340 results found
Alexandrou G, Moser N, Mantikas K-T, et al., 2021, Detection of Multiple Breast Cancer ESR1 mutations on an ISFET based Lab-on-Chip Platform., IEEE Trans Biomed Circuits Syst, Vol: PP
ESR1 mutations are important biomarkers in metastatic breast cancer. Specifically, p.E380Q and p.Y537S mu- tations arise in response to hormonal therapies given to patients with hormone receptor positive (HR+) breast cancer (BC). This paper demonstrates the efficacy of an ISFET based CMOS integrated Lab-on-Chip (LoC) system, coupled with variant- specific isothermal amplification chemistries, for detection and discrimination of wild type (WT) from mutant (MT) copies of the ESR1 gene. Hormonal resistant cancers often lead to increased chances of metastatic disease which leads to high mortality rates, especially in low-income regions and areas with low healthcare coverage. Design and optimization of bespoke primers was carried out and tested on a qPCR instrument and then benchmarked versus the LoC platform. Assays for detection of p.Y537S and p.E380Q were developed and tested on the LoC platform, achieving amplification in under 25 minutes and sensitivity of down to 1000 copies of DNA per reaction for both target assays. The LoC system hereby presented, is cheaper and smaller than other standard industry equivalent technologies such as qPCR and sequencing. The LoC platform proposed, has the potential to be used at a breast cancer point-of-care testing setting, offering mutational tracking of circulating tumour DNA in liquid biopsies to assist patient stratification and metastatic monitoring.
Panteli C, Georgiou P, Fobelets K, 2021, Reduced Drift of CMOS ISFET pH Sensors Using Graphene Sheets, IEEE SENSORS JOURNAL, Vol: 21, Pages: 14609-14618, ISSN: 1530-437X
Rawson TM, Hernandez B, Moore L, et al., 2021, A real-world evaluation of a case-based reasoning algorithm to support antimicrobial prescribing decisions in acute care, Clinical Infectious Diseases, Vol: 72, Pages: 2103-2111, ISSN: 1058-4838
BackgroundA locally developed Case-Based Reasoning (CBR) algorithm, designed to augment antimicrobial prescribing in secondary care was evaluated.MethodsPrescribing recommendations made by a CBR algorithm were compared to decisions made by physicians in clinical practice. Comparisons were examined in two patient populations. Firstly, in patients with confirmed Escherichia coli blood stream infections (‘E.coli patients’), and secondly in ward-based patients presenting with a range of potential infections (‘ward patients’). Prescribing recommendations were compared against the Antimicrobial Spectrum Index (ASI) and the WHO Essential Medicine List Access, Watch, Reserve (AWaRe) classification system. Appropriateness of a prescription was defined as the spectrum of the prescription covering the known, or most-likely organism antimicrobial sensitivity profile.ResultsIn total, 224 patients (145 E.coli patients and 79 ward patients) were included. Mean (SD) age was 66 (18) years with 108/224 (48%) female gender. The CBR recommendations were appropriate in 202/224 (90%) compared to 186/224 (83%) in practice (OR: 1.24 95%CI:0.392-3.936;p=0.71). CBR recommendations had a smaller ASI compared to practice with a median (range) of 6 (0-13) compared to 8 (0-12) (p<0.01). CBR recommendations were more likely to be classified as Access class antimicrobials compared to physicians’ prescriptions at 110/224 (49%) vs. 79/224 (35%) (OR: 1.77 95%CI:1.212-2.588 p<0.01). Results were similar for E.coli and ward patients on subgroup analysis.ConclusionsA CBR-driven decision support system provided appropriate recommendations within a narrower spectrum compared to current clinical practice. Future work must investigate the impact of this intervention on prescribing behaviours more broadly and patient outcomes.
