Machine learning for non-invasive sensing of hypoglycaemia while driving in people with diabetes.

AIM: To develop and evaluate the concept of a non-invasive machine learning (ML) approach for detecting hypoglycaemia based exclusively on combined driving (CAN) and eye tracking (ET) data. MATERIALS AND METHODS: We first developed and tested our ML approach in pronounced hypoglycaemia, and then we applied it to mild hypoglycaemia to evaluate its early warning potential. For this, we conducted two consecutive, interventional studies in individuals with type 1 diabetes. In study 1 (n = 18), we collected CAN and ET data in a driving simulator during euglycaemia and pronounced hypoglycaemia (blood glucose [BG] 2.0-2.5 mmol L-1 ). In study 2 (n = 9), we collected CAN and ET data in the same simulator but in euglycaemia and mild hypoglycaemia (BG 3.0-3.5 mmol L-1 ). RESULTS: Here, we show that our ML approach detects pronounced and mild hypoglycaemia with high accuracy (area under the receiver operating characteristics curve 0.88 ± 0.10 and 0.83 ± 0.11, respectively). CONCLUSIONS: Our findings suggest that an ML approach based on CAN and ET data, exclusively, enables detection of hypoglycaemia while driving. This provides a promising concept for alternative and non-invasive detection of hypoglycaemia.

Noninvasive Hypoglycemia Detection in People With Diabetes Using Smartwatch Data.

OBJECTIVE: To develop a noninvasive hypoglycemia detection approach using smartwatch data. RESEARCH DESIGN AND METHODS: We prospectively collected data from two wrist-worn wearables (Garmin vivoactive 4S, Empatica E4) and continuous glucose monitoring values in adults with diabetes on insulin treatment. Using these data, we developed a machine learning (ML) approach to detect hypoglycemia (<3.9 mmol/L) noninvasively in unseen individuals and solely based on wearable data. RESULTS: Twenty-two individuals were included in the final analysis (age 54.5 ± 15.2 years, HbA1c 6.9 ± 0.6%, 16 males). Hypoglycemia was detected with an area under the receiver operating characteristic curve of 0.76 ± 0.07 solely based on wearable data. Feature analysis revealed that the ML model associated increased heart rate, decreased heart rate variability, and increased tonic electrodermal activity with hypoglycemia. CONCLUSIONS: Our approach may allow for noninvasive hypoglycemia detection using wearables in people with diabetes and thus complement existing methods for hypoglycemia detection and warning.

Lack of persistence of influenza vaccine antibody titers in patients with heart failure.

BACKGROUND: Patients with heart failure (HF) have lower initial antibody responses to the influenza vaccine compared with healthy individuals. Whether antibody titers wane faster in this population remains unknown. METHODS AND RESULTS: We studied 62 HF patients (18 ischemic, 44 idiopathic) and 40 healthy control subjects (HC) during the 2006-2007 and 2007-2008 influenza seasons. Antibody titers were measured before and 2-4 weeks and 11-12 months after vaccination. Serum antibody production was measured by hemagglutination inhibition assay, and antibody titers to individual vaccine viral strains between the HF and HC groups were compared after the influenza season to measure persistence of antibody response. All participants demonstrated early antibody seroprotection (titers 40 hemmaglutination inhibition units to 1 strain). Although antibody titers waned over time in both groups, titers to A/H3N2 and A/H1N1 strains decreased more in HF than in HC participants (P = .004 and P = .04, respectively). Titers to the B-type strain decreased to below seroprotective levels in both groups. CONCLUSIONS: Antibody titers to influenza A vaccine strains wane to below seroprotective levels in HF patients compared with HC, despite similar rates of initial seroprotection and seroconversion. These findings suggest that HF patients may remain at increased risk for influenza infection despite annual vaccination.

Interleukin 1 beta (IL1B) gene polymorphisms are not associated with gastric carcinogenesis in Germany.

BACKGROUND: Polymorphisms of interleukin-1 beta gene (IL1B-511C>T) are considered as risk factor for gastric carcinogenesis, but conflicting data have been reported recently. PATIENTS AND METHODS: The distribution of the four major IL1B variants (IL1B-3737C>T, -1464G>C, - 511C>T, -31T>C) were analyzed in 116 and 142 patients with gastric cancer and 'high risk gastritis', respectively, as well as 94 healthy controls. RESULTS: While identified frequencies of genotypes, haplotypes and haplotype pairs corresponded to those of other studies in Caucasians, none were significantly associated with the presence of gastric cancer or premalignant alterations. CONCLUSION: None of the four major polymorphisms is individually or in its haplotype configuration linked to the development of GC in this Caucasian population in Germany.