Search

This article discusses the use of smartwatches and machine learning algorithms for detecting hypoglycemia in individuals with diabetes. The study conducted at the University Hospital Bern involved participants with type 1 diabetes who were subjected to hypoglycemia while driving in a simulator. The results showed that smartwatches can accurately detect pronounced hypoglycemia, but their performance in detecting mild hypoglycemia was less reliable. The study also found that electrodermal activity was a crucial feature for detecting hypoglycemia. Further research is needed to optimize the models for detecting milder hypoglycemia. The study was funded by various organizations and the authors declare no conflicts of interest. [Extracted from the article]

Background: To provide effective care for inpatients with COVID-19, clinical practitioners need systems that monitor patient health and subsequently allow for risk scoring. Existing approaches for risk scoring in patients with COVID-19 focus primarily on intensive care units (ICUs) with specialized medical measurement devices but not on hospital general wards. Objective: In this paper, we aim to develop a risk score for inpatients with COVID-19 in general wards based on consumer-grade wearables (smartwatches). Methods: Patients wore consumer-grade wearables to record physiological measurements, such as the heart rate (HR), heart rate variability (HRV), and respiration frequency (RF). Based on Bayesian survival analysis, we validated the association between these measurements and patient outcomes (ie, discharge or ICU admission). To build our risk score, we generated a low-dimensional representation of the physiological features. Subsequently, a pooled ordinal regression with time-dependent covariates inferred the probability of either hospital discharge or ICU admission. We evaluated the predictive performance of our developed system for risk scoring in a single-center, prospective study based on 40 inpatients with COVID-19 in a general ward of a tertiary referral center in Switzerland. Results: First, Bayesian survival analysis showed that physiological measurements from consumer-grade wearables are significantly associated with patient outcomes (ie, discharge or ICU admission). Second, our risk score achieved a time-dependent area under the receiver operating characteristic curve (AUROC) of 0.73-0.90 based on leave-one-subject-out cross-validation. Conclusions: Our results demonstrate the effectiveness of consumer-grade wearables for risk scoring in inpatients with COVID-19. Due to their low cost and ease of use, consumer-grade wearables could enable a scalable monitoring system. [ABSTRACT FROM AUTHOR]

Introduction: The COVID‐19 pandemic has forced rapid reconsideration as to the way in which health care is delivered. One potential means to provide care while avoiding unnecessary person‐to‐person contact is to offer remote services (telemedicine). This study aimed to (1) gather real‐time information on the use and perception of telemedicine in people living with type 1 diabetes and (2) assess the challenges, such as restricted access to health care and/or medical supplies. Methods: An anonymous questionnaire was widely distributed between 24 March and 5 May 2020 using an open‐access web‐based platform. Data were analysed descriptively, and results were stratified according to age, sex and HbA1c. Results: There were 7477 survey responses from individuals in 89 countries. Globally, 30% reported that the pandemic had affected their healthcare access due to cancelled physical appointments with their healthcare providers. Thirty‐two per cent reported no fundamental change in their medical follow‐up during this period, with 9% stating that no personal contact was established with their doctors over the duration of the study. Twenty‐eight per cent received remote care through telephone (72%) or video‐calls (28%). Of these, 86% found remote appointments useful and 75% plan to have remote appointments in the future. Glucose control, indicated by HbA1c, was positively associated with positive perception of telemedicine. In males, 45% of respondents with an HbA1c > 9% rated telemedicine not useful compared to those with lower HbA1c, while 20% of females with an HbA1c > 9% rated it not useful (χ2 = 14.2, P =.0016). Conclusion: Remote appointments have largely been perceived as positive in people with type 1 diabetes with the majority (75%) stating that they would consider remote appointments beyond the pandemic. Age and level of education do not appear to influence perception of telemedicine, whereas poor glucose control, particularly in males, seems to negatively affect perception. [ABSTRACT FROM AUTHOR]

