Insulin dosage form selection and dosage adjustment method and system

Abstract

The invention discloses an insulin dosage form selection and dosage adjustment method and system, and the method comprises the steps: giving an insulin scheme suitable for a patient based on a diabetes guide / expert consensus through and a machine learning model, wherein the insulin scheme comprises the time of taking insulin and a corresponding insulin dosage form; collecting patient medical records of type 2 diabetes mellitus, wherein each medical record includes examination and inspection during hospitalization of the patient, one-statement five-history, medical advice and basic attribute data of the patient, and establishing characteristic fields according to the medical records; substituting the characteristic fields into an Xgboost model to carry out machine learning training so as totrain characteristic variables in the model; establishing an insulin initial total dose model, and substituting the characteristic fields of the medical records of the patient into the Xgboost modelfor machine learning training to obtain an insulin initial total dose, wherein insulin is divided into three types: basic insulin, premixed insulin and dinner insulin, and is divided into seven typesaccording to different injection time; establishing insulin dose adjustment model.

Description

technical field [0001] The invention relates to the technical field of insulin dosage adjustment, in particular to a method and system for selecting insulin dosage form and adjusting dosage. Background technique [0002] With the change of lifestyle and diet structure, diabetes presents a global epidemic trend. According to the survey results of the International Diabetes Federation, the number of diabetic patients in the world reached 415 million in 2015, and it is estimated that the number of diabetic patients will rise to 642 million in 2040. China is the hardest-hit area of ​​diabetes epidemic. The number of diabetic patients is as high as 114 million, which has caused a huge economic burden to the society. [0003] In the face of a high diabetes prevalence rate of 11.6%, the diabetes awareness rate is only 30.1%. However, among the people who knew about diabetes, the treatment rate was only 25.8%. Among the people receiving treatment, the control rate of diabetes was...

AI Technical Summary

Problems solved by technology

However, the shortage of grassroots doctors, uneven diagnosis and treatment, and lack of confidence in insulin use often delay the timing of insulin treatment, or lead to long-term low-dose or high-dose insulin use, resulting in poor overall blood sugar control

Images