Triazole antifungals used for prophylaxis and treatment of invasive fungal disease in adult haematology patients: Trough serum concentrations in relation to outcome.

Triazole antifungal drugs are widely used for the prophylaxis and treatment of invasive fungal disease (IFD). Efficacy may depend on attaining minimum effective plasma concentrations. The aim of this study was to ascertain the proportion of samples in which the recommended concentrations were achieved in patients given these drugs in relation to outcome. In-patients prescribed standard doses of fluconazole, itraconazole solution, posaconazole suspension, or oral voriconazole for at least one week were studied. Pre-dose serum triazole concentrations were measured using validated methods. There were 359 samples from 90 patients. The median (range) number of samples per patient was 3 (1-13), and the median (range) fluconazole, itraconazole, posaconazole (prophylaxis), posaconazole (treatment), and voriconazole serum concentrations were 5.64 (0.11-18), 0.57 (0-5.3), 0.31 (0.02-2.5), 0.65 (0.02-2.5), and 0.95 (0.10-5.4) mg/l, respectively. The number of samples in which the recommended pre-dose concentrations were achieved was 98 (54%), 9 (20%), 2 (18%), and 29 (49%) for itraconazole, posaconazole (>0.7 mg/l prophylaxis), posaconazole (treatment), and voriconazole, respectively. No significant differences were detected in the median triazole trough concentrations between patients with proven/probable IFD compared to those with no evidence of IFD. However, itraconazole was not detected in 10 samples (7 patients). The small number of patients who achieved the recommended trough posaconazole concentrations may explain the high rate of break-through IFD observed in patients prescribed this drug. Except for fluconazole, the number of patients prescribed standard doses of triazoles who achieved recommended trough triazole concentrations was low. The prospective use of serum triazole measurements assay may have improved outcomes with itraconazole, posaconazole, and with voriconazole.

Eye center localization and gaze gesture recognition for human-computer interaction.

This paper introduces an unsupervised modular approach for accurate and real-time eye center localization in images and videos, thus allowing a coarse-to-fine, global-to-regional scheme. The trajectories of eye centers in consecutive frames, i.e., gaze gestures, are further analyzed, recognized, and employed to boost the human-computer interaction (HCI) experience. This modular approach makes use of isophote and gradient features to estimate the eye center locations. A selective oriented gradient filter has been specifically designed to remove strong gradients from eyebrows, eye corners, and shadows, which sabotage most eye center localization methods. A real-world implementation utilizing these algorithms has been designed in the form of an interactive advertising billboard to demonstrate the effectiveness of our method for HCI. The eye center localization algorithm has been compared with 10 other algorithms on the BioID database and six other algorithms on the GI4E database. It outperforms all the other algorithms in comparison in terms of localization accuracy. Further tests on the extended Yale Face Database b and self-collected data have proved this algorithm to be robust against moderate head poses and poor illumination conditions. The interactive advertising billboard has manifested outstanding usability and effectiveness in our tests and shows great potential for benefiting a wide range of real-world HCI applications.

Gender recognition from facial images: two or three dimensions?

This paper seeks to compare encoded features from both two-dimensional (2D) and three-dimensional (3D) face images in order to achieve automatic gender recognition with high accuracy and robustness. The Fisher vector encoding method is employed to produce 2D, 3D, and fused features with escalated discriminative power. For 3D face analysis, a two-source photometric stereo (PS) method is introduced that enables 3D surface reconstructions with accurate details as well as desirable efficiency. Moreover, a 2D+3D imaging device, taking the two-source PS method as its core, has been developed that can simultaneously gather color images for 2D evaluations and PS images for 3D analysis. This system inherits the superior reconstruction accuracy from the standard (three or more light) PS method but simplifies the reconstruction algorithm as well as the hardware design by only requiring two light sources. It also offers great potential for facilitating human computer interaction by being accurate, cheap, efficient, and nonintrusive. Ten types of low-level 2D and 3D features have been experimented with and encoded for Fisher vector gender recognition. Evaluations of the Fisher vector encoding method have been performed on the FERET database, Color FERET database, LFW database, and FRGCv2 database, yielding 97.7%, 98.0%, 92.5%, and 96.7% accuracy, respectively. In addition, the comparison of 2D and 3D features has been drawn from a self-collected dataset, which is constructed with the aid of the 2D+3D imaging device in a series of data capture experiments. With a variety of experiments and evaluations, it can be proved that the Fisher vector encoding method outperforms most state-of-the-art gender recognition methods. It has also been observed that 3D features reconstructed by the two-source PS method are able to further boost the Fisher vector gender recognition performance, i.e., up to a 6% increase on the self-collected database.

