Time series prediction of personalized insulin dosage for type 2 diabetics

Careful blood glucose monitoring and consistent insulin administration are necessary for managing diabetes. People with demanding schedules or little access to medical personnel may find this difficult. Fortunately, without having visit a doctor every day, daily dosage now be customized person’s unique needs using technology customised algorithms based on their food intake, exercise routines, levels. This information can entered into diabetes management app device, where an algorithm will determine the proper offer real-time feedback assist maintain ideal A patient's dietary preferences, degree of physical activity, sugar taken account determining bolus basal dosages in study. According tracked body data, patient’s appropriate is predicted artificial neural network (ANN)-based models. Based patient exercise, past administration, projections created. To forecast individual’s requirements, long short-term memory (LSTM) random forest regression models employed. Accuracy both tested shows better accuracy which used prediction system.