3 results about "INSULIN USE" patented technology

The application discloses a kind of dabigatran bleeding risk prediction methods based on machine learning, it is related to computer-aided drug risk management technical field, the method is by obtaining patient baseline and follow-up data, multiple imputation method is handled missing value;With HAS-BLED score as the basis, candidate variables are screened from potential risk factors using LassoCV algorithm, and anemia, insulin use and antifungal agent use are determined as new prediction variables through clinical correlation analysis to construct a set of prediction variables;Finally, a random forest or gradient boosting algorithm is used to train the model to output the bleeding risk assessment results of the individual to be tested.The application combines machine learning algorithm, improves the prediction accuracy of dabigatran bleeding risk in Chinese non-valvular atrial fibrillation patients, solves the problem of insufficient prediction accuracy of traditional HAS-BLED score, and provides a more reliable basis for clinical individualized anticoagulant therapy decision.

The invention belongs to the field of biological agriculture, and discloses rumen bypass glucose based on a polymer gel technology and a preparation method and application thereof. The rumen bypass glucose is prepared from 15 to 30 parts of agar, 10 to 25 parts of zein, 5 to 15 parts of locust bean gum and 40 to 65 parts of anhydrous dextrose. The preparation method comprises the steps of raw material crushing, pre-melting, twin-screw melt extrusion, pelletizing, cooling, screening and the like. According to the invention, agar-locust bean gum is utilized to form a compact gel network to realize physical blocking and screening, and low release (in vitro 12-hour release rate lt, 5%) in rumen and rapid and complete release (in vitro 8-hour release rate gt, 90%) in small intestines are realized by relying on hydrophobicity and enzyme response characteristics of zein. The product is suitable for a feed for dairy cows in a perinatal period and an initial lactation period, can remarkably improve energy negative balance, shorten non-pregnant time by about 20 days and increase milk yield by about 3.0 kg / head per day, and is natural in raw materials, simple and convenient in process and suitable for industrial production.

The application discloses an automatic peritoneal dialysis method based on blood glucose dynamic monitoring, and comprises the following steps: acquiring blood glucose monitoring data of a user and diet time, carbohydrate intake, insulin use record, dialysate concentration and its ratio of the last peritoneal dialysis treatment of the user, extracting blood glucose key change points according to the same, and obtaining a blood glucose key structure sequence; constructing a blood glucose prediction model through a time series model, inputting the blood glucose key structure sequence into the pre-trained blood glucose prediction model to obtain a first blood glucose prediction sequence; taking blood glucose stability as a first layer optimization target based on the first blood glucose prediction sequence, calculating an optimal dialysate concentration and its ratio, updating the blood glucose key structure sequence according to the same, inputting the blood glucose prediction model, and obtaining a second blood glucose prediction sequence; calculating a blood glucose fluctuation risk index based on the second blood glucose prediction sequence, constructing a second layer stage control target according to the blood glucose fluctuation risk index of each peritoneal dialysis stage, and generating peritoneal dialysis control parameters.