China Medical University Hospital uses Google Cloud’s generative AI to support doctors in providing cancer care.
In December last year, a formal partnership between CMUH and Google Cloud was signed to take advantage of this MedLMa healthcare-specific gene AI based on the large language model, Med-PaLM 2.
MedLM, which has proven to have intelligence comparable to that of licensed physicians by scoring 85% on the MedQA-USMLE (United States Medical Licensing Examination), has become the foundation of CMUH’s AI-enabled physician system for setting disease diagnoses, treatment planning and patient education and medical research.
According to a statement, their partnership aims to introduce tools to support doctors in precise cancer treatment. To date, they have developed two genAI-based tools that help develop cancer treatment plans, provide personalized treatment-related information to patients, and provide answers to patient health education questions:
-
Updated guidelines for the treatment of cancer: Developed based on National Comprehensive Cancer Network guidelines, allowing physicians to quickly capture accurate information. It can also generate cancer treatment plans and provide personalized treatment recommendations that doctors can review, edit and use with patients.
-
Questions and answers about cancer therapy: a system integrated with CMUH’s cancer care health education content. It helps healthcare professionals quickly search for information while providing comprehensive treatment options.
In addition, CMUH uses Google’s AI accelerators, TPU (Tensor Processing Unit), for the development of new medicines. Citing findings from preliminary testing, CMUH said the AI can help reduce the computational time associated with protein folding “by more than tenfold.”
WHY IT MATTERS
CMUH is an early adopter of MedLM among university hospitals in Asia. The hospital plans to use it to build industry-leading healthcare AI models for the region’s Chinese-speaking market while facilitating access to accurate medical information.
CMUH Superintendent Professor Der-Yang Cho noted how genAI can provide accurate and rapid data analysis for drug guidelines, disease gene sequencing and medical records, significantly accelerating the discovery of new treatments for difficult-to-treat diseases and the development of treatment plans for diseases. patients.
By reducing workload, genAI can ease the mental burden on staff and allow physicians to spend more time with their patients, said Aashima Gupta, Global Director of Healthcare Strategy and Solutions at Google Cloud.
“(Our partnership with Google Cloud) positions smart hospitals in Taiwan (like ours) is leading the way in providing more precision and safety-oriented support to both healthcare professionals and patients,” said Prof. Cho.
THE GREATER CONTEXT
MedLM contributes to the CMUH Artificial Intelligence Center’s foundational technology for the development of AI-powered medical services, which now include more than 20. One of the notable applications of AI is the Intelligent Anti-Mbiotic System (iAMS), a four-in-one platform that can predict sepsis risk, identify resistant strains, make smart dosing recommendations, and automatically compare drug interactions and allergy history.
iAMS was cited by HIMSS as a commendable example of EMR use during CMUHs extension for Phase 7 of the HIMSS Electronic Medical Record Adoption Model last year. In the same year, the hospital was also validated for phase 7 of the Infrastructure Adoption Model and phase 6 of the Adoption Model for Analytics Maturity. CMUH proved its capabilities in digital health in part through the use of AI and also ranked third globally in the 2022 HIMSS Digital Health Indicator.
ON THE RECORD
“Life sciences problems are essentially data problems, and this is where AI can fully unleash its potential. Generative AI solutions from Google Cloud can help healthcare and life sciences organizations operate more efficiently and improve patient outcomes,” said Kathy Lee , Managing Director of Google Cloud, North Asia.