Corrigendum: Automatic inference of hypoglycemia causes in type 1 diabetes: a feasibility study.

[This corrects the article DOI: 10.3389/fcdhc.2023.1095859.].

Automatic inference of hypoglycemia causes in type 1 diabetes: a feasibility study.

Background: Hypoglycemia is the most common adverse consequence of treating diabetes, and is often due to suboptimal patient self-care. Behavioral interventions by health professionals and self-care education helps avoid recurrent hypoglycemic episodes by targeting problematic patient behaviors. This relies on time-consuming investigation of reasons behind the observed episodes, which involves manual interpretation of personal diabetes diaries and communication with patients. Therefore, there is a clear motivation to automate this process using a supervised machine learning paradigm. This manuscript presents a feasibility study of automatic identification of hypoglycemia causes. Methods: Reasons for 1885 hypoglycemia events were labeled by 54 participants with type 1 diabetes over a 21 months period. A broad range of possible predictors were extracted describing a hypoglycemic episode and the subject's general self-care from participants' routinely collected data on the Glucollector, their diabetes management platform. Thereafter, the possible hypoglycemia reasons were categorized for two major analysis sections - statistical analysis of relationships between the data features of self-care and hypoglycemia reasons, and classification analysis investigating the design of an automated system to determine the reason for hypoglycemia. Results: Physical activity contributed to 45% of hypoglycemia reasons on the real world collected data. The statistical analysis provided a number of interpretable predictors of different hypoglycemia reasons based on self-care behaviors. The classification analysis showed the performance of a reasoning system in practical settings with different objectives under F1-score, recall and precision metrics. Conclusion: The data acquisition characterized the incidence distribution of the various hypoglycemia reasons. The analyses highlighted many interpretable predictors of the various hypoglycemia types. Also, the feasibility study presented a number of concerns valuable in the design of the decision support system for automatic hypoglycemia reason classification. Therefore, automating the identification of the causes of hypoglycemia may help objectively to target behavioral and therapeutic changes in patients' care.

Protocol for a cluster randomised controlled trial of the DAFNEplus (Dose Adjustment For Normal Eating) intervention compared with 5x1 DAFNE: a lifelong approach to promote effective self-management in adults with type 1 diabetes.

INTRODUCTION: The successful treatment of type 1 diabetes (T1D) requires those affected to employ insulin therapy to maintain their blood glucose levels as close to normal to avoid complications in the long-term. The Dose Adjustment For Normal Eating (DAFNE) intervention is a group education course designed to help adults with T1D develop and sustain the complex self-management skills needed to adjust insulin in everyday life. It leads to improved glucose levels in the short term (manifest by falls in glycated haemoglobin, HbA1c), reduced rates of hypoglycaemia and sustained improvements in quality of life but overall glucose levels remain well above national targets. The DAFNEplus intervention is a development of DAFNE designed to incorporate behavioural change techniques, technology and longer-term structured support from healthcare professionals (HCPs). METHODS AND ANALYSIS: A pragmatic cluster randomised controlled trial in adults with T1D, delivered in diabetes centres in National Health Service secondary care hospitals in the UK. Centres will be randomised on a 1:1 basis to standard DAFNE or DAFNEplus. Primary clinical outcome is the change in HbA1c and the primary endpoint is HbA1c at 12 months, in those entering the trial with HbA1c >7.5% (58 mmol/mol), and HbA1c at 6 months is the secondary endpoint. Sample size is 662 participants (approximately 47 per centre); 92% power to detect a 0.5% difference in the primary outcome of HbA1c between treatment groups. The trial also measures rates of hypoglycaemia, psychological outcomes, an economic evaluation and process evaluation. ETHICS AND DISSEMINATION: Ethics approval was granted by South West-Exeter Research Ethics Committee (REC ref: 18/SW/0100) on 14 May 2018. The results of the trial will be published in a National Institute for Health Research monograph and relevant high-impact journals. TRIAL REGISTRATION NUMBER: ISRCTN42908016.

A Deep Neural Network Application for Improved Prediction of [Formula: see text] in Type 1 Diabetes.

[Formula: see text] is a primary marker of long-term average blood glucose, which is an essential measure of successful control in type 1 diabetes. Previous studies have shown that [Formula: see text] estimates can be obtained from 5-12 weeks of daily blood glucose measurements. However, these methods suffer from accuracy limitations when applied to incomplete data with missing periods of measurements. The aim of this article is to overcome these limitations improving the accuracy and robustness of [Formula: see text] prediction from time series of blood glucose. A novel data-driven [Formula: see text] prediction model based on deep learning and convolutional neural networks is presented. The model focuses on the extraction of behavioral patterns from sequences of self-monitored blood glucose readings on various temporal scales. Assuming that subjects who share behavioral patterns have also similar capabilities for diabetes control and resulting [Formula: see text], it becomes possible to infer the [Formula: see text] of subjects with incomplete data from multiple observations of similar behaviors. Trained and validated on a dataset, containing 1543 real world observation epochs from 759 subjects, the model has achieved the mean absolute error of 4.80 [Formula: see text] mmol/mol, median absolute error of 3.81 [Formula: see text] mmol/mol and [Formula: see text] of 0.71 ± 0.09 on average during the 10 fold cross validation. Automatic behavioral characterization via extraction of sequential features by the proposed convolutional neural network structure has significantly improved the accuracy of [Formula: see text] prediction compared to the existing methods.

Feature Extraction for BCIs Based on Electromagnetic Source Localization and Multiclass Filter Bank Common Spatial Patterns.

Brain-Computer Interfaces (BCIs) provide means for communication and control without muscular movement and, therefore, can offer significant clinical benefits. Electrical brain activity recorded by electroencephalography (EEG) can be interpreted into software commands by various classification algorithms according to the descriptive features of the signal. In this paper we propose a novel EEG BCI feature extraction method employing EEG source reconstruction and Filter Bank Common Spatial Patterns (FBCSP) based on Joint Approximate Diagonalization (JAD). The proposed method is evaluated by the commonly used reference EEG dataset yielding an average classification accuracy of 77.1 ± 10.1 %. It is shown that FBCSP feature extraction applied to reconstructed source components outperforms conventional CSP and FBCSP feature extraction methods applied to signals in the sensor domain.