Supervised and Unsupervised Approaches for the Real-Time Detection of Undesired Insulin Suspension Caused by Malfunctions.

BACKGROUND: Automated insulin delivery (AID) systems, permit improved treatment of type 1 diabetes (T1D). Unfortunately, malfunctioning in the insulin pump or in the infusion set can prevent insulin from being administered, reducing the AID efficacy and posing the patient at risk. Different data-driven methods available in the literature can be used to deal with the problem of automatically detecting complete insulin suspension in real-time. This article investigates both supervised and unsupervised strategies and proposes a fair comparison under either population or personalized settings. METHODS: Several algorithms are compared using data generated through the UVA/Padova T1D simulator, a computer simulator widely used to test control strategies in silico and accepted by the Food and Drugs Administration (FDA) as a substitute to animal pre-clinical trials. Two synthetic data sets, each consisting of 100 virtual subjects monitored for 1 month, were generated. Occasional faults of the insulin pump are simulated as complete occlusions by suspending the therapy administration. Personalized algorithms are investigated with unsupervised approaches only, since personalized labels are hardly available. RESULTS: In the population scenario, the supervised approach outperforms the unsupervised strategy. In particular, logistic regression and random forest achieves a recall of 72% and 82%, with 0.12 and 0.21 false positives (FP) per day, respectively. In the personalized setting scenario, the unsupervised algorithms are tailored on each patient and outperform the population ones, in particular isolation forest achieves a recall 80% and 0.06 FPs per day. CONCLUSIONS: This article suggests that unsupervised personalized approach, by addressing the large variability in glucose response among individuals with T1D, is superior to other one-fits-all approaches in detecting insulin suspensions caused by malfunctioning. Population methodologies can be effectively used while waiting to collect sufficient patient data, when the system is installed on a new patient.

EEG Microstates as a Signature of Hemispheric Lateralization in Stroke.

Stroke recovery trajectories vary substantially. The need for tracking and prognostic biomarkers in stroke is utmost for prognostic and rehabilitative goals: electroencephalography (EEG) advanced signal analysis may provide useful tools toward this aim. EEG microstates quantify changes in configuration of neuronal generators of short-lasting periods of coordinated synchronized communication within large-scale brain networks: this feature is expected to be impaired in stroke. To characterize the spatio-temporal signatures of EEG microstates in stroke survivors in the acute/subacute phase, EEG microstate analysis was performed in 51 first-ever ischemic stroke survivors [(28-82) years, 24 with right hemisphere (RH) lesion] who underwent a resting-state EEG recording in the acute and subacute phase (from 48 h up to 42 days after the event). Microstates were characterized based on 4 parameters: global explained variance (GEV), mean duration, occurrences per second, and percentage of coverage. Wilcoxon Rank Sum tests were performed to compare features of each microstate across the two groups [i.e., left hemisphere (LH) and right hemisphere (RH) stroke survivors]. The canonical microstate map D, characterized by a mostly frontal topography, displayed greater GEV, occurrence per second, and percentage of coverage in LH than in RH stroke survivors (p < 0.05). The EEG microstate map B, with a left-frontal to right-posterior topography, and F, with an occipital-to-frontal topography, exhibited a greater GEV in RH than in LH stroke survivors (p = 0.015). EEG microstates identified specific topographic maps which characterize stroke survivors' lesioned hemisphere in the acute and early subacute phase. Microstate features offer an additional tool to identify different neural reorganization.

Risk of hypoglycemia in type 1 diabetes management: An in-silico sensitivity analysis to assess and rank the quantitative impact of different behavioral factors.

