Deep Learning-Based Diabetes Prediction Using a Bayesian Artificial Neural Network with Clinical Risk Factors

Description:

Diabetes is a major chronic disease that affects millions of people worldwide and can lead to serious health complications when it is not detected and managed at an early stage. The development of diabetes is associated with various clinical and demographic factors, including age, body mass index, blood glucose level, HbA1c level, hypertension, heart disease, gender, and smoking history. Considering these factors together is important for identifying individuals who may be at higher risk of diabetes.

Traditional diabetes assessment generally relies on clinical measurements and expert evaluation, which may require considerable time and may not fully capture the complex relationships among multiple risk factors. With the increasing availability of healthcare data, machine learning and deep learning techniques can provide an effective data-driven approach for identifying patterns associated with diabetes.

Input  :  Clinical and demographic risk factors

Output  : Diabetes prediction

Tags:

#DiabetesPrediction #DiabetesDetection  #BayesianNeuralNetwork #ArtificialNeuralNetwork #MachineLearning #ClinicalRiskFactors #HealthcareAI #MedicalAI #DiabetesRiskPrediction #PredictiveAnalytics #ArtificialIntelligence #DeepLearningHealthcare  #HealthcareAnalytics #Python #TensorFlow #DataScience #EarlyDiabetesDetection

References:

1. Shaheen, I., Javaid, N., Ali, Z., Ahmed, I., Khan, F. A., & Pamucar, D. (2026). A trustworthy and patient privacy-conscious framework for early diabetes prediction using Deep Residual Networks and proximity-based data. Biomedical Signal Processing and Control, 112, 108361.

2.Shobha, T., Pradeep, S., Patil, S., Subramanya, J., & Mitra, G. S. (2026). A data-driven machine learning model for effective diabetes diagnosis. Scientific Reports.