Publications
171 results found
Avari P, Leal Y, Herrero Vinas P, et al., 2021, Safety and feasibility of the PEPPER adaptive bolus advisor and safety system; a randomized control study, Diabetes Technology and Therapeutics, Vol: 23, Pages: 175-186, ISSN: 1520-9156
Background: The Patient Empowerment through Predictive Personalized Decision Support (PEPPER) system provides personalized bolus advice for people with type 1 diabetes. The system incorporates an adaptive insulin recommender system (based on case-based reasoning, an artificial intelligence methodology), coupled with a safety system, which includes predictive glucose alerts and alarms, predictive low-glucose suspend, personalized carbohydrate recommendations, and dynamic bolus insulin constraint. We evaluated the safety and efficacy of the PEPPER system compared to a standard bolus calculator.Methods: This was an open-labeled multicenter randomized controlled crossover study. Following 4-week run-in, participants were randomized to PEPPER/Control or Control/PEPPER in a 1:1 ratio for 12 weeks. Participants then crossed over after a washout period. The primary end-point was percentage time in range (TIR, 3.9–10.0 mmol/L [70–180 mg/dL]). Secondary outcomes included glycemic variability, quality of life, and outcomes on the safety system and insulin recommender.Results: Fifty-four participants on multiple daily injections (MDI) or insulin pump completed the run-in period, making up the intention-to-treat analysis. Median (interquartile range) age was 41.5 (32.3–49.8) years, diabetes duration 21.0 (11.5–26.0) years, and HbA1c 61.0 (58.0–66.1) mmol/mol. No significant difference was observed for percentage TIR between the PEPPER and Control groups (62.5 [52.1–67.8] % vs. 58.4 [49.6–64.3] %, respectively, P = 0.27). For quality of life, participants reported higher perceived hypoglycemia with the PEPPER system despite no objective difference in time spent in hypoglycemia.Conclusions: The PEPPER system was safe, but did not change glycemic outcomes, compared to control. There is wide scope for integrating PEPPER into routine diabetes management for pump and MDI users. Further studies are required to confir
Rawson TM, Hernandez B, Wilson R, et al., 2021, Supervised machine learning to support the diagnosis of bacterial infection in the context of COVID-19, JAC-Antimicrobial Resistance, Vol: 3, Pages: 1-4, ISSN: 2632-1823
Background: Bacterial infection has been challenging to diagnose in patients with COVID-19. We developed and evaluated supervised machine learning algorithms to support the diagnosis of secondary bacterial infection in hospitalized patients during COVID-19.Methods: Inpatient data at three London hospitals for the first COVD-19 wave in March and April 2020 were extracted. Demographic, blood test, and microbiology data for individuals with and without SARS-CoV-2 positive PCR were obtained. A Gaussian-Naïve Bayes (GNB), Support Vector Machine (SVM), and Artificial Neuronal Network (ANN) were trained and compared using the area under the receiver operating characteristic curve (AUCROC). The best performing algorithm (SVM with 21 blood test variables) was prospectively piloted in July 2020. AUCROC was calculated for the prediction of a positive microbiological sample within 48 hours of admission. Results: A total of 15,599 daily blood profiles for 1,186 individual patients were identified to train the algorithms. 771/1186 (65%) individuals were SARS-CoV-2 PCR positive. Clinically significant microbiology results were present for 166/1186 (14%) patients during admission. A SVM algorithm trained with 21 routine blood test variables and over 8000 individual profiles had the best performance. AUCROC was 0.913, sensitivity 0.801, and specificity 0.890. Prospective testing on 54 patients on admission (28/54, 52% SARS-CoV-2 PCR positive) demonstrated an AUCROC of 0.960 (0.90-1.00). Conclusion: A SVM using 21 routine blood test variables had excellent performance at inferring the likelihood of positive microbiology. Further prospective evaluation of the algorithms ability to support decision making for the diagnosis of bacterial infection in COVID-19 cohorts is underway.
