A Machine Learning Approach for Blood Glucose Level Prediction Using a LSTM Network

Article Endocrinology & Metabolism

2. Classification and Diagnosis of Diabetes: Standards of Medical Care in Diabetes-2021

Summary: The American Diabetes Association's Standards of Medical Care in Diabetes provides clinical practice recommendations, treatment goals, guidelines, and tools for evaluating care quality. It is updated annually by a multidisciplinary expert committee, and readers are invited to comment on the standards at professional.diabetes.org/SOC.

DIABETES CARE (2021)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Adversarial multi-source transfer learning in healthcare: Application to glucose prediction for diabetic people

Maxime De Bois et al.

Summary: The study introduces a multisource adversarial transfer learning framework to enhance knowledge transfer in healthcare by learning a more general feature representation that is similar across different sources of data. By analyzing learned feature representations and utilizing adversarial training, statistical and clinical accuracies can be further improved. Contrary to standard transfer methods, adversarial transfer does not discriminate patients and datasets, leading to a more general feature representation.

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE (2021)

Add to Collection

Article Medical Informatics

Stacked LSTM based deep recurrent neural network with kalman smoothing for blood glucose prediction

Md Fazle Rabby et al.

Summary: This study utilizes a stacked LSTM deep recurrent neural network model and Kalman smoothing technique to improve blood glucose level prediction accuracy. Experimental results demonstrate higher average prediction accuracy on the OhioT1DM dataset.

BMC MEDICAL INFORMATICS AND DECISION MAKING (2021)

Add to Collection

Article Endocrinology & Metabolism