Imperial College London

Dr Pau Herrero-Viñas

Faculty of EngineeringDepartment of Electrical and Electronic Engineering

Research Fellow
 
 
 
//

Contact

 

p.herrero-vinias CV

 
 
//

Location

 

B422Bessemer BuildingSouth Kensington Campus

//

Summary

 

Publications

Publication Type
Year
to

128 results found

Guemes A, Cappon G, Hernandez B, Reddy M, Oliver N, Georgiou P, Herrero Pet 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).

Journal article

Rawson TM, Hernandez B, Moore L, Herrero P, Charani E, Ming D, Wilson R, Blandy O, Sriskandan S, Toumazou C, Georgiou P, Holmes Aet al., 2020, A real-world evaluation of a Case-Based Reasoning algorithm to support antimicrobial prescribing decisions in acute care, Clinical Infectious Diseases, ISSN: 1058-4838

BackgroundA locally developed Case-Based Reasoning (CBR) algorithm, designed to augment antimicrobial prescribing in secondary care was evaluated.MethodsPrescribing recommendations made by a CBR algorithm were compared to decisions made by physicians in clinical practice. Comparisons were examined in two patient populations. Firstly, in patients with confirmed Escherichia coli blood stream infections (‘E.coli patients’), and secondly in ward-based patients presenting with a range of potential infections (‘ward patients’). Prescribing recommendations were compared against the Antimicrobial Spectrum Index (ASI) and the WHO Essential Medicine List Access, Watch, Reserve (AWaRe) classification system. Appropriateness of a prescription was defined as the spectrum of the prescription covering the known, or most-likely organism antimicrobial sensitivity profile.ResultsIn total, 224 patients (145 E.coli patients and 79 ward patients) were included. Mean (SD) age was 66 (18) years with 108/224 (48%) female gender. The CBR recommendations were appropriate in 202/224 (90%) compared to 186/224 (83%) in practice (OR: 1.24 95%CI:0.392-3.936;p=0.71). CBR recommendations had a smaller ASI compared to practice with a median (range) of 6 (0-13) compared to 8 (0-12) (p<0.01). CBR recommendations were more likely to be classified as Access class antimicrobials compared to physicians’ prescriptions at 110/224 (49%) vs. 79/224 (35%) (OR: 1.77 95%CI:1.212-2.588 p<0.01). Results were similar for E.coli and ward patients on subgroup analysis.ConclusionsA CBR-driven decision support system provided appropriate recommendations within a narrower spectrum compared to current clinical practice. Future work must investigate the impact of this intervention on prescribing behaviours more broadly and patient outcomes.

Journal article

Moscardó V, Herrero P, Reddy M, Hill N, Georgiou P, Oliver Net al., 2020, Assessment of Glucose Control Metrics by Discriminant Ratio., Diabetes Technol Ther

OBJECTIVE: Increasing use of continuous glucose monitoring data has created an array of glucose metrics for glucose variability, temporal patterns and times in ranges. However, a gold standard metric has not been defined. We assess the performance of multiple glucose metrics to determine their ability to detect intra- and inter-person variability in order to determine a set of recommended metrics. METHODS: The Juvenile Diabetes Research Foundation (JDRF) dataset, a randomized controlled study of continuous glucose monitoring and self-monitored blood glucose conducted in children and adults with type 1 diabetes was used. To determine the ability of the evaluated glycemic metrics to discriminate between different subjects and attenuate the effect of within-subject variation, the Discriminant Ratio was calculated and compared for each metric. Then, the findings were confirmed using data from two other recent randomized clinical trials. RESULTS: Mean Absolute Glucose (MAG) has the highest discriminant ratio value (2.98 [95% CI 1.64-3.67]). In addition, Low Blood Glucose Index (LBGI) and Index of Glycemic Control (IGC) performed well (1.93 [95% CI 1.15-3.44] and 1.92 [95% CI 1.27-2.93], respectively). For percentage times in glucose target ranges, the optimal discriminator was percentage time in glucose target 70-180 mg/dL. CONCLUSIONS: Mean Absolute Glucose (MAG) is the optimal index to differentiate glucose variability in people with type 1 diabetes, and may be a complementary therapeutic monitoring tool in addition to HbA1c and a measure of hypoglycemia. Percentage time in glucose target 70-180 mg/dL is the optimal percentage time in range to report.

Journal article

Herrero P, Alalitei A, Reddy M, Georgiou P, Oliver Net 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

Conference paper

Daniels J, Zhu T, Li K, Uduku C, Herrero P, Oliver N, Georgiou Pet 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

Conference paper

Zhu T, Li K, Uduku C, Herrero P, Oliver N, Georgiou Pet 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

Conference paper

Avari P, Leal Y, Wos M, Jugnee N, Thomas M, Massana J, Lopez B, Nita L, Martin C, Herrero P, Oliver N, Fernandez-Real J, Reddy M, Fernandez-Balsells Met 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

Conference paper

Spence R, Li K, Uduku C, Zhu T, Redmond L, Herrero P, Oliver N, Georgiou Pet 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

Conference paper

Li K, Daniels J, Liu C, Herrero-Vinas P, Georgiou Pet 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.

