Is quality measurement about proving, or improving? Is it about helping clinicians provide better care, or about satisfying funders and regulators? The answer has usually been: both. The tension between proving and improving explains much of where quality measurement has been, and why it may need a new direction. In the United States, quality measurement …
My previous article [1] discussed the fact that large language models lack a formal model of the physical world in which care takes place. This is a problem for AI in healthcare. Healthcare may be described in language but health care, disease, and its treatment are not linguistic phenomena. They are part of the physical …
Five ideas from a new paper In an earlier article, I wrote about artificial intelligence (AI) world models: systems built to represent how the world behaves and changes over time, rather than working only via language and other static data. An April 2026 paper (preprint) takes that idea into medicine. Its main argument is that …
Years ago, my hospital in the US was considering buying an anaesthesia information system. This was a major purchase in the 1-2 million dollar range. The system would automatically record vital signs, document anaesthesia care and become part of the daily workflow of every operating room (OR) in a large academic medical center. During the …
Large language models (LLMs) are now routinely used to write clinical notes, discharge summaries, referral letters, patient instructions and insurance correspondence. Their appeal is obvious: they are fast, fluent and usually accurate. As the documentation burden increases and clinical time shrinks, AI-generated text is becoming embedded in everyday clinical workflows. The dominant safety response has …
Development of artificial intelligence (AI) is moving along two distinct paths. The last decade has been centred on large language models (LLM) that generate fluent text by predicting the next word in a sequence. A newer approach focuses on building world models – systems that learn how the physical world behaves and changes over time. …
World models and word models: layers of the AI cake Read More »
Intraoperative EEG-guided depth of anaesthesia monitoring may reduce postoperative complications such as delirium, but the evidence is mixed. This uncertainty is a useful lens for seeing how clinical evidence is produced, evaluated and trusted. A brief report We examined the association between intraoperative EEG-based depth of anaesthesia (DoA) guidance and postoperative delirium in a retrospective …
Plausibility is not proof: what two studies reveal about trust in clinical research Read More »
Artificial intelligence (AI) is a set of technologies that will profoundly impact healthcare in all dimensions of quality. At times, however, the AI industry and the community of healthcare quality specialists talk past each other. This is because they operate with different epistemologies – the term for descriptions about what we treat as knowledge, how …
Albert Invent is a new software platform for chemists and materials scientists – the people who combine substances in the lab to make products for the modern world. The company doesn’t disclose who or what it is named after. Albert Einstein seems the reasonable guess. But an even better fit is someone further back in …
It’s common for private doctors in Mexico City, and across Latin America, to wake up each morning and be greeted by 100 or more WhatsApp messages. The messages typically contain urgent clinical concerns mixed with routine administrative requests. Often, no clinical record is available at the point of review to help the practitioner deal safely …
WhatsApp is part of healthcare: how can it be used safely and reliably? Read More »
