AI + physicians

Some enthusiasts believe that computers the answer to diagnostic errors.  As I have written before, the biggest problem with AI comes from data entry.  Who collects the data and who picks which data to enter? Mukherjee has an interesting article in the New Yorker about AI. The most powerful element in these clinical encounters, I realized, was not knowing that or knowing how—not mastering the facts of the case, or perceiving the patterns they formed. It lay in yet a third realm of knowledge: knowing why. AI does wonderful work when paired with a clinician who understands which data the computer needs. Our most important skill involves taking a history.  Experienced expert clinicians get so much more from the history than novices.  This fascinating article may provide some insights – Language: Why We Hear More Than Words … we decode more than the words spoken to us. This is inferential communication, and it means that we understand not only the words spoken, but the context in which they are spoken. Contrary to the languages of other animals, which are decidedly less ambiguous, human language requires a lot of subjective interpretation. This subjective interpretation follows from experience.  The same words from patients of different backgrounds can have very different meanings.  History taking really requires understanding the patient’s context, how they describe things, and what questions we should ask to better define that history. History taking ...
Source: DB's Medical Rants - Category: Internal Medicine Authors: Tags: Medical Rants Source Type: blogs