The application relates to the technical field of
warfarin dose regulation, and discloses a
warfarin dose prediction adjustment method and
system based on multiple
linear regression, which comprises a
patient data acquisition module, a
gene data acquisition module, a model construction module, a
dose adjustment module, a real-time prediction module and an adjustment execution module. The
patient data acquisition module synchronously acquires multi-dimensional parameters under different treatment states to build a treatment
data set; the
gene data acquisition module acquires
gene polymorphism and age data, combines the treatment
data set to build a refined patient
characteristic space, and the model construction module builds and trains a multiple
linear regression prediction model according to the patient
characteristic space to extract a dose index; the
dose adjustment module builds a
dose adjustment level and a mapping relationship with the dose index; the real-time prediction module acquires real-time
treatment parameters, combines the model to obtain a real-time self-adaptive dose index; the adjustment execution module obtains a prediction adjustment level according to the mapping relationship, and if the prediction adjustment level exceeds a preset threshold, a
dose adjustment mechanism is triggered.