Imperial College London

Dr Pantelis Georgiou

Faculty of EngineeringDepartment of Electrical and Electronic Engineering

Reader in Biomedical Electronics
 
 
 
//

Contact

 

+44 (0)20 7594 6326pantelis Website

 
 
//

Location

 

902Electrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Publication Type
Year
to

279 results found

Georgiou P, Malpartida Cardenas K, Yu L-S, Baum J, Miscourides N, Rodriguez Manzano Jet al., 2019, Method for detecting a single nucleotide polymorphism (snp) using lamp and blocking primers, WO2019234251A1

The present application relates to methods for detecting a first allele of a single nucleotide polymorphism (SNP) in a nucleic acid sequence under isothermal conditions using primers specific for said first allele, in particular using Loop mediated isothermal amplification (LAMP), wherein the amplification of a second allele is prevented by using blocking primers.

Patent

Georgiou P, Yu L-S, Malpartida-Cardenas K, Fisher M, Moser N, Rodriguez Manzano Jet al., 2019, Method for detecting a tandem repeat, WO2019234252A1

The present application relates to methods for detecting a tandem repeat in a nucleic acid sequence under isothermal conditions using primers.

Patent

Georgiou P, Moniri A, Rodriguez Manzano J, 2019, A method for analysis of real-time amplification data, WO2019234247A1

This disclosure relates to methods, systems, computer programs and computer- readable media for the multidimensional analysis of real-time amplification data. A framework is presented that shows that the benefits of standard curves extend beyond absolute quantification when observed in a multidimensional environment. Relating to the field of Machine Learning, the disclosed method combines multiple extracted features (e.g. linear features) in order to analyse real-time amplification data using a multidimensional view. The method involves two new concepts: the multidimensional standard curve and its 'home', the feature space. Together they expand the capabilities of standard curves, allowing for simultaneous absolute quantification, outlier detection and providing insights into amplification kinetics. The new methodology thus enables enhanced quantification of nucleic acids, single-channel multiplexing, outlier detection, characteristic patterns in the multidimensional space related to amplification kinetics and increased robustness for sample identification and quantification.

Patent

Georgiou P, Moniri A, Moser N, Rodriguez Manzano Jet al., 2019, Devices and method for detecting an amplification event, WO2019234451A1

A method is disclosed herein for detecting an amplification reaction in a solution containing a biological sample using an array of ion sensors. The amplification reaction is indicative of the presence of a nucleic acid. The method comprises monitoring a signal from each respective sensor of the array of ion sensors, detecting a change in the signal from a first sensor of the array of ion sensors, and comparing the signal from the first sensor with the signal of at least one neighbouring sensor, the at least one neighbouring sensor being proximate to the first sensor in the array. The method further comprises determining, based on the comparing, that an amplification event has occurred in the solution in the vicinity of the first sensor.

Patent

Malpartida-Cardenas K, Miscourides N, Rodriguez-Manzano J, Yu L-S, Moser N, Baum J, Georgiou Pet al., 2019, Quantitative and rapid Plasmodium falciparum malaria diagnosis and artemisinin-resistance detection using a CMOS Lab-on-Chip platform, Biosensors and Bioelectronics, Vol: 145, ISSN: 0956-5663

Early and accurate diagnosis of malaria and drug-resistance is essential to effective disease management. Available rapid malaria diagnostic tests present limitations in analytical sensitivity, drug-resistance testing and/or quantification. Conversely, diagnostic methods based on nucleic acid amplification stepped forwards owing to their high sensitivity, specificity and robustness. Nevertheless, these methods commonly rely on optical measurements and complex instrumentation which limit their applicability in resource-poor, point-of-care settings. This paper reports the specific, quantitative and fully-electronic detection of Plasmodium falciparum, the predominant malaria-causing parasite worldwide, using a Lab-on-Chip platform developed in-house. Furthermore, we demonstrate on-chip detection of C580Y, the most prevalent single-nucleotide polymorphism associated to artemisinin-resistant malaria. Real-time non-optical DNA sensing is facilitated using Ion-Sensitive Field-Effect Transistors, fabricated in unmodified complementary metal-oxide-semiconductor (CMOS) technology, coupled with loop-mediated isothermal amplification. This work holds significant potential for the development of a fully portable and quantitative malaria diagnostic that can be used as a rapid point-of-care test.