BACKGROUND AND OBJECTIVE: In type 1 diabetes (T1D), a quantitative evaluation of the impact on hypoglycemia of suboptimal therapeutic decision (e.g. incorrect estimation of the ingested carbohydrates, inaccurate insulin timing, etc) is unavailable. Clinical trials to measure sensitivity to patient actions would be expensive, exposed to confounding factors and risky for the participants. In this work, a T1D patient decision simulator (T1D-PDS), realistically reproducing blood glucose dynamics in a large virtual population, is used to perform extensive in-silico trials and the so-derived data employed to implement a sensitivity analysis that ranks different behavioral factors based on their impact on a clinically meaningful parameter, the time below range (TBR). METHODS: Eleven behavioral factors impacting on hypoglycemia are considered. The T1D-PDS was used to perform multiple 2-week simulations involving 100 adults, by testing about 3500 different perturbations for nominal behavior. A local linear approximation of the function linking the TBR and the factors were computed to derive sensitivity indices (SIs), quantifying the impact of each factor on TBR variations. RESULTS: The obtained ranking quantifies importance of factors w.r.t. the others. Factors apparently related to hypoglycemia were correctly placed on the top of the ranking, including systematic (SI=2.05%) and random (SI=1.35%) carb-counting error, hypotreatment dose (SI=-1.21%), insulin bolus time w.r.t. mealtime (SI=1.09%). CONCLUSIONS: The obtained SIs allowed to rank behavioral factors based on their impact on TBR. The behavioral factors identified as most influential can be prioritized in patient training.

Bayesian denoising algorithm dealing with colored, non-stationary noise in continuous glucose monitoring timeseries.

Introduction: The retrospective analysis of continuous glucose monitoring (CGM) timeseries can be hampered by colored and non-stationary measurement noise. Here, we introduce a Bayesian denoising (BD) algorithm to address both autocorrelation of measurement noise and temporal variability of its variance. Methods: BD utilizes adaptive, a-priori models of signal and noise, whose unknown variances are derived on partially-overlapped CGM windows, via smoothing approach based on linear mean square estimation. The CGM signal and noise variability profiles are then reconstructed using a kernel smoother. BD is first assessed on two simulated datasets, DS1 and DS2. On DS1, the effectiveness of accounting for colored noise is evaluated by comparison against a literature algorithm; on DS2, the effectiveness of accounting for the noise variance temporal variability is evaluated by comparison against a Butterworth filter. BD is then evaluated on 15 CGM timeseries measured by the Dexcom G6 (DR). Results: On DS1, BD allows reducing the root-mean-square-error (RMSE) from 8.10 [6.79-9.24] mg/dL to 6.28 [5.47-7.27] mg/dL (median [IQR]); on DS2, RMSE decreases from 6.85 [5.50-8.72] mg/dL to 5.35 [4.48-6.49] mg/dL. On DR, BD performs a reasonable tracking of noise variance variability and a satisfactory denoising. Discussion: The new algorithm effectively addresses the nature of CGM measurement error, outperforming existing denoising algorithms.

drCORRECT: An Algorithm for the Preventive Administration of Postprandial Corrective Insulin Boluses in Type 1 Diabetes Management.

BACKGROUND: In type 1 diabetes therapy, precise tuning of postprandial corrective insulin boluses (CIBs) is crucial to mitigate hyperglycemia without inducing dangerous hypoglycemic events. Several heuristic formulas accounting for continuous glucose monitoring (CGM) trend have been proposed in the literature. However, these formulas suggest a lot of quantized CIB adjustments, and they lack personalization. METHOD: drCORRECT algorithm proposed in this work employs a patient-specific time parameter and the "dynamic risk" (DR) measure to determine postprandial CIB suggestion. The expected benefits include the reduction of time in hyperglycemia, thanks to the preventive action exploited through DR. drCORRECT has been assessed retrospectively vs the literature methods proposed by Aleppo et al (AL), Bruttomesso et al (BR), and Ziegler et al (ZI) using a data set of 49 CGM daily traces recorded in free-living conditions. Retrospective evaluation of the algorithms is made possible by the use of ReplayBG, a digital twin-based tool that allows assessing alternative insulin therapies on already collected glucose data. Efficacy in terms of glucose control was measured by temporal, risk indicators, and dedicated hyperglycemic/hypoglycemic events metrics. RESULTS: drCORRECT significantly reduces time spent in hyperglycemia when compared with AL and BR (33.52 [24.16, 39.89]% vs 39.76 [22.54, 48.15]% and 36.32 [26.91, 45.93]%, respectively); significantly reduces daily injected insulin (5.97 [3.80, 8.06] U vs 7.5 [5.21, 10.34] U), glycemia risk index (38.78 [26.58, 55.39] vs 40.78 [27.95, 70.30]), and time spent in hypoglycemia (0.00 [0.00, 1.74]% vs 0.00 [0.00, 10.23]%) when compared with ZI, resulting overall in a safer strategy. CONCLUSIONS: The proposed drCORRECT algorithm allows preventive actions thanks to the personalized timing configuration and the introduction of the innovative DR-based CIB threshold, proving to be a valid alternative to the available heuristic literature methods.