Contreras I, Calm R, Sainz MA, et al., 2021, Combining Grammatical Evolution with Modal Interval Analysis: An Application to Solve Problems with Uncertainty, MATHEMATICS, Vol: 9
- Author Web Link
- Cite
- Citations: 1
Zhu T, Kuang L, Li K, et al., 2021, Blood Glucose Prediction in Type 1 Diabetes Using Deep Learning on the Edge, IEEE International Symposium on Circuits and Systems (IEEE ISCAS), Publisher: IEEE, ISSN: 0271-4302
- Author Web Link
- Cite
- Citations: 1
Kuang L, Zhu T, Li K, et al., 2021, Live Demonstration: An IoT Wearable Device for Real-time Blood Glucose Prediction with Edge AI, IEEE Biomedical Circuits and Systems Conference (IEEE BioCAS), Publisher: IEEE
- Author Web Link
- Cite
- Citations: 1
Moscardo V, Herrero P, Reddy M, et al., 2020, Assessment of Glucose Control Metrics by Discriminant Ratio, DIABETES TECHNOLOGY & THERAPEUTICS, Vol: 22, Pages: 719-726, ISSN: 1520-9156
Zhu T, Li K, Chen J, et al., 2020, Dilated Recurrent Neural Networks for Glucose Forecasting in Type 1 Diabetes, JOURNAL OF HEALTHCARE INFORMATICS RESEARCH, Vol: 4, Pages: 308-324, ISSN: 2509-4971
Zhu T, Li K, Kuang L, et al., 2020, An Insulin Bolus Advisor for Type 1 Diabetes Using Deep Reinforcement Learning, SENSORS, Vol: 20
- Author Web Link
- Cite
- Citations: 17
Guemes A, Cappon G, Hernandez B, et al., 2020, Predicting quality of overnight glycaemic control in type 1 diabetes using binary classifiers, IEEE Journal of Biomedical and Health Informatics, Vol: 24, Pages: 1439-1446, ISSN: 2168-2194
In type 1 diabetes management, maintaining nocturnal blood glucose within target range can be challenging. Although semi-automatic systems to modulate insulin pump delivery, such as low-glucose insulin suspension and the artificial pancreas, are starting to become a reality, their elevated cost and performance below user expectations is hindering their adoption. Hence, a decision support system that helps people with type 1 diabetes, on multiple daily injections or insulin pump therapy, to avoid undesirable overnight blood glucose fluctuations (hyper- or hypoglycaemic) is an attractive alternative. In this paper, we introduce a novel data-driven approach to predict the quality of overnight glycaemic control in people with type 1 diabetes by analyzing commonly gathered data during the day-time period (continuous glucose monitoring data, meal intake and insulin boluses). The proposed approach is able to predict whether overnight blood glucose concentrations are going to remain within or outside the target range, and therefore allows the user to take the appropriate preventive action (snack or change in basal insulin). For this purpose, a number of popular established machine learning algorithms for classification were evaluated and compared on a publicly available clinical dataset (i.e. OhioT1DM). Although there is no clearly superior classification algorithm, this study indicates that, by using commonly gathered data in type 1 diabetes management, it is possible to predict the quality of overnight glycaemic control with reasonable accuracy (AUC-ROC= 0.7).
Fernandes AFM, Henriques CAO, Mano RDP, et al., 2020, Low-diffusion Xe-He gas mixtures for rare-event detection: electroluminescence yield, JOURNAL OF HIGH ENERGY PHYSICS, ISSN: 1029-8479
- Author Web Link
- Cite
- Citations: 5
Zhu T, Li K, Uduku C, et al., 2020, PERSONALIZED MEAL INSULIN BOLUS FOR TYPE 1 DIABETES USING DEEP REINFORCEMENT LEARNING, Publisher: MARY ANN LIEBERT, INC, Pages: A115-A116, ISSN: 1520-9156
Daniels J, Zhu T, Li K, et al., 2020, Arises: an advanced clinical decision support platform for the management of type 1 diabetes, The conference name (including place and date(s) of the conference): 13th International Conference on Advanced Technologies & Treatments for Diabetes (ATTD 2020), Publisher: Mary Ann Liebert, Pages: A57-A57, ISSN: 1520-9156