Journal article

Rawson TM, Gowers SAN, Freeman DME, Wilson RC, Sharma S, Gilchrist M, MacGowan A, Lovering A, Bayliss M, Kyriakides M, Georgiou P, Cass AEG, O'Hare D, Holmes AHet al., 2019, Microneedle biosensors for real-time, minimally invasive drug monitoring of phenoxymethylpenicillin: a first-in-human evaluation in healthy volunteers, The Lancet Digital Health, Vol: 1, Pages: e335-e343, ISSN: 2589-7500

BackgroundEnhanced methods of drug monitoring are required to support the individualisation of antibiotic dosing. We report the first-in-human evaluation of real-time phenoxymethylpenicillin monitoring using a minimally invasive microneedle-based β-lactam biosensor in healthy volunteers.MethodsThis first-in-human, proof-of-concept study was done at the National Institute of Health Research/Wellcome Trust Imperial Clinical Research Facility (Imperial College London, London, UK). The study was approved by London-Harrow Regional Ethics Committee. Volunteers were identified through emails sent to a healthy volunteer database from the Imperial College Clinical Research Facility. Volunteers, who had to be older than 18 years, were excluded if they had evidence of active infection, allergies to penicillin, were at high risk of skin infection, or presented with anaemia during screening. Participants wore a solid microneedle β-lactam biosensor for up to 6 h while being dosed at steady state with oral phenoxymethylpenicillin (five 500 mg doses every 6 h). On arrival at the study centre, two microneedle sensors were applied to the participant's forearm. Blood samples (via cannula, at −30, 0, 10, 20, 30, 45, 60, 90, 120, 150, 180, 210, 240 min) and extracellular fluid (ECF; via microdialysis, every 15 min) pharmacokinetic (PK) samples were taken during one dosing interval. Phenoxymethylpenicillin concentration data obtained from the microneedles were calibrated using locally estimated scatter plot smoothing and compared with free-blood and microdialysis (gold standard) data. Phenoxymethylpenicillin PK for each method was evaluated using non-compartmental analysis. Area under the concentration–time curve (AUC), maximum concentration, and time to maximum concentration were compared. Bias and limits of agreement were investigated with Bland–Altman plots. Microneedle biosensor limits of detection were estimated. The study was registered with ClinicalTria

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 Y, Constandinou TG, Georgiou P, 2019, Ultrafast large-scale chemical sensing with CMOS ISFETs: a level-crossing time-domain approach, IEEE Transactions on Biomedical Circuits and Systems, ISSN: 1932-4545

The introduction of large-scale chemical sensing systems in CMOS which integrate millions of ISFET sensors have allowed applications such as DNA sequencing and fine-pixel chemical imaging systems to be realised. Using CMOS ISFETs provides advantages of digitisation directly at the sensor as well as correcting for non-linearity in its response. However, for this to be beneficial and scale, the readout circuits need to have the minimum possible footprint and power consumption. Within this context, this paper analyses an ISFET based pH-to-time readout using an inverter in the time-domain as a level-crossing detector and presents a 32×32 array with in-pixel digitisation for pH sensing. The inverter-based sensing pixel, controlled by a triangular waveform, converts the pH response into a time-domain signal whilst also compensating for sensor offset and thus resulting in an increase in dynamic range. The sensor pixels interface to a 15-bit asynchronous column-wise time-to-digital converter (TDC), enabling fast asynchronous conversion whilst using minimal silicon area. Parallel outputs of 32 TDC interfaces are serialised to achieve fast data throughput. This system is implemented in a standard 0.18um CMOS technology, with a pixel size of 26μm×26μm and a TDC area of 26μm×180μm. Measured results demonstrate the system is able to sense reliably with an average pH sensitivity of 30mVpH, whilst being able to compensate for sensor offset by up to ±7V. A resolution of 0.013pH is achieved and noise measurements show an integrated noise of 0.08pH within 2-500Hz and SFDR of 42.6dB. Total power consumption is 11.286mW.