Deep-learning-based natural-language-processing models to identify cardiovascular disease hospitalisations of patients with diabetes from routine visits' text.

Writing notes is the most widespread method to report clinical events. Therefore, most of the information about the disease history of a patient remains locked behind free-form text. Natural language processing (NLP) provides a solution to automatically transform free-form text into structured data. In the present work, electronic healthcare records data of patients with diabetes were used to develop deep-learning based NLP models to automatically identify, within free-form text describing routine visits, the occurrence of hospitalisations related to cardiovascular disease (CVDs), an outcome of diabetes. Four possible time windows of increasing level of expected difficulty were considered: infinite, 24 months, 12 months, and 6 months. Model performance was evaluated by means of the area under the precision recall curve, as well as precision, recall, and F1-score after thresholding. Results showed that the proposed NLP approach was successful for both the infinite and 24-month windows, while, as expected, performance deteriorated with shorter time windows. Possible clinical applications of tools based on the proposed NLP approach include the retrospective filling of medical records with respect to a patient's CVD history for epidemiological and research purposes as well as for clinical decision making.

The importance of interpreting machine learning models for blood glucose prediction in diabetes: an analysis using SHAP.

Machine learning has become a popular tool for learning models of complex dynamics from biomedical data. In Type 1 Diabetes (T1D) management, these models are increasingly been integrated in decision support systems (DSS) to forecast glucose levels and provide preventive therapeutic suggestions, like corrective insulin boluses (CIB), accordingly. Typically, models are chosen based on their prediction accuracy. However, since patient safety is a concern in this application, the algorithm should also be physiologically sound and its outcome should be explainable. This paper aims to discuss the importance of using tools to interpret the output of black-box models in T1D management by presenting a case-of-study on the selection of the best prediction algorithm to integrate in a DSS for CIB suggestion. By retrospectively "replaying" real patient data, we show that two long-short term memory neural networks (LSTM) (named p-LSTM and np-LSTM) with similar prediction accuracy could lead to different therapeutic decisions. An analysis with SHAP-a tool for explaining black-box models' output-unambiguously shows that only p-LSTM learnt the physiological relationship between inputs and glucose prediction, and should therefore be preferred. This is verified by showing that, when embedded in the DSS, only p-LSTM can improve patients' glycemic control.

A Markov Model of Gap Occurrence in Continuous Glucose Monitoring Data for Realistic in Silico Clinical Trials.

BACKGROUND AND OBJECTIVE: Continuous glucose monitoring (CGM) sensors measure interstitial glucose concentration every 1-5 min for days or weeks. New CGM-based diabetes therapies are often tested in in silico clinical trials (ISCTs) using diabetes simulators. Accurate models of CGM sensor inaccuracies and failures could help improve the realism of ISCTs. However, the modeling of CGM failures has not yet been fully addressed in the literature. This work aims to develop a mathematical model of CGM gaps, i.e., occasional portions of missing data generated by temporary sensor errors (e.g., excessive noise or artifacts). METHODS: Two datasets containing CGM traces collected in 167 adults and 205 children, respectively, using the Dexcom G6 sensor (Dexcom Inc., San Diego, CA) were used. Four Markov models, of increasing complexity, were designed to describe three main characteristics: number of gaps for each sensor, gap distribution in the monitoring days, and gap duration. Each model was identified on a portion of each dataset (training set). The remaining portion of each dataset (real test set) was used to evaluate model performance through a Monte Carlo simulation approach. Each model was used to generate 100 simulated test sets with the same size as the real test set. The distributions of gap characteristics on the simulated test sets were compared with those observed on the real test set, using the two-sample Kolmogorov-Smirnov test and the Jensen-Shannon divergence. RESULTS: A six-state Markov model, having two states to describe normal sensor operation and four states to describe gap occurrence, achieved the best results. For this model, the Kolmogorov-Smirnov test found no significant differences between the distribution of simulated and real gap characteristics. Moreover, this model obtained significantly lower Jensen-Shannon divergence values than the other models. CONCLUSIONS: A Markov model describing CGM gaps was developed and validated on two real datasets. The model describes well the number of gaps for each sensor, the gap distribution over monitoring days, and the gap durations. Such a model can be integrated into existing diabetes simulators to realistically simulate CGM gaps in ISCTs and thus enable the development of more effective and robust diabetes management strategies.

