Innovations include Health Companion research project powered by agent AI
Additional early innovations will explore pressing care needs, including identifying new ways to detect breast cancer and improving the quality of care for mothers and babies.
CHICAGO, Oct. 21, 2024–(BUSINESS WIRE)–GE Healthcare (Nasdaq: GEHC) today announced a new AI Innovation Lab aimed at accelerating early-concept AI innovation within the company. . These projects are part of GE Healthcare's broader AI and digital strategy to integrate AI into medical devices, build AI applications that enhance decision-making across care journeys and disease states, and use AI to Our focus is on supporting better results and operational efficiency. The whole system. The company's investments in cloud technology support this strategy and provide the computing power to drive large-scale AI development.
“The AI Innovation Lab kickstarts the work we are doing at the forefront of healthcare innovation.At GE Healthcare, we are not just developing technology. ”For example, through projects like Health Companion, we bring the clinical knowledge and problem-solving insights of multidisciplinary medical teams to clinicians. We are evaluating how agent AI can be applied to deliver and assist clinicians in their actions. ” said Taha Kas Hout, Global Chief Science and Technology Officer, GE Healthcare. “The pioneering projects we are introducing today are just a few of the innovations we are making, enabled by our AI and cloud computing capabilities. We will find ways to help apply AI to data” and transform information into actionable care enhancement strategies. ”
GE Healthcare's AI and cloud-related R&D efforts are introducing new concepts to improve diagnostic accuracy, reduce administrative burden, and ensure all patients receive the most relevant information. We are focused on redefining the daily experience of clinicians by creating Care possible. Examples of these concept projects:
Use agent AI to put the knowledge of a multidisciplinary team at the fingertips of clinicians: In the Health Companion project, an agential AI approach driven by multiple agents, each agent being an expert in a particular field (genomics, radiology, pathology, etc.), will streamline and improve clinical decision-making for physicians. We are looking at whether we can provide personalized care. . The project's vision is for these agents to work together to analyze multimodal data and proactively generate treatment planning recommendations while continuously adapting based on new information. For example, GE HealthCare is studying whether multi-agent AI can understand the difference between a symptom expected as a result of a treatment and the same symptom as a signal of disease progression, such as cancer spread. , intended to alert the treatment team. The proposed next steps are appropriate. Health Companion is designed to provide the same collaboration and discussion as a multidisciplinary care team of expert clinicians. This project is built to incorporate the principles of safety and explainability.
story continues
Using AI to better predict recurrence in triple-negative breast cancer: GE Healthcare supports Emory University Winship Cancer Institute's research focused on early prediction of triple-negative breast cancer recurrence. Triple-negative breast cancer is the most aggressive breast cancer subtype, but tools to predict recurrence are lacking. Currently, as many as 50% of patients diagnosed with early stage triple-negative breast cancer (stages I to III) experience recurrence. i The goal of this study is to use deep learning to evaluate multimodal data, including genomic and pathological information, to investigate whether AI can more accurately predict the likelihood of recurrence and help care teams improve treatment outcomes. Help inform planning and monitoring schedules. This research was funded by a grant from the National Institutes of Health (NIH Grant# 1R01CA281932-01A1). The project's principal investigator (PI) is Dr. Sunil Badve of Emory University, and Dr. Soumya Ghose of GE HealthCare is a co-PI.
Innovative solutions to enhance mother and baby care: Preventable risks associated with childbirth are one of the most pressing health issues facing women today. GE Healthcare is working directly with health systems and their care teams to develop solutions to help address this challenge. For example, GE HealthCare is working on a Care Companion initiative that explores how generative AI can minimize the effort spent searching data and exploring best practices. Leveraging large-scale language models, this effort uses historical and current multimodal data that medical teams can easily find information about standard treatment protocols and clinical definitions, and potentially use for handoffs and transfers. The aim is to further explore ways to generate patient summaries using Transition of care.