Herrero P, Alalitei A, Reddy M, et al., 2020, Robust determination of the optimal continuous glucose monitoring length of intervention to evaluate long-term glycaemic control, 13th International Conference on Advanced Technologies & Treatments for Diabetes (ATTD 2020), Publisher: Mary Ann Liebert, Pages: A130-A130, ISSN: 1520-9156
Waite M, Aldea A, Avari P, et al., 2020, TRUST AND CONTEXTUAL ENGAGEMENT WITH THE PEPPER SYSTEM: THE QUALITATIVE FINDINGS OF A CLINICAL FEASIBILITY STUDY, Publisher: MARY ANN LIEBERT, INC, Pages: A18-A19, ISSN: 1520-9156
Spence R, Li K, Uduku C, et al., 2020, A NOVEL HAND-HELD INTERFACE SUPPORTING THE SELF-MANAGEMENT OF TYPE 1 DIABETES, Publisher: MARY ANN LIEBERT, INC, Pages: A58-A58, ISSN: 1520-9156
- Author Web Link
- Cite
- Citations: 1
Li K, Daniels J, Liu C, et al., 2020, Convolutional recurrent neural networks for glucose prediction, IEEE Journal of Biomedical and Health Informatics, Vol: 24, Pages: 603-613, ISSN: 2168-2194
Control of blood glucose is essential for diabetes management. Current digital therapeutic approaches for subjects with Type 1 diabetes mellitus (T1DM) such as the artificial pancreas and insulin bolus calculators leverage machine learning techniques for predicting subcutaneous glucose for improved control. Deep learning has recently been applied in healthcare and medical research to achieve state-of-the-art results in a range of tasks including disease diagnosis, and patient state prediction among others. In this work, we present a deep learning model that is capable of forecasting glucose levels with leading accuracy for simulated patient cases (RMSE = 9.38±0.71 [mg/dL] over a 30-minute horizon, RMSE = 18.87±2.25 [mg/dL] over a 60-minute horizon) and real patient cases (RMSE = 21.07±2.35 [mg/dL] for 30-minute, RMSE = 33.27±4.79\% for 60-minute). In addition, the model provides competitive performance in providing effective prediction horizon ( PHeff) with minimal time lag both in a simulated patient dataset ( PHeff = 29.0±0.7 for 30-min and PHeff = 49.8±2.9 for 60-min) and in a real patient dataset ( PHeff = 19.3±3.1 for 30-min and PHeff = 29.3±9.4 for 60-min). This approach is evaluated on a dataset of 10 simulated cases generated from the UVa/Padova simulator and a clinical dataset of 10 real cases each containing glucose readings, insulin bolus, and meal (carbohydrate) data. Performance of the recurrent convolutional neural network is benchmarked against four algorithms. The proposed algorithm is implemented on an Android mobile phone, with an execution time of 6ms on a phone compared to an execution time of 780ms on a laptop.
Avari P, Leal Y, Wos M, et al., 2020, Efficacy and safety of the patient empowerment through predictive personalised decision support (pepper) system: an open-label randomised controlled trial, The conference name (including place and date(s) of the conference): 13th International Conference on Advanced Technologies & Treatments for Diabetes (ATTD 2020), Publisher: Mary Ann Liebert, Pages: A104-A104, ISSN: 1520-9156
Daniels J, Herrero P, Georgiou P, 2020, Personalised glucose prediction via deep multitask networks, Pages: 110-114, ISSN: 1613-0073
Glucose control is an essential requirement in primary therapy for diabetes management. Digital approaches to maintaining tight glycaemic control, such as clinical decision support systems and artificial pancreas systems rely on continuous glucose monitoring devices and self-reported data, which is usually improved through glucose forecasting. In this work, we develop a multitask approach using convolutional recurrent neural networks (MTCRNN) to provide short-term forecasts using the OhioT1DM dataset which comprises 12 participants. We obtain the following results - 30 min: 19.79±0.06 mg/dL (RMSE); 13.62±0.05 mg/dL (MAE) and 60 min: 33.73±0.24 mg/dL (RMSE); 24.54±0.15 mg/dL (MAE). Multitask learning facilitates an approach that allows for learning with the data from all available subjects, thereby overcoming the common challenge of insufficient individual datasets while learning appropriate individual models for each participant.