Journal article

Waite M, Aldea A, Avari P, Leal Y, Martin C, Fernandez-Balsells M, Fernandez-Real J, Herrero P, Jugnee N, Lopez B, Reddy M, Wos M, Oliver Net 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

Conference paper

Liu C, Avari P, Leal Y, Wos M, Sivasithamparam K, Georgiou P, Reddy M, Fernández-Real JM, Martin C, Fernández-Balsells M, Oliver N, Herrero Pet 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.

Journal article

Avari P, Uduku C, George D, Herrero P, Reddy M, Oliver Net 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

Journal article

Herrero P, El-Sharkawy M, Daniels J, Jugnee N, Uduku CN, Reddy M, Oliver N, Georgiou Pet 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.

Journal article

Liu C, Vehí J, Avari P, Reddy M, Oliver N, Georgiou P, Herrero Pet 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

Journal article

Moscardo V, Herrero P, Diez J-L, Gimenez M, Rossetti P, Georgiou P, Bondia Jet al., 2019, Coordinated dual-hormone artificial pancreas with parallel control structure, COMPUTERS & CHEMICAL ENGINEERING, Vol: 128, Pages: 322-328, ISSN: 0098-1354

Journal article

Li K, Liu C, Zhu T, Herrero P, Georgiou Pet 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.

Journal article

Cappon, Facchinetti, Sparacino, Georgiou, Herreroet 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 &lt; 0.01) without increasing hypoglycemia.</jats:p>

Journal article

Moscardo V, Herrero P, Diez JL, Gimenez M, Rossetti P, Bondia Jet al., 2019, In silico evaluation of a parallel control-based coordinated dual-hormone artificial pancreas with insulin on board limitation, Pages: 4759-4764, ISSN: 0743-1619

© 2019 American Automatic Control Council. A closed-loop glucose control system with automatic insulin and glucagon delivery (dual-hormone artificial pancreas) has the potential to reduce the self-management and the risk of hypo- and hyperglycemia in type 1 diabetic subjects. A novel dual-hormone closed-loop system based on a parallel control structure with intrinsic coordination among insulin and glucagon delivery is presented here, and the potential benefit of incorporating insulin-on-board limitation in such scheme is analyzed. To this end, the coordinated configuration (CC) has been extended with insulin-on-board (IOB) limitation through Sliding Mode Reference Conditioning (CC-SMRC), previously successfully tested in the context of single-hormone systems. Performance of CC and CC-SMRC has been compared through an in-silico study using the UVA-Padova simulator, extended to include various sources of variability. Three scenarios have been considered, comprising meals, snacks and exercise. The proposed coordinated strategy with the IOB limitation showed slightly lower time in hypoglycemia in meal and meals+snack scenario (0.00% vs 0.14% in meal scenario; 0.01% vs 0.11% in snack scenario), but they were not statistically significant (\mathbf{p}=0.180 and \mathbf{p}=0.179, respectively). However, the reduction during exercise scenario was statistically significant (1.45% vs 3.40%, \mathbf{p} < 0.001). Likewise, the time in range was similar in both configurations during meal and meals+snack scenarios (93.80% vs 94.13%, \mathbf{p}=0.803, in meal scenario; 93.97% vs 94.32%, \mathbf{p}=0.356, in meals+snack; CC-SMRC vs CC), although it was greater in CC-SMRC during exercise scenario (92.98% vs 91.56%, \mathbf{p}=0.023; CC-SMRC vs CC). Moreover, insulin delivery was lower in CC-SMRC during the most demanding exercise scenario (45.91 /day vs 46.53U/day, \mathbf{p}=0.001) at the expense of higher glucagon delivery to reduce hypoglycemia (1.03\pm 0.83\mathbf{mg}/\ma

Conference paper

Guemes A, Herrero P, Bondia J, Georgiou Pet 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.

Journal article

Rawson TM, Hernandez B, Moore L, Blandy O, Herrero P, Gilchrist M, Gordon A, Toumazou C, Sriskandan S, Georgiou P, Holmes Aet 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.

Journal article

Li K, Chen J, Herrero P, Uduku C, Georgiou Pet al., 2019, A DEEP NEURAL NETWORK PLATFORM FOR PREDICTING BLOOD GLUCOSE LEVELS, Publisher: MARY ANN LIEBERT, INC, Pages: A80-A80, ISSN: 1520-9156

Conference paper

Martin C, Aldea A, Alshaigy B, Avari P, Duce D, Fernandez-Balsells M, Fernandez-Real JM, Harrison R, Herrero P, Jugnee N, Lui C, Lopez B, Massana J, Leal Y, Russell A, Reddy M, Waite M, Wos M, Oliver Net al., 2019, APPLICATION OF USABILITY ENGINEERING TO THE DEVELOPMENT OF A PERSONALISED DECISION SUPPORT SYSTEM FOR TYPE 1 DIABETES SELF-MANAGEMENT, Publisher: MARY ANN LIEBERT, INC, Pages: A73-A73, ISSN: 1520-9156

