Search

Abstract In hybrid automatic insulin delivery (HAID) systems, meal disturbance is compensated by feedforward control, which requires the announcement of the meal by the patient with type 1 diabetes (DM1) to achieve the desired glycemic control performance. The calculation of insulin bolus in the HAID system is based on the amount of carbohydrates (CHO) in the meal and patient-specific parameters, i.e. carbohydrate-to-insulin ratio (CR) and insulin sensitivity-related correction factor (CF). The estimation of CHO in a meal is prone to errors and is burdensome for patients. This study proposes a fully automatic insulin delivery (FAID) system that eliminates patient intervention by compensating for unannounced meals. This study exploits the deep reinforcement learning (DRL) algorithm to calculate insulin bolus for unannounced meals without utilizing the information on CHO content. The DRL bolus calculator is integrated with a closed-loop controller and a meal detector (both previously developed by our group) to implement the FAID system. An adult cohort of 68 virtual patients based on the modified UVa/Padova simulator was used for in-silico trials. The percentage of the overall duration spent in the target range of 70–180 mg/dL was $$71.2\%$$ 71.2 % and $$76.2\%$$ 76.2 % , $$180$$ > 180 mg/dL was $$26.7\%$$ 26.7 % and $$21.1\%$$ 21.1 % , respectively, for the FAID system and HAID system utilizing a standard bolus calculator (SBC) including CHO misestimation. The proposed algorithm can be exploited to realize FAID systems in the future.

Summary: Background: Dengue epidemics impose considerable strain on healthcare resources. Real-time continuous and non-invasive monitoring of patients admitted to the hospital could lead to improved care and outcomes. We evaluated the performance of a commercially available wearable (SmartCare) utilising photoplethysmography (PPG) to stratify clinical risk for a cohort of hospitalised patients with dengue in Vietnam. Methods: We performed a prospective observational study for adult and paediatric patients with a clinical diagnosis of dengue at the Hospital for Tropical Disease, Ho Chi Minh City, Vietnam. Patients underwent PPG monitoring early during admission alongside standard clinical care. PPG waveforms were analysed using machine learning models. Adult patients were classified between 3 severity classes: i) uncomplicated (ward-based), ii) moderate-severe (emergency department-based), and iii) severe (ICU-based). Data from paediatric patients were split into 2 classes: i) severe (during ICU stay) and ii) follow-up (14–21 days after the illness onset). Model performances were evaluated using standard classification metrics and 5-fold stratified cross-validation. Findings: We included PPG and clinical data from 132 adults and 15 paediatric patients with a median age of 28 (IQR, 21–35) and 12 (IQR, 9–13) years respectively. 1781 h of PPG data were available for analysis. The best performing convolutional neural network models (CNN) achieved a precision of 0.785 and recall of 0.771 in classifying adult patients according to severity class and a precision of 0.891 and recall of 0.891 in classifying between disease and post-disease state in paediatric patients. Interpretation: We demonstrate that the use of a low-cost wearable provided clinically actionable data to differentiate between patients with dengue of varying severity. Continuous monitoring and connectivity to early warning systems could significantly benefit clinical care in dengue, particularly within an endemic setting. Work is currently underway to implement these models for dynamic risk predictions and assist in individualised patient care. Funding: EPSRC Centre for Doctoral Training in High-Performance Embedded and Distributed Systems (HiPEDS) (Grant: EP/L016796/1) and the Wellcome Trust (Grants: 215010/Z/18/Z and 215688/Z/19/Z).

Abstract Antimicrobial resistance (AMR) and healthcare associated infections pose a significant threat globally. One key prevention strategy is to follow antimicrobial stewardship practices, in particular, to maximise targeted oral therapy and reduce the use of indwelling vascular devices for intravenous (IV) administration. Appreciating when an individual patient can switch from IV to oral antibiotic treatment is often non-trivial and not standardised. To tackle this problem we created a machine learning model to predict when a patient could switch based on routinely collected clinical parameters. 10,362 unique intensive care unit stays were extracted and two informative feature sets identified. Our best model achieved a mean AUROC of 0.80 (SD 0.01) on the hold-out set while not being biased to individuals protected characteristics. Interpretability methodologies were employed to create clinically useful visual explanations. In summary, our model provides individualised, fair, and interpretable predictions for when a patient could switch from IV-to-oral antibiotic treatment. Prospectively evaluation of safety and efficacy is needed before such technology can be applied clinically.

Current diagnostic and prognostic tests for prostate cancer require specialised laboratories and have low specificity for prostate cancer detection. As such, recent advancements in electrochemical devices for point of care (PoC) prostate cancer detection have seen significant interest. Liquid-biopsy detection of relevant circulating and exosomal nucleic acid markers presents the potential for minimally invasive testing. In combination, electrochemical devices and circulating DNA and RNA detection present an innovative approach for novel prostate cancer diagnostics, potentially directly within the clinic. Recent research in electrochemical impedance spectroscopy, voltammetry, chronoamperometry and potentiometric sensing using field-effect transistors will be discussed. Evaluation of the PoC relevance of these techniques and their fulfilment of the WHO’s REASSURED criteria for medical diagnostics is described. Further areas for exploration within electrochemical PoC testing and progression to clinical implementation for prostate cancer are assessed.

Abstract Developing multiplex PCR assays requires extensive experimental testing, the number of which exponentially increases by the number of multiplexed targets. Dedicated efforts must be devoted to the design of optimal multiplex assays ensuring specific and sensitive identification of multiple analytes in a single well reaction. Inspired by data-driven approaches, we reinvent the process of developing and designing multiplex assays using a hybrid, simple workflow, named Smart-Plexer, which couples empirical testing of singleplex assays and computer simulation to develop optimised multiplex combinations. The Smart-Plexer analyses kinetic inter-target distances between amplification curves to generate optimal multiplex PCR primer sets for accurate multi-pathogen identification. In this study, the Smart-Plexer method is applied and evaluated for seven respiratory infection target detection using an optimised multiplexed PCR assay. Single-channel multiplex assays, together with the recently published data-driven methodology, Amplification Curve Analysis (ACA), were demonstrated to be capable of classifying the presence of desired targets in a single test for seven common respiratory infection pathogens.

