This book starts with discussions over how large language models are used in healthcare and the opportunities we have to change portions of the healthcare paradigm. There are amazing opportunities to save both time as a business unit as well as improve patient experiences.
Large language models (LLMs) are machine learning models that can comprehend and generate human language text. They work by analyzing massive data sets of language. They can be used for text generation, a form of generative AI, by taking an input text and repeatedly predicting the next token or word. Some notable LLMs are OpenAI's GPT series of models, Google's PaLM and Gemini, and Meta's LLaMA family of open-source models to name a few.This book starts with discussions over how large language models are used in healthcare and the opportunities we have to change portions of the healthcare paradigm. There are amazing opportunities to save both time as a business unit as well as improve patient experiences. The book then continues with broad-reaching descriptions of what is reasonable to expect and not expect a large language model to be able to accomplish. The author also discusses why large language models are important and how they are going to change the industry with a detailed description of large language models. He brings a highly technical discussion of vector maths and interprets it to something that non-specialists can understand. He also explains how large language model transformers work and why we’ve seen success in image generation, language generation, and implementation. Also provided is a discussion of the planning and strategy for implementing LLM solutions and recommendations for measuring their impact. Finally, the book discusses future trends in healthcare LLMs, emerging technologies and their potential impact in the coming years and decades.
Chapter 1: Introduction to Large Language Models for HealthcareChapter
2: Who Makes the BEST ExpertChapter 3: Understanding the Technology Behind
LLMsChapter 4: The Current State of LLMs in HealthcareChapter 5: The Data
that Feeds LLMsChapter 6: Basic Prompt EngineeringChapter 7: Prompt
Engineering versus Fine-TuningChapter 8: In-house Development of LLMs for
Healthcare ApplicationsChapter 9: Evaluating LLM Vendors' Maturity for
HealthcareChapter 10: Bias in LLMs and Its Implications for HealthcareChapter
11: Ensuring Compliance and Ethical UseChapter 12: LLMs in Clinical Decision
Support SystemsChapter 13: Patient Engagement and LLMsChapter 14: Training
and Educating Healthcare Professionals on LLMsChapter 15: Security and
Privacy Concerns with Healthcare LLMsChapter 16: The Role of
Interdisciplinary Teams in LLM ProjectsChapter 17: Implementing LLM
SolutionsChapter 18: Integration with Electronic Health RecordsChapter 19:
Measuring the Impact of LLMs in HealthcareChapter 20: Looking Ahead: The
Future of Healthcare with LLMs References
Jeremy Harper is President of Owl Health Works, a consulting firm providing quality management, health informatics, and business services for their clients. He has 20 years of healthcare industry experience including academic medical centers, community hospitals, and software vendors. As an executive, his responsibilities have included planning, implementation, and management of deployments and enterprise-enhancing initiatives. He is an authority for best practices in artificial intelligence/machine learning, business strategy, data management, transformations, turnarounds, and organization growth strategies.
