Also: This open textbook (or wiki channel) is intended to help librarians and other information professionals learn about AI. It is not, in itself, meant to be seen as promotion of AI. If anything, the goal is harms mitigation or harms reduction.
Introduction
Abridge https://www.abridge.com/ is a generative artificial intelligence (GenAI) platform that assists clinicians by automatically recording, transcribing, summarizing, and documenting conversations between healthcare providers and patients. Founded in 2018 by cardiologist and entrepreneur Dr. Shiv Rao, Abridge aims to reduce administrative burden while improving the quality and efficiency of clinical documentation.
Using large language models (LLMs) and automatic speech recognition (ASR), Abridge listens to clinical encounters (with patient consent), identifies medically relevant information, and generates structured clinical notes that can be reviewed and edited by clinicians before integrated into the electronic health record (EHR). The platform supports multiple note formats, including SOAP notes, and integrates with major EHR systems. Since the widespread adoption of generative AI following the release of large language models in 2022–2023, Abridge has become one of the leading examples of "ambient clinical intelligence"—AI systems designed to work unobtrusively during clinical encounters by automating documentation tasks.
Discussion
Healthcare documentation is a significant contributor to clinician workload and burnout. Physicians frequently spend hours each day completing electronic health record documentation, often after patient visits have ended ("pajama time"). Ambient AI tools such as Abridge seek to shift clinicians' attention away from computers and back toward patients by automating note creation.
Abridge combines several AI technologies:
Automatic speech recognition (ASR) to convert spoken conversations into text.
Large language models (LLMs) to summarize clinically relevant information.
Natural language processing (NLP) to identify diagnoses, medications, procedures, and follow-up plans.
Clinical validation mechanisms that link generated summaries to supporting portions of the original conversation for transparency.
The platform is designed as a "human-in-the-loop" system. Clinicians remain responsible for reviewing, editing, approving, and signing all documentation before it becomes part of the permanent medical record.
Reported benefits include:
Reduced documentation time.
Improved clinician satisfaction.
Greater patient engagement through increased eye contact and conversation.
More consistent and complete clinical documentation.
Potential reductions in clinician burnout.
Several large health systems in North America have implemented or evaluated Abridge, reflecting growing interest in AI-assisted clinical documentation.
Presentation
Guest: Dr Jessica Morley — Associate Research Scientist, Yale Digital Ethics Center; formerly UK Department of Health and Social Care and the Bennett Institute, University of Oxford. Morley argues we systematically overestimate what these tools can do and underestimate the harm. She makes the case for "skeptical optimism," explains why bioethics principles built for one-to-one care break down against many-to-many AI harms, and reframes ambient scribes as inference engines rather than transcription services — with real consequences for coding, billing and patient records. Then she gets practical: the guardrails, prompts and habits patients (and clinicians) can use today.
Note: Please use your critical reading skills while reading entries. No warranties, implied or actual, are granted for any health or medical search or AI information obtained while using these pages. Check with your librarian for more contextual, accurate information.
