This is a repository copy of A deep neural network application for improved prediction of HbA1c in type 1 diabetes.

IntroductionThe 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 analysisA 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 disseminationEthics 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 numberISRCTN42908016.

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.

No abstract

No abstract