Open source artificial pancreas systems (OpenAPS) have gained considerable interest in the diabetes community. We analyzed continuous glucose monitoring (CGM) records of 80 OpenAPS users with type 1 diabetes (T1D). A total of 19 495 days (53.4 years) of CGM records were available. Mean glucose was 7.6 ± 1.1 mmol/L, time in range 3.9–10 mmol/L was 77.5 ± 10.5%, <3.9 mmol/L was 4.3 ± 3.6%, <3.0 mmol/L was 1.3 ± 1.9%, >10 mmol/L was 18.2 ± 11.0% and > 13.9 mmol/L was 4.1 ± 4.0%, respectively. In 34 OpenAPS users, additional CGM records were obtained while using sensor‐augmented pump therapy (SAP). After changing from SAP to OpenAPS, lower mean glucose (−0.6 ± 0.7; P < 0.0001), lower estimated HbA1c (−0.4 ± 0.5%; P < 0.0001), higher time in range 3.9–10 mmol/L (+9.3 ± 9.5%; P < 0.0001), less time < 3.0 mmol/L (−0.7 ± 2.2%; P = 0.0171), lower coefficient of variation (−2.4 ± 5.8; P = 0.0198) and lower mean of daily differences (−0.6 ± 0.9 mmol/L; P = 0.0005) was observed. Glycaemic control using OpenAPS was comparable with results of more rigorously developed and tested AP systems. However, OpenAPS was used by a highly selective, motivated and technology‐adept cohort, despite not being approved for the treatment of individuals with T1D. [ABSTRACT FROM AUTHOR]

Studies on CGM assume equal glycemic control between MDI and CSII. However, observation periods are often short and the impact of hypoglycemia on glycemic control and variability is unclear. In this study, we analyzed 12846 days (35 years; CSII 2232 days [6 years]; MDI 10614 days [29 years]) of CGM readings obtained from 99 patients with T1D. In the overall analysis mean glucose was 169.6 ± 18.9mg/dl for CSII and 175.0 ± 29.5 mg/dl for MDI. Estimated A1c was 7.54 ± 0.66% (CSII) and 7.7 ± 1.0% (MDI). Percentage of readings in target range (70-180mg/dL) was 54.0 ± 15.5% for CSII and 57.4 ± 11.4% for MDI. In total, 3.1/2.2% of readings were < 54 mg/dL and 14.9/12.4% were > 250mg/dL for CSII and MDI, respectively. In total, 464 hypoglycemic events (< 54mg/dL) occurred in CSII (day: 305 [64%]; night: 170 [36%]), corresponding to 0.21 hypoglycemic events daily. In MDI, 2297 hypoglycemic events occurred (day: 1507/66%; night: 783/34%), corresponding to 0.22 hypoglycemic events daily. Mean duration of hypoglycemia was 146.5 ± 65.9 minutes (CSII) and 132.8 ± 42.8 minutes (MDI); 233 (CSII) vs. 982 (MDI) events were prolonged (>120 minutes). CV was 41.1 ± 6.7% for CSII and 40.8 ± 3.8% for MDI. In the 24 hours prior to hypoglycemia, mean glucose was higher (182.9 ± 30.5 vs. 166.9 ± 26.6mg/dl; p<0.001 for CSII and 167.2 ± 14.7 vs. 152.7 ± 19.1mg/dl; p=0.013 for MDI) and CV was lower (p<0.001 for both treatments) compared to the subsequent 24 hours. Age correlated to CV (r=-.254; p=0.028 for MDI), HbA1c to eA1c (r=.611; p=0.009 for CSII; r=.482; p=0.028 for MDI), and C-peptide to CGM-readings in target range (r=.246; p=0.042 for MDI), which negatively correlated to HbA1c (r=-.484; p<0.001 for MDI). Glycemic control was comparable between MDI and CSII in T1D. Glycemic variability was lower prior to a hypoglycemic event and in older patients, while remaining insulin secretion was associated with longer time in target range. Disclosure: A. Melmer: None. T. Züger: None. T. Pöttler: None. H. Kojzar: None. M. Cigler: None. F. Aberer: None. M. Laimer: None. J.K. Mader: Advisory Panel; Self; Boehringer Ingelheim International GmbH, Eli Lilly and Company, Prediktor Medical, Roche Diabetes Care, Sanofi. Speaker's Bureau; Self; Abbott, AstraZeneca, Dexcom, Inc., Novo Nordisk Inc. Stock/Shareholder; Self; decide Clinical Software GmbH. [ABSTRACT FROM AUTHOR]

