A new textbook published by Springer will offer researchers and scholars a practical guide to the use of natural language processing (NLP) in biomedicine. Co-edited by Hua Xu, PhD, FACMI, vice chair and assistant dean of biomedical informatics at Yale School of Medicine, and Dina Demner Fushman, MD, PhD, the book discusses NLP methods, systems and applications as well as pedagogical features such as learning objectives, glossaries, references, key readings and example questions. Titled Natural Language Processing in Biomedicine: A Practical Guide, the book contains contributions from faculty in the department of biomedical informatics and data science, including Kalpana Raja, PhD, MRSB, CSci, and Na Hong, PhD, as well as a foreword written by Lucila Ohno-Machado, MD, PhD, MBA, chair and deputy dean of biomedical informatics and Waldemar von Zedtwitz Professor of Medicine and Biomedical Informatics and Data Science.
Natural Language Processing (NLP) is a major component of artificial intelligence (AI), and automates computer understanding of the meaning of text in a given document. The end goal of NLP, the authors suggest, is to approach human understanding of language. In biomedicine, NLP offers an attractive tool for researchers to efficiently extract useful information from clinical texts and biomedical literature.
Composed of 15 chapters, Natural Language Processing in Biomedicine introduces readers to NLP as a means of analyzing clinical text. The first section covers the bases of machine learning, deep learning algorithms and computational linguistics. In the second section, the authors focus on traditional biomedical NLP tasks and methods such as named entity recognition (identifying and categorizing entities within a text into specific categories such as people or medical codes) and relation extraction (detecting and classifying the relationships between entities mentioned in a text), as well as recent advancements created by large language models (LLM). The third section discusses various example systems and their applications in biomedical, clinical, social media, and other biomedical texts.
"With recent advancements in generative AI, there has been a notable increase in researchers from diverse fields such as computer science, medicine, and public health, developing and applying NLP technologies to healthcare," said Xu. "Addressing the challenge of effectively training individuals from varied backgrounds to develop and evaluate NLP methods tailored to the specific requirements of medical applications is crucial. This textbook aims to serve as a comprehensive resource, equipping NLP educators, researchers, and developers in the medical domain with the essential skills and knowledge necessary for success."
"Early-career researchers will find state-of-the-art research and challenges discussed in the book useful," said Hong, an instructor of biomedical informatics at Yale School of Medicine and contributor to the book. "Experienced professionals will be interested in the systematical organization and comprehensive methodologies in the field."
The book's contributors also include Steven Bethard, University of Arizona; Trevor Cohen, University of Washington; Murthy V. Devarakonda, Novartis; Marcelo Fiszman, Pontifical Catholic University of Rio de Janeiro; Carol Friedman, Columbia University; Dimitar Hristovski, University of Ljubljana; Andrej Kastrin, University of Ljubljana; Halil Kilicoglu, University of Illinois; Serguei Pakhomov, University of Minnesota; Amandalynne Paullada, University of Washington; Kirk Roberts, University of Texas Health; Abeed Sarker, Emory University; Yanshan Wang, University of Pittsburgh; Yonghui Wu, University of Florida; Meliha Yetisgen, University of Washington; and Rui Zhang, University of Minnesota.
The book is part of Springer's series on Cognitive Informatics in Biomedicine and Healthcare, edited by Vimla L. Patel.
The digital version of the book is available for free to members of the Yale community, with a hardcover edition to be released July 10, 2024.