The linear no-threshold model (LNT) is a dose-response model used in radiation protection to estimate stochastic health effects such as radiation-induced cancer, genetic mutations and teratogenic effects on the human body due to exposure to ionizing radiation. The model statistically extrapolates effects of radiation from very high doses (where they are observable) into very low doses, where no biological effects may be observed. The LNT model lies at a foundation of a postulate that all exposure to ionizing radiation is harmful, regardless of how low the dose is, and that the effect is cumulative over lifetime.

The LNT model is commonly used by regulatory bodies as a basis for formulating public health policies that set regulatory dose limits to protect against the effects of radiation. The model has also been used in the assessment of cancer risks of mutagenic chemicals. The validity of the LNT model, however, is disputed, and other significant models exist: the threshold model, which assumes that very small exposures are harmless, the radiation hormesis model, which says that radiation at very small doses can be beneficial, and the supra-linear model based on observational data. Whenever the cancer risk is estimated from real data at low doses, and not from extrapolation of observations at high doses, the supra-linear model is verified. It has been argued that the LNT model may have created an irrational fear of radiation.

Different organizations take different approaches to the LNT model. For example, the US Nuclear Regulatory Commission and United States Environmental Protection Agency endorse the model, while a number of other bodies deprecate it. One of the organizations for establishing recommendations on radiation protection guidelines internationally, the United Nations Scientific Committee on the Effects of Atomic Radiation (UNSCEAR) that previously supported the LNT model, no longer supports the model for very low radiation doses.