping reduce risks of hallucinations or inaccurate responses.
5.) Data platform integration – Gen AI and search applications require high-quality data to ensure that the outputs of gen AI are useful. HDE also offers automated tooling and components to build a unified, high-quality patient data platform quickly and easily. The out-of-the-box integration of Vertex AI Search with HDE enables search and summarization use cases without custom integrations.
6.) Deeper medical understanding – Even though MedLM tools work well in complex medical topics, Vertex AI Search for Healthcare provides medically-tuned search capabilities grounded in the patient record. And when combined, healthcare organizations can find the relevant answers to complex medical questions both from MedLM, and within the patient’s medical record. Select customers will have early access to Vertex AI Search for healthcare and life science integration with MedLM.
Google Cloud also revealed today a new consumption-priced managed service of Healthcare Data Engine (HDE) and expanded availability internationally with new features. The key features include:
1.) Simplified management and pricing—Customers can deploy HDE as a consumption-priced, pay-as-you-go, managed service, which opens up the product to more healthcare organizations and helps them deploy, build, and manage a near real-time healthcare data platform in the cloud.
2.) Global Availability – HDE expands beyond North America to most cloud regions in Europe and in the Asia Pacific.
3.) Low-code graphical data mapping IDE—By introducing HDE Data Mapper, a new low-code graphical integrated development environment (IDE) purpose-built by Google Research for healthcare, customers can easily transform their data to build high-quality longitudinal patient records in FHIR format to power next-gen AI applications.
4.) Foundation for AI and analytics solutions—By integrating HDE with Vertex AI Search for Healthcare, clinicians can search across multiple systems and formats in one search. This saves valuable time focused on patient engagement and improving overall patient experiences. The integration with MedLM enables customers to answer complex questions grounded in the patient’s data.
MedLM – a family of foundation models fine-tuned for the healthcare industry – will add two new capabilities for Google Cloud customers to explore/test. MedLM for Chest X-ray can help classify chest X-rays for operational, screening, and diagnostics use cases. This domain-specialized model is launched as an application programming interface (API) that converts chest x-ray images into embeddings. And app developers and data scientists can use these embeddings with ground truth labels to train a simple classification model in Vertex AI.
The second new capability is a task-specific API known as Condition Summary, which aims to highlight a chronological list of patient conditions with AI-generated briefs about each condition, with citations from the original text.
Over the next few months, Google Cloud plans to bring additional functionality to the MedLM suite to offer even more capabilities.
Google Cloud’s customers can retain control over their data. For healthcare settings, access and use of patient data are protected through the implementation of Google Cloud’s reliable infrastructure and secure data storage, which support HIPAA compliance, along with each customer’s security, privacy controls, and processes.
KEY QUOTES:
“Not all generative AI is created equal, and in healthcare, the stakes are particularly high. Healthcare organizations require enterprise-grade gen AI solutions, grounded in real data. Vertex AI Search for Healthcare is already making a difference for healthcare organizations by helping ensure clinicians have the right information and insights at the right time to inform decisions and improve the overall quality of patient care.”
– Aashima Gupta, global director for Healthcare Strategy & Solutions, Google Cloud
“At Highmark Health, we are constantly seeking ways to harness the power of data and technology to transform the healthcare ecosystem. Google Cloud’s Vertex AI Search integration with Healthcare Data Engine will enable us to provide even more personalized and proactive care to our members.”
– Richard Clarke, chief data and analytics officer, Highmark Health
“MEDITECH is dedicated to providing healthcare organizations with innovative tools to improve patient outcomes and streamline clinician experiences. The ability to quickly locate information within EHRs is a well-documented problem today. MEDITECH’s vision to embed search within the Expanse workflows allows us to leverage Google Clould’s AI capabilities to ease this burden. We will continue to empower clinicians with cutting edge decision making tools and enable clinician efficiency.”
– MEDITECH Executive Vice President and Chief Operating Officer Helen Waters
“At HCA Healthcare, we’re focused on integrating technology into solutions that will empower our clinicians to perform at the top of their license and deliver exceptional patient care. Google Cloud understands our commitment. Through our partnership and by deploying its Healthcare Data Engine, HCA Healthcare has the ability to harmonize data from disparate sources into a comprehensive longitudinal patient record, which is fundamental to our advanced analytics and Responsible AI initiatives.”
– Michael J. Schlosser, MD, MBA, FAANS, SVP, Care Transformation and Innovation, HCA Healthcare
“Oscar is focused on reorienting the healthcare system around the consumer. Our end-to-end tech stack enables us to capture the emerging opportunities of new technologies – from machine learning to generative AI – to deliver seamless experiences for members. We continue to partner with forward-looking companies like Google Cloud to accelerate our efforts and drive the change we want to see in healthcare.”
– Mario Schlosser, co-founder and Chief Technology Officer of Oscar Health
“Becoming the world’s most trusted wellbeing company is a complex journey, and one of the most critical foundational elements is a strong data strategy. Google Cloud’s Healthcare Data Engine, search and gen AI capabilities combined with our unmatched range of services and tools to support the total health and wellbeing of our global population, will help us streamline workflows at scale, unlock deeper insights from healthcare data, and ultimately drive better health outcomes for the nearly 70 million lives we serve worldwide.”
– Steve Fast, CIO, TELUS Health