Background: Thousands with type 1 diabetes are estimated to be using open source Artificial Pancreas Systems (APS) with commercially available insulin pumps, continuous glucose monitors (CGM), and an open source control algorithm to process glucose readings and adjust insulin delivery. OpenAPS and similar do-it-yourself (DIY) closed loop systems gained considerable interest in the online diabetes community. Many using DIY closed loop systems have chosen to donate their data to a shared, anonymized data repository called the "OpenAPS Data Commons." The present study evaluated glycemic control and glycemic variability of CGM readings of 80 DIY closed loop users. Methods: We analyzed 19251 days (53 years) of CGM readings with a mean duration of 134 days per patient (min. 3 days, max. 917 days) after the patient started looping. Results: Mean glucose was 137 ± 20mg/dl and estimated glycated hemogloblin A1c (eA1c) was 6.40 ± 0.70%. Time in target range (70-180mg/dL) was 77.5 ± 10.5%, 4.3% of CGM readings were below 70mg/dL, 1.3% were below 54mg/dL, 18.2% were above 180mg/dL, and 4.1% of CGM readings were above 250mg/dL, respectively. A total of 6474 hypoglycemic events (CGM reading < 54mg/dL) was observed (daytime: 5004 [73.9%]; nighttime: 1765 [26.1%]), which corresponds to 0.34 hypoglycemic events per day. The mean duration of each hypoglycemia event was 65.4 ± 41.4 minutes, and 1484 events were prolonged (duration > 120 minutes; daytime: 1043 [76.30%]; nighttime: 324 [23.7%]). Coefficient of variation (CV) was 35.5 ± 5.9% (daytime: 35.4%; nighttime: 33.9%) and mean of daily differences (MODD) was 50.1 ± 13.5 mg/dL. Conclusion: Open source AP systems show potential to support stable glycemic control in people with T1D. This is the largest descriptive analysis of open source APS data to date. The results are promising, but open source APS should be investigated in additional detail before a conclusion about their safety and efficacy can be drawn. Disclosure: A. Melmer: None. T. Züger: None. D.M. Lewis: Consultant; Self; Diabeloop SA, Roche Diabetes Care. S.M. Leibrand: Consultant; Self; Diabeloop SA, Roche Diabetes Care. M. Laimer: None. [ABSTRACT FROM AUTHOR]

Background: Hypoglycemia threatens cognitive function and driving safety. Previous research investigated in-vehicle voice assistants as hypoglycemia warnings. However, they could startle drivers. To address this, we combine voice warnings with ambient LEDs., Objective: The study assesses the effect of in-vehicle multimodal warning on emotional reaction and technology acceptance among drivers with type 1 diabetes., Methods: Two studies were conducted, one in simulated driving and the other in real-world driving. A quasi-experimental design included 2 independent variables (blood glucose phase and warning modality) and 1 main dependent variable (emotional reaction). Blood glucose was manipulated via intravenous catheters, and warning modality was manipulated by combining a tablet voice warning app and LEDs. Emotional reaction was measured physiologically via skin conductance response and subjectively with the Affective Slider and tested with a mixed-effect linear model. Secondary outcomes included self-reported technology acceptance. Participants were recruited from Bern University Hospital, Switzerland., Results: The simulated and real-world driving studies involved 9 and 10 participants with type 1 diabetes, respectively. Both studies showed significant results in self-reported emotional reactions (P<.001). In simulated driving, neither warning modality nor blood glucose phase significantly affected self-reported arousal, but in real-world driving, both did (F 2,68 =4.3; P<.05 and F 2,76 =4.1; P=.03). Warning modality affected self-reported valence in simulated driving (F 2,68 =3.9; P<.05), while blood glucose phase affected it in real-world driving (F 2,76 =9.3; P<.001). Skin conductance response did not yield significant results neither in the simulated driving study (modality: F 2,68 =2.46; P=.09, blood glucose phase: F 2,68 =0.3; P=.74), nor in the real-world driving study (modality: F 2,76 =0.8; P=.47, blood glucose phase: F 2,76 =0.7; P=.5). In both simulated and real-world driving studies, the voice+LED warning modality was the most effective (simulated: mean 3.38, SD 1.06 and real-world: mean 3.5, SD 0.71) and urgent (simulated: mean 3.12, SD 0.64 and real-world: mean 3.6, SD 0.52). Annoyance varied across settings. The standard warning modality was the least effective (simulated: mean 2.25, SD 1.16 and real-world: mean 3.3, SD 1.06) and urgent (simulated: mean 1.88, SD 1.55 and real-world: mean 2.6, SD 1.26) and the most annoying (simulated: mean 2.25, SD 1.16 and real-world: mean 1.7, SD 0.95). In terms of preference, the voice warning modality outperformed the standard warning modality. In simulated driving, the voice+LED warning modality (mean rank 1.5, SD rank 0.82) was preferred over the voice (mean rank 2.2, SD rank 0.6) and standard (mean rank 2.4, SD rank 0.81) warning modalities, while in real-world driving, the voice+LED and voice warning modalities were equally preferred (mean rank 1.8, SD rank 0.79) to the standard warning modality (mean rank 2.4, SD rank 0.84)., Conclusions: Despite the mixed results, this paper highlights the potential of implementing voice assistant-based health warnings in cars and advocates for multimodal alerts to enhance hypoglycemia management while driving., Trial Registration: ClinicalTrials.gov NCT05183191; https://classic.clinicaltrials.gov/ct2/show/NCT05183191, ClinicalTrials.gov NCT05308095; https://classic.clinicaltrials.gov/ct2/show/NCT05308095., (©Caterina Bérubé, Martin Maritsch, Vera Franziska Lehmann, Mathias Kraus, Stefan Feuerriegel, Thomas Züger, Felix Wortmann, Christoph Stettler, Elgar Fleisch, A Baki Kocaballi, Tobias Kowatsch. Originally published in JMIR Human Factors (https://humanfactors.jmir.org), 18.04.2024.)