Modern orthopaedic implants use lattice structures that act as 3D scaffolds to enhance bone growth into and around implants. Stochastic scaffolds are of particular interest as they mimic the architecture of trabecular bone and can combine isotropic properties and adjustable structure. The existing research mainly concentrates on controlling the mechanical and biological performance of periodic lattices by adjusting pore size and shape. Still, less is known on how we can control the performance of stochastic lattices through their design parameters: nodal connectivity, strut density and strut thickness. To elucidate this, four lattice structures were evaluated with varied strut densities and connectivity, hence different local geometry and mechanical properties: low apparent modulus, high apparent modulus, and two with near-identical modulus. Pre-osteoblast murine cells were seeded on scaffolds and cultured in vitro for 28 days. Cell adhesion, proliferation and differentiation were evaluated. Additionally, the expression levels of key osteogenic biomarkers were used to assess the effect of each design parameter on the quality of newly formed tissue. The main finding was that increasing connectivity increased the rate of osteoblast maturation, tissue formation and mineralisation. In detail, doubling the connectivity, over fixed strut density, increased collagen type-I by 140%, increased osteopontin by 130% and osteocalcin by 110%. This was attributed to the increased number of acute angles formed by the numerous connected struts, which facilitated the organization of cells and accelerated the cell cycle. Overall, increasing connectivity and adjusting strut density is a novel technique to design stochastic structures which combine a broad range of biomimetic properties and rapid ossification.

Abstract Background Dengue is a common viral illness and severe disease results in life-threatening complications. Healthcare services in low- and middle-income countries treat the majority of dengue cases worldwide. However, the clinical decision-making processes which result in effective treatment are poorly characterised within this setting. In order to improve clinical care through interventions relating to digital clinical decision-support systems (CDSS), we set out to establish a framework for clinical decision-making in dengue management to inform implementation. Methods We utilised process mapping and task analysis methods to characterise existing dengue management at the Hospital for Tropical Diseases, Ho Chi Minh City, Vietnam. This is a tertiary referral hospital which manages approximately 30,000 patients with dengue each year, accepting referrals from Ho Chi Minh city and the surrounding catchment area. Initial findings were expanded through semi-structured interviews with clinicians in order to understand clinical reasoning and cognitive factors in detail. A grounded theory was used for coding and emergent themes were developed through iterative discussions with clinician-researchers. Results Key clinical decision-making points were identified: (i) at the initial patient evaluation for dengue diagnosis to decide on hospital admission and the provision of fluid/blood product therapy, (ii) in those patients who develop severe disease or other complications, (iii) at the point of recurrent shock in balancing the need for fluid therapy with complications of volume overload. From interviews the following themes were identified: prioritising clinical diagnosis and evaluation over existing diagnostics, the role of dengue guidelines published by the Ministry of Health, the impact of seasonality and caseload on decision-making strategies, and the potential role of digital decision-support and disease scoring tools. Conclusions The study highlights the contemporary priorities in delivering clinical care to patients with dengue in an endemic setting. Key decision-making processes and the sources of information that were of the greatest utility were identified. These findings serve as a foundation for future clinical interventions and improvements in healthcare. Understanding the decision-making process in greater detail also allows for development and implementation of CDSS which are suited to the local context.

ABSTRACT Human malaria is a life-threatening parasitic disease with high impact in the sub-Saharan Africa region, where 95% of global cases occurred in 2021. While most malaria diagnostic tools are focused on Plasmodium falciparum, there is a current lack of testing non-P. falciparum cases, which may be underreported and, if undiagnosed or untreated, may lead to severe consequences. In this work, seven species-specific loop-mediated isothermal amplification (LAMP) assays were designed and evaluated against TaqMan quantitative PCR (qPCR), microscopy, and enzyme-linked immunosorbent assays (ELISAs). Their clinical performance was assessed with a cohort of 164 samples of symptomatic and asymptomatic patients from Ghana. All asymptomatic samples with a parasite load above 80 genomic DNA (gDNA) copies per μL of extracted sample were detected with the Plasmodium falciparum LAMP assay, reporting 95.6% (95% confidence interval [95% CI] of 89.9 to 98.5) sensitivity and 100% (95% CI of 87.2 to 100) specificity. This assay showed higher sensitivity than microscopy and ELISA, which were 52.7% (95% CI of 39.7 to 67%) and 67.3% (95% CI of 53.3 to 79.3%), respectively. Nine samples were positive for P. malariae, indicating coinfections with P. falciparum, which represented 5.5% of the tested population. No samples were detected as positive for P. vivax, P. ovale, P. knowlesi, or P. cynomolgi by any method. Furthermore, translation to the point-of-care was demonstrated with a subcohort of 18 samples tested locally in Ghana using our handheld lab-on-chip platform, Lacewing, showing comparable results to a conventional fluorescence-based instrument. The developed molecular diagnostic test could detect asymptomatic malaria cases, including submicroscopic parasitemia, and it has the potential to be used for point-of-care applications. IMPORTANCE The spread of Plasmodium falciparum parasites with Pfhrp2/3 gene deletions presents a major threat to reliable point-of-care diagnosis with current rapid diagnostic tests (RDTs). Novel molecular diagnostics based on nucleic acid amplification are needed to address this liability. In this work, we overcome this challenge by developing sensitive tools for the detection of Plasmodium falciparum and non-P. falciparum species. Furthermore, we evaluate these tools with a cohort of symptomatic and asymptomatic malaria patients and test a subcohort locally in Ghana. The findings of this work could lead to the implementation of DNA-based diagnostics to fight against the spread of malaria and provide reliable, sensitive, and specific diagnostics at the point of care.