Thomas K, Lazarini A, Kaltsonoudis E, et al., 2021, Incidence, risk factors and validation of the RABBIT score for serious infections in a cohort of 1557 patients with rheumatoid arthritis, RHEUMATOLOGY, Vol: 60, Pages: 2223-2230, ISSN: 1462-0324
Miglietta L, Moniri A, Pennisi I, et al., 2021, Coupling machine learning and high throughput multiplex digital PCR enables accurate detection of carbapenem-resistant genes in clinical isolates, medRxiv
<jats:p>Background: The emergence and spread of carbapenemase-producing organisms (CPO) are a significant clinical and public health concern. Rapid and accurate identification of patients colonised with CPO is essential to adopt prompt prevention measures in order to reduce the risk of transmission. Recent proof-of-concept studies have demonstrated the ability to combine machine learning (ML) algorithms with real-time digital PCR (dPCR) instruments to increase classification accuracy of multiplex assays. From this, we sought to determine if this ML based methodology could accurately identify five major carbapenem-resistant genes in clinical CPO-isolates.Methods: We collected 253 clinical isolates (including 221 CPO-positive samples) and developed a novel 5-plex assay for detection of blaVIM, blaOXA-48, blaNDM, blaIMP and blaKPC. Combining the recently reported ML method "Amplification and Melting Curve Analysis" (AMCA) with the abovementioned multiplex assay, we assessed the performance of the methodology in detecting these five carbapenem-resistant genes. The classification accuracy relies on the usage of real-time data from a single fluorescent channel and benefits from the kinetic and thermodynamic information encoded in the thousands of amplification events produced by high throughput dPCR.Results: The 5-plex showed a lower limit of detection of 100 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 163,966 positive amplification events), which represents a 7.9% increase compared to the conventional ML-based melting curve analysis (MCA) method.Conclusion: This work demonstrates the utility of the AMCA method to increase the throughput and performance of state-of-the-art molecular diagnostic platforms, reducing costs without any changes
Zhu T, Li K, Herrero P, et al., 2021, Basal Glucose Control in Type 1 Diabetes Using Deep Reinforcement Learning: An In Silico Validation, IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, Vol: 25, Pages: 1223-1232, ISSN: 2168-2194
Ma D, Ghoreishizadeh SS, Georgiou P, 2021, Concurrent potentiometric and amperometric sensing with shared reference electrodes, IEEE Sensors Journal, Vol: 21, Pages: 5720-5727, ISSN: 1530-437X
Potentiometry and amperometry are the two most common electrochemical sensing methods. They are conventionally performed at different times, although new applications are emerging that require their simultaneous usage in a single electrochemical cell. This paper investigates the feasibility and potential drawbacks of such a setup. We use a potentiometric and an amperometric sensor to compare their output signals when they are used individually, as well as when they are combined together with a shared reference electrode. Our results in particular show that potentiometric readings with a shared reference electrode show a high correlation of 0.9981 with conventional potentiometry. In the case of amperometric sensing, the cross correlation of the simultaneous versus individual measurement is 0.9959. Furthermore, we also demonstrate concurrent measurement for potentiometry in the presence of cell current through the design of innovative test systems. This is done through measuring both varying pH values and varying concentrations of H2O2 to showcase the operation of the circuit.
Rawson TM, Hernandez B, Wilson R, et al., 2021, Supervised machine learning to support the diagnosis of bacterial infection in the context of COVID-19, JAC-Antimicrobial Resistance, Vol: 3, Pages: 1-4, ISSN: 2632-1823
Background: Bacterial infection has been challenging to diagnose in patients with COVID-19. We developed and evaluated supervised machine learning algorithms to support the diagnosis of secondary bacterial infection in hospitalized patients during COVID-19.Methods: Inpatient data at three London hospitals for the first COVD-19 wave in March and April 2020 were extracted. Demographic, blood test, and microbiology data for individuals with and without SARS-CoV-2 positive PCR were obtained. A Gaussian-Naïve Bayes (GNB), Support Vector Machine (SVM), and Artificial Neuronal Network (ANN) were trained and compared using the area under the receiver operating characteristic curve (AUCROC). The best performing algorithm (SVM with 21 blood test variables) was prospectively piloted in July 2020. AUCROC was calculated for the prediction of a positive microbiological sample within 48 hours of admission. Results: A total of 15,599 daily blood profiles for 1,186 individual patients were identified to train the algorithms. 771/1186 (65%) individuals were SARS-CoV-2 PCR positive. Clinically significant microbiology results were present for 166/1186 (14%) patients during admission. A SVM algorithm trained with 21 routine blood test variables and over 8000 individual profiles had the best performance. AUCROC was 0.913, sensitivity 0.801, and specificity 0.890. Prospective testing on 54 patients on admission (28/54, 52% SARS-CoV-2 PCR positive) demonstrated an AUCROC of 0.960 (0.90-1.00). Conclusion: A SVM using 21 routine blood test variables had excellent performance at inferring the likelihood of positive microbiology. Further prospective evaluation of the algorithms ability to support decision making for the diagnosis of bacterial infection in COVID-19 cohorts is underway.
