Workplace oral cancer screening now, a licensed saliva triage test later
TL;DR Oralguard screens tobacco and areca-nut users for oral precancer at workplaces and camps. Dentists do the checks first, and a saliva triage test follows once it is validated and licensed. Employers, CSR funders and state programmes pay per person screened. Anyone flagged high-risk gets booked straight in for a biopsy.
India recorded 143,759 new lip and oral cavity cancers and 79,979 deaths in 2022, more cases than any other country[1][2]. The risk sits mostly with people who chew tobacco, gutka or areca nut, and a lot of them are men in factories, depots and construction sites.
Over half of patients turn up at stage III or IV, when five-year survival falls below 50%, yet fewer than 15% of high-risk adults have ever been screened[1]. And screening works when it happens. A Kerala cluster-randomised trial cut oral cancer deaths among screened high-risk people by 26%[1].
So what gets in the way? Dentists are scarce outside cities, and a daily-wage worker keeps putting off the biopsy trip.
First, the clinical bit - Oralguard does screening and triage only. It finds people who need a closer look and sends them for examination and biopsy. A pathologist's biopsy report diagnoses cancer and Oralguard does not. A saliva test that claims cancer risk is a regulated diagnostic, likely Class C under CDSCO rules[3].
Stage one works today. A trained dentist examines each worker's mouth with a light and logs findings on a tablet. Anyone with a suspicious patch gets a slot at a partner cancer hospital that week, and a coordinator keeps chasing until the biopsy is done. Everyone gets brief help to cut down on tobacco.
With ethics approval and tiered consent, Oralguard collects saliva linked to examination and biopsy results. That biobank feeds a licensed saliva test, built in-house or licensed in, so health workers can triage and dentists see only the higher-risk people.
The original version promised real-time saliva analysis for many diseases. Continuous saliva sensing works for only a few molecules in research settings[4], so Oralguard narrows down to the one condition where saliva evidence and Indian need are strongest.
The people screened rarely pay. Employers in manufacturing, mining, logistics and construction pay to cut absence and insurance costs, and so do CSR foundations focused on cancer. State NCD drives are bigger buyers but slower. My rough estimate is ₹250–600 per person screened. Once licensed, kits could sell per test to clinics and programmes, and for reference a US lab saliva test runs about US$10 (about ₹970) per sample[5].
Three meta-analyses published between January and May 2026 pooled salivary marker results, with sensitivity between 0.64 and 0.76[6][7]. That's not good enough for everyone but usable for triage in high-risk groups. One Indian oral-cancer diagnostics startup raised ₹16 Cr in January 2025 for a 15-minute saliva kit[8], and CDSCO added online classification for diagnostic kits in February 2026[3].
Nobody publishes a size for saliva diagnostics in India. The nearest neighbour comes from one market research firm, which puts India's in-vitro diagnostics market at US$1.82 bn in 2025 (about ₹17,600 Cr), with point-of-care testing growing 14.93% a year[9].
If you want a screening-service number then multiply high-risk adults by uptake and price. Fewer than 15% of them have ever been checked[1], so the gap is large but nobody has priced it.
That same startup is building a saliva kit that sorts people into low, moderate and high risk, and it reported a 1,000-patient trial at four hospital sites in December 2025[10]. It's the nearest Indian comparable and could well be your supplier. US consumer gut-health brands sell saliva tests labelled as wellness, which is a route not open to an Indian product claiming early detection.
Nobody pairs workplace screening with a referral desk that actually gets people to biopsy. That's the gap.
| Difficulty | Hard (74/100) |
| Starting capital | ₹10.2–18.5 Cr |
| Time to launch | 3–4 months for screening; 30–36 months for a licensed test |
The screening service is simple and can start for well under ₹2 Cr. The saliva test is where it gets hard, because you need an assay that behaves on messy samples, a clinical performance evaluation in India, ISO 13485 and a Class C licence. Running dentists and referral coordinators across districts adds steady operational weight on top.
Stage one, dentist-led screening, needs little. The saliva test needs a lot, and you need it before you sell a single kit.
Building this outside India? The categories above usually have a local equivalent, so check with your own regulator.
Don't let AI diagnose cancer. Oralguard screens and refers, and only a pathologist's biopsy report confirms anything.
Want to work out the AI layer for Oralguard? Talk to Yash →
Here's what can go south -
I'd call the screening service a sound business on its own, with the saliva test as the long bet. It suits a founder with dental or public-health networks who can sell to employers and raise patient capital for lab work. If you want a quick consumer product then look elsewhere.
Prove one thing first - that 60% of referred workers complete a biopsy within 30 days.
My estimate is ₹10.2–18.5 Cr, because the licensed saliva test needs a biobank, a clinical study and a CDSCO licence. Stage-one dentist screening costs far less.
Dentist-led screening camps need little, but a saliva test is a regulated diagnostic, likely Class C, and needs a CDSCO licence after a clinical study.
Yes, especially where tobacco and areca nut use is common. Diagnostic test rules differ everywhere, so check with your own regulator.
The free Oralguard validation kit has the line-by-line capital breakdown, the effort scoring, the CDSCO and ethics checklist, a 14-day validation sprint with pass/fail targets, a 90-day launch plan, 10 interview questions for employers and CSR heads, and 5 assumptions to test. Download the kit →
Thinking of building Oralguard or something like it? The make-or-break bit is planning the clinical evaluation properly before you collect a single sample, and that's exactly where I help founders. If you need a hand, you know where to find me. Talk to Yash →
For illustration only. Names are fictional and ideas hypothetical; sourced facts are real but may be out of date. Nothing here is legal, financial or professional advice, and Yash Khatri is not personally liable for any use of it. Read the full disclaimer.