Functional and genetic predisposition to rhinovirus lower respiratory tract infections in prematurely born infants.

Term born infants are predisposed to human rhinovirus (HRV) lower respiratory tract infections (LRTI) by reduced neonatal lung function and genetic susceptibility. Our aim was to investigate whether prematurely born infants were similarly predisposed to HRV LRTIs or any other viral LRTIs. Infants born less than 36 weeks of gestational age were recruited. Prior to neonatal/maternity unit discharge, lung function (functional residual capacity by helium gas dilution and multiple breath washout, lung clearance index and compliance (Crs), and resistance (Rrs) of the respiratory system) was assessed and DNA samples assessed for eight single nucleotide polymorphisms (SNPs) in seven genes: ADAM33, IL10, MMP16 NFκB1A,SFTPC, VDR, and NOS2A. Infants were prospectively followed until 1 year corrected age. Nasopharyngeal aspirates (NPAs) were sent whenever an infant developed a LRTI and tested for 13 viruses. One hundred and thirty-nine infants were included in the analysis. Infants who developed HRV LRTIs had reduced Crs (1.6 versus 1.2 mL/cmH2O/kg, p = 0.044) at 36 weeks postmenstrual age. A SNP in the gene coding for the vitamin D receptor was associated with the development of HRV LRTIs and any viral LRTIs (p = 0.02). CONCLUSION: Prematurely born infants may have both a functional and genetic predisposition to HRV LRTIs. What is Known: • Term born infants are predisposed to rhinovirus lower respiratory tract (HRV LRTIs) infection by reduced neonatal lung function. • Term born infants requiring hospitalisation due to HRV bronchiolitis were more likely to have single nucleotide polymorphism (SNP) in the IL-10 gene. What is New: • Prematurely born infants who developed a HRV LRTI had lower C rs before maternity unit discharge. • A SNP in the gene coding for the vitamin D receptor was associated with the development of HRV LRTIs and overall respiratory viral LRTIs in prematurely born infants.

A comprehensive diagnostic approach using galactomannan, targeted ß-d-glucan, baseline computerized tomography and biopsy yields a significant burden of invasive fungal disease in at risk haematology patients.

Invasive fungal disease (IFD) is difficult to diagnose. We investigated the incidence of IFD and risk factors using the revised European Organization for Research and Treatment of Cancer (EORTC) and the Mycoses Study Group (MSG) definitions. Patients (N = 203) undergoing intensive therapy with expected neutropenia ≥10 d were recruited prospectively and followed for a median (range) of 556 (12-730) d. Baseline chest computerized tomography (CT) was performed pre-therapy. Twice-weekly surveillance with galactomannan (GM) was combined with targeted ß-d-glucan (BDG) testing on patients with possible IFD or who were GM-positive. Tissue diagnosis was obtained whenever possible. The cumulative incidence of proven/probable IFD among the 202 evaluable cases after 2 years follow-up was 21%, including 14 proven and 30 probable IFDs. Using either GM or BDG as the sole biomarker (plus host and clinical evidence) the apparent overall incidence of proven/probable IFD was 11% and 16%, respectively. Combined GM/BDG detected all biopsy-proven mould IFD. Baseline CT abnormalities were found in 76/202 (38%) patients. Baseline CT abnormalities and Karnofsky score <90, monocytopenia >10 d and bacteraemia were independent risk factors associated with greater than twofold increased IFD risk. This combined diagnostic approach identified a high incidence of IFD and important risk factors in this cohort.

