A meal detection approach based on parity space to detect untreated meals in subjects with Type 1 diabetes*

In this paper a data-driven fault detection technique based on parity space is applied to the problem of detecting unannounced meals for type 1 diabetes patients. This method involves the generation and evaluation of a residual signal to detect faults (unannounced meals) acting on the system (patient). Insulin on Board (IOB), meal intake, glucose and its second derivative have been selected as input signals to generate the residuals, and the parity space matrices are estimated using 8-hour training in silico data generated by the UVA/Padova simulator. The residual evaluation module compares the residual with a threshold that is optimized for each patient using 2-day tuning data. The complete system is evaluated on 1-week scenario obtaining promising results (TPR =9 5 %, PPV=7 2 %) with a detection delay of 4 2 minutes for 8 0 % of patients. For the 20 outlier patients, a fine-tuning and patient-tailored input signal processing are proposed as a future development.