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

Terracina D, Moniri A, Rodriguez-Manzano J, Strutton PH, Georgiou Pet al., 2019, Real-Time forecasting and classification of trunk muscle fatigue using surface electromyography

© 2019 IEEE. Low Back Pain (LBP) affects the vast majority of the population at some point in their lives. People with LBP show altered trunk muscle activity and enhanced fatigability of trunk muscles is associated with the development and future risk of LBP. Therefore, a system that can forecast trunk muscle activity and detect fatigue can help subjects, practitioners and physiotherapists in the diagnosis, monitoring and recovery of LBP. In this paper, we present a novel approach in order to determine whether subjects are fatigued, or transitioning to fatigue, 25 seconds ahead of time using surface Electromyography (sEMG) from 14 trunk muscles. This is achieved using a three-step approach: A) extracting features related to fatigue from sEMG, B) forecasting the features using a real-Time adaptive filter and C) performing dimensionality reduction (from 70 to 2 features) and then classifying subjects using a supervised machine learning algorithm. The forecasting classification accuracy across 13 patients is 99.1% ± 0.004 and the area under the micro and macro ROC curve is 0.935 ± 0.036 and 0.940 ±0.034 as determined by 10-fold cross validation. The proposed approach enables a computationally efficient solution which could be implemented in a wearable device for preventing muscle injury.

Conference paper

Cicatiello C, Moser N, Boutelle M, Georgiou Pet al., 2019, Live Demonstration : A Portable Multi-Ion Platform with Integrated Microfluidics

© 2019 IEEE. A novel microfluidic analysis platform is demonstrated for the real-Time monitoring of traumatic brain injury (TBI) patients in intensive care. The system uses an on-chip array of Complementary Metal-Oxide-Semiconductor (CMOS) sensors implemented in an unmodified process to perform ion imaging. Specificity to several ionic species is achieved by depositing ion-selective membranes at the surface of the chip. Image processing techniques on the sensing array data enable the visualisation of the pattern of neurochemical changes caused by the evolving injury.

Conference paper

Douthwaite M, Garcia-Redondo F, Georgiou P, Das Set al., 2019, A Time-Domain Current-Mode MAC Engine for Analogue Neural Networks in Flexible Electronics

© 2019 IEEE. Flexible electronics is becoming more prevalent in a wide range of applications, particularly wearable biomedical devices. These devices would greatly benefit from in-built intelligence allowing them to process data and identify features, in order to reduce transmission and power requirements. In this work, we present a novel time-domain multiply-Accumulate (MAC) engine architecture that can act as the basic block of an artificial analogue neural network. The design does not require analogue voltage buffers, making them easier to realise in flexible technologies and consumes less power than conventional methods. The research could be used in future to construct a low power classifier for a low cost, flexible wearable biomedical sensor.

Conference paper

Cacho-Soblechero M, Malpartida-Cardenas K, Moser N, Georgiou Pet al., 2019, Programmable Ion-Sensing Using Oscillator-Based ISFET Architectures, IEEE SENSORS JOURNAL, Vol: 19, Pages: 8563-8575, ISSN: 1530-437X

Journal article

Daniels J, Georgiou P, 2019, A Data-Driven Detection System for Predicting Stress Levels from Autonomic Signals

© 2019 IEEE. This paper introduces and details a detection system for continuous monitoring of psychological stress. The formulation of classes relating to varying levels of stress intensity is described. This is necessary for determining the therapy needed to alleviate the associated effects, particularly in population groups suffering from chronic and mental illnesses such as diabetes and depression. The data-driven detection system mainly comprises kernel principal component analysis for dimensionality reduction, and nearest neighbour classifier for supervised learning to determine the associated stress intensity. We evaluate the generalised stress detection system using a 3-fold cross validation and a test set comprising an independent subject. We obtain a 0.66 F1-score with a precision of 0.70 and a recall of 0.67 over 4 classes of stress: no stress, low stress, moderate stress, and high stress.