Background: Hypoglycemia is a frequent and acute complication in type 1 diabetes mellitus (T1DM) and is associated with a higher risk of car mishaps. Currently, hypoglycemia can be detected and signaled through flash glucose monitoring or continuous glucose monitoring devices, which require manual and visual interaction, thereby removing the focus of attention from the driving task. Hypoglycemia causes a decrease in attention, thereby challenging the safety of using such devices behind the wheel. Here, we present an investigation of a hands-free technology-a voice warning that can potentially be delivered via an in-vehicle voice assistant., Objective: This study aims to investigate the feasibility of an in-vehicle voice warning for hypoglycemia, evaluating both its effectiveness and user perception., Methods: We designed a voice warning and evaluated it in 3 studies. In all studies, participants received a voice warning while driving. Study 0 (n=10) assessed the feasibility of using a voice warning with healthy participants driving in a simulator. Study 1 (n=18) assessed the voice warning in participants with T1DM. Study 2 (n=20) assessed the voice warning in participants with T1DM undergoing hypoglycemia while driving in a real car. We measured participants' self-reported perception of the voice warning (with a user experience scale in study 0 and with acceptance, alliance, and trust scales in studies 1 and 2) and compliance behavior (whether they stopped the car and reaction time). In addition, we assessed technology affinity and collected the participants' verbal feedback., Results: Technology affinity was similar across studies and approximately 70% of the maximal value. Perception measure of the voice warning was approximately 62% to 78% in the simulated driving and 34% to 56% in real-world driving. Perception correlated with technology affinity on specific constructs (eg, Affinity for Technology Interaction score and intention to use, optimism and performance expectancy, behavioral intention, Session Alliance Inventory score, innovativeness and hedonic motivation, and negative correlations between discomfort and behavioral intention and discomfort and competence trust; all P<.05). Compliance was 100% in all studies, whereas reaction time was higher in study 1 (mean 23, SD 5.2 seconds) than in study 0 (mean 12.6, SD 5.7 seconds) and study 2 (mean 14.6, SD 4.3 seconds). Finally, verbal feedback showed that the participants preferred the voice warning to be less verbose and interactive., Conclusions: This is the first study to investigate the feasibility of an in-vehicle voice warning for hypoglycemia. Drivers find such an implementation useful and effective in a simulated environment, but improvements are needed in the real-world driving context. This study is a kickoff for the use of in-vehicle voice assistants for digital health interventions., (©Caterina Bérubé, Vera Franziska Lehmann, Martin Maritsch, Mathias Kraus, Stefan Feuerriegel, Felix Wortmann, Thomas Züger, Christoph Stettler, Elgar Fleisch, A Baki Kocaballi, Tobias Kowatsch. Originally published in JMIR Human Factors (https://humanfactors.jmir.org), 09.01.2024.)