ReplayBG: A Digital Twin-Based Methodology to Identify a Personalized Model From Type 1 Diabetes Data and Simulate Glucose Concentrations to Assess Alternative Therapies.

OBJECTIVE: Design and assessment of new therapies for type 1 diabetes (T1D) management can be greatly facilitated by in silico simulations. The ReplayBG simulation methodology here proposed allows "replaying" the scenario behind data already collected by simulating the glucose concentration obtained in response to alternative insulin/carbohydrate therapies and evaluate their efficacy leveraging the concept of digital twin. METHODS: ReplayBG is based on two steps. First, a personalized model of glucose-insulin dynamics is identified using insulin, carbohydrate, and continuous glucose monitoring (CGM) data. Then, this model is used to simulate the glucose concentration that would have been obtained by "replaying" the same portion of data using a different therapy. The validity of the methodology was evaluated on 100 virtual subjects using the UVa/Padova T1D Simulator (T1DS). In particular, the glucose concentration traces simulated by ReplayBG are compared with those provided by T1DS in five different scenarios of insulin and carbohydrate treatment modifications. Furthermore, we compared ReplayBG with a state-of-the-art methodology for the scope. Finally, two case studies using real data are also presented. RESULTS: ReplayBG simulates with high accuracy the effect of the considered insulin and carbohydrate treatment alterations, performing significantly better than state-of-art method in almost all considered situations. CONCLUSION: ReplayBG proved to be a reliable and robust tool to retrospectively explore the effect of new treatments for T1D on the glucose dynamics. It is freely available as open source software at https://github.com/gcappon/replay-bg. SIGNIFICANCE: ReplayBG offers a new approach to preliminary evaluate new therapies for T1D management before clinical trials.

Individualized Models for Glucose Prediction in Type 1 Diabetes: Comparing Black-Box Approaches to a Physiological White-Box One.

OBJECTIVE: Accurate blood glucose (BG) prediction are key in next-generation tools for type 1 diabetes (T1D) management, such as improved decision support systems and advanced closed-loop control. Glucose prediction algorithms commonly rely on black-box models. Large physiological models, successfully adopted for simulation, were little explored for glucose prediction, mostly because their parameters are hard to individualize. In this work, we develop a BG prediction algorithm based on a personalized physiological model inspired by the UVA/Padova T1D Simulator. Then we compare white-box and advanced black-box personalized prediction techniques. METHODS: A personalized nonlinear physiological model is identified from patient data through a Bayesian approach based on Markov Chain Monte Carlo technique. The individualized model was integrated within a particle filter (PF) to predict future BG concentrations. The black-box methodologies considered are non-parametric models estimated via gaussian regression (NP), three deep learning methods: long-short-term-memory (LSTM), gated recurrent unit (GRU), temporal convolutional networks (TCN), and a recursive autoregressive with exogenous input model (rARX). BG forecasting performances are assessed for several prediction horizons (PH) on 12 individuals with T1D, monitored in free-living conditions under open-loop therapy for 10 weeks. RESULTS: NP models provide the most effective BG predictions by achieving a root mean square error (RMSE), RMSE = 18.99 mg/dL, RMSE = 25.72 mg/dL and RMSE = 31.60 mg/dL, significantly outperforming: LSTM, GRU (for PH = 30 minutes), TCN, rARX, and the proposed physiological model for PH=30, 45 and 60 minutes. CONCLUSIONS: Black-box strategies remain preferable for glucose prediction even when compared to a white-box model with sound physiological structure and individualized parameters.

AGATA: A Toolbox for Automated Glucose Data Analysis.