Measurement(s) Proteomic Profiling Technology Type(s) Liquid Chromatography Mass Spectrometry Factor Type(s) Palbociclib dosage Sample Characteristic - Organism Homo sapiens Sample Characteristic - Environment cell culture

Abstract People living with type 1 diabetes (T1D) require lifelong self-management to maintain glucose levels in a safe range. Failure to do so can lead to adverse glycemic events with short and long-term complications. Continuous glucose monitoring (CGM) is widely used in T1D self-management for real-time glucose measurements, while smartphone apps are adopted as basic electronic diaries, data visualization tools, and simple decision support tools for insulin dosing. Applying a mixed effects logistic regression analysis to the outcomes of a six-week longitudinal study in 12 T1D adults using CGM and a clinically validated wearable sensor wristband (NCT ID: NCT03643692), we identified several significant associations between physiological measurements and hypo- and hyperglycemic events measured an hour later. We proceeded to develop a new smartphone-based platform, ARISES (Adaptive, Real-time, and Intelligent System to Enhance Self-care), with an embedded deep learning algorithm utilizing multi-modal data from CGM, daily entries of meal and bolus insulin, and the sensor wristband to predict glucose levels and hypo- and hyperglycemia. For a 60-minute prediction horizon, the proposed algorithm achieved the average root mean square error (RMSE) of 35.28 ± 5.77 mg/dL with the Matthews correlation coefficients for detecting hypoglycemia and hyperglycemia of 0.56 ± 0.07 and 0.70 ± 0.05, respectively. The use of wristband data significantly reduced the RMSE by 2.25 mg/dL (p

Abstract Cervical cancer affects over half a million people worldwide each year, the majority of whom are in resource-limited settings where cytology screening is not available. As persistent human papilloma virus (HPV) infections are a key causative factor, detection of HPV strains now complements cytology where screening services exist. This work demonstrates the efficacy of a handheld Lab-on-Chip (LoC) device, with an external sample extraction process, in detecting cervical cancer from biopsy samples. The device is based on Ion-Sensitive Field-Effect Transistor (ISFET) sensors used in combination with loop-mediated isothermal amplification (LAMP) assays, to amplify HPV DNA and human telomerase reverse transcriptase (hTERT) mRNA. These markers were selected because of their high levels of expression in cervical cancer cells, but low to nil expression in normal cervical tissue. The achieved analytical sensitivity for the molecular targets resolved down to a single copy per reaction for the mRNA markers, achieving a limit of detection of 102 for hTERT. In the tissue samples, HPV-16 DNA was present in 4/5 malignant and 2/5 benign tissues, with HPV-18 DNA being present in 1/5 malignant and 1/5 benign tissues. hTERT mRNA was detected in all malignant and no benign tissues, with the demonstrated pilot data to indicate the potential for using the LoC in cervical cancer screening in resource-limited settings on a large scale.

BackgroundIncreased data availability has prompted the creation of clinical decision support systems. These systems utilise clinical information to enhance health care provision, both to predict the likelihood of specific clinical outcomes or evaluate the risk of further complications. However, their adoption remains low due to concerns regarding the quality of recommendations, and a lack of clarity on how results are best obtained and presented.MethodsWe used autoencoders capable of reducing the dimensionality of complex datasets in order to produce a 2D representation denoted as latent space to support understanding of complex clinical data. In this output, meaningful representations of individual patient profiles are spatially mapped in an unsupervised manner according to their input clinical parameters. This technique was then applied to a large real-world clinical dataset of over 12,000 patients with an illness compatible with dengue infection in Ho Chi Minh City, Vietnam between 1999 and 2021. Dengue is a systemic viral disease which exerts significant health and economic burden worldwide, and up to 5% of hospitalised patients develop life-threatening complications.ResultsThe latent space produced by the selected autoencoder aligns with established clinical characteristics exhibited by patients with dengue infection, as well as features of disease progression. Similar clinical phenotypes are represented close to each other in the latent space and clustered according to outcomes broadly described by the World Health Organisation dengue guidelines. Balancing distance metrics and density metrics produced results covering most of the latent space, and improved visualisation whilst preserving utility, with similar patients grouped closer together. In this case, this balance is achieved by using the sigmoid activation function and one hidden layer with three neurons, in addition to the latent dimension layer, which produces the output (Pearson, 0.840; Spearman, 0.830; Procrustes, 0.301; GMM 0.321).ConclusionThis study demonstrates that when adequately configured, autoencoders can produce two-dimensional representations of a complex dataset that conserve the distance relationship between points. The output visualisation groups patients with clinically relevant features closely together and inherently supports user interpretability. Work is underway to incorporate these findings into an electronic clinical decision support system to guide individual patient management.

Dengue is a mosquito-borne disease caused by dengue virus (DENV) serotypes 1-4 which affects 100-400 million adults and children each year. Reverse-transcriptase (RT) quantitative polymerase chain reaction (qPCR) assays are the current gold-standard in diagnosis and serotyping of infections, but their use in low-middle income countries (LMICs) has been limited by laboratory infrastructure requirements. Loop-mediated isothermal amplification (LAMP) assays do not require thermocycling equipment and therefore could potentially be deployed outside laboratories and/or miniaturised. This scoping literature review aimed to describe the analytical and diagnostic performance characteristics of previously developed serotype-specific dengue RT-LAMP assays and evaluate potential for use in portable molecular diagnostic devices. A literature search in Medline was conducted. Studies were included if they were listed before 4th May 2022 (no prior time limit set) and described the development of any serotype-specific DENV RT-LAMP assay ('original assays') or described the further evaluation, adaption or implementation of these assays. Technical features, analytical and diagnostic performance characteristics were collected for each assay. Eight original assays were identified. These were heterogenous in design and reporting. Assays' lower limit of detection (LLOD) and linear range of quantification were comparable to RT-qPCR (with lowest reported values 2.2x101 and 1.98x102 copies/ml, respectively, for studies which quantified target RNA copies) and analytical specificity was high. When evaluated, diagnostic performance was also high, though reference diagnostic criteria varied widely, prohibiting comparison between assays. Fourteen studies using previously described assays were identified, including those where reagents were lyophilised or 'printed' into microfluidic channels and where several novel detection methods were used. Serotype-specific DENV RT-LAMP assays are high-performing and have potential to be used in portable molecular diagnostic devices if they can be integrated with sample extraction and detection methods. Standardised reporting of assay validation and diagnostic accuracy studies would be beneficial.