Conference paper

Avari P, Leal Y, Wos M, Sivasithamparam K, Liu C, Jugnee N, Thomas M, Reddy M, Herrero P, Martin C, Fernandez-Real J, Oliver N, Fernandez-Balsells Met al., 2019, FEASIBILITY OF SAFETY SYSTEM WITHIN A NOVEL PERSONALISED DECISION SUPPORT TOOL FOR INSULIN DOSING, Publisher: MARY ANN LIEBERT, INC, Pages: A16-A16, ISSN: 1520-9156

Conference paper

Herrero P, Reddy M, Georgiou P, Oliver Net al., 2019, A BETTER CARE FOR DIABETES, Publisher: MARY ANN LIEBERT, INC, Pages: A7-A7, ISSN: 1520-9156

Conference paper

Gonzalez AG, Herrero P, Georgiou P, 2019, A CONTROLLER FOR BLOOD GLUCOSE REGULATION BASED ON MODULATION OF INSULIN SENSITIVITY IN PEOPLE WITH TYPE I DIABETES, Publisher: MARY ANN LIEBERT, INC, Pages: A48-A48, ISSN: 1520-9156

Conference paper

Koch F, Koster A, Bichindaritz I, Herrero P, Riaño D, Montagna S, Schumacher M, ten Teije A, Guttmann C, Reichert M, Lenz R, López B, Marling C, Martin C, Montani S, Wiratunga Net al., 2019, Preface, ISBN: 9783030127374

Book

Liu C, Vehi J, Oliver N, Georgiou P, Herrero Pet al., 2019, Enhancing Blood Glucose Prediction with Meal Absorption and Physical Exercise Information

Objective: Numerous glucose prediction algorithm have been proposed toempower type 1 diabetes (T1D) management. Most of these algorithms only accountfor input such as glucose, insulin and carbohydrate, which limits theirperformance. Here, we present a novel glucose prediction algorithm which, inaddition to standard inputs, accounts for meal absorption and physical exerciseinformation to enhance prediction accuracy. Methods: a compartmental model ofglucose-insulin dynamics combined with a deconvolution technique for stateestimation is employed for glucose prediction. In silico data correspondingfrom the 10 adult subjects of UVa-Padova simulator, and clinical data from 10adults with T1D were used. Finally, a comparison against a validated glucoseprediction algorithm based on a latent variable with exogenous input (LVX)model is provided. Results: For a prediction horizon of 60 minutes, accountingfor meal absorption and physical exercise improved glucose forecastingaccuracy. In particular, root mean square error (mg/dL) went from 26.68 to23.89, p<0.001 (in silico data); and from 37.02 to 35.96, p<0.001 (clinicaldata - only meal information). Such improvement in accuracy was translated intosignificant improvements on hypoglycaemia and hyperglycaemia prediction.Finally, the performance of the proposed algorithm is statistically superior tothat of the LVX algorithm (26.68 vs. 32.80, p<0.001 (in silico data); 37.02 vs.49.17, p<0.01 (clinical data). Conclusion: Taking into account meal absorptionand physical exercise information improves glucose prediction accuracy.

Journal article

Rawson T, Ming D, Gowers S, Freeman D, Herrero P, Georgiou P, Cass AEG, O'Hare D, Holmes Aet al., 2019, Public acceptability of computer-controlled antibiotic management: an exploration of automated dosing and opportunities for implementation, Journal of Infection, Vol: 78, Pages: 75-86, ISSN: 0163-4453

Journal article

Guemes A, Herrero P, Georgiou P, 2019, A Novel Glucose Controller Using Insulin Sensitivity Modulation for Management of Type 1 Diabetes, IEEE International Symposium on Circuits and Systems (IEEE ISCAS), Publisher: IEEE, ISSN: 0271-4302

Conference paper

Herrero P, Rawson TM, Philip A, Moore LSP, Holmes AH, Georgiou Pet al., 2018, Closed-loop control for precision antimicrobial delivery: an In silico proof-of-concept, IEEE Transactions on Biomedical Engineering, Vol: 65, Pages: 2231-2236, ISSN: 0018-9294

IEEE Objective: Inappropriate dosing of patients with antibiotics is a driver of antimicrobial resistance, toxicity, and poor outcomes of therapy. In this paper, we investigate, in silico, the hypothesis that the use of a closed-loop control system could improve the attainment of pharmacokinetic-pharmacodynamic targets for antimicrobial therapy, where wide variations in target attainment have been reported. This includes patients in critical care, patients with renal disease and patients with obesity.

Journal article

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.

Request URL: http://wlsprd.imperial.ac.uk:80/respub/WEB-INF/jsp/search-html.jsp Request URI: /respub/WEB-INF/jsp/search-html.jsp Query String: respub-action=search.html&id=00655605&limit=30&person=true