Viral lower respiratory tract infections and preterm infants' healthcare utilisation.

UNLABELLED: The aim of this study was to determine whether respiratory syncytial virus (RSV) and other viral lower respiratory tract infections (LRTI) in prematurely born infants were associated with similar effects on healthcare utilisation and related cost of care in the second compared to the first year after birth. Thirteen infants who had RSV LRTIs (RSV), 21 who had other viral LRTIs (other viral) and 25 had no viral LRTIs (no LRTI) were prospectively followed. Nasopharyngeal aspirates were collected whenever an infant had an LRTI regardless of whether it was in the hospital or in the community. Healthcare utilisation and the health-related cost of care were determined. Only the RSV group compared to the no LRTI group had higher overall respiratory costs in both year 1 (mean, £3,917 versus £24; p < 0.041) and year 2 (mean, £1,164 versus £61; p = 0.012). Only the RSV group required respiratory admissions; the RSV admission rate in year 2 was 3.4 % (number needed to treat 59). CONCLUSION: RSV LRTIs are associated with increased healthcare utilisation and cost of care in the first and second year; nevertheless, if prophylaxis is to be cost-effective in the second year, a high risk group needs to be identified.

Adjunctive mecA PCR for routine detection of methicillin susceptibility in clinical isolates of coagulase-negative staphylococci.

Concerns over the reliability of routine sensitivity testing in coagulase-negative staphylococci often lead to the use of potentially less-effective antibiotics as few laboratories have access to routine tests for the mecA resistance gene. Although previous studies have shown a reasonable correlation between oxacillin disc and automated sensitivity testing, changing epidemiology and methodology dictate periodic reappraisal of these methods. In the present study, we evaluated two real-time PCR assays against novel targets in the mecA gene as an adjunct to routine susceptibility testing using the Vitek II AST-P620 card. All samples were further examined for the presence of the mecC gene. Of 118 strains of coagulase-negative staphylococci tested, 81 were oxacillin resistant and 37 oxacillin susceptible by the Vitek II assay compared with 103 positive and 15 negative by mecA PCR. In-house PCR results correlated well with a previously published reference PCR, though little correlation was found between mecA PCR or Vitek II and PBP 2a latex agglutination. Incubation conditions may have affected the accuracy of the latter test. None of the strains tested were mecC PCR positive. The inclusion of dual-target PCRs in the testing algorithm was inexpensive and offered the safest strategy for determining beta-lactam susceptibility in coagulase-negative staphylococci in our laboratory.

Respiratory outcome of prematurely born infants following human rhinovirus A and C infections.

UNLABELLED: Human rhinoviruses (HRVs) are a common cause of lower respiratory tract infections (LRTIs) and are associated with chronic respiratory morbidity. Our aim was to determine whether HRV species A or C were associated with chronic respiratory morbidity and increased health care utilisation in prematurely born infants. A number of 153 infants with a median gestational age of 34 (range 23-35) weeks were prospectively followed. Nasopharyngeal aspirates were collected whenever the infants had LRTIs regardless of hospitalisation status. Parents completed a respiratory diary card and health questionnaire about their infant when they were 11 and 12 months corrected age, respectively. The health-related cost of care during infancy was calculated from the medical records using the National Health Service (NHS) reference costing scheme and the British National Formulary for children. There were 32 infants that developed 40 HRV LRTIs; samples were available from 23 of the 32 infants for subtyping. Nine infants had HRV-A LRTIs, 13 HRV-C LRTIs, and one infant had a HRV-B LRTI. Exclusion of infants who also had RSV LRTIs revealed that the infants who had a HRV-C LRTI were more likely to wheeze (p < 0.0005) and use respiratory medications (p < 0.0005) and had more days of wheeze (p = 0.01) and used an inhaler (p = 0.02) than the no LRTI group. In addition, the respiratory cost of care was greater for the HRV-C LRTI than the no LRTI group (p < 0.0005). CONCLUSION: Our results suggest HRV-C is associated with chronic respiratory morbidity during infancy in prematurely born infants.