The decision on when it is appropriate to stop antimicrobial treatment in an individual patient is complex and under-researched. Ceasing too early can drive treatment failure, while excessive treatment risks adverse events. Under- and over-treatment can promote the development of antimicrobial resistance (AMR). We extracted routinely collected electronic health record data from the MIMIC-IV database for 18,988 patients (22,845 unique stays) who received intravenous antibiotic treatment during an intensive care unit (ICU) admission. A model was developed that utilises a recurrent neural network autoencoder and a synthetic control-based approach to estimate patients’ ICU length of stay (LOS) and mortality outcomes for any given day, under the alternative scenarios of if they were to stop vs. continue antibiotic treatment. Control days where our model should reproduce labels demonstrated minimal difference for both stopping and continuing scenarios indicating estimations are reliable (LOS results of 0.24 and 0.42 days mean delta, 1.93 and 3.76 root mean squared error, respectively). Meanwhile, impact days where we assess the potential effect of the unobserved scenario showed that stopping antibiotic therapy earlier had a statistically significant shorter LOS (mean reduction 2.71 days, p-value

Electrocardiogram (ECG) and photoplethysmogram (PPG) are commonly used to determine the vital signs of heart rate, respiratory rate, and oxygen saturation in patient monitoring. In addition to simple observation of those summarized indexes, waveform signals can be analyzed to provide deeper insights into disease pathophysiology and support clinical decisions. Such data, generated from continuous patient monitoring from both conventional bedside and low-cost wearable monitors, are increasingly accessible. However, the recorded waveforms suffer from considerable noise and artifacts and, hence, are not necessarily used prior to certain quality control (QC) measures, especially by those with limited programming experience. Various signal quality indices (SQIs) have been proposed to indicate signal quality. To facilitate and harmonize a wider usage of SQIs in practice, we present a Python package, named vital_sqi, which provides a unified interface to the state-of-the-art SQIs for ECG and PPG signals. The vital_sqi package provides with seven different peak detectors and access to more than 70 SQIs by using different settings. The vital_sqi package is designed with pipelines and graphical user interfaces to enable users of various programming fluency to use the package. Multiple SQI extraction pipelines can take the PPG and ECG waveforms and generate a bespoke SQI table. As these SQI scores represent the signal features, they can be input in any quality classifier. The package provides functions to build simple rule-based decision systems for signal segment quality classification using user-defined SQI thresholds. An experiment with a carefully annotated PPG dataset suggests thresholds for relevant PPG SQIs.

Background and objective: Sub-therapeutic dosing of piperacillin-tazobactam in critically-ill patients is associated with poor clinical outcomes and may promote the emergence of drug-resistant infections. In this paper, an in silico investigation of whether closed-loop control can improve pharmacokinetic-pharmacodynamic (PK-PD) target attainment is described.Method: An in silico platform was developed using PK data from 20 critically-ill patients receiving piperacillin-tazobactam where serum and tissue interstitial fluid (ISF) PK were defined. Intra-day variability on renal clearance, ISF sensor error, and infusion constraints were taken into account. Proportional-integral-derivative (PID) control was selected for drug delivery modulation. Dose adjustment was made based on ISF sensor data with a 30-min sampling period, targeting a serum piperacillin concentration between 32 and 64 mg/L. A single tuning parameter set was employed across the virtual population. The PID controller was compared to standard therapy, including bolus and continuous infusion of piperacillin-tazobactam.Results: Despite significant inter-subject and simulated intra-day PK variability and sensor error, PID demonstrated a significant improvement in target attainment compared to traditional bolus and continuous infusion approaches.Conclusion: A PID controller driven by ISF drug concentration measurements has the potential to precisely deliver piperacillin-tazobactam in critically-ill patients undergoing treatment for sepsis.

Dengue is one of the most prevalent infectious diseases in the world. Rapid, accurate and scalable diagnostics are key to patient management and epidemiological surveillance of the dengue virus (DENV), however current technologies do not match required clinical sensitivity and specificity or rely on large laboratory equipment. In this work, we report the translation of our smartphone-connected handheld Lab-on-Chip (LoC) platform for the quantitative detection of two dengue serotypes. At its core, the approach relies on the combination of Complementary Metal-Oxide-Semiconductor (CMOS) microchip technology to integrate an array of 78 × 56 potentiometric sensors, and a label-free reverse-transcriptase loop mediated isothermal amplification (RT-LAMP) assay. The platform communicates to a smartphone app which synchronises results in real time with a secure cloud server hosted by Amazon Web Services (AWS) for epidemiological surveillance. The assay on our LoC platform (RT-eLAMP) was shown to match performance on a gold-standard fluorescence-based real-time instrument (RT-qLAMP) with synthetic DENV-1 and DENV-2 RNA and extracted RNA from 9 DENV-2 clinical isolates, achieving quantitative detection in under 15 min. To validate the portability of the platform and the geo-tagging capabilities, we led our study in the laboratories at Imperial College London, UK, and Kaohsiung Medical Hospital, Taiwan. This approach carries high potential for application in low resource settings at the point of care (PoC).

BackgroundCritically ill patients often require complex clinical care by highly trained staff within a specialized intensive care unit (ICU) with advanced equipment. There are currently limited data on the costs of critical care in low-and middle-income countries (LMICs). This study aims to investigate the direct-medical costs of key infectious disease (tetanus, sepsis, and dengue) patients admitted to ICU in a hospital in Ho Chi Minh City (HCMC), Vietnam, and explores how the costs and cost drivers can vary between the different diseases.MethodsWe calculated the direct medical costs for patients requiring critical care for tetanus, dengue and sepsis. Costing data (stratified into different cost categories) were extracted from the bills of patients hospitalized to the adult ICU with a dengue, sepsis and tetanus diagnosis that were enrolled in three studies conducted at the Hospital for Tropical Diseases in HCMC from January 2017 to December 2019. The costs were considered from the health sector perspective. The total sample size in this study was 342 patients.ResultsICU care was associated with significant direct medical costs. For patients that did not require mechanical ventilation, the median total ICU cost per patient varied between US$64.40 and US$675 for the different diseases. The costs were higher for patients that required mechanical ventilation, with the median total ICU cost per patient for the different diseases varying between US$2,590 and US$4,250. The main cost drivers varied according to disease and associated severity.ConclusionThis study demonstrates the notable cost of ICU care in Vietnam and in similar LMIC settings. Future studies are needed to further evaluate the costs and economic burden incurred by ICU patients. The data also highlight the importance of evaluating novel critical care interventions that could reduce the costs of ICU care.

BackgroundSymptomatic dengue infection can result in a life-threatening shock syndrome and timely diagnosis is essential. Point-of-care tests for non-structural protein 1 and IgM are used widely but performance can be limited. We developed a supervised machine learning model to predict whether patients with acute febrile illnesses had a diagnosis of dengue or other febrile illnesses (OFI). The impact of seasonality on model performance over time was examined.MethodsWe analysed data from a prospective observational clinical study in Vietnam. Enrolled patients presented with an acute febrile illness of 90%).ConclusionSupervised machine learning models are able to discriminate between dengue and OFI diagnoses in patients presenting with an early undifferentiated febrile illness. These models could be of clinical utility in supporting healthcare decision-making and provide passive surveillance across dengue endemic regions. Effects of seasonality and changing disease prevalence must however be taken into account—this is of significant importance given unpredictable effects of human-induced climate change and the impact on health.

