Method for assisting gestation period diabetes genetic risk prediction based on artificial intelligence

Abstract

The invention discloses a method for assisting gestation period diabetes genetic risk prediction based on artificial intelligence. The method comprises the following steps of acquiring and integrating patient body examination data and gene testing information, establishing a medical record database of the gestation period diabetes; performing preprocessing on data in the medical record database, namely performing segmenting a training-testing set, screening the medical record and filling vacancy values; extracting characteristics according to an information value and a Bayesian network, and constructing a characteristic set which is related with the gestation period diabetes genetic risk, performing modeling and diagnosis on the medical record data after characteristic screening based on a CatBoost model; searching a parameter value with optimal score by means of Grid Search, and performing cross validation by means of the training set. The method for assisting gestation period diabetes genetic risk prediction based on artificial intelligence can well applied to an actual medical environment according to the gene data and the body examination data, thereby finding out the gestation period diabetes high-risk population, saving expensive intervention time, realizing early intervention and changing a mother-and-fetus result.

Description

technical field [0001] The invention relates to the technical field of gestational diabetes prediction, in particular to a method for assisted prediction of genetic risk of gestational diabetes based on artificial intelligence. Background technique [0002] Gestational diabetes is one of the major diseases during pregnancy. It is a temporary form of diabetes in which the body does not produce enough insulin to regulate blood sugar during pregnancy. If gestational diabetes is not treated, it will seriously endanger the health of mothers and children, specifically manifested as increased risks of pregnancy-induced hypertension, fetal arrest, polyhydramnios, etc., and the incidence of premature birth and macrosomia will increase significantly high. [0003] At present, the traditional diagnosis of gestational diabetes is based on questionnaires of risk factors, the prediction accuracy rate is low, and the missed diagnosis rate is as high as 30-40%. Other screening methods are...

AI Technical Summary

Problems solved by technology

[0004] The existing similar patent publication number is CN109524118A, a screening method for gestational diabetes based on machine learning and physical examination data. This method proposes a screening method for gestational diabetes based on the LightGBM algorithm and physical examination data, although it also combines individual genes However, it has not processed and screened the genetic data, which has a high probability that the data will retain a lot of noise, cause the model to overfit, and cause problems such as a decline in diagnostic accuracy; Shift prediction problem, the Catboost algorithm is significantly better than LightGBM

Images