Rodriguez-Manzano J, Malpartida-Cardenas K, Moser N, et al., 2021, Handheld point-of-care system for rapid detection of SARS-CoV-2 extracted RNA in under 20 min, ACS Central Science, Vol: 7, Pages: 307-317, ISSN: 2374-7943
The COVID-19 pandemic is a global health emergency characterized by the high rate of transmission and ongoing increase of cases globally. Rapid point-of-care (PoC) diagnostics to detect the causative virus, SARS-CoV-2, are urgently needed to identify and isolate patients, contain its spread and guide clinical management. In this work, we report the development of a rapid PoC diagnostic test (<20 min) based on reverse transcriptase loop-mediated isothermal amplification (RT-LAMP) and semiconductor technology for the detection of SARS-CoV-2 from extracted RNA samples. The developed LAMP assay was tested on a real-time benchtop instrument (RT-qLAMP) showing a lower limit of detection of 10 RNA copies per reaction. It was validated against extracted RNA from 183 clinical samples including 127 positive samples (screened by the CDC RT-qPCR assay). Results showed 91% sensitivity and 100% specificity when compared to RT-qPCR and average positive detection times of 15.45 ± 4.43 min. For validating the incorporation of the RT-LAMP assay onto our PoC platform (RT-eLAMP), a subset of samples was tested (n = 52), showing average detection times of 12.68 ± 2.56 min for positive samples (n = 34), demonstrating a comparable performance to a benchtop commercial instrument. Paired with a smartphone for results visualization and geolocalization, this portable diagnostic platform with secure cloud connectivity will enable real-time case identification and epidemiological surveillance.
Pennisi I, Rodriguez Manzano J, Moniri A, et al., 2021, Translation of a host blood RNA Signature distinguishing bacterial from viral infection into a platform suitable for development as a point-of-care test, JAMA Pediatrics, Vol: 175, Pages: 417-419, ISSN: 2168-6203
Zhu T, Li K, Georgiou P, 2021, Personalized Dual-Hormone Control for Type 1 Diabetes Using Deep Reinforcement Learning, Pages: 45-53, ISSN: 1860-949X
We introduce a dual-hormone control algorithm for people with Type 1 Diabetes (T1D) which uses deep reinforcement learning (RL). Specifically, double dilated recurrent neural networks are used to learn the control strategy, trained by a variant of Q-learning. The inputs to the model include the real-time sensed glucose and meal carbohydrate content, and the outputs are the actions necessary to deliver dual-hormone (basal insulin and glucagon) control. Without prior knowledge of the glucose-insulin metabolism, we develop a data-driven model using the UVA/Padova Simulator. We first pre-train a generalized model using long-term exploration in an environment with average T1D subject parameters provided by the simulator, then adopt importance sampling to train personalized models for each individual. In-silico, the proposed algorithm largely reduces adverse glycemic events, and achieves time in range, i.e., the percentage of normoglycemia, for the adults and for the adolescents, which outperforms previous approaches significantly. These results indicate that deep RL has great potential to improve the treatment of chronic diseases such as diabetes.