Zhu T, Yao X, Li K, et al., 2020, Blood glucose prediction for type 1 diabetes using generative adversarial networks, Pages: 90-94, ISSN: 1613-0073
Maintaining blood glucose in a target range is essential for people living with Type 1 diabetes in order to avoid excessive periods in hypoglycemia and hyperglycemia which can result in severe complications. Accurate blood glucose prediction can reduce this risk and enhance early interventions to improve diabetes management. However, due to the complex nature of glucose metabolism and the various lifestyle related factors which can disrupt this, diabetes management still remains challenging. In this work we propose a novel deep learning model to predict future BG levels based on the historical continuous glucose monitoring measurements, meal ingestion, and insulin delivery. We adopt a modified architecture of the generative adversarial network that comprises of a generator and a discriminator. The generator computes the BG predictions by a recurrent neural network with gated recurrent units, and the auxiliary discriminator employs a one-dimensional convolutional neural network to distinguish between the predictive and real BG values. Two modules are trained in an adversarial process with a combination of loss. The experiments were conducted using the OhioT1DM dataset that contains the data of six T1D contributors over 40 days. The proposed algorithm achieves an average root mean square error (RMSE) of 18.34 ± 0.17 mg/dL with a mean absolute error (MAE) of 13.37 ± 0.18 mg/dL for the 30-minute prediction horizon (PH) and an average RMSE of 32.31 ± 0.46 mg/dL with a MAE of 24.20 ± 0.42 for the 60-minute PH. The results are compared for clinical relevance using the Clarke error grid which confirms the promising performance of the proposed model.
Duce DA, Martin C, Russell A, et al., 2020, Visualizing Usage Data from a Diabetes Management System, Pages: 1-9
This article explores the role for visualization in interpreting data collected by a customised analytics framework within a healthcare technology project. It draws on the work of the EU-funded PEPPER project, which has created a personalised decision-support system for people with type 1 diabetes. Our approach was an exercise in exploratory visualization, as described by Bergeron's three category taxonomy. The charts revealed different patterns of interaction, including variability in insulin dosing schedule, and potential causes of rejected advice. These insights into user behaviour are of especial value to this field, as they may help clinicians and developers understand some of the obstacles that hinder the uptake of diabetes technology.
Liu C, Avari P, Leal Y, et al., 2020, A modular safety system for an insulin dose recommender: a feasibility study., Journal of Diabetes Science and Technology, Vol: 14, Pages: 87-96, ISSN: 1932-2968
BACKGROUND: Delivering insulin in type 1 diabetes is a challenging, and potentially risky, activity; hence the importance of including safety measures as part of any insulin dosing or recommender system. This work presents and clinically evaluates a modular safety system that is part of an intelligent insulin dose recommender platform developed within the EU-funded PEPPER project. METHODS: The proposed safety system is composed of four modules which use a novel glucose forecasting algorithm. These modules are predictive glucose alerts and alarms; a predictive low-glucose basal insulin suspension module; an advanced rescue carbohydrate recommender for resolving hypoglycemia; and a personalized safety constraint applied to insulin recommendations. The technical feasibility of the proposed safety system was evaluated in a pilot study including eight adult subjects with type 1 diabetes on multiple daily injections over a duration of six weeks. Glycemic control and safety system functioning were compared between the two-weeks run-in period and the end point at eight weeks. A standard insulin bolus calculator was employed to recommend insulin doses. RESULTS: Overall, glycemic control improved over the evaluated period. In particular, percentage time in the hypoglycemia range (<3.0 mmol/l) significantly decreased from 0.82% (0.05-4.79) at run-in to 0.33% (0.00-0.93) at endpoint ( P = .02). This was associated with a significant increase in percentage time in target range (3.9-10.0 mmol/l) from 52.8% (38.3-61.5) to 61.3% (47.5-71.7) ( P = .03). There was also a reduction in number of carbohydrate recommendations. CONCLUSION: A safety system for an insulin dose recommender has been proven to be a viable solution to reduce the number of adverse events associated to glucose control in type 1 diabetes.