Actinobacillus pleuropneumoniae (APP) is the causative agent of porcine pleuropneumonia, resulting in high economic impact worldwide. There are currently 19 known serovars of APP, with different ones being predominant in specific geographic regions. Outbreaks of pleuropneumonia, characterized by sudden respiratory difficulties and high mortality, can occur when infected pigs are brought into naïve herds, or by those carrying different serovars. Good biosecurity measures include regular diagnostic testing for surveillance purposes. Current gold standard diagnostic techniques lack sensitivity (bacterial culture), require expensive thermocycling machinery (PCR) and are time consuming (culture and PCR). Here we describe the development of an isothermal point-of-care diagnostic test - utilizing recombinase polymerase amplification (RPA) for the detection of APP, targeting the species-specific apxIVA gene. Our APP-RPA diagnostic test achieved a sensitivity of 10 copies/μL using a strain of APP serovar 8, which is the most prevalent serovar in the UK. Additionally, our APP-RPA assay achieved a clinical sensitivity and specificity of 84.3 and 100%, respectively, across 61 extracted clinical samples obtained from farms located in England and Portugal. Using a small subset (n = 14) of the lung tissue samples, we achieved a clinical sensitivity and specificity of 76.9 and 100%, respectively) using lung imprints made on FTA cards tested directly in the APP-RPA reaction. Our results demonstrate that our APP-RPA assay enables a suitable rapid and sensitive screening tool for this important veterinary pathogen.

Optimal management of infectious diseases is guided by up-to-date information at the individual and public health levels. For infections of global importance, including emerging pandemics such as COVID-19 or prevalent endemic diseases such as dengue, identifying patients at risk of severe disease and clinical deterioration can be challenging, considering that the majority present with a mild illness. In our article, we describe the use of wearable technology for continuous physiological monitoring in healthcare settings. Deployment of wearables in hospital settings for the management of infectious diseases, or in the community to support syndromic surveillance during outbreaks, could provide significant, cost-effective advantages and improve healthcare delivery. We highlight a range of promising technologies employed by wearable devices and discuss the technical and ethical issues relating to implementation in the clinic, focusing on low- and middle- income countries. Finally, we propose a set of essential criteria for the rollout of wearable technology for clinical use.

Abstract The increasing prevalence of antimicrobial resistance is a serious threat to global public health. One of the most concerning trends is the rapid spread of Carbapenemase-Producing Organisms (CPO), where colistin has become the last-resort antibiotic treatment. The emergence of colistin resistance, including the spread of mobilized colistin resistance (mcr) genes, raises the possibility of untreatable bacterial infections and motivates the development of improved diagnostics for the detection of colistin-resistant organisms. This work demonstrates a rapid response for detecting the most recently reported mcr gene, mcr−9, using a portable and affordable lab-on-a-chip (LoC) platform, offering a promising alternative to conventional laboratory-based instruments such as real-time PCR (qPCR). The platform combines semiconductor technology, for non-optical real-time DNA sensing, with a smartphone application for data acquisition, visualization and cloud connectivity. This technology is enabled by using loop-mediated isothermal amplification (LAMP) as the chemistry for targeted DNA detection, by virtue of its high sensitivity, specificity, yield, and manageable temperature requirements. Here, we have developed the first LAMP assay for mcr−9 - showing high sensitivity (down to 100 genomic copies/reaction) and high specificity (no cross-reactivity with other mcr variants). This assay is demonstrated through supporting a hospital investigation where we analyzed nucleic acids extracted from 128 carbapenemase-producing bacteria isolated from clinical and screening samples and found that 41 carried mcr−9 (validated using whole genome sequencing). Average positive detection times were 6.58 ± 0.42 min when performing the experiments on a conventional qPCR instrument (n = 41). For validating the translation of the LAMP assay onto a LoC platform, a subset of the samples were tested (n = 20), showing average detection times of 6.83 ± 0.92 min for positive isolates (n = 14). All experiments detected mcr−9 in under 10 min, and both platforms showed no statistically significant difference (p-value > 0.05). When sample preparation and throughput capabilities are integrated within this LoC platform, the adoption of this technology for the rapid detection and surveillance of antimicrobial resistance genes will decrease the turnaround time for DNA detection and resistotyping, improving diagnostic capabilities, patient outcomes, and the management of infectious diseases.

Abstract Modulation of the nervous system by delivering electrical or pharmaceutical agents has contributed to the development of novel treatments to serious health disorders. Recent advances in multidisciplinary research has enabled the emergence of a new powerful therapeutic approach called bioelectronic medicine. Bioelectronic medicine exploits the fact that every organ in our bodies is neurally innervated and thus electrical interfacing with peripheral nerves can be a potential pathway for diagnosing or treating diseases such as diabetes. In this context, a plethora of studies have confirmed the important role of the nervous system in maintaining a tight regulation of glucose homeostasis. This has initiated new research exploring the opportunities of bioelectronic medicine for improving glucose control in people with diabetes, including regulation of gastric emptying, insulin sensitivity, and secretion of pancreatic hormones. Moreover, the development of novel closed-loop strategies aims to provide effective, specific and safe interfacing with the nervous system, and thereby targeting the organ of interest. This is especially valuable in the context of chronic diseases such as diabetes, where closed-loop bioelectronic medicine promises to provide real-time, autonomous and patient-specific therapies. In this article, we present an overview of the state-of-the-art for closed-loop neuromodulation systems in relation to diabetes and discuss future related opportunities for management of this chronic disease.