Conference paper

Cacho-Soblechero M, Karolcik S, Haci D, Cicatiello C, Maxoutis C, Georgiou Pet al., 2019, Live Demonstration: A Portable ISFET Platform for PoC Diagnosis Powered by Solar Energy

© 2019 IEEE. This demonstration presents a portable and low-power ISFET platform, powered by a solar panel battery system. A 32x32 ISFET array is connected to the portable platform using a custom cartridge, which interface with a Raspberry Pi that controls biasing, configuration and data acquisition, while displaying the results on a touchscreen. Inspired by classic videogame consoles, we present a GUI for screening and diagnosis which provides an intuitive experience for non-expert users, ultimately offering an end-To-end system for ISFET-based Point-of-Care diagnosis.

Conference paper

Rodriguez-Manzano J, Miscourides N, Malpartida-Cardenas K, Pennisi I, Moser N, Holmes A, Georgiou Pet al., 2019, Rapid detection of Klebsiella pneumoniae using an auto-calibrated ISFET-Array Lab-on-Chip platform

© 2019 IEEE. This paper presents the rapid detection of Klebsiella pneumonia, a major worldwide source and shuttle for antibiotic resistance, by a CMOS-based Lab-on-chip (LoC) platform. The LoC platform comprises a 64 × 200 ISFET array including a programmable gate for mismatch calibration. Calibration takes place on a pixel per pixel basis, with the array carrying-out simultaneous calibration and readout. The LoC platform is used to detect the pH changes occurring during DNA amplification and is demonstrated for the rapid detection of Klebsiella pneumoniae using isothermal molecular methods. Nucleic acids from the bacterial strain have been isolated from pure microbiological cultures and are detected in under 10 minutes. Overall, the presented Lab-on-Chip platform paired with the molecular methods hold significant potential for the rapid detection of Klebsiella pneumoniae at the point-of-care.

Conference paper

Guemes A, Cappon G, Hernandez B, Reddy M, Oliver N, Georgiou P, Herrero Pet al., 2019, Predicting quality of overnight glycaemic control in type 1 diabetes using binary classifiers, IEEE Journal of Biomedical and Health Informatics, 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

Peiffer-Smadja N, Rawson TM, Ahmad R, Buchard A, Pantelis G, Lescure F-X, Birgand G, Holmes Aet al., Machine learning for clinical decision support in infectious diseases: A narrative review of current applications, Clinical Microbiology and Infection, ISSN: 1198-743X

