David Liu, Amanda Centi PhD, Matthew Butler MBA, Rebecca Mishuris MD MPH, Haipeng Zhang DO
Haipeng Zhang DO
Generative AI (GenAI) refers to a subset of artificial intelligence that focuses on generating new data samples, often leveraging deep learning models such as Generative Adversarial Networks (GANs). In medicine, GenAI promises various transformative advancements including drug discovery, clinical note automation, and personalized patient treatment plans. As the medical landscape rapidly evolves, understanding the applications of GenAI becomes paramount. Mass General Brigham (MGB), a leading healthcare system, must remain closely involved and informed to lead innovation. Thus, it is urgent and necessary to first map the internal landscape of MGB’s GenAI endeavors. In this study, we 1) identified current projects across MGB and its affiliated hospitals through database searches and interviews with project leaders, and 2) synthesized our findings to evaluate the trends in the development of GenAI at MGB. To date, we have found 32 past or current research projects or use-cases involving GenAI at MGB. GenAI use cases at MGB are very broad, including biomedical engineering, radiological image improvement, space medicine, medical education, ophthalmology, neurology, logistical operations, electronic medical record analysis, genetics, clinical note automation, and MyChart patient interaction. We will continue our search and we anticipate identifying more early-stage research and use-cases.
Generative AI (GenAI) is a type of artificial intelligence that learns from patterns to create new data. One popular example is OpenAI’s ChatGPT that you can converse with on any topic without prior training of ChatGPT on that topic. In medicine, the applications of GenAI are vast and include creating new therapeutic drugs, helping scribe patient visit notes, and personalized patient treatment plans. For Mass General Brigham (MGB), a leading healthcare system, it is important to be up-to-date and lead positive changes for medicine using GenAI technology. Therefore, in this study, we 1) searched the web and conducted interviews to find examples of GenAI being used by researchers and clinicians at MGB and 2) used our findings to evaluate the trends of GenAI at MGB. We have found 32 projects so far but are continuing to find more projects through research and interviews. The scope of these projects is broad and includes biomedical engineering, radiology, space medicine, medical education, ophthalmology, neurology, genetics, and workflow optimization for healthcare providers. The results of this study can be used to inform 1) where MGB is right now with GenAI research and 2) what direction we need to go in the near future.