The challenge of predicting blood glucose concentration changes in patients with type I diabetes

Abstract

Patients with Type I Diabetes (T1D) must take insulin injections to prevent the serious long term effects of hyperglycemia. They must also be careful not to inject too much insulin because this could induce (potentially fatal) hypoglycemia. Patients therefore follow a “regimen” that determines how much insulin to inject at each time, based on various measurements. We can produce an effective regimen if we can accurately predict a patient’s future blood glucose (BG) values from his/her current features. This study explores the challenges of predicting future BG by applying a number of machine learning algorithms, as well as various data preprocessing variations (corresponding to 312 [learner, preprocessed-dataset] combinations), to a new T1D dataset that contains 29,601 entries from 47 different patients. Our most accurate predictor, a weighted ensemble of two Gaussian Process Regression models, achieved a (cross-validation) [Formula: see text] loss of 2.7 mmol/L (48.65 mg/dl). This result was unexpectedly poor given that one can obtain an [Formula: see text] of 2.9 mmol/L (52.43 mg/dl) using the naive approach of simply predicting the patient’s average BG. These results suggest that the diabetes diary data that is typically collected may be insufficient to produce accurate BG prediction models; additional data may be necessary to build accurate BG prediction models over hours.

Recent applications of machine learning and deep learning models in the prediction, diagnosis, and management of diabetes: a comprehensive review

“…Patients with T1DM should receive insulin to avoid the long-term consequence of hyperglycemia and they also should be cautious to take the proper amount of insulin and prevent hypoglycemia [ 134 ]. Therefore, the patients should obey a “regimen” to specify the injected value of insulin at each time.…”

Data Mining Classification Techniques for Diabetes Prediction

“…The dataset includes 768 tests, each of which has 9 attributes and 1 class with two possibilities such as positive and negative evaluated [21]. [23] .Artificial intelligence subset that utilizes large volumes of data to retrieve substantial data using previously undisclosed patpredictions [24][25] [26]. Data mining methods have been examined in many health cares trials to forecast the prevalence and characteristics of patients in pandemic conditions.…”

Proposal for a Methodology to Create an Artificial Pancreas for the Control of Type 1 Diabetes using Machine Learning and Automated Insulin Dosing Systems (AID)

“…Processing: Apply regression models to the control groups, using a physician-assisted insulin delivery process and with control of the glycemic response through the FreeStyle Libre of individuals belonging to the control groups [60,9].…”