Troppoli T, Zanos P, Georgiou P, et al., 2020, An alpha 5-Containing Benzodiazepine Site on the GABAAR is Required for the Fast Antidepressant-Like Actions of MRK-016 on Stress-Induced Anhedonia and Weakened Synaptic Function, 59th Annual Meeting of the American-College-of-Neuropsychopharmacology (ACNP), Publisher: SPRINGERNATURE, Pages: 111-111, ISSN: 0893-133X
Karolcik S, Miscourides N, Cacho-Soblechero M, et al., 2020, A High-Performance Raspberry Pi-Based Interface for Ion Imaging Using ISFET Arrays, IEEE SENSORS JOURNAL, Vol: 20, Pages: 12837-12847, ISSN: 1530-437X
Yu L-S, Rodriguez-Manzano J, Moser N, et al., 2020, Rapid detection of azole-resistant Aspergillus fumigatus in clinical and environmental isolates using lab-on-a-chip diagnostic system, Journal of Clinical Microbiology, Vol: 58, Pages: 1-11, ISSN: 0095-1137
Aspergillus fumigatus has widely evolved resistance to the most commonly used class of antifungal chemicals, the azoles. Current methods for identifying azole resistance are time-consuming and depend on specialized laboratories. There is an urgent need for rapid detection of these emerging pathogens at point-of-care to provide the appropriate treatment in the clinic and to improve management of environmental reservoirs to mitigate the spread of antifungal resistance. Our study demonstrates the rapid and portable detection of the two most relevant genetic markers linked to azole resistance, the mutations TR34 and TR46, found in the promoter region of the gene encoding the azole target, cyp51A. We developed a lab-on-a-chip platform consisting of: (1) tandem-repeat loop-mediated isothermal amplification, (2) state-of-the-art complementary metal-oxide-semiconductor microchip technology for nucleic-acid amplification detection and, (3) and a smartphone application for data acquisition, visualization and cloud connectivity. Specific and sensitive detection was validated with isolates from clinical and environmental samples from 6 countries across 5 continents, showing a lower limit-of-detection of 10 genomic copies per reaction in less than 30 minutes. When fully integrated with a sample preparation module, this diagnostic system will enable the detection of this ubiquitous fungus at the point-of-care, and could help to improve clinical decision making, infection control and epidemiological surveillance.
Keeble L, Moser N, Rodriguez-Manzano J, et al., 2020, ISFET-Based Sensing and Electric Field Actuation of DNA for On-Chip Detection: A Review, IEEE SENSORS JOURNAL, Vol: 20, Pages: 11044-11065, ISSN: 1530-437X
Moscardo V, Herrero P, Reddy M, et al., 2020, Assessment of Glucose Control Metrics by Discriminant Ratio, DIABETES TECHNOLOGY & THERAPEUTICS, Vol: 22, Pages: 719-726, ISSN: 1520-9156
Moniri A, Miglietta L, Holmes A, et al., 2020, High-level multiplexing in digital PCR with intercalating dyes by coupling real-time kinetics and melting curve analysis., Analytical Chemistry, Vol: 92, Pages: 14181-14188, ISSN: 0003-2700
Digital polymerase chain reaction (dPCR) is a mature technique that has enabled scientific breakthroughs in several fields. However, this technology is primarily used in research environments with high-level multiplexing representing a major challenge. Here, we propose a novel method for multiplexing, referred to as amplification and melting curve analysis (AMCA), which leverages the kinetic information in real-time amplification data and the thermodynamic melting profile using an affordable intercalating dye (EvaGreen). The method trains a system comprised of supervised machine learning models for accurate classification, by virtue of the large volume of data from dPCR platforms. As a case study, we develop a new 9-plex assay to detect mobilised colistin resistant (mcr) genes as clinically relevant targets for antimicrobial resistance. Over 100,000 amplification events have been analysed, and for the positive reactions, the AMCA approach reports a classification accuracy of 99.33 ± 0.13%, an increase of 10.0% over using melting curve analysis. This work provides an affordable method of high-level multiplexing without fluorescent probes, extending the benefits of dPCR in research and clinical settings.