BackgroundIdentifying patients at risk of dengue shock syndrome (DSS) is vital for effective healthcare delivery. This can be challenging in endemic settings because of high caseloads and limited resources. Machine learning models trained using clinical data could support decision-making in this context.MethodsWe developed supervised machine learning prediction models using pooled data from adult and paediatric patients hospitalised with dengue. Individuals from 5 prospective clinical studies in Ho Chi Minh City, Vietnam conducted between 12th April 2001 and 30th January 2018 were included. The outcome was onset of dengue shock syndrome during hospitalisation. Data underwent random stratified splitting at 80:20 ratio with the former used only for model development. Ten-fold cross-validation was used for hyperparameter optimisation and confidence intervals derived from percentile bootstrapping. Optimised models were evaluated against the hold-out set.FindingsThe final dataset included 4,131 patients (477 adults and 3,654 children). DSS was experienced by 222 (5.4%) of individuals. Predictors were age, sex, weight, day of illness at hospitalisation, indices of haematocrit and platelets over first 48 hours of admission and before the onset of DSS. An artificial neural network model (ANN) model had best performance with an area under receiver operator curve (AUROC) of 0.83 (95% confidence interval [CI], 0.76-0.85) in predicting DSS. When evaluated against the independent hold-out set this calibrated model exhibited an AUROC of 0.82, specificity of 0.84, sensitivity of 0.66, positive predictive value of 0.18 and negative predictive value of 0.98.InterpretationThe study demonstrates additional insights can be obtained from basic healthcare data, when applied through a machine learning framework. The high negative predictive value could support interventions such as early discharge or ambulatory patient management in this population. Work is underway to incorporate these findings into an electronic clinical decision support system to guide individual patient management.

ObjectiveTo establish the sensitivity and specificity of a human papillomavirus (HPV) and tumor marker DNA/mRNA assay for detecting cervical cancer that is transferrable to a Lab-on-a-chip platform and determine its diagnostic benefit in early stage disease when used in conjunction with high-resolution endovaginal magnetic resonance imaging (MRI).MethodsForty-one patients (27 with Stage1 cervical cancer [Group1] and 14 non-cancer HPV negative controls [Group2]) had DNA and RNA extracted from cervical cytology swab samples. HPV16, HPV18, hTERT, TERC/GAPDH and MYC/GAPDH concentration was established using a loop mediated isothermal amplification (LAMP) assay. Thresholds for tumor marker detection for Group1 were set from Group2 analysis (any hTERT, TERC/GAPDH 3.12, MYC/GAPDH 0.155). Group 1 participants underwent endovaginal MRI. Sensitivity and specificity for cancer detection by LAMP and MRI individually and combined was documented by comparison to pathology.ResultsSensitivity and specificity for cancer detection was 68.8% and 77.8% if any tumor marker was positive regardless of HPV status (scenario1), and 93.8% and 55.8% if tumor marker or HPV were positive (scenario 2). Adding endovaginal MRI improved specificity to 88.9% in scenario 1 (sensitivity 68.8%) and to 77.8%% in scenario2 (sensitivity 93.8%).ConclusionSpecificity for cervical cancer detection using a LAMP assay is superior with tumor markers; low sensitivity is improved by HPV detection. Accuracy for early stage cervical cancer detection is optimal using a spatially multiplexed tumor marker/HPV LAMP assay together with endovaginal MRI.

Summary: Background: Emergency admissions for infection often lack initial diagnostic certainty. COVID-19 has highlighted a need for novel diagnostic approaches to indicate likelihood of viral infection in a pandemic setting. We aimed to derive and validate a blood transcriptional signature to detect viral infections, including COVID-19, among adults with suspected infection who presented to the emergency department. Methods: Individuals (aged ≥18 years) presenting with suspected infection to an emergency department at a major teaching hospital in the UK were prospectively recruited as part of the Bioresource in Adult Infectious Diseases (BioAID) discovery cohort. Whole-blood RNA sequencing was done on samples from participants with subsequently confirmed viral, bacterial, or no infection diagnoses. Differentially expressed host genes that met additional filtering criteria were subjected to feature selection to derive the most parsimonious discriminating signature. We validated the signature via RT-qPCR in a prospective validation cohort of participants who presented to an emergency department with undifferentiated fever, and a second case-control validation cohort of emergency department participants with PCR-positive COVID-19 or bacterial infection. We assessed signature performance by calculating the area under receiver operating characteristic curves (AUROCs), sensitivities, and specificities. Findings: A three-gene transcript signature, comprising HERC6, IGF1R, and NAGK, was derived from the discovery cohort of 56 participants with bacterial infections and 27 with viral infections. In the validation cohort of 200 participants, the signature differentiated bacterial from viral infections with an AUROC of 0·976 (95% CI 0·919−1·000), sensitivity of 97·3% (85·8−99·9), and specificity of 100% (63·1−100). The AUROC for C-reactive protein (CRP) was 0·833 (0·694−0·944) and for leukocyte count was 0·938 (0·840−0·986). The signature achieved higher net benefit in decision curve analysis than either CRP or leukocyte count for discriminating viral infections from all other infections. In the second validation analysis, which included SARS-CoV-2-positive participants, the signature discriminated 35 bacterial infections from 34 SARS-CoV-2-positive COVID-19 infections with AUROC of 0·953 (0·893−0·992), sensitivity 88·6%, and specificity of 94·1%. Interpretation: This novel three-gene signature discriminates viral infections, including COVID-19, from other emergency infection presentations in adults, outperforming both leukocyte count and CRP, thus potentially providing substantial clinical utility in managing acute presentations with infection. Funding: National Institute for Health Research, Medical Research Council, Wellcome Trust, and EU-FP7.

Rapid and accurate identification of patients colonised with carbapenemase-producing organisms (CPOs) is essential to adopt prompt prevention measures to reduce the risk of transmission. Recent studies have demonstrated the ability to combine machine learning (ML) algorithms with real-time digital PCR (dPCR) instruments to increase classification accuracy of multiplex PCR assays when using synthetic DNA templates. We sought to determine if this novel methodology could be applied to improve identification of the five major carbapenem-resistant genes in clinical CPO-isolates, which would represent a leap forward in the use of PCR-based data-driven diagnostics for clinical applications. We collected 253 clinical isolates (including 221 CPO-positive samples) and developed a novel 5-plex PCR assay for detection of blaIMP, blaKPC, blaNDM, blaOXA-48, and blaVIM. Combining the recently reported ML method “Amplification and Melting Curve Analysis” (AMCA) with the abovementioned multiplex assay, we assessed the performance of the AMCA methodology in detecting these genes. The improved classification accuracy of AMCA relies on the usage of real-time data from a single-fluorescent channel and benefits from the kinetic/thermodynamic information encoded in the thousands of amplification events produced by high throughput real-time dPCR. The 5-plex showed a lower limit of detection of 10 DNA copies per reaction for each primer set and no cross-reactivity with other carbapenemase genes. The AMCA classifier demonstrated excellent predictive performance with 99.6% (CI 97.8–99.9%) accuracy (only one misclassified sample out of the 253, with a total of 160,041 positive amplification events), which represents a 7.9% increase (p-value