Lung function of preterm infants before and after viral infections.

UNLABELLED: Our aim was to determine whether viral lower respiratory tract infections (LRTIs) adversely affect prematurely born infants' lung function at follow up. Seventy infants, median gestational age 34 (range, 24-35) weeks were prospectively followed; 32 had an RSV (n = 14) or another respiratory viral (n = 18) LRTI (viral LRTI group) and 38 had no LRTI (no LRTI group). Six of the viral LRTI and five of the no LRTI group had been hospitalised. Nasopharyngeal aspirates (NPAs) obtained whenever the infants had an LRTI. Lung function (functional residual capacity [FRCHe], compliance [Crs] and resistance [Rrs] of the respiratory system) was measured at 36 weeks postmenstrual age (PMA) and 1 year corrected. At 1 year, lung volume (FRCpleth) and airways resistance (Raw) were also assessed. There were no significant differences in the lung function of the two groups at 36 weeks PMA but at 1 year, the viral LRTI compared to the no LRTI group had a higher mean Raw (23 versus 17 cm H2O/l/s, p = 0.0068), the differences remained significant after adjustment. CONCLUSION: These results suggest viral LRTIs, regardless of whether hospitalisation is required, adversely affect prematurely born infants' airway resistance at follow up.

Genetic predisposition of RSV infection-related respiratory morbidity in preterm infants.

UNLABELLED: The aim of this study was to assess whether prematurely born infants have a genetic predisposition to respiratory syncytial virus (RSV) infection-related respiratory morbidity. One hundred and forty-six infants born at less than 36 weeks of gestation were prospectively followed. Nasopharygeal aspirates were obtained on every occasion the infants had a lower respiratory tract infection (LRTI) regardless of need for admission. DNA was tested for 11 single-nucleotide polymorphisms (SNPs). Chronic respiratory morbidity was assessed using respiratory health-related questionnaires, parent-completed diary cards at a corrected age of 1 year and review of hospital notes. Lung function was measured at a post menstrual age (PMA) of 36 weeks and corrected age of 1 year. A SNP in ADAM33 was associated with an increased risk of developing RSV LRTIs, but not with significant differences in 36-week PMA lung function results. SNPs in several genes were associated with increased chronic respiratory morbidity (interleukin 10 (IL10), nitric oxide synthase 2A (NOS2A), surfactant protein C (SFTPC), matrix metalloproteinase 16 (MMP16) and vitamin D receptor (VDR)) and reduced lung function at 1 year (MMP16, NOS2A, SFTPC and VDR) in infants who had had RSV LRTIs. CONCLUSIONS: Our results suggest that prematurely born infants may have a genetic predisposition to RSV LRTIs and subsequent respiratory morbidity which is independent of premorbid lung function.

A selected screening programme was less effective in the detection of methicillin-resistant Staphylococcus aureus colonisation in an orthopaedic unit.

PURPOSE: Our unit has used a selective screening policy for methicillin-resistant Staphylococcus aureus (MRSA) colonisation using standard chromogenic growth media, based upon risk stratification. The aim of this study was to examine the effectiveness of this selective screening policy. METHODS: A cohort of 429 patients was assessed for their risk status for MRSA colonisation using both rapid polymerase chain reaction (PCR) swabs and traditional culture and sensitivity analysis. The sensitivity, specificity, positive predictive values and negative predictive values of the traditional selective approach were calculated compared to universal rapid screening. RESULTS: One hundred eighteen patients were considered high risk and would traditionally be further screened with standard culture of swabs. The prevalence of MRSA was 15/429 (3.5%). The sensitivity of selective screening was 53% identifying eight of 15 cases. The false-negative rate was therefore 47% and seven would have been missed. PCR results were available within four to six hours, whereas culture results were only available at 24 hours for the media showing no growth and not until 72 hours for positive MRSA cases. CONCLUSIONS: We now advocate universal screening prior to, or on admission, using this rapid PCR test, as we consider this identifies MRSA colonisation more effectively and facilitates "ring-fencing" of orthopaedic beds.