Aims of the Study: To assess glucose levels in adults with diabetes at a Swiss tertiary hospital when transitioning from insulin delivery with a sensor-augmented pump with (predictive) low-glucose suspend ([P]LGS) to a hybrid-closed loop (HCL) and from a HCL to an advanced hybrid-closed loop (AHCL)., Methods: Continuous glucose monitoring data for 44 adults with type 1 diabetes transitioning from (P)LGS to hybrid-closed loop and from hybrid-closed loop to advanced hybrid-closed loop were analysed, including the percentage of time spent within, below, and above glucose ranges. In addition, a subgroup analysis (n = 14) of individuals undergoing both transitions was performed., Results: The transition from a (P)LGS to a hybrid-closed loop was associated with increased time in range (6.6% [2.6%-12.7%], p <0.001) and decreased time above range (5.6% [2.3%-12.7%], p <0.001). The transition from a hybrid-closed loop to an advanced hybrid-closed loop was associated with increased time in range (1.6% [-0.5%-4.5%], p = 0.046) and decreased time above range (1.5% [-1.8%-5.6%], p = 0.050). Both transitions did not change the time below range. In the subgroup analysis ([P]LGS → HCL → AHCL), the time in range increased from 69.4% (50.3%-79.2%) to 76.5% (65.3%-81.3%) and 78.7% (69.7%-85.8%), respectively (p <0.001)., Conclusions: Glucose levels significantly improved when transitioning from a (P)LGS to a hybrid-closed loop. Glucose levels improved further when switching from a hybrid-closed loop to an advanced hybrid-closed loop. However, the added benefit of an advanced hybrid-closed loop was comparably smaller. This pattern was also reflected in the subgroup analysis.

Introduction: The COVID-19 pandemic has forced rapid reconsideration as to the way in which health care is delivered. One potential means to provide care while avoiding unnecessary person-to-person contact is to offer remote services (telemedicine). This study aimed to (1) gather real-time information on the use and perception of telemedicine in people living with type 1 diabetes and (2) assess the challenges, such as restricted access to health care and/or medical supplies., Methods: An anonymous questionnaire was widely distributed between 24 March and 5 May 2020 using an open-access web-based platform. Data were analysed descriptively, and results were stratified according to age, sex and HbA 1c ., Results: There were 7477 survey responses from individuals in 89 countries. Globally, 30% reported that the pandemic had affected their healthcare access due to cancelled physical appointments with their healthcare providers. Thirty-two per cent reported no fundamental change in their medical follow-up during this period, with 9% stating that no personal contact was established with their doctors over the duration of the study. Twenty-eight per cent received remote care through telephone (72%) or video-calls (28%). Of these, 86% found remote appointments useful and 75% plan to have remote appointments in the future. Glucose control, indicated by HbA 1c , was positively associated with positive perception of telemedicine. In males, 45% of respondents with an HbA 1c  > 9% rated telemedicine not useful compared to those with lower HbA 1c, while 20% of females with an HbA 1c  > 9% rated it not useful (χ 2  = 14.2, P  = .0016)., Conclusion: Remote appointments have largely been perceived as positive in people with type 1 diabetes with the majority (75%) stating that they would consider remote appointments beyond the pandemic. Age and level of education do not appear to influence perception of telemedicine, whereas poor glucose control, particularly in males, seems to negatively affect perception., Competing Interests: The authors have no conflicts of interest to disclose., (© 2020 The Authors. Endocrinology, Diabetes & Metabolism published by John Wiley & Sons Ltd.)

Introduction: Early warning of future hypoglycemic and hyperglycemic events can improve the safety of type 1 diabetes mellitus (T1DM) patients. The aim of this study is to design and evaluate a hypoglycemia/hyperglycemia early warning system (EWS) for T1DM patients under sensor-augmented pump (SAP) therapy., Methods: The EWS is based on the combination of data-driven online adaptive prediction models and a warning algorithm. Three modeling approaches have been investigated: (i) autoregressive (ARX) models, (ii) auto-regressive with an output correction module (cARX) models, and (iii) recurrent neural network (RNN) models. The warning algorithm performs postprocessing of the models' outputs and issues alerts if upcoming hypoglycemic/hyperglycemic events are detected. Fusion of the cARX and RNN models, due to their complementary prediction performances, resulted in the hybrid autoregressive with an output correction module/recurrent neural network (cARN)-based EWS., Results: The EWS was evaluated on 23 T1DM patients under SAP therapy. The ARX-based system achieved hypoglycemic (hyperglycemic) event prediction with median values of accuracy of 100.0% (100.0%), detection time of 10.0 (8.0) min, and daily false alarms of 0.7 (0.5). The respective values for the cARX-based system were 100.0% (100.0%), 17.5 (14.8) min, and 1.5 (1.3) and, for the RNN-based system, were 100.0% (92.0%), 8.4 (7.0) min, and 0.1 (0.2). The hybrid cARN-based EWS presented outperforming results with 100.0% (100.0%) prediction accuracy, detection 16.7 (14.7) min in advance, and 0.8 (0.8) daily false alarms., Conclusion: Combined use of cARX and RNN models for the development of an EWS outperformed the single use of each model, achieving accurate and prompt event prediction with few false alarms, thus providing increased safety and comfort., (© 2013 Diabetes Technology Society.)