The medical AI space is almost entirely English-first. When teams build for another language, they usually scrape Western datasets and run them through a translator. In healthcare, that shortcut is dangerous.
Translation flattens the clinic
How a patient describes pain is clinical signal, not surface style. Vietnamese carries distinctions that English collapses. Đau nhức is a dull, deep ache. Đau buốt is a sharp, piercing pain. Đau thắt is a tight, gripping pain, the word a patient reaches for when describing the chest pain that should make a doctor sit up.
Flatten those three into "aching," "sharp," and "tight" and you lose the texture a clinician triages on. A model trained on translated data learns the English mapping, then meets a Vietnamese patient and quietly misreads them.
Culture is part of the history
Symptom language is only half of it. Patients here report differently. Stoicism runs deep, and a patient may understate what they feel or describe it in terms a Western-trained model has never seen. A system that does not expect that under-reporting will take a calm description at face value and miss the severity underneath.
These are not edge cases. They are the median Vietnamese consultation. A clinical model that cannot read them is not a slightly worse model. It is the wrong tool.
Built from the ground up
Vietnamese has more than 100 million native speakers, and they deserve clinical AI built for how they actually speak. meddies-consultant is generated natively, not translated, so the nuance survives into the training data instead of being lost in a pre-processing step.
Translated leftovers will always carry the accent of the language they came from. For a tool that has to understand a patient in a Vietnamese clinic, that accent is a defect, not a detail.