The scope and trajectory of today’s escalating antimicrobial resistance (AMR) crisis is inadequately captured by existing surveillance systems, particularly those of lower income settings. AMR surveillance systems typically collate data from routine culture and susceptibility testing performed in diagnostic bacteriology laboratories to support healthcare. Limited access to high quality culture and susceptibility testing results in the dearth of AMR surveillance data, typical of many parts of the world where the infectious disease burden and antimicrobial need are high. Culture and susceptibility testing by traditional techniques is also slow, which limits its value in infection management. Here, we outline hurdles to effective resistance surveillance in many low-income settings and encourage an open attitude towards new and evolving technologies that, if adopted, could close resistance surveillance gaps. Emerging advancements in point-of-care testing, laboratory detection of resistance through or without culture, and in data handling, have the potential to generate resistance data from previously unrepresented locales while simultaneously supporting healthcare. Among them are microfluidic, nucleic acid amplification technology and next-generation sequencing approaches. Other low tech or as yet unidentified innovations could also rapidly accelerate AMR surveillance. Parallel advances in data handling further promise to significantly improve AMR surveillance, and new frameworks that can capture, collate and use alternate data formats may need to be developed. We outline the promise and limitations of such technologies, their potential to leapfrog surveillance over currently available, conventional technologies in use today and early steps that health systems could take towards preparing to adopt them.

Current artificial pancreas (AP) systems are hybrid closed-loop systems that require manual meal announcements to manage postprandial glucose control effectively. This poses a cognitive burden and challenge to users with T1D since this relies on frequent user engagement to maintain tight glucose control. In order to move towards fully automated closed-loop glucose control, we propose an algorithm based on a deep learning framework that performs multitask quantile regression, for both meal detection and carbohydrate estimation. Our proposed method is evaluated in silico on 10 adult subjects from the UVa/Padova simulator with a Bio-inspired Artificial Pancreas (BiAP) control algorithm over a 2 month period. Three different configurations of the AP are evaluated -BiAP without meal announcement (BiAP-NMA), BiAP with meal announcement (BiAP-MA), and BiAP with meal detection (BiAP-MD). We present results showing an improvement of BiAP-MD over BiAP-NMA, demonstrating 144.5 ± 6.8 mg/dL mean blood glucose level (−4.4 mg/dL, p< 0.01) and 77.8 ± 6.3% mean time between 70 and 180 mg/dL (+3.9%, p< 0.001). This improvement in control is realised without a significant increase in mean in hypoglycaemia (+0.1%, p= 0.4). In terms of detection of meals and snacks, the proposed method on average achieves 93% precision and 76% recall with a detection delay time of 38 ± 15 min (92% precision, 92% recall, and 37 min detection time for meals only). Furthermore, BiAP-MD handles hypoglycaemia better than BiAP-MA based on CVGA assessment with fewer control errors (10% vs. 20%). This study suggests that multitask quantile regression can improve the capability of AP systems for postprandial glucose control without increasing hypoglycaemia.

Summary: Background: Enhanced 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. Methods: This 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 ClinicalTrials.gov, number NCT03847610. Findings: Ten healthy volunteers participated in the study. Mean age was 42 years (SD 14). Seven (70%) were men. Microdialysis and microneedle results were similar for phenoxymethylpenicillin ECF maximum concentration (0·74 mg/L vs 0·64 mg/L; 95% CI −0·24 to 0·44; p=0·53), time to maximum concentration (1·18 h vs 1·10 h; −0·52 to 0·67; p=0·79), and AUC (1·54 mg × h/L vs 1·67 mg × h/L; −1·10 to 0·85; p=0·79). In total, 440 time points were compared with mean difference between measurements −0·16 mg/L (95% CI −1·30 to 0·82). Mean phenoxymethylpenicillin AUCs for free serum and microneedle PK were similar (1·77 mg × h/L [SD 0·59] vs 1·67 mg × h/L [1·00]; −0·77 to 0·97; p=0·81). Median coefficient of variation between sensors within individuals was 7% (IQR 4–17). Limit of detection for the microneedles was estimated at 0·17 mg/L. Interpretation: This study is proof-of-concept of real-time, microneedle sensing of penicillin in vivo. Future work will explore microneedle use in patient populations, their role in data generation to inform dosing recommendations, and their incorporation into closed-loop control systems for automated drug delivery. Funding: National Institute for Health Research Imperial Biomedical Research Centre, Mérieux Foundation.

Abstract Diabetes is a disease caused by a breakdown in the glucose metabolic process resulting in abnormal blood glucose fluctuations. Traditionally, control has involved external insulin injection in response to elevated blood glucose to substitute the role of the beta cells in the pancreas which would otherwise perform this function in a healthy individual. The central nervous system (CNS), however, also plays a vital role in glucose homoeostasis through the control of pancreatic secretion and insulin sensitivity which could potentially be used as a pathway for enhancing glucose control. In this review, we present an overview of the brain regions, peripheral nerves and molecular mechanisms by which the CNS regulates glucose metabolism and the potential benefits of modulating them for diabetes management. Development of technologies to interface to the nervous system will soon become a reality through bioelectronic medicine and we present the emerging opportunities for the treatment of type 1 and type 2 diabetes.