Research on multimodal X-ray basic model: GE HealthCare is working on a research project to create a whole-body baseline model built on a dataset of 1.2 million anonymized PHI-free X-ray images taken from various regions of the body. The model shows great potential, with promising early internal benchmark tests on key tasks such as segmentation, classification, and visual localization. The project is also experimenting with automating the generation of medical reports with this model, with the aim of reducing the administrative burden on medical teams, and interpreting images into text to accelerate the workflow of radiologists. Masu. The goal of GE Healthcare's research in this area is to provide practical value by reducing the cognitive burden on healthcare professionals seeking efficient and reliable diagnostic tools. This model was developed as a result of a strategic collaboration between GE Healthcare and Amazon Web Services.
Helping radiologists expand mammography screening: Although approximately 90% of screening mammograms in the United States are normal, there is no efficient way for radiologists to quickly separate clearly normal scans from potentially suspicious scans. ii GE Healthcare is developing this cloud-based AI concept to explore how the underlying model can help. Clinicians can quickly identify routine breast screening tests, allowing radiologists to focus more time on suspicious cases. As countries grapple with radiologist shortages, GE Healthcare is working with strategic and clinical partners to advance in the field, increasing accuracy, expanding screening, and increasing access to this important type of preventive treatment. We aim to improve access globally.
GE Healthcare is committed to AI-powered innovations that span the spectrum of maturity and market readiness. For example, GE HealthCare has filed a 510(k) with the U.S. Food and Drug Administration (FDA) seeking approval for a new solution that addresses the needs of clinicians providing care for mothers and infants. This AI-powered Fetal Heart Rate Interpretation (FHR AI, FDA 510(k) submitted) III applies deep learning to waveform data to analyze fetal heart rate. This feature is designed to identify events such as accelerations or decelerations of the fetal heart rate to give care teams a quick picture of the baby's health, which is currently a highly manual and subjective task. Improve your current work.
These projects showcase the groundbreaking work underway at GE Healthcare. GE Healthcare applies its 125-year heritage of innovation and startup energy to solve the healthcare industry's most pressing challenges. GE Healthcare has been investing in AI for years and has topped the FDA's AI-enabled device approval list for three years in a row with 80 approvals. iv
For more information on these projects, visit GE HealthCare in the AI Pavilion, booth number 3816, at HLTH 2024 in Las Vegas, Nevada, October 20-23, or visit https://www.gehealthcare.com Please.
About GE Healthcare Technologies, Inc.
GE Healthcare is a world-leading medical technology, pharmaceutical diagnostics, and digital solutions innovator dedicated to providing integrated solutions, services, and data analytics to improve hospital efficiency, improve clinician effectiveness, and improve care. Increase accuracy and make your patients healthier and happier. Serving patients and healthcare providers for more than 125 years, GE Healthcare promotes personalized, connected and compassionate care while simplifying patient movement throughout the care pathway. Our imaging, ultrasound, patient care solutions and pharmaceutical diagnostics businesses work together to improve patient care from diagnosis to treatment and monitoring. We are a $19.6 billion company with approximately 51,000 colleagues working to build a world without limits in health care.
For the latest news, follow us on LinkedIn, X, Facebook, Instagram, and Insights. For more information, please visit our website https://www.gehealthcare.com/.
i National Institutes of Health, “Early prediction of lethal phenotype in triple-negative breast cancer using a multiscale, multimodality platform” https://reporter.nih.gov/project-details/10883284.
ii “Breast Cancer Screening (PDQ®) – Health Professional Edition,” March 28, 2024, https://www.cancer.gov/types/breast/hp/breast-screening-pdq.
iii FHR AI 510(k) has been filed with the FDA but is not currently marketed in the United States.
iv U.S. Food and Drug Administration, “Artificial Intelligence and Machine Learning (AI/ML)-Enabled Medical Devices,” August 7, 2024, https://www.fda.gov/medical-devices/software-medical-device- samd/artificial intelligence and machine learning-aiml-enabled-medical-devices.
View source version on businesswire.com. https://www.businesswire.com/news/home/20241021089725/ja/
contact address
GE Healthcare Media:
Sophia Mata-Leclerc
Director of Communication Science
Sofia.Mata-Leclerc@gehealthcare.com
