With the rapid development of artificial intelligence technology, artificial intelligence and other data-driven models are gradually penetrating into all aspects of medical health, especially in clinical auxiliary diagnosis and treatment. By combining a large amount of medical data, genetic data, pathological images, and clinical follow-up treatment plans, researchers hope to help doctors evaluate the condition more quickly and accurately and make clinical decisions by training statistical models or artificial intelligence models. However, this progress also brings new challenges, one of which is "automation bias", that is, people tend to rely too much on the recommendations of automated systems when making decisions, while ignoring or belittling other information. In clinical assisted decision-making, although artificial intelligence and statistical models provide a lot of useful information, if you rely too much on the output results of the models, you may neglect your own professional judgment and practical experience, and rely on the automation bias that may be caused by human-computer interaction, which may negatively affect the quality of decision-making.