目的:构建乳腺癌死亡率预测模型。方法:基于硒、铜、锌、镉、铬、锰和砷7种元素日常摄入量和自适应增强算偏最小二乘法,建立预测乳腺癌死亡率的集成模型,并对其性能进行评价。结果:集成模型的预测精度明显优于单个偏最小二乘模型。结论:自适应增强策略在该类任务中是一个有力工具。 Objective: To construct a prediction model of breast cancer mortality. Methods: Based on the daily intake of seven elements of selenium, copper, zinc, cadmium, chromium, manganese and arsenic and the adaptive partial least squares method, an integrated model for predicting breast cancer mortality was established and its performance was evaluated. Results: The prediction accuracy of the integrated model is obviously better than the single partial least squares model. Conclusion: Adaptive enhancement strategy is a powerful tool in this type of task.