Google AI Introduces MedLM: A Family of Foundation Models Fine-Tuned for Healthcare Industry Use Cases

Google Researchers have introduced a foundation of models fine-tuned for the healthcare industry, MedLM, which is currently available in the US. It is built on earlier research of Google in healthcare and medicine, Med-PaLM 2, a medically-tuned large language model. The MedLM consists of two models having separate endpoints and providing customers with additional flexibility for their use cases.  MedLM works brilliantly for answering medical Q&A and summarization.

The first model, a larger variant, is designed to handle intricate and complex tasks, while the second, a medium-sized model, offers flexibility for fine-tuning and scalability across various applications. The models, informed by specific healthcare and life sciences requirements, are poised to augment AI adoption in healthcare from basic functions to sophisticated workflows.

Google has collaborated with big organizations- HCA Healthcare, BenchSci, Accenture, and Deloitte to employ MedLM for various stages of healthcare, providing better performance and efficiency in the existing projects. MedLM in collaboration with HCA Healthcare, where the technology is integrated into Augmedix’s platform. The app, powered by MedLM, employs natural language processing to convert clinician-patient conversations into draft medical notes, complying with healthcare regulations. This automation not only enhances performance but also contributes to time savings, reduced burnout, and improved patient care.

In the realm of pre-clinical research and development, BenchSci is leveraging MedLM within its ASCEND platform. The goal is to accelerate drug discovery by enhancing the speed and quality of pre-clinical research. ASCEND, an AI-powered evidence engine, collaborates with MedLM to bolster the identification and classification of biomarkers, thereby streamlining the scientific discovery process.

Collaborating with Accenture, Google aims to leverage generative AI to enhance patient access, experience, and outcomes. By integrating Google Cloud’s Claims Acceleration Suite and MedLM, healthcare organizations can uncover new insights, ultimately leading to better patient outcomes. By piloting MedLM’s capabilities, Deloitte and Google Cloud aim to simplify information retrieval from provider directories and benefits documents, assisting contact center agents in identifying suitable providers based on various criteria.

All the projects have shown the use of MedLM can help the growth of AI in the healthcare and medicine industry. Looking ahead, Google Research plans to expand the MedLM suite by incorporating Gemini-based models to offer even more capabilities in the coming months. The collaborative efforts with industry leaders underscore the transformative potential of generative AI in healthcare. As the technology progresses, Google remains committed to ensuring a safe and responsible use of AI in healthcare, working closely with practitioners, researchers, and healthcare organizations to push forward breakthrough research in health and life sciences.