Cost is a dose

In Bangladesh seventy-three percent of health spending comes straight from the patient's pocket, and health costs push four and a half percent of the population into poverty every year. In that system, the price of a test or a drug is not an administrative detail. It is part of whether the treatment happens at all. A correct prescription the patient cannot afford is not a correct prescription. It is advice that will not be followed, which is the same as no advice, at a cost the family still pays in worry.

This makes cost a clinical variable, as real as a lab value. A clinical tool that recommends the textbook-best investigation without regard to its price is giving an answer that looks right on paper and fails at the pharmacy counter. The right answer in this system is the cheapest one that actually resolves the question, and that is a medical judgment, not a budgeting one.

So Glyph carries cost the way it carries any clinical fact. It reaches for Bangladeshi brand and generic names a patient can find and afford, Napa rather than Tylenol, the local generic rather than the imported brand, instead of the Western defaults a foreign-trained model offers first. It prefers the investigation that answers the question at a price the patient can pay over the one a wealthier system would order by reflex. And it surfaces these as options, with their costs, for the doctor to weigh.

None of this is the model deciding to economize for the patient. It is the model refusing to pretend that cost is somebody else's department. In a system with insurance and gatekeepers, a doctor can leave price to the back office. In a system that runs on cash from a day laborer's pocket, leaving cost out of the clinical picture is not neutrality. It is a way of being confidently, tidily wrong about what this patient can actually do.