Moniri A, Miglietta L, Malpartida Cardenas K, et al., 2020, Amplification curve analysis: Data-driven multiplexing using real-time digital PCR, Analytical Chemistry, Vol: 92, Pages: 13134-13143, ISSN: 0003-2700
Information about the kinetics of PCR reactions are encoded in the amplification curve. However, in digital PCR (dPCR), this information is typically neglected by collapsing each amplification curve into a binary output (positive/negative). Here, we demonstrate that the large volume of raw data obtained from realtime dPCR instruments can be exploited to perform data-driven multiplexing in a single fluorescent channel using machine learning methods, by virtue of the information in the amplification curve. This new approach, referred to as amplification curve analysis (ACA), was shown using an intercalating dye (EvaGreen), reducing the cost and complexity of the assay and enabling the use of melting curve analysis for validation. As a case study, we multiplexed 3 carbapenem-resistant genes to show the impact of this approach on global challenges such as antimicrobial resistance. In the presence of single targets, we report a classification accuracy of 99.1% (N = 16188) which represents a 19.7% increase compared to multiplexing based on the final fluorescent intensity. Considering all combinations of amplification events (including coamplifications), the accuracy was shown to be 92.9% (N = 10383). To support the analysis, we derived a formula to estimate the occurrence of co-amplification in dPCR based on multivariate Poisson statistics, and suggest reducing the digital occupancy in the case of multiple targets in the same digital panel. The ACA approach takes a step towards maximizing the capabilities of existing real-time dPCR instruments and chemistries, by extracting more information from data to enable data-driven multiplexing with high accuracy. Furthermore, we expect that combining this method with existing probe-based assays will increase multiplexing capabilities significantly. We envision that once emerging point-of-care technologies can reliably capture real-time data from isothermal chemistries, the ACA method will facilitate the implementation of dPCR outs
Zhu T, Li K, Kuang L, et al., 2020, An Insulin Bolus Advisor for Type 1 Diabetes Using Deep Reinforcement Learning, SENSORS, Vol: 20
Zhu T, Li K, Chen J, et al., 2020, Dilated Recurrent Neural Networks for Glucose Forecasting in Type 1 Diabetes, Journal of Healthcare Informatics Research, Vol: 4, Pages: 308-324
Diabetes is a chronic disease affecting 415 million people worldwide. People with type 1 diabetes mellitus (T1DM) need to self-administer insulin to maintain blood glucose (BG) levels in a normal range, which is usually a very challenging task. Developing a reliable glucose forecasting model would have a profound impact on diabetes management, since it could provide predictive glucose alarms or insulin suspension at low-glucose for hypoglycemia minimisation. Recently, deep learning has shown great potential in healthcare and medical research for diagnosis, forecasting and decision-making. In this work, we introduce a deep learning model based on a dilated recurrent neural network (DRNN) to provide 30-min forecasts of future glucose levels. Using dilation, the DRNN model gains a much larger receptive field in terms of neurons aiming at capturing long-term dependencies. A transfer learning technique is also applied to make use of the data from multiple subjects. The proposed approach outperforms existing glucose forecasting algorithms, including autoregressive models (ARX), support vector regression (SVR) and conventional neural networks for predicting glucose (NNPG) (e.g. RMSE = NNPG, 22.9 mg/dL; SVR, 21.7 mg/dL; ARX, 20.1 mg/dl; DRNN, 18.9 mg/dL on the OhioT1DM dataset). The results suggest that dilated connections can improve glucose forecasting performance efficiently.
Pennisi I, Rodriguez Manzano J, Miscourides N, et al., 2020, A method for determining a diagnostic outcome
Rodriguez Manzano J, Moniri A, Miglietta L, et al., 2020, Identifying a target nucleic acid
Peiffer-Smadja N, Rawson TM, Ahmad R, et al., 2020, machine learning for clinical decision support in infectious diseases: a narrative review of current applications (vol 26, pg 584, 2020), CLINICAL MICROBIOLOGY AND INFECTION, Vol: 26, Pages: 1118-1118, ISSN: 1198-743X
Moniri A, Terracina D, Rodriguez-Manzano J, et al., 2020, Real-time forecasting of sEMG features for trunk muscle fatigue using machine learning, IEEE Transactions on Biomedical Engineering, Vol: 68, Pages: 718-727, ISSN: 0018-9294
Objective: Several features of the surface electromyography (sEMG) signal are related to muscle activity and fatigue. However, the time-evolution of these features are non-stationary and vary between subjects. The aim of this study is to investigate the use of adaptive algorithms to forecast sMEG feature of the trunk muscles. Methods: Shallow models and a deep convolutional neural network (CNN) were used to simultaneously learn and forecast 5 common sEMG features in real-time to provide tailored predictions. This was investigated for: up to a 25 second horizon; for 14 different muscles in the trunk; across 13 healthy subjects; while they were performing various exercises. Results: The CNN was able to forecast 25 seconds ahead of time, with 6.88% mean absolute percentage error and 3.72% standard deviation of absolute percentage error, across all the features. Moreover, the CNN outperforms the best shallow model in terms of a figure of merit combining accuracy and precision by at least 30% for all the 5 features. Conclusion: Even though the sEMG features are non-stationary and vary between subjects, adaptive learning and forecasting, especially using CNNs, can provide accurate and precise forecasts across a range of physical activities. Significance: The proposed models provide the groundwork for a wearable device which can forecast muscle fatigue in the trunk, so as to potentially prevent low back pain. Additionally, the explicit realtime forecasting of sEMG features provides a general model which can be applied to many applications of muscle activity monitoring, which helps practitioners and physiotherapists improve therapy.