EM-COGLOAD: An investigation into age and cognitive load detection using eye tracking and deep learning.

Alzheimer's Disease is the most prevalent neurodegenerative disease, and is a leading cause of disability among the elderly. Eye movement behaviour demonstrates potential as a non-invasive biomarker for Alzheimer's Disease, with changes detectable at an early stage after initial onset. This paper introduces a new publicly available dataset: EM-COGLOAD (available at https://osf.io/zjtdq/, DOI: 10.17605/OSF.IO/ZJTDQ). A dual-task paradigm was used to create effects of declined cognitive performance in 75 healthy adults as they carried out visual tracking tasks. Their eye movement was recorded, and time series classification of the extracted eye movement traces was explored using a range of deep learning techniques. The results of this showed that convolutional neural networks were able to achieve an accuracy of 87.5% when distinguishing between eye movement under low and high cognitive load, and 76% when distinguishing between the oldest and youngest age groups.

Rhinovirus infection and healthcare utilisation in prematurely born infants.

Our aim was to determine whether rhinovirus (RV) lower respiratory tract infections (LRTIs) in prematurely born infants increase health-related cost of care during infancy. 153 infants born at <36 weeks of gestation were prospectively followed to 1 year. Cost of care was calculated from the National Health Service reference costing scheme and healthcare utilisation determined by examining hospital/general practitioner records. 20 infants developed RV LRTIs (RV group), 17 respiratory syncytial virus (RSV) LRTIs (RSV group), 12 both RV and RSV LRTIs (RV/RSV group) and 74 had no LRTI (no LRTI group). Compared with the no LRTI group, the RV/RSV LRTI group had the greatest increase in adjusted mean cost (difference GBP 5769), followed by the RV LRTI group (difference GBP 278) and, finally, the RSV LRTI group (difference GBP 172) (p=0.045). The RV group had more outpatient (p<0.05) and respiratory-related general practitioner (p<0.05) attendances, more wheezed at follow-up (p<0.001) than the no LRTI group and more had respiratory-related outpatient attendances than the RSV LRTI group (p<0.05). We conclude that RV LRTIs were associated with increased health-related cost of care during infancy; our results suggest that the RV group compared with the RSV group suffered greater chronic respiratory morbidity.

Pharmacovigilance teaching in UK undergraduate pharmacy programmes.

PURPOSE: Pharmacists in the UK are able to report spontaneous adverse drug reactions (ADRs) to the Medicines and Healthcare Products Regulatory Authority. The level of reporting by UK pharmacists remains low. This could be explained by poor knowledge of ADR reporting. The primary objective of this study was to investigate the level of pharmacovigilance education provided to pharmacy students on undergraduate pharmacy programmes in the UK. METHODS: A cross-sectional survey was used to obtain data relating to the teaching of pharmacovigilance within schools of pharmacy. The survey was designed to reveal whether core elements pertinent to pharmacovigilance and specifically to spontaneous reporting were taught and to what extent. RESULTS: All of the respondents taught pharmacovigilance within an assessed compulsory module. A small number (23%) did not include pharmacovigilance law within their syllabus. In 54%, the amount of time devoted to teaching pharmacy students about their role in pharmacovigilance was less than 4 h in the 4-year course; only one respondent spent approximately 20 h, the remaining respondents (38%) spent between 4 and 8 h. CONCLUSIONS: The amount of time dedicated to the teaching of pharmacovigilance on pharmacy undergraduate degree programmes is low. Considering the importance of spontaneous reporting in drug safety and the shift in the role of the pharmacists, more time may need to be devoted to pharmacovigilance on pharmacy undergraduate courses. By doing so, new pharmacists would be more informed of the important role they play in drug safety and thereby potentially help enhance the level of ADR reporting.