BACKGROUNDMachine learning (ML) is a growing field in medicine. This narrative review describes the current body of literature on ML for clinical decision support in infectious diseases (ID). OBJECTIVESWe aim to inform clinicians about the use of ML for diagnosis, classification, outcome prediction and antimicrobial management in ID.SOURCESReferences for this review were identified through searches of MEDLINE/PubMed, EMBASE, Google Scholar, biorXiv, ACM Digital Library, arXiV and IEEE Xplore Digital Library up to July 2019.CONTENTWe found 60 unique ML-CDSS aiming to assist ID clinicians. Overall, 37 (62%) focused on bacterial infections, 10 (17%) on viral infections, nine (15%) on tuberculosis and four (7%) on any kind of infection. Among them, 20 (33%) addressed the diagnosis of infection, 18 (30%) the prediction, early detection or stratification of sepsis, 13 (22%) the prediction of treatment response, four (7%) the prediction of antibiotic resistance, three (5%) the choice of antibiotic regimen and two (3%) the choice of a combination antiretroviral therapy. The ML-CDSS were developed for intensive care units (n=24, 40%), ID consultation (n=15, 25%), medical or surgical wards (n=13, 20%), emergency department (n=4, 7%), primary care (n=3, 5%) and antimicrobial stewardship (n=1, 2%). Fifty-three ML-CDSS (88%) were developed using data from high-income countries and seven (12%) with data from low- and middle-income countries (LMIC). The evaluation of ML-CDSS was limited to measures of performance (e.g. sensitivity, specificity) for 57 ML-CDSS (95%) and included data in clinical practice for three (5%). IMPLICATIONSConsidering comprehensive patient data from socioeconomically diverse health care settings, including primary care and LMICs, may improve the ability of ML-CDSS to suggest decisions adapted to various clinical contexts. Currents gaps identified in the evaluation of ML-CDSS must also be addressed in order to know the potential impact of such tools for cli

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

Moser N, Panteli C, Fobelets K, Georgiou Pet al., 2019, Mechanisms for enhancement of sensing performance in CMOS ISFET arrays using reactive ion etching, Sensors and Actuators B: Chemical, Vol: 292, Pages: 297-307, ISSN: 0925-4005

In this work, we investigate the impact of successively removing the passivation layers of ISFET sensors implemented in a standard CMOS process to improve sensing performance. Reactive ion etching is used as a post-processing technique of the CMOS chips for uniform and accurate etching. The removal of the passivation layers addresses common issues with commercial implementation of ISFET sensors, including pH sensitivity, capacitive attenuation, trapped charge, drift and noise. The process for removing the three standard layers (polyimide, Si3N4 and SiO2) is tailored to minimise the surface roughness of the sensing layer throughout an array of more than 4000 ISFET sensors. By careful calibration of the plasma recipe we perform material-wise etch steps at the top and middle of the nitride layer and top of the oxide layer. The characterisation of the ISFET array proves that the location of the trapped charge in the passivation layers is mainly at the interface of the layers. Etching to the top of the oxide layer is shown to induce an improvement of 80% in the offset range throughout the array and an increase in SNR of almost 40 dB compared to the non-processed configuration. The performance enhancement demonstrates the benefit of a controlled industry-standard etch process on CMOS ISFET array system-on-chips.

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, Pages: 1-9, 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

Guemes A, Herrero P, Bondia J, Georgiou Pet al., 2019, Modeling the effect of the cephalic phase of insulin secretion on glucose metabolism, MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING, Vol: 57, Pages: 1173-1186, ISSN: 0140-0118

Journal article

Liu Y, Constandinou TG, Georgiou P, 2019, A 32 x 32 ISFET array with in-pixel digitisation and column-wise TDC for ultra-fast chemical sensing, IEEE International Symposium on Circuits and Systems (IEEE ISCAS), Publisher: IEEE, ISSN: 0271-4302

This paper presents a 32×32 ISFET sensing array with in-pixel digitisation for pH sensing. The in-pixel digitisation is achieved using an inverter-based sensing pixel that is controlled by a triangular waveform. This converts the pH response of the ISFET into a time-domain signal whilst also increasing dynamic range and thus the ability to tolerate sensor offset. The pixels are interfaced to a 15-bit asynchronous column-wise time-to-digital converter (TDC), enabling fast sensor readout whilst using minimal silicon area. Parallel output of 32 TDC interfaces are serialised to achieve fast data though-put. This system is implemented in a standard 0.18 μm standard CMOS technology, with a pixel size of 26 μm × 26 μm and a TDC of 26 μm × 180 μm. Simulation results demonstrate that chemical sampling of up to 5k frames per second can be achieved with a clock frequency of 160 MHz and a TDC resolution of 190 ps. The total power consumption of the overall system is 7.34 mW.

