Warfarin dose prediction method and prediction device

Abstract

The invention discloses a warfarin dose prediction method and prediction device, and the method comprises the steps of: extracting a sample set from a database, carrying out the normalization of the sample set, and dividing the normalized sample set into a plurality of groups; sequentially selecting one group as a first verification set and the rest groups as a training set, constructing a singlemodel according to the training set and a preset algorithm, verifying the single model through the currently selected first verification set to obtain an error of the single model, and, according to the error corresponding to the same preset algorithm, calculating the precision corresponding to the preset algorithm; selecting the algorithm with the precision meeting the requirement as the optimalalgorithm; adjusting the parameters of the optimal algorithm through grid search; training according to the sample set and the optimal algorithm obtained after parameter adjustment to obtain a warfarin dose prediction model; and acquiring user information, and inputting the user information into the warfarin dose prediction model to obtain a warfarin dose corresponding to the user information. Byadopting the method, the prediction accuracy can be improved.

Description

technical field [0001] The invention relates to a warfarin dose prediction method and a prediction device, belonging to the technical field of drug detection. Background technique [0002] Warfarin is a coumarin oral anticoagulant synthesized by the University of Wisconsin in the United States in the 1940s. It can block the production of reduced vitamin K by inhibiting the activity of vitamin K epoxide reductase, thereby inhibiting Vitamin K-dependent activation of coagulation factors II, VII, IX, and X plays an anticoagulant role. Warfarin is the most commonly used oral anticoagulant drug and has been on the market for more than 60 years. It is widely used clinically in atrial fibrillation (AF), deep vein thrombosis (deep vein thrombosis DVT) and other diseases, and can effectively reduce the risk of such patients. risk of thromboembolism. In 2010, warfarin was used in more than 25 million prescriptions in the United States, which is equivalent to 0.5-1.5% of the populati...

AI Technical Summary

Problems solved by technology

Therefore MLR may not be the most feasible method to accurately predict these warfarin doses and a more applicable modeling approach needs to be explored

Images