In vivo measurement of skin microrelief using photometric stereo in the presence of interreflections.

This paper proposes and describes an implementation of a photometric stereo-based technique for in vivo assessment of three-dimensional (3D) skin topography in the presence of interreflections. The proposed method illuminates skin with red, green, and blue colored lights and uses the resulting variation in surface gradients to mitigate the effects of interreflections. Experiments were carried out on Caucasian, Asian, and African American subjects to demonstrate the accuracy of our method and to validate the measurements produced by our system. Our method produced significant improvement in 3D surface reconstruction for all Caucasian, Asian, and African American skin types. The results also illustrate the differences in recovered skin topography due to the nondiffuse bidirectional reflectance distribution function (BRDF) for each color illumination used, which also concur with the existing multispectral BRDF data available for skin.

Effect of early EBV and/or CMV viremia on graft function and acute cellular rejection in pediatric liver transplantation.

BACKGROUND: The clinical impact of Epstein-Barr virus (EBV) and cytomegalovirus (CMV) infections in the early post-transplantation period are poorly documented. We investigated the prevalence and timing of EBV and CMV infections during the first 21 d post-transplantation in relation to graft function and acute cellular rejection in a large cohort of pediatric liver transplantation recipients. PATIENTS AND METHODS: Clinical, biochemical, virological, and histopathological data of 62 consecutive children who received a liver transplant were reviewed retrospectively. RESULTS: Seventeen patients (27%) developed EBV and 11 (18%) CMV viremia (mean interval from surgery: 7.6 d, SD 3.6 and 8.7 d, SD 6.4, respectively). EBV and CMV viremia were more common as a consequence of reactivation than of primary infection. EBV viremic recipients had more often abnormal bilirubin levels [p = 0.01; OR 5.8: 95% CI 1.3-25.5]. Acute rejection was diagnosed in 20 recipients (32.3%). No correlation was found between rejection and EBV and CMV serology before transplantation and viremia after transplantation (mean interval between the diagnosis of rejection and the detection of EBV DNA and CMV DNA: one d, SD 4.4 and five d, SD 9.2, respectively). CONCLUSION: EBV and CMV viremia occur at a very early-stage post-transplantation and do not appear to affect the short-term outcome of the transplant.

Unsupervised sub-segmentation for pigmented skin lesions.

BACKGROUND: Early identification of malignant melanoma with the surgical removal of thin lesions is the most effective treatment for skin cancers. A computer-aided diagnostic system assists to improve the diagnostic accuracy, where segmenting lesion from normal skin is usually considered as the first step. One of the challenges in the automated segmentation of skin lesions arises from the fact that darker areas within the lesion should be considered separate from the more general suspicious lesion as a whole, because these pigmented areas can provide significant additional diagnostic information. METHODS: This paper presents, for the first time, an unsupervised segmentation scheme to allow the isolation of normal skin, pigmented skin lesions, and interesting darker areas inside the lesion simultaneously. An adaptive mean-shift is first applied with a 5D spatial colour-texture feature space to generate a group of homogenous regions. Then the sub-segmentation maps are calculated by integrating maximal similarity-based region merging and the kernel k-means algorithm, where the number of segments is defined by a cluster validity measurement. RESULTS: The proposed method has been validated extensively on both normal digital photographs and dermoscopy images, which demonstrates competitive performance in achieving automatic segmentation. The isolated dark areas have proved helpful in the discrimination of malignant melanomas from atypical benign nevi. Compared with the results obtained from the asymmetry measure of the entire lesion, the asymmetry distribution of the isolated dark areas helped increase the accuracy of the identification of malignant melanoma from 65.38% to 73.07%, and this classification accuracy reached 80.77% on integrating both asymmetry descriptors. CONCLUSION: The proposed segmentation scheme gives the lesion boundary closed to the manual segmentation obtained by experienced dermatologists. The initial classification results indicate that the study of the distributions of darker areas inside the lesions is very promising in characterizing melanomas.