Avari P, Uduku C, George D, et al., 2019, Differences for Percentage Times in Glycemic Range Between Continuous Glucose Monitoring and Capillary Blood Glucose Monitoring in Adults with Type 1 Diabetes: Analysis of the REPLACE-BG Dataset., Diabetes Technol Ther
Background: Self-monitored blood glucose (SMBG) and real-time continuous glucose monitoring (rtCGM) are used by people living with type 1 diabetes (T1D) to assess glucose and inform decision-making. Percentage time in range (%TIR) between 3.9 and 10 mmol/L has been associated with incident microvascular complications using historical SMBG data. However, the association between %TIR calculated from rtCGM data has not been identified. This study investigates whether %TIR values generated from rtCGM and SMBG data significantly differ from each other in adults with T1D. Materials and Methods: rtCGM and SMBG data from the REPLACE-BG study were obtained and analyzed. The dataset contained rtCGM (Dexcom G4 Platinum) and SMBG (Contour Next) values for 226 participants during a run-in phase lasting up to 10 weeks, followed by the 26-week trial. Percentages times in hypoglycemic, euglycemia and hyperglycemic ranges were generated from rtCGM and SMBG data using last observation carry forward method (zero-order hold) and linear interpolation (first-order hold). Results: Participants had a median (interquartile range [IQR]) age of 43.0 (31.0-55.0) years, and hemoglobin A1C of 53 (49-57) mmol/mol [7.0 (6.6-7.4)%]. The median (IQR) %TIR was significantly higher with rtCGM than with SMBG; 63.0 (55.9-71.0)% versus 54.6 (45.6-63.0)%, respectively, P < 0.001. Median %times in hypoglycemia and hyperglycemia were significantly different with SMBG than rtCGM (P < 0.001). SMBG-derived data using linear interpolation significantly differed from the carry forward method (P < 0.001 for all glycemic ranges). Differences reported were greater at night than during the day (P < 0.001 for all glycemic ranges). Conclusion: The %time in all glycemic ranges reported by SMBG an
Herrero P, El-Sharkawy M, Daniels J, et al., 2019, The bio-inspired artificial pancreas for type 1 diabetes control in the home: System architecture and preliminary results, Journal of Diabetes Science and Technology, Vol: 13, Pages: 1017-1025, ISSN: 1932-2968
BACKGROUND: Artificial pancreas (AP) technology has been proven to improve glucose and patient-centered outcomes for people with type 1 diabetes (T1D). Several approaches to implement the AP have been described, clinically evaluated, and in one case, commercialized. However, none of these approaches has shown a clear superiority with respect to others. In addition, several challenges still need to be solved before achieving a fully automated AP that fulfills the users' expectations. We have introduced the Bio-inspired Artificial Pancreas (BiAP), a hybrid adaptive closed-loop control system based on beta-cell physiology and implemented directly in hardware to provide an embedded low-power solution in a dedicated handheld device. In coordination with the closed-loop controller, the BiAP system incorporates a novel adaptive bolus calculator which aims at improving postprandial glycemic control. This paper focuses on the latest developments of the BiAP system for its utilization in the home environment. METHODS: The hardware and software architectures of the BiAP system designed to be used in the home environment are described. Then, the clinical trial design proposed to evaluate the BiAP system in an ambulatory setting is introduced. Finally, preliminary results corresponding to two participants enrolled in the trial are presented. RESULTS: Apart from minor technical issues, mainly due to wireless communications between devices, the BiAP system performed well (~88% of the time in closed-loop) during the clinical trials conducted so far. Preliminary results show that the BiAP system might achieve comparable glycemic outcomes to the existing AP systems (~73% time in target range 70-180 mg/dL). CONCLUSION: The BiAP system is a viable platform to conduct ambulatory clinical trials and a potential solution for people with T1D to control their glucose control in a home environment.
