What is known, what Muna measures, how we checked it, and what we are still testing. We would rather this page be honest than impressive.
Periodontitis, the chronic infection of the gums that loosens teeth, is one of the most common diseases in the world and goes largely untreated in Nigeria. It is not only a dental problem. People with periodontitis are more likely to have diabetes, and diabetes makes periodontitis worse; treating the gums improves blood-sugar control.1
The same inflammation is associated with cardiovascular disease, independently of the risk factors the two share, which is why cardiology and periodontology now issue joint guidance.2 In pregnancy, gum disease is common and treatable, though the evidence that treating it changes birth outcomes is mixed, and we say so.3
Dental and medical care rarely talk to each other, and most people see neither until something hurts. Muna sits in that gap: a short set of questions about the mouth and the body together, on a phone, and a route to the right care.
The questions about the gums are the self-report items developed by the US Centers for Disease Control and the American Academy of Periodontology, which were validated against full-mouth examination and have since been tested across cultures.45 The mental-health items are the PHQ-2, word for word.
Before the questionnaire went live in August 2026 we scored it on 10,683 adults from the US National Health and Nutrition Examination Survey who had a six-site, full-mouth periodontal examination.6 The question was simple: does the oral score separate people with measured periodontitis from people without?
The oral score reached an area under the curve of 0.72 against examined periodontitis, slightly better than the longer questionnaire it replaced. That is a screening-grade result, not a diagnostic one, and it is why Muna is a screening.
A result on American survey data is not a result in Lagos. So at every Health Day our clinical lead examines mouths in the chair, with a full periodontal chart, and we compare what the score said with what she found.
On the first 27 charted mouths, from our first workplace pilot in September 2026, the oral score did not yet separate measured gum disease well. That sample is far too small to conclude anything, and we are saying it here anyway, because the alternative is a page that only reports the good news.
The benchmark we hold ourselves to is written down: about 150 examined people, with blood pressure and weight measured at the chair, blood work from a partner lab for the heart and metabolic domains, and a decision rule agreed with our clinicians before the data is looked at. The pilots in the last week of October 2026 are the start of it. We will publish the result here, whichever way it goes.
Questionnaires cannot see bleeding gums; a photograph can. With separate, explicit consent, Muna keeps the four guided photos a person takes and the clinician’s findings from the chair as pairs, and uses them to teach a model to read the mouth. Until that model meets our clinicians’ bar, the photos do not change anyone’s score, and the app says so.
Wrote the clinical methodology the score is built from, signs off every clinical line in the app, and examines the chair at every Health Day herself.
The score is a fixed set of rules, not a learned model: every weight is written down, clinically endorsed and reviewable. Anyone can ask for a human review of their score from the app, and we answer within five working days.
Muna is a screening, not a diagnosis. It points you to the right care. It does not replace it.What the score is not
Sanz M, et al. Scientific evidence on the links between periodontal diseases and diabetes: consensus report of the International Diabetes Federation and the European Federation of Periodontology. Diabetes Research and Clinical Practice, 2018. Source ↗
Sanz M, et al. Periodontitis and cardiovascular diseases: consensus report of the European Federation of Periodontology and the World Heart Federation. Journal of Clinical Periodontology, 2020. Source ↗
American College of Obstetricians and Gynecologists. Oral health care during pregnancy and through the lifespan. Committee Opinion 569, 2013. Source ↗
Eke PI, Dye BA, et al. Self-reported measures for surveillance of periodontitis. Journal of Dental Research, 2013. The CDC and AAP questionnaire items, validated against full-mouth examination. Source ↗
Diagnostic accuracy of self-reported questionnaires for detecting periodontitis across multiple cultures and geographic locations: a systematic review and meta-analysis, 2025. Source ↗
Eke PI, et al. Periodontitis in US adults: National Health and Nutrition Examination Survey 2009 to 2014. Journal of the American Dental Association, 2018. The full-mouth examination protocol our validation uses. Source ↗