ideasIdea
Community health workers with smartphone AI screen for mouth cancer in South Asia
Mouth cancer is common where tobacco is chewed and is visible to the naked eye. Health workers with a phone camera and AI could find it early in villages.
The Kerala cluster RCT showed visual oral screening reduces oral cancer mortality in tobacco and alcohol users; smartphone photo triage with AI has shown promising accuracy in India. Propose scaling community-worker screening with an AI second read and tele-referral in high-incidence districts.
Hypothesis
AI-assisted community screening achieves at least 80% sensitivity for oral potentially malignant disorders and shifts stage distribution at diagnosis by at least 15 percentage points toward stage I-II.
Rationale
Mortality benefit is shown; the missing piece is scalable, low-cost delivery.
What would test it
Run a stepped-wedge rollout across districts in India with registry linkage.
Maturity
early clinical
Who has to act
policy
Cost to try
Medium ($1M to $50M)
Years to first evidence
4
Bottlenecks it attacks
- Most lethal cancers are found late · Screening exists for only a few cancers. Pancreatic, ovarian, liver, oesophageal and most lung cancers are found when cure is unlikely.
- Most of the world has almost no cancer care · Seven in ten cancer deaths happen in low- and middle-income countries, where radiotherapy, pathology, surgery and drugs are scarce.