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., 2019, A modular safety system for an insulin dose recommender: a feasibility study., Journal of Diabetes Science and Technology, Pages: 1-10, 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

Malpartida-Cardenas K, Miscourides N, Rodriguez-Manzano J, Yu LS, Baum J, Georgiou Pet al., 2019, Quantitative and rapid Plasmodium falciparum malaria diagnosis and artemisinin-resistance detection using a CMOS Lab-on-Chip platform, Publisher: Cold Spring Harbor Laboratory

<jats:title>Abstract</jats:title><jats:p>Early and accurate diagnosis of malaria and drug-resistance is essential to effective disease management. Available rapid malaria diagnostic tests present limitations in analytical sensitivity, drug-resistant testing and/or quantification. Conversely, diagnostic methods based on nucleic acid amplification stepped forwards owing to their high sensitivity, specificity and robustness. Nevertheless, these methods commonly rely on optical measurements and complex instrumentation which limit their applicability in resource-poor, point-of-care settings. This paper reports the specific, quantitative and fully-electronic detection of <jats:italic>Plas-modium falciparum</jats:italic>, the predominant malaria-causing parasite worldwide, using a Lab-on-Chip platform developed in-house. Furthermore, we demonstrate on-chip detection of C580Y, the most prevalent single-nucleotide polymorphism associated to artemisinin-resistant malaria. Real-time non-optical DNA sensing is facilitated using Ion-Sensitive Field-Effect Transistors, fabricated in unmodified complementary metal-oxide-semiconductor technology, coupled with loop-mediated isothermal amplification. This work holds significant potential for the development of a fully portable and quantitative malaria diagnostic that can be used as a rapid point-of-care test.</jats:p>

Working paper

Moniri A, Rodriguez-Manzano J, Malpartida-Cardenas K, Yu L-S, Didelot X, Holmes A, Georgiou Pet al., 2019, Framework for DNA quantification and outlier detection using multidimensional standard curves, Analytical Chemistry, Vol: 91, Pages: 7426-7434, ISSN: 0003-2700

Real-time PCR is a highly sensitive and powerful technology for the quantification of DNA and has become the method of choice in microbiology, bioengineering, and molecular biology. Currently, the analysis of real-time PCR data is hampered by only considering a single feature of the amplification profile to generate a standard curve. The current “gold standard” is the cycle-threshold (Ct) method which is known to provide poor quantification under inconsistent reaction efficiencies. Multiple single-feature methods have been developed to overcome the limitations of the Ct method; however, there is an unexplored area of combining multiple features in order to benefit from their joint information. Here, we propose a novel framework that combines existing standard curve methods into a multidimensional standard curve. This is achieved by considering multiple features together such that each amplification curve is viewed as a point in a multidimensional space. Contrary to only considering a single-feature, in the multidimensional space, data points do not fall exactly on the standard curve, which enables a similarity measure between amplification curves based on distances between data points. We show that this framework expands the capabilities of standard curves in order to optimize quantification performance, provide a measure of how suitable an amplification curve is for a standard, and thus automatically detect outliers and increase the reliability of quantification. Our aim is to provide an affordable solution to enhance existing diagnostic settings through maximizing the amount of information extracted from conventional instruments.

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, Daniels J, Liu C, Herrero-Vinas P, Georgiou Pet al., 2019, Convolutional recurrent neural networks for glucose prediction, IEEE Journal of Biomedical and Health Informatics, 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

Rawson TM, Ahmad R, Toumazou C, Georgiou P, Holmes Aet al., 2019, Artificial intelligence can improve decision-making in infection management, Nature Human Behaviour, Vol: 3, Pages: 543-545, ISSN: 2397-3374

Antibiotic resistance is an emerging global danger. Reaching responsible prescribing decisions requires the integration of broad and complex information. Artificial intelligence tools could support decision-making at multiple levels, but building them needs a transparent co-development approach to ensure their adoption upon implementation.

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=00322765&limit=30&person=true