Abstract Background We developed a personalised antimicrobial information module co-designed with patients. This study aimed to evaluate the potential impact of this patient-centred intervention on short-term knowledge and understanding of antimicrobial therapy in secondary care. Methods Thirty previous patients who had received antibiotics in hospital within 12 months were recruited to co-design an intervention to promote patient engagement with infection management. Two workshops, containing five focus-groups were held. These were audio-recorded. Data were analysed using a thematic framework developed deductively based on previous work. Line-by-line coding was performed with new themes added to the framework by two researchers. This was used to inform the development of a patient information module, embedded within an electronic decision support tool (CDSS). The intervention was piloted over a four-week period at Imperial College Healthcare NHS Trust on 30 in-patients. Pre- and post-intervention questionnaires were developed and implemented to assess short term changes in patient knowledge and understanding and provide feedback on the intervention. Data were analysed using SPSS and NVIVO software. Results Within the workshops, there was consistency in identified themes. The participants agreed upon and co-designed a personalised PDF document that could be integrated into an electronic CDSS to be used by healthcare professionals at the point-of-care. Their aim for the tool was to provide individualised practical information, signpost to reputable information sources, and enhance communication between patients and healthcare professionals. Eighteen out of thirty in-patients consented to participant in the pilot evaluation with 15/18(83%) completing the study. Median (range) age was 66(22–85) years. The majority were male (10/15;66%). Pre-intervention, patients reported desiring further information regarding their infections and antibiotic therapy, including side effects of treatment. Deployment of the intervention improved short term knowledge and understanding of individuals infections and antibiotic management with median (IQR) scores improving from 3(2–5)/13 to 10(6–11)/13. 13/15(87%) reported that they would use the intervention again. Conclusion A personalised, patient-centred intervention improved understanding and short-term knowledge of infections and antibiotic therapy in participating patients’. Long term impact on attitudes and behaviours post discharge will be further investigated.

Abstract Background Antimicrobial Resistance is threatening our ability to treat common infectious diseases and overuse of antimicrobials to treat human infections in hospitals is accelerating this process. Clinical Decision Support Systems (CDSSs) have been proven to enhance quality of care by promoting change in prescription practices through antimicrobial selection advice. However, bypassing an initial assessment to determine the existence of an underlying disease that justifies the need of antimicrobial therapy might lead to indiscriminate and often unnecessary prescriptions. Methods From pathology laboratory tests, six biochemical markers were selected and combined with microbiology outcomes from susceptibility tests to create a unique dataset with over one and a half million daily profiles to perform infection risk inference. Outliers were discarded using the inter-quartile range rule and several sampling techniques were studied to tackle the class imbalance problem. The first phase selects the most effective and robust model during training using ten-fold stratified cross-validation. The second phase evaluates the final model after isotonic calibration in scenarios with missing inputs and imbalanced class distributions. Results More than 50% of infected profiles have daily requested laboratory tests for the six biochemical markers with very promising infection inference results: area under the receiver operating characteristic curve (0.80-0.83), sensitivity (0.64-0.75) and specificity (0.92-0.97). Standardization consistently outperforms normalization and sensitivity is enhanced by using the SMOTE sampling technique. Furthermore, models operated without noticeable loss in performance if at least four biomarkers were available. Conclusion The selected biomarkers comprise enough information to perform infection risk inference with a high degree of confidence even in the presence of incomplete and imbalanced data. Since they are commonly available in hospitals, Clinical Decision Support Systems could benefit from these findings to assist clinicians in deciding whether or not to initiate antimicrobial therapy to improve prescription practices.

In the last years, there has been an increase of antimicrobial resistance rates around the world with the misuse and overuse of antimicrobials as one of the main leading drivers. In response to this threat, a variety of initiatives have arisen to promote the efficient use of antimicrobials. These initiatives rely on antimicrobial surveillance systems to promote appropriate prescription practices and are provided by national or global health care institutions with limited consideration of the variations within hospitals. As a consequence, physicians’ adherence to these generic guidelines is still limited. To fill this gap, this work presents an automated approach to performing local antimicrobial surveillance from microbiology data. Moreover, in addition to the commonly reported resistance rates, this work estimates secular resistance trends through regression analysis to provide a single value that effectively communicates the resistance trend to a wider audience. The methods considered for trend estimation were ordinary least squares regression, weighted least squares regression with weights inversely proportional to the number of microbiology records available and autoregressive integrated moving average. Among these, weighted least squares regression was found to be the most robust against changes in the granularity of the time series and presented the best performance. To validate the results, three case studies have been thoroughly compared with the existing literature: (i) Escherichia coli in urine cultures; (ii) Escherichia coli in blood cultures; and (iii) Staphylococcus aureus in wound cultures. The benefits of providing local rather than general antimicrobial surveillance data of a higher quality is two fold. Firstly, it has the potential to stimulate engagement among physicians to strengthen their knowledge and awareness on antimicrobial resistance which might encourage prescribers to change their prescription habits more willingly. Moreover, it provides fundamental knowledge to the wide range of stakeholders to revise and potentially tailor existing guidelines to the specific needs of each hospital.

(1) Background: People living with type 1 diabetes (T1D) require self-management to maintain blood glucose (BG) levels in a therapeutic range through the delivery of exogenous insulin. However, due to the various variability, uncertainty and complex glucose dynamics, optimizing the doses of insulin delivery to minimize the risk of hyperglycemia and hypoglycemia is still an open problem. (2) Methods: In this work, we propose a novel insulin bolus advisor which uses deep reinforcement learning (DRL) and continuous glucose monitoring to optimize insulin dosing at mealtime. In particular, an actor-critic model based on deep deterministic policy gradient is designed to compute mealtime insulin doses. The proposed system architecture uses a two-step learning framework, in which a population model is first obtained and then personalized by subject-specific data. Prioritized memory replay is adopted to accelerate the training process in clinical practice. To validate the algorithm, we employ a customized version of the FDA-accepted UVA/Padova T1D simulator to perform in silico trials on 10 adult subjects and 10 adolescent subjects. (3) Results: Compared to a standard bolus calculator as the baseline, the DRL insulin bolus advisor significantly improved the average percentage time in target range (70–180 mg/dL) from 74.1%±8.4% to 80.9%±6.9% (p<0.01) and 54.9%±12.4% to 61.6%±14.1% (p<0.01) in the the adult and adolescent cohorts, respectively, while reducing hypoglycemia. (4) Conclusions: The proposed algorithm has the potential to improve mealtime bolus insulin delivery in people with T1D and is a feasible candidate for future clinical validation.

(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 prediction horizon, the percentage improvement on prediction accuracy measured with the root mean square error, A-region of error grid analysis (EGA), and hypoglycaemia prediction calculated by the Matthews correlation coefficient, was 18.8 % , 17.9 % , and 80.9 % , respectively. Although showing a trend towards improvement, the addition of meal absorption information did not provide clinically significant improvements. (4) Conclusion: The proposed glucose forecasting algorithm is potentially well-suited for T1D management applications which require long-term glucose predictions.

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.