A Machine Learning Approach to Analyze the Factors that Influence Juvenile Diabetic Patients For Better Medication
Diabetes is always a major concern and challenge across the world. The main factor of diabetes is high level complications that varies with every patient. So the analysis of the data on various advances in health science leads to significant production of data. These data lead to a high throughput genetic data and clinical information. The main focus of this research is to generate outcomes with various analytic patterns based on the existing datasets. These outcome will assist the diabetic practitioner to prescribe the patients based on their genetics and clinical information. To have an effective analytic model this paper focuses on building an Incremental approach that identifies the factors for type 1 juvenile patientís data and apply analytics through Machine learning algorithm to monitor glucose level in the patients. The model will be trained to adapt new learnings based on the data to analyse the glucose requirement level after following the diabetes prescription regime. The first step is to identify all the potential factors that should be a part of analysis in juvenile data sets. ML model are used to classify the data and group them based on potential achievable factors. The model will use incremental approach to learn new patterns and to generate analytical outcomes. Further this will assist for better medication and prescription for preventing and curing juvenile diabetes.
Keywords - Juvenile diabetes, Machine learning, genetic data, Incremental approach, training set, clinical information, Decision tree algorithm.