Diabetes mellitus prediction and diagnosis from a data preprocessing and machine learning perspective.

BACKGROUND AND OBJECTIVE: Diabetes mellitus is a metabolic disorder characterized by hyperglycemia, which results from the inadequacy of the body to secrete and respond to insulin. If not properly managed or diagnosed on time, diabetes can pose a risk to vital body organs such as the eyes, kidneys, nerves, heart, and blood vessels and so can be life-threatening. The many years of research in computational diagnosis of diabetes have pointed to machine learning to as a viable solution for the prediction of diabetes. However, the accuracy rate to date suggests that there is still much room for improvement. In this paper, we are proposing a machine learning framework for diabetes prediction and diagnosis using the PIMA Indian dataset and the laboratory of the Medical City Hospital (LMCH) diabetes dataset. We hypothesize that adopting feature selection and missing value imputation methods can scale up the performance of classification models in diabetes prediction and diagnosis. METHODS: In this paper, a robust framework for building a diabetes prediction model to aid in the clinical diagnosis of diabetes is proposed. The framework includes the adoption of Spearman correlation and polynomial regression for feature selection and missing value imputation, respectively, from a perspective that strengthens their performances. Further, different supervised machine learning models, the random forest (RF) model, support vector machine (SVM) model, and our designed twice-growth deep neural network (2GDNN) model are proposed for classification. The models are optimized by tuning the hyperparameters of the models using grid search and repeated stratified k-fold cross-validation and evaluated for their ability to scale to the prediction problem. RESULTS: Through experiments on the PIMA Indian and LMCH diabetes datasets, precision, sensitivity, F1-score, train-accuracy, and test-accuracy scores of 97.34%, 97.24%, 97.26%, 99.01%, 97.25 and 97.28%, 97.33%, 97.27%, 99.57%, 97.33, are achieved with the proposed 2GDNN model, respectively. CONCLUSION: The data preprocessing approaches and the classifiers with hyperparameter optimization proposed within the machine learning framework yield a robust machine learning model that outperforms state-of-the-art results in diabetes mellitus prediction and diagnosis. The source code for the models of the proposed machine learning framework has been made publicly available.

Potential pitfalls in analysing a SARS-CoV-2 RT-PCR assay and how to standardise data interpretation.

The emergence of SARS-CoV-2 in December 2019 lead to the rapid implementation of assays for virus detection, with real-time RT-PCR arguably considered the gold-standard. In our laboratory Altona RealStar SARS-Cov-2 RT-PCR kits are used with Applied Biosystems QuantStudio 7 Flex thermocyclers. Real-time PCR data interpretation is potentially complex and time-consuming, particularly for SARS-CoV-2, where the laboratory handles up to 2000 samples each day. To simplify this, an automated system that rapidly interprets the curves, developed by diagnostics.ai was introduced. QuantStudio software provides two methods for interpretation, relative threshold and baseline threshold. Many of our assays are analysed using relative threshold and directly exported into pcr.ai software, however, in some rare cases the QuantStudio software assigns positive results to 'ambiguous' curves, flagged by pcr.ai, requiring manual intervention. Due to the sample numbers processed and the proportionate increase in curves flagged by pcr.ai, the two methods were investigated. An audit was carried out to determine the frequency of these curves, involving 138 samples tested during November 2020, including 97 serial samples from 38 patients and it was determined that the relative threshold method produced unreliable results in many of these cases. In addition, we present a solution to simplify the interpretation and automate the process.