Renner J, Diaz Lopez G, Ferrario P, et al., 2019, Energy calibration of the NEXT-White detector with 1% resolution near Q<i><sub>ββ</sub></i> of <SUP>136</SUP>Xe, JOURNAL OF HIGH ENERGY PHYSICS, ISSN: 1029-8479
- Author Web Link
- Cite
- Citations: 18
Liu C, Vehí J, Avari P, et al., 2019, Long-term glucose forecasting using a physiological model and deconvolution of the continuous glucose monitoring signal, Sensors, Vol: 19, Pages: 1-19, ISSN: 1424-8220
(1) Objective: Blood glucose forecasting in type 1 diabetes (T1D) management is a maturing field with numerous algorithms being published and a few of them having reached the commercialisation stage. However, accurate long-term glucose predictions (e.g., >60 min), which are usually needed in applications such as precision insulin dosing (e.g., an artificial pancreas), still remain a challenge. In this paper, we present a novel glucose forecasting algorithm that is well-suited for long-term prediction horizons. The proposed algorithm is currently being used as the core component of a modular safety system for an insulin dose recommender developed within the EU-funded PEPPER (Patient Empowerment through Predictive PERsonalised decision support) project. (2) Methods: The proposed blood glucose forecasting algorithm is based on a compartmental composite model of glucose–insulin dynamics, which uses a deconvolution technique applied to the continuous glucose monitoring (CGM) signal for state estimation. In addition to commonly employed inputs by glucose forecasting methods (i.e., CGM data, insulin, carbohydrates), the proposed algorithm allows the optional input of meal absorption information to enhance prediction accuracy. Clinical data corresponding to 10 adult subjects with T1D were used for evaluation purposes. In addition, in silico data obtained with a modified version of the UVa-Padova simulator was used to further evaluate the impact of accounting for meal absorption information on prediction accuracy. Finally, a comparison with two well-established glucose forecasting algorithms, the autoregressive exogenous (ARX) model and the latent variable-based statistical (LVX) model, was carried out. (3) Results: For prediction horizons beyond 60 min, the performance of the proposed physiological model-based (PM) algorithm is superior to that of the LVX and ARX algorithms. When comparing the performance of PM against the secondly ranked method (ARX) on a 120 min
Moscardo V, Herrero P, Diez J-L, et al., 2019, Coordinated dual-hormone artificial pancreas with parallel control structure, COMPUTERS & CHEMICAL ENGINEERING, Vol: 128, Pages: 322-328, ISSN: 0098-1354
- Author Web Link
- Cite
- Citations: 6
Li K, Liu C, Zhu T, et al., 2019, GluNet: A deep learning framework for accurate glucose forecasting., IEEE Journal of Biomedical and Health Informatics, Vol: 24, Pages: 414-423, ISSN: 2168-2194
For people with Type 1 diabetes (T1D), forecasting of \red{blood glucose (BG)} can be used to effectively avoid hyperglycemia, hypoglycemia and associated complications. The latest continuous glucose monitoring (CGM) technology allows people to observe glucose in real-time. However, an accurate glucose forecast remains a challenge. In this work, we introduce GluNet, a framework that leverages on a personalized deep neural network to predict the probabilistic distribution of short-term (30-60 minutes) future CGM measurements for subjects with T1D based on their historical data including glucose measurements, meal information, insulin doses, and other factors. It adopts the latest deep learning techniques consisting of four components: data pre-processing, label transform/recover, multi-layers of dilated convolution neural network (CNN), and post-processing. The method is evaluated in-silico for both adult and adolescent subjects. The results show significant improvements over existing methods in the literature through a comprehensive comparison in terms of root mean square error (RMSE) (8.88 ± 0.77 mg/dL) with short time lag (0.83 ± 0.40 minutes) for prediction horizons (PH) = 30 mins (minutes), and RMSE (19.90 ± 3.17 mg/dL) with time lag (16.43 ± 4.07 mins) for PH = 60 mins for virtual adult subjects. In addition, GluNet is also tested on two clinical data sets. Results show that it achieves an RMSE (19.28 ± 2.76 mg/dL) with time lag (8.03 ± 4.07 mins) for PH = 30 mins and an RMSE (31.83 ± 3.49 mg/dL) with time lag (17.78 ± 8.00 mins) for PH = 60 mins. These are the best reported results for glucose forecasting when compared with other methods including the neural network for predicting glucose (NNPG), the support vector regression (SVR), the latent variable with exogenous input (LVX), and the auto regression with exogenous input (ARX) algorithm.