BACKGROUND: Analyzing continuous glucose monitoring (CGM) data is a mandatory step for multiple purposes spanning from reporting clinical trial outcomes to developing new algorithms for diabetes management. This task is repetitive, and scientists struggle in computing literature glucose control metrics and waste time in reproducing possibly complex plots and reports. For this reason, to provide the diabetes technology community a unified tool, here we present Automated Glucose dATa Analysis (AGATA), an automated glucose data analysis toolbox developed in MATLAB/Octave. METHODS: Automated Glucose dATa Analysis is an open-source software program to visualize and preprocess CGM data, compute glucose control metrics, detect adverse events, evaluate the effectiveness of users' prediction algorithms, and compare study arms. Automated Glucose dATa Analysis can be used as a standalone computer application accessible through a dedicated graphical user interface, particularly suitable for clinicians, or by integrating its functionalities in user-defined MATLAB/Octave scripts, which fits the need of researchers and developers. To demonstrate its features, we used AGATA to analyze CGM data of two subjects extracted from a publicly available data set of individuals with type one diabetes. Finally, AGATA's features are compared against those of 12 noncommercial software programs for CGM data analysis. RESULTS: Using AGATA, we easily preprocessed, analyzed, and visualized CGM data in a handy way, in compliance with the requirements and the standards defined in the literature. Compared to the other considered software programs, AGATA offers more functionalities and capabilities. CONCLUSION: Automated Glucose dATa Analysis is easy to use and reduces the burden of CGM data analysis. It is freely available in GitHub at https://github.com/gcappon/agata.

Methods for Insulin Bolus Adjustment Based on the Continuous Glucose Monitoring Trend Arrows in Type 1 Diabetes: Performance and Safety Assessment in an In Silico Clinical Trial.

BACKGROUND: Providing real-time magnitude and direction of glucose rate-of-change (ROC) via trend arrows represents one of the major strengths of continuous glucose monitoring (CGM) sensors in managing type 1 diabetes (T1D). Several literature methods were proposed to adjust the standard formula (SF) used for insulin bolus calculation by accounting for glucose ROC, but each of them provides different suggestions, making it difficult to understand which should be applied in practice. This work aims at performing an extensive in-silico assessment of their performance and safety. METHODS: The methods of Buckingham (BU), Scheiner (SC), Pettus/Edelman (PE), Klonoff/Kerr (KL), Aleppo/Laffel (AL), Ziegler (ZI), and Bruttomesso (BR) were evaluated using the UVa/Padova T1D simulator, in single-meal scenarios, where ROC and glucose at mealtime varied between [-2,+2] mg/dL/min and [80,200] mg/dL, respectively. Efficacy of postprandial glucose control was quantitatively assessed by time in, above and below range (TIR, TAR, and TBR, respectively). RESULTS: For negative ROCs, all methods proved to increase TIR and decrease TAR and TBR vs SF, with KL, PE, and BR being the most effective. For positive ROCs, a general worsening of the performances is present, only BR improved the glycemic control when mealtime glucose was close to hypoglycemia, while SC resulted the safest in the other conditions. CONCLUSIONS: Insulin bolus adjustment methods are effective for negative ROCs, but they generally appear to overdose for positive ROCs, calling for safer strategies in such a scenario. These results can be useful in outlining guidelines to identify which adjustment to apply based on the mealtime condition.

Combined Use of Glucose-Specific Model Identification and Alarm Strategy Based on Prediction-Funnel to Improve Online Forecasting of Hypoglycemic Events.

