In a groundbreaking collaboration, China Medical University Hospital (CMUH) has harnessed the power of Google Cloud’s generative AI to enhance cancer care services for patients. The formal agreement between CMUH and Google Cloud, signed in December of the previous year, introduced MedLM, a healthcare-specific generative AI model based on the extensive language model, Med-PaLM 2.
MedLM, boasting an intelligence score comparable to licensed doctors at 85% on the MedQA-USMLE (United States Medical Licensing Examination), now serves as the cornerstone for CMUH’s AI-assisted Physician system. This system aids doctors in disease diagnosis, treatment planning, patient education, and medical research.
The partnership’s primary focus is on providing assistive tools to support physicians in precision cancer treatment. Two generative AI-based tools have been developed thus far, streamlining the creation of cancer treatment plans, offering personalized treatment information to patients, and addressing health education inquiries:
Customized Cancer Treatment Guidelines: Developed in alignment with the National Comprehensive Cancer Network guidelines, this tool allows clinicians to efficiently gather accurate information, generate treatment plans, and provide personalized treatment recommendations for further review and use with patients.
Cancer Therapy Q&As: Integrated with CMUH’s cancer care-related health educational content, this system enables healthcare professionals to swiftly search for information and access comprehensive treatment options.
Furthermore, CMUH is utilizing Google’s AI accelerators, Tensor Processing Unit (TPU), to expedite the development of new drugs. Preliminary tests indicate that the AI can significantly reduce computation time related to protein folding “by over tenfold.”
CMUH stands out as an early adopter of MedLM among university hospitals in Asia, aiming to establish industry-leading healthcare AI models for the Chinese-speaking market and facilitate access to accurate medical information in the region.
Professor Der-Yang Cho, CMUH superintendent, emphasized the role of generative AI in precise and rapid data analysis for drug guidelines, disease gene sequencing, and medical records. The technology accelerates the discovery of novel treatments for challenging diseases, ultimately aiding in the development of effective treatment plans for patients.
Aashima Gupta, Global Director of Healthcare Strategy and Solutions at Google Cloud, highlighted how generative AI can alleviate the mental burden on healthcare staff by reducing workload, allowing clinicians to dedicate more time to patient care.
In Prof Cho’s words, “[Our collaboration with Google Cloud] positions smart hospitals in Taiwan [like ours] at the front of providing more precision- and safety-oriented support to healthcare professionals and patients alike.”
This initiative contributes to the broader efforts of CMUH’s Artificial Intelligence Center, which boasts over 20 AI-powered medical services. Notable applications include the Intelligent Anti-Microbial System (i.A.M.S.), recognized by HIMSS for its ability to predict sepsis risk, identify drug-resistant strains, make smart drug dosage recommendations, and automatically analyze drug interactions and allergy history.
CMUH’s digital health capabilities were further validated by achieving Stage 7 of the HIMSS Electronic Medical Record Adoption Model, Stage 7 of the Infrastructure Adoption Model, and Stage 6 of the Adoption Model for Analytics Maturity in the previous year. The hospital also secured the global third position in the 2022 HIMSS Digital Health Indicator.
Kathy Lee, Managing Director of Google Cloud, North Asia, emphasized the potential of generative AI solutions in addressing data challenges, stating, “Life sciences problems are fundamentally data problems, and this is where AI can fully unleash its potential. Generative AI solutions from Google Cloud can help healthcare and life sciences organisations operate more efficiently and improve patient outcomes.”