Cappon, Facchinetti, Sparacino, et al., 2019, Classification of postprandial glycemic status with application to insulin dosing in type 1 diabetes—an in silico proof-of-concept, Sensors, Vol: 19, Pages: 3168-3168, ISSN: 1424-8220
In the daily management of type 1 diabetes (T1D), determining the correct insulin dose to be injected at meal-time is fundamental to achieve optimal glycemic control. Wearable sensors, such as continuous glucose monitoring (CGM) devices, are instrumental to achieve this purpose. In this paper, we show how CGM data, together with commonly recorded inputs (carbohydrate intake and bolus insulin), can be used to develop an algorithm that allows classifying, at meal-time, the post-prandial glycemic status (i.e., blood glucose concentration being too low, too high, or within target range). Such an outcome can then be used to improve the efficacy of insulin therapy by reducing or increasing the corresponding meal bolus dose. A state-of-the-art T1D simulation environment, including intraday variability and a behavioral model, was used to generate a rich in silico dataset corresponding to 100 subjects over a two-month scenario. Then, an extreme gradient-boosted tree (XGB) algorithm was employed to classify the post-prandial glycemic status. Finally, we demonstrate how the XGB algorithm outcome can be exploited to improve glycemic control in T1D through real-time adjustment of the meal insulin bolus. The proposed XGB algorithm obtained good accuracy at classifying post-prandial glycemic status (AUROC = 0.84 [0.78, 0.87]). Consequently, when used to adjust, in real-time, meal insulin boluses obtained with a bolus calculator, the proposed approach improves glycemic control when compared to the baseline bolus calculator. In particular, percentage time in target [70, 180] mg/dL was improved from 61.98 (± 13.89) to 67.00 (± 11.54; p < 0.01) without increasing hypoglycemia.</jats:p>
Guemes A, Herrero P, Bondia J, et al., 2019, Modeling the effect of the cephalic phase of insulin secretion on glucose metabolism, Medical and Biological Engineering and Computing, Vol: 57, Pages: 1173-1186, ISSN: 0140-0118
The nervous system has a significant impact in glucose homeostasis and endocrine pancreatic secretion in humans, especially during the cephalic phase of insulin release (CPIR); that is, before a meal is absorbed. However, the underlying mechanisms of this neural-pancreatic interaction are not well understood and therefore often neglected, despite their significance to achieving an optimal glucose control. As a result, the dynamics of insulin release from the pancreas are currently described by mathematical models that reproduce the behavior of the β cells using exclusively glucose levels and other hormones as inputs. To bridge this gap, we have combined, for the first time, metabolic and neural mathematical models in a unified system to reproduce to a great extent the ideal glucoregulation observed in healthy subjects. Our results satisfactorily replicate the CPIR and its impact during the post-absorptive phase. Furthermore, the proposed model gives insight into the physiological interaction between the brain and the pancreas in healthy people and suggests the potential of considering the neural information for restoring glucose control in people with diabetes.
Rawson TM, Hernandez B, Moore L, et al., 2019, Supervised machine learning for the prediction of infection on admission to hospital: a prospective observational cohort study, Journal of Antimicrobial Chemotherapy, Vol: 74, Pages: 1108-1115, ISSN: 0305-7453
BackgroundInfection diagnosis can be challenging, relying on clinical judgement and non-specific markers of infection. We evaluated a supervised machine learning (SML) algorithm for diagnosing bacterial infection using routinely available blood parameters on presentation to hospital.MethodsAn SML algorithm was developed to classify cases into infection versus no infection using microbiology records and six available blood parameters (C-reactive protein, white cell count, bilirubin, creatinine, ALT and alkaline phosphatase) from 160 203 individuals. A cohort of patients admitted to hospital over a 6 month period had their admission blood parameters prospectively inputted into the SML algorithm. They were prospectively followed up from admission to classify those who fulfilled clinical case criteria for a community-acquired bacterial infection within 72 h of admission using a pre-determined definition. Predictive ability was assessed using receiver operating characteristics (ROC) with cut-off values for optimal sensitivity and specificity explored.ResultsOne hundred and four individuals were included prospectively. The median (range) cohort age was 65 (21–98) years. The majority were female (56/104; 54%). Thirty-six (35%) were diagnosed with infection in the first 72 h of admission. Overall, 44/104 (42%) individuals had microbiological investigations performed. Treatment was prescribed for 33/36 (92%) of infected individuals and 4/68 (6%) of those with no identifiable bacterial infection. Mean (SD) likelihood estimates for those with and without infection were significantly different. The infection group had a likelihood of 0.80 (0.09) and the non-infection group 0.50 (0.29) (P < 0.01; 95% CI: 0.20–0.40). ROC AUC was 0.84 (95% CI: 0.76–0.91).ConclusionsAn SML algorithm was able to diagnose infection in individuals presenting to hospital using routinely available blood parameters.
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.