Validate and reimburse AI contouring and planning to expand radiotherapy capacity
Drawing targets and planning radiotherapy takes hours of scarce expert time. Properly tested AI could do much of it, letting the same staff treat far more patients, if regulators and payers set clear rules for proving and paying for it.
A programme with three parts: prospective, multi-centre validation studies of auto-contouring and auto-planning against expert consensus with clinical-acceptability and time-saved endpoints; a regulatory pathway that accepts these endpoints for clearance; and payer recognition that shifts payment from planning time to plan quality, so that time saved translates into more patients treated rather than lost revenue. Radiotherapy workforce shortages (physicists, dosimetrists, radiation oncologists) limit capacity in rich and poor countries alike, and AI planning is the most mature clinical AI in oncology, yet its adoption is slowed by unclear evidence standards and payment rules.
- Surgery and radiotherapy cure most, get least · Surgery and radiotherapy cure more people than drugs do, but attract a fraction of the research investment.
- Not enough oncologists, nurses, pathologists, physicists · The number of people with cancer is rising faster than the workforce trained to treat them.
- AI that is built but not validated or deployed · Thousands of cancer AI models are published; a handful are in clinical use, and fewer have shown they help patients.