A Deep Learning Framework for Automatic Meal Detection and Estimation in Artificial Pancreas Systems

Current artificial pancreas (AP) systems are hybrid closed-loop systems that require manual meal announcements to manage postprandial glucose control effectively. This poses a cognitive burden and challenge to users with T1D since this relies on frequent user engagement to maintain tight glucose control. In order to move towards fully automated closed-loop glucose control, we propose an algorithm based on a deep learning framework that performs multitask quantile regression, for both meal detection and carbohydrate estimation. Our proposed method is evaluated in silico on 10 adult subjects from the UVa/Padova simulator with a Bio-inspired Artificial Pancreas (BiAP) control algorithm over a 2 month period. Three different configurations of the AP are evaluated -BiAP without meal announcement (BiAP-NMA), BiAP with meal announcement (BiAP-MA), and BiAP with meal detection (BiAP-MD). We present results showing an improvement of BiAP-MD over BiAP-NMA, demonstrating 144.5 ± 6.8 mg/dL mean blood glucose level (−4.4 mg/dL, p< 0.01) and 77.8 ± 6.3% mean time between 70 and 180 mg/dL (+3.9%, p< 0.001). This improvement in control is realised without a significant increase in mean in hypoglycaemia (+0.1%, p= 0.4). In terms of detection of meals and snacks, the proposed method on average achieves 93% precision and 76% recall with a detection delay time of 38 ± 15 min (92% precision, 92% recall, and 37 min detection time for meals only). Furthermore, BiAP-MD handles hypoglycaemia better than BiAP-MA based on CVGA assessment with fewer control errors (10% vs. 20%). This study suggests that multitask quantile regression can improve the capability of AP systems for postprandial glucose control without increasing hypoglycaemia.

Diabetes and COVID-19 Vaccination

Diabetes is one of the major comorbidities associated with increased risk of mortality and severe clinical outcomes in coronavirus disease 19 (COVID-19) patients. Thus, timely and appropriate vaccination is the most effective strategy for mitigating the risk of COVID-19 infection in people with diabetes. Recent studies have shown that immune response after vaccination is significant in both diabetes and non-diabetes groups, but slightly lower in patients with diabetes. Inadequate glucose control might impair the immune response. Blood glucose monitoring is required more often than usual for several days after vaccination. If a patient’s blood glucose is not controlled adequately, appropriate management should be provided.

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)

The number of children, adolescents, and adults living with diabetes increases annually due to the lack of physical activity, poor diet habits, stress, and genetic factors, and there are greater numbers in low-income countries. Therefore, the aim of this article is to present a proposal for a methodology for developing a pancreas using artificial intelligence to control the required doses of insulin for a patient with type 1 diabetes (T1D), according to data received from monitoring sensors. The information collected can be used by physicians to make medication changes and improve patients’ glucose control using insulin pumps for optimum performance. Therefore, using the model proposed in this work, the patient is offered a gain in glucose control and, therefore, an improvement in quality of life, as well as in the costs related to hospitalization.

Increased risk of cognitive impairment and hyperglycemia-related mortality in late middle-aged African Americans with low serum adropin levels

Recent data implicate the secreted peptide adropin in the physiology of aging. In humans, adropin is highly expressed in brain tissues, and correlates positively with transcriptomic signatures of mitochondrial and synaptic functions. Adropin treatment improves performance of old mice in cognitive tests requiring learning and memory. While detected in the circulation of humans, no studies have investigated relationships between adropin, cognitive decline and aging. Here we compared serum adropin concentrations with Mini-Mental State Exam (MMSE) and animal naming test results from a cohort study of African Americans in late-middle age (baseline ages 49-65y, n=357). Using the lowest quintile of the MMSE to identify participants at risk for mild cognitive impairment (MCI) indicated lower serum concentrations (2.95±1.32 ng/ml vs. 3.31±1.56, P<0.05). Grouping into bins using 1-ng/ml increments in serum adropin concentrations further indicated an association between very low serum adropin concentrations and MCI. Using fructosamine as an indicator of moderate-term glucose levels suggested low serum adropin concentration correlate with increased risk of 10-year all-cause mortality in situations of poor glucose control. In summary, these data suggest low circulating adropin concentrations identify late-middle aged people at risk for cognitive impairment, and for all-cause mortality in situations of poor glucose control.

'Real-world' clinical trials in diabetes care: meaningful or meaningless?

So-called 'real-world' studies seem increasingly popular in diabetes care, as are the economic evaluations in secondary literature based upon them. The term is usually used for pharmacoepidemiological uncontrolled observational studies of different designs. Interpretation of the study findings is, however, badly undermined by the very reasons that the randomised controlled blinded study was invented – namely, non-medication study effects and biases in investigator selection and behaviour. In diabetes studies, glucose control seems particularly susceptible to such effects, perhaps through changes in patient motivation and education. Further, insulin studies are heavily influenced by baseline factors such as the site of starting insulin, the health circumstances of the patient at the time and the clinician involved. It is rare to see these issues adequately addressed or attempts made to understand their influence. In this article an attempt is made to discuss some of the issues further.