Ming DK, Sorawat S, Chanh HQ, et al., 2020, Continuous physiological monitoring using wearable technology to inform individual management of infectious diseases, public health and outbreak responses, International Journal of Infectious Diseases, Vol: 96, Pages: 648-654, ISSN: 1201-9712
Optimal management of infectious diseases is guided by up-to-date information at the individual and public health level. For infections of global importance including emerging pandemics such as COVID-19 or prevalent endemic diseases such like dengue, identifying patients at risk of severe disease and clinical deterioration can be challenging given the majority present with a mild illness. In our article, we describe the use of wearable technology for continuous physiological monitoring in healthcare. 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, with specific focus on low- and middle- income countries. Finally, we propose a set of essential criteria for the roll-out of wearable technology for clinical use.
Rodriguez Manzano J, Moser N, Malpartida Cardenas K, et al., 2020, Rapid detection of mobilized colistin resistance using a nucleic acid based lab-on-a-chip diagnostic system, Scientific Reports, Vol: 10, ISSN: 2045-2322
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 o
Miscourides N, Georgiou P, 2020, Calibrating for Trapped Charge in Large-Scale ISFET Arrays, IEEE SENSORS JOURNAL, Vol: 20, Pages: 5110-5118, ISSN: 1530-437X
Peiffer-Smadja N, Rawson TM, Ahmad R, et al., 2020, Machine learning for clinical decision support in infectious diseases: A narrative review of current applications, Clinical Microbiology and Infection, Vol: 26, Pages: 584-595, 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
Guemes A, Cappon G, Hernandez B, et al., 2020, Predicting quality of overnight glycaemic control in type 1 diabetes using binary classifiers, IEEE Journal of Biomedical and Health Informatics, Vol: 24, Pages: 1439-1446, ISSN: 2168-2194
In type 1 diabetes management, maintaining nocturnal blood glucose within target range can be challenging. Although semi-automatic systems to modulate insulin pump delivery, such as low-glucose insulin suspension and the artificial pancreas, are starting to become a reality, their elevated cost and performance below user expectations is hindering their adoption. Hence, a decision support system that helps people with type 1 diabetes, on multiple daily injections or insulin pump therapy, to avoid undesirable overnight blood glucose fluctuations (hyper- or hypoglycaemic) is an attractive alternative. In this paper, we introduce a novel data-driven approach to predict the quality of overnight glycaemic control in people with type 1 diabetes by analyzing commonly gathered data during the day-time period (continuous glucose monitoring data, meal intake and insulin boluses). The proposed approach is able to predict whether overnight blood glucose concentrations are going to remain within or outside the target range, and therefore allows the user to take the appropriate preventive action (snack or change in basal insulin). For this purpose, a number of popular established machine learning algorithms for classification were evaluated and compared on a publicly available clinical dataset (i.e. OhioT1DM). Although there is no clearly superior classification algorithm, this study indicates that, by using commonly gathered data in type 1 diabetes management, it is possible to predict the quality of overnight glycaemic control with reasonable accuracy (AUC-ROC= 0.7).
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.