China Medical University Hospital has entered into a formal partnership with Google Cloud, signing an agreement in December of the previous year to utilize Google Cloud's generative AI technology in supporting its healthcare professionals in cancer care. This collaboration involves the deployment of MedLM, a healthcare-specific generative AI model derived from the extensive language model, Med-PaLM 2. With its demonstrated intelligence comparable to licensed doctors, scoring 85% on the MedQA-USMLE, MedLM serves as the cornerstone of CMUH's AI-assisted Physician system. This system aids in disease diagnosis, treatment planning, patient education, and medical research endeavors.
Their collaboration is focused on implementing supportive tools to aid physicians in precision cancer treatment. To date, they have created two generative AI-powered tools to facilitate the formulation of cancer treatment strategies, deliver personalized treatment insights to patients, and address inquiries regarding patient health education. Furthermore, CMUH has adopted Google's AI accelerators, known as TPUs (Tensor Processing Units), for the advancement of novel drug development. Preliminary assessments have indicated that AI can significantly decrease the computation time associated with protein folding, exceeding a tenfold reduction according to CMUH's reports.
Among university hospitals in Asia, CMUH stands out as an early adopter of MedLM. The hospital's objective is to utilize this technology to pioneer cutting-edge healthcare AI models tailored for the Chinese-speaking market in the region. Simultaneously, it aims to enhance accessibility to reliable medical information. Professor Der-Yang Cho, the superintendent of CMUH, emphasized the potential of generative AI in delivering accurate and swift data analysis for drug guidelines, disease gene sequencing, and medical records. This capability holds the promise of significantly expediting the discovery of innovative treatments for challenging diseases and facilitating the development of personalized treatment plans for patients.
By reducing workload, genAI can help ease the mental burden of staff and allow clinicians to spare more time with their patients, added Aashima Gupta, global director of Healthcare Strategy and Solutions at Google Cloud. "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", Prof Cho said.
The MedLM technology enhances the existing infrastructure of the CMUH Artificial Intelligence Center, supporting the advancement of over 20 AI-driven medical services. Among these innovations is the Intelligent Anti-Microbial System (i.A.M.S.), a comprehensive platform capable of predicting sepsis risk, detecting drug-resistant strains, providing intelligent drug dosage suggestions, and automatically assessing drug interactions and allergy histories.
i.A.M.S. was acknowledged by HIMSS as a notable instance of EMR utilization during CMUH's reassessment for Stage 7 of the HIMSS Electronic Medical Record Adoption Model in the previous year. Concurrently, the hospital achieved validation for Stage 7 of the Infrastructure Adoption Model and Stage 6 of the Adoption Model for Analytics Maturity. Demonstrating its proficiency in digital healthcare, partly attributed to AI implementation, CMUH also attained the global third position in the 2022 HIMSS Digital Health Indicator rankings.
"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 organizations operate more efficiently and improve patient outcomes", said Kathy Lee, Managing Director of Google Cloud, North Asia.
