A Camera Pointed at Your Throat Could Replace the Dreaded Nose Swab
A Japanese AI device diagnoses influenza by photographing the back of your throat in ten seconds, no swab required. It's already in use at more than 2,000 clinics, and its maker believes the same technology could one day screen for diabetes and high blood pressure.
Key points
- Iris, a Japanese medical company, received national health insurance approval in Japan for its AI throat-scanning device, Nodoca, in 2022.
- Nodoca delivers an influenza assessment in just over ten seconds by analysing a photograph of the back of the throat, skipping the nasal swab most patients dread.
- More than 2,000 medical clinics across Japan had adopted the device as of 2025.
- In October 2025, Nodoca received Japanese regulatory approval to assess Covid-19 as well as influenza.
- Iris is exploring clinical trials in the United States, arguing that human mucous membranes are consistent enough across populations for its models to transfer.
Anyone who's had a flu test knows the moment: a nurse slides a long cotton swab deep into your nostril, your eyes water, and the result takes fifteen minutes. A Japanese startup wants to end that routine.
The company is called Iris. Its device, Nodoca, works like this: a doctor holds a small handheld camera to a patient's open mouth, photographs the pharynx (the back of the throat), and feeds that image into an AI model alongside data from the patient's initial questionnaire. Within roughly ten seconds the system returns an influenza assessment. No swab, no waiting.
How does photographing your throat tell a doctor anything?
The patterns of redness and blood vessel changes visible on the throat's lining shift in specific ways depending on which pathogen is present. Iris founder Sho Okuyama, a former emergency physician who once worked on remote Japanese islands with little more than a stethoscope, noticed that experienced doctors were reading these patterns intuitively. He wanted to make that reading automatic.
Building the system from scratch took years. When Iris was founded in 2017, no database of labelled throat images existed anywhere. Okuyama lent dedicated cameras to around 100 clinics and spent roughly three years collecting images with patient consent. That initial dataset ran to hundreds of thousands of images. Today, with Nodoca in routine clinical use, the figure has grown to several million. Each anonymised image sharpens the model, which makes Nodoca harder for a rival to match without starting that same multi-year data collection process from zero.
What does this mean for patients right now?
Visit one of the 2,000-plus Japanese clinics that have adopted Nodoca and you skip the swab, getting a result in seconds. The device can also be used earlier in an illness, before viral loads in the nose are high enough for a conventional swab to detect anything. Japanese regulators extended Nodoca's approval in October 2025 to cover Covid-19 assessment as well. It's worth comparing this with Hemispheric's brain-scan diagnostic we covered on 15 July 2026: both bets rest on the idea that a camera pointed at the body can surface what a clinician's eye misses, but Nodoca has regulatory approval and millions of real-world images behind it already.
For patients outside Japan, the benefit isn't here yet. Iris is weighing clinical trials in the United States before any American regulatory submission.
| Milestone | Date |
|---|---|
| Iris founded | 2017 |
| Training data collection completed | approx. 2020 |
| Japanese national health insurance approval | 2022 |
| Clinics using Nodoca in Japan | 2,000+ (2025) |
| Covid-19 function approved in Japan | October 2025 |
Could a throat photo ever screen for diabetes?
Okuyama thinks so. Lifestyle diseases like diabetes and high blood pressure quietly alter the tiny blood vessels visible in the throat lining. If an AI model learns to spot those changes reliably, a single photograph taken during a routine visit could flag a patient for follow-up blood tests before symptoms appear.
"The cost of AI inference is extremely low," Okuyama told Wired Japan, "so even if we increase the number of tests, the cost of providing them hardly changes." Adding a diabetes screen to a flu visit would cost a clinic almost nothing in compute once the model exists. That's the genuinely interesting part of this story: not the throat camera itself, but the economic argument that marginal cost approaches zero as you stack more conditions onto a single image. Watch whether Iris can get a diabetes study into a peer-reviewed journal before any competitor builds a comparable dataset.