BACKGROUND: Advanced decision support systems for type 1 diabetes (T1D) management often embed prediction modules, which allow T1D people to take preventive actions to avoid critical episodes like hypoglycemia. Real-time prediction of blood glucose (BG) concentration relies on a subject-specific model of glucose-insulin dynamics. Model parameter identification is usually based on the mean square error (MSE) cost function, and the model is usually used to predict BG at a single prediction horizon (PH). Finally, a hypo-alarm is raised if the predicted BG crosses a threshold. This work aims to show that real-time hypoglycemia forecasting can be improved by leveraging: a glucose-specific mean square error (gMSE) cost function in model's parameters identification, and a "prediction-funnel," that is, confidence intervals (CIs) for multiple PHs, within the hypo-alarm-raising strategy. METHODS: Autoregressive integrated moving average with exogenous input (ARIMAX) models are selected to illustrate the proposed solution (use of gMSE and prediction-funnel) and its assessment against the conventional approach (MSE and single PH). The gMSE penalizes the model misfit in unsafe BG ranges (e.g., hypoglycemia), and the prediction-funnel allows raising an alarm by monitoring if the CIs cross a suitable threshold. The algorithms were evaluated by measuring precision (P), recall (R), F1-score (F1), false positive per day (FP/day), and time gain (TG) on a real dataset collected in 11 T1D individuals. RESULTS: The best performance is achieved exploiting both the gMSE and the prediction-funnel: P = 65%, R = 88%, F1 = 75%, FP/day = 0.29, and mean TG = 15 minutes. CONCLUSIONS: The combined use of a glucose-specific metric and an alarm-raising strategy based on the prediction-funnel allows achieving a more effective and reliable hypoglycemia prediction algorithm.

Management of type 2 diabetes with a treat-to-benefit approach improved long-term cardiovascular outcomes under routine care.

BACKGROUND: Results of cardiovascular outcome trials enabled a shift from "treat-to-target" to "treat-to-benefit" paradigm in the management of type 2 diabetes (T2D). However, studies validating such approach are limited. Here, we examined whether treatment according to international recommendations for the pharmacological management of T2D had an impact on long-term outcomes. METHODS: This was an observational study conducted on outpatient data collected in 2008-2018 (i.e. prior to the "treat-to-benefit" shift). We defined 6 domains of treatment based on the ADA/EASD consensus covering all disease stages: first- and second-line treatment, intensification, use of insulin, cardioprotective, and weight-affecting drugs. At each visit, patients were included in Group 1 if at least one domain deviated from recommendation or in Group 2 if aligned with recommendations. We used Cox proportional hazard models with time-dependent co-variates or Cox marginal structural models (with inverse-probability of treatment weighing evaluated at each visit) to adjust for confounding factors and evaluate three outcomes: major adverse cardiovascular events (MACE), hospitalization for heart failure or cardiovascular mortality (HF-CVM), and all-cause mortality. RESULTS: We included 5419 patients, on average 66-year old, 41% women, with a baseline diabetes duration of 7.6 years. Only 11.7% had pre-existing cardiovascular disease. During a median follow-up of 7.3 years, patients were seen 12 times at the clinic, and we recorded 1325 MACE, 1593 HF-CVM, and 917 deaths. By the end of the study, each patient spent on average 63.6% of time in Group 1. In the fully adjusted model, being always in Group 2 was associated with a 45% lower risk of MACE (HR 0.55; 95% C.I. 0.46-0.66; p < 0.0001) as compared to being in Group 1. The corresponding HF-CVM and mortality risk were similar (HR 0.56; 95%CI 0.47-0.66, p < 0.0001 and HR 0.56; 95% C.I. 0.45-0.70; p < 0.0001. respectively). Sensitivity analyses confirmed these results. No single domain individually explained the better outcome of Group 2, which remained significant in all subgroups. CONCLUSION: Managing patients with T2D according to a "treat-to-benefit" approach based international standards was associated with a lower risk of MACE, heart failure, and mortality. These data provide ex-post validation of the ADA/EASD treatment algorithm.

Assessment of Seasonal Stochastic Local Models for Glucose Prediction without Meal Size Information under Free-Living Conditions.

