Reasoning model
A type of AI model that works through a problem in steps before giving a final answer, rather than responding in one shot. This step-by-step working is often called chain-of-thought. Reasoning models tend to do better on harder problems that need several linked judgments, which is why they have become a distinct category. The trade-offs matter for healthcare use: they are usually slower and cost more to run, and producing visible reasoning is not the same as being correct, so the steps should be treated as a model showing its work, not as a guarantee.
A pharmacist trials a reasoning model on renal dose adjustments, pasting in an extract from the record, and each answer comes back with a page of orderly steps: weight, creatinine, estimated clearance, adjusted dose. In one case it picks up the weight from a clinic visit two years earlier, and every later step follows neatly from that wrong number. Before acting on any answer, check each input value against the current chart and recompute the clearance yourself.
Terms like this come up in real clinical scenarios across the HelloAI courses: bite-sized modules with verifiable certificates. An account takes one minute, no password needed.
Sign in →