The invention discloses an
asymptomatic myocardial infarction prediction method and related equipment based on a transferable space-time
mask Transformer, and the method comprises the steps: carrying out the space-time
mask modeling and model self-supervision pre-training of an electrocardiogram feature sequence constructed based on electrocardiogram data, and obtaining a pre-trained electrocardiogram feature extractor; carrying out migration
fine tuning on the pre-trained electrocardiogram feature extractor by utilizing the
small sample data set, and constructing a target electrocardiogram feature extractor for identifying the
asymptomatic myocardial infarction; the method comprises the following steps: extracting electrocardiogram feature representation of a target object through a target electrocardiogram feature extractor, performing
feature extraction and modeling on
cardiac magnetic resonance imaging and clinical structural data of the target
object based on a
feature extraction module, and performing adaptive fusion on multi-
modal features; and finally, generating an
asymptomatic myocardial infarction risk prediction result based on the fusion features. The method can realize early accurate prediction of the asymptomatic myocardial
infarction, and can be widely applied to the technical field of
artificial intelligence.