Accurate blood glucose (BG) forecasting is key in diabetes management, as it allows preventive actions to mitigate harmful hypoglycemic/hyperglycemic episodes. Considering the encouraging results obtained by seasonal stochastic models in proof-of-concept studies, this work assesses the methodology in two datasets (open-loop and closed-loop) recorded in free-living conditions. First, similar postprandial glycemic profiles are grouped together with fuzzy C-means clustering. Then, a seasonal stochastic model is identified for each cluster. Finally, real-time BG forecasting is performed by weighting each model's prediction. The proposed methodology (named C-SARIMA) is compared to other linear and nonlinear black-box methods: autoregressive integrated moving average (ARIMA), its variant with input (ARIMAX), a feed-forward neural network (NN), and its modified version (NN-X) fed by BG, insulin, and carbohydrates (timing and dosing) information for several prediction horizons (PHs). In the open-loop dataset, C-SARIMA grants a median root-mean-squared error (RMSE) of 20.13 mg/dL (PH = 30) and 27.23 mg/dL (PH = 45), not significantly different from ARIMA and NN. Over a longer PH, C-SARIMA achieves an RMSE = 31.96 mg/dL (PH = 60) and RMSE = 33.91 mg/dL (PH = 75), significantly outperforming the ARIMA and NN, without significant differences from the ARIMAX for PH ≥ 45 and the NN-X for PH ≥ 60. Similar results hold on the closed-loop dataset: for PH = 30 and 45 min, the C-SARIMA achieves an RMSE = 21.63 mg/dL and RMSE = 29.67 mg/dL, not significantly different from the ARIMA and NN. On longer PH, the C-SARIMA outperforms the ARIMA for PH > 45 and the NN for PH > 60 without significant differences from the ARIMAX for PH ≥ 45. Although using less input information, the C-SARIMA achieves similar performance to other prediction methods such as the ARIMAX and NN-X and outperforming the CGM-only approaches on PH > 45min.

Data-Driven Supervised Compression Artifacts Detection on Continuous Glucose Sensors.

Continuous Glucose Monitoring (CGM) sensors micro-invasively provide frequent glucose readings, improving the management of Type 1 diabetic patients' life and making available reach data-sets for retrospective analysis. Unlikely, CGM sensors are subject to failures, such as compression artifacts, that might impact on both real-time and respective CGM use. In this work is focused on retrospective detection of compression artifacts. An in-silico dataset is generated using the T1D UVa/Padova simulator and compression artifacts are subsequently added in known position, thus creating a dataset with perfectly accurate faulty/not-faulty labels. The problem of compression artifact detection is then faced with supervised data-driven techniques, in particular using Random Forest algorithm. The detection performance guaranteed by the method on in-silico data is satisfactory, opening the way for further analysis on real-data.

Sleep spindles changes in people with previous COVID-19 infection.

Stage 2 sleep spindles are considered useful biomarkers for the integrity of the central nervous system and for cognitive and memory skills. We investigated sleep spindles patterns in subjects after 12 months of their hospitalization in the intensive care unit (ICU) of the Padova Teaching Hospital due to COVID-19 between March and November 2020. Before the nap, participants (13 hospitalized in ICU - ICU; 9 hospitalized who received noninvasive ventilation - nonlCU; 9 age and sex-matched healthy controls - CTRL, i.e., not infected by COVID-19) underwent a cognitive and psychological as-sessment. During the nap, high-density electroencephalography (EEG) recordings were acquired. Slow (i.e., [9]-[12] Hz) and fast (i.e.,]12-16] Hz) spindles were automatically detected. Spindle density and spindle source reconstruction in brain grey matter were extracted. The psychological assessment revealed a statistical difference comparing CTRL and nonlCU in Beck Depression Inventory score and in the Physical Quality of Life index (pvalue = 0.03). The cognitive assessment revealed a trend of worsening results in executive functions in COVID-19 survivors. Slow spindle density significantly decreased comparing CTRL to COVID-19 survivors (pvalue= 0.001). There were statistically significant differences in EEG source-waveforms fast spindle amplitude onset among the three groups, mainly between CTRL and nonlCU. Clinical Relevance- Our results suggest that nonlCU were more susceptible to the hospitalization experience than ICU participants with a slight effect on cognitive tests. This impacted the spindle generation revealing a decreased density of slow spindles and affecting the generators of fast spindles in COVID-19 survivors especially in nonlCU.

Time-resolved trajectory of glucose lowering medications and cardiovascular outcomes in type 2 diabetes: a recurrent neural network analysis.

