How GDM Predictor Works

GDM Predictor takes input from the user in the form of clinical and bichemical factors such as age, day, and family history of diabetes. The input is then used to generate a prediction of the risk of GDM using a random forest algorithm. The random forest algorithm is a machine learning algorithm that uses an ensemble of decision trees to make predictions. The algorithm is trained on a dataset of clinical and demographic factors from pregnant women with and without GDM. The dataset is used to identify patterns and relationships between the input factors and the risk of GDM. GDM Predictor can also provide personalized treatment recommendations based on the patient's risk factors and medical history. The web server can be used to improve pregnancy outcomes by identifying patients who may benefit from early intervention and management of GDM.

Using GDM Predictor

To use GDM Predictor, users can visit the web server and input their clinical and biochemical factors.

Input factor

Clinical history:

AP: Adverse pregnancy (default:NO)

ICP: Intrahepatic cholestasis of pregnancy (default:NO)

TD: Thyroid Diseases (default:NO)

Eclampsia: Eclampsia of pregnancy (default:NO)

Twins: Twins of pregnancy (default:NO)

Day: Day of pregnancy, Age: Age of pregnancy

BMI: BMI of pregnancy

Biochemical:

A1MG: Alpha-1-microglobulin, BMG: Beta-2-microglobulin

CysC: Cystatin C, TBA: total bile acid

FPG: Fasting blood glucose, CREA: Serum creatinine

CO2: Carbon dioxide