AIM: Treatment algorithms define lines of glucose lowering medications (GLM) for the management of type 2 diabetes (T2D), but whether therapeutic trajectories are associated with major adverse cardiovascular events (MACE) is unclear. We explored whether the temporal resolution of GLM usage discriminates patients who experienced a 4P-MACE (heart failure, myocardial infarction, stroke, death for all causes). METHODS: We used an administrative database (Veneto region, North-East Italy, 2011-2018) and implemented recurrent neural networks (RNN) with outcome-specific attention maps. The model input included age, sex, diabetes duration, and a matrix of GLM pattern before the 4P-MACE or censoring. Model output was discrimination, reported as area under receiver characteristic curve (AUROC). Attention maps were produced to show medications whose time-resolved trajectories were the most important for discrimination. RESULTS: The analysis was conducted on 147,135 patients for training and model selection and on 10,000 patients for validation. Collected data spanned a period of ~ 6 years. The RNN model efficiently discriminated temporal patterns of GLM ending in a 4P-MACE vs. those ending in an event-free censoring with an AUROC of 0.911 (95% C.I. 0.904-0.919). This excellent performance was significantly better than that of other models not incorporating time-resolved GLM trajectories: (i) a logistic regression on the bag-of-words encoding all GLM ever taken by the patient (AUROC 0.754; 95% C.I. 0.743-0.765); (ii) a model including the sequence of GLM without temporal relationships (AUROC 0.749; 95% C.I. 0.737-0.761); (iii) a RNN model with the same construction rules but including a time-inverted or randomised order of GLM. Attention maps identified the time-resolved pattern of most common first-line (metformin), second-line (sulphonylureas) GLM, and insulin (glargine) as those determining discrimination capacity. CONCLUSIONS: The time-resolved pattern of GLM use identified patients with subsequent cardiovascular events better than the mere list or sequence of prescribed GLM. Thus, a patient's therapeutic trajectory could determine disease outcomes.

High-density EEG sleep correlates of cognitive and affective impairment at 12-month follow-up after COVID-19.

OBJECTIVE: To disentangle the pathophysiology of cognitive/affective impairment in Coronavirus Disease-2019 (COVID-19), we studied long-term cognitive and affective sequelae and sleep high-density electroencephalography (EEG) at 12-month follow-up in people with a previous hospital admission for acute COVID-19. METHODS: People discharged from an intensive care unit (ICU) and a sub-intensive ward (nonICU) between March and May 2020 were contacted between March and June 2021. Participants underwent cognitive, psychological, and sleep assessment. High-density EEG recording was acquired during a nap. Slow and fast spindles density/amplitude/frequency and source reconstruction in brain gray matter were extracted. The relationship between psychological and cognitive findings was explored with Pearson correlation. RESULTS: We enrolled 33 participants ( 17 nonICU) and 12 controls. We observed a lower Physical Quality of Life index, higher post-traumatic stress disorder (PTSD) score, and a worse executive function performance in nonICU participants. Higher PTSD and Beck Depression Inventory scores correlated with lower executive performance. The same group showed a reorganization of spindle cortical generators. CONCLUSIONS: Our results show executive and psycho-affective deficits and spindle alterations in COVID-19 survivors - especially in nonICU participants - after 12 months from discharge. SIGNIFICANCE: These findings may be suggestive of a crucial contribution of stress experienced during hospital admission on long-term cognitive functioning.

Performance assessment across different care settings of a heart failure hospitalisation risk-score for type 2 diabetes using administrative claims.

Predicting the risk of cardiovascular complications, in particular heart failure hospitalisation (HHF), can improve the management of type 2 diabetes (T2D). Most predictive models proposed so far rely on clinical data not available at the higher Institutional level. Therefore, it is of interest to assess the risk of HHF in people with T2D using administrative claims data only, which are more easily obtainable and could allow public health systems to identify high-risk individuals. In this paper, the administrative claims of > 175,000 patients with T2D were used to develop a new risk score for HHF based on Cox regression. Internal validation on the administrative data cohort yielded satisfactory results in terms of discrimination (max AUROC = 0.792, C-index = 0.786) and calibration (Hosmer-Lemeshow test p value < 0.05). The risk score was then tested on data gathered from two independent centers (one diabetes outpatient clinic and one primary care network) to demonstrate its applicability to different care settings in the medium-long term. Thanks to the large size and broad demographics of the administrative dataset used for training, the proposed model was able to predict HHF without significant performance loss concerning bespoke models developed within each setting using more informative, but harder-to-acquire clinical variables.