Missing data in emergency care: a pitfall in the interpretation of analysis and research based on electronic patient records.

Electronic patient records (EPRs) are potentially valuable sources of data for service development or research but often contain large amounts of missing data. Using complete case analysis or imputation of missing data seem like simple solutions, and are increasingly easy to perform in software packages, but can easily distort data and give misleading results if used without an understanding of missingness. So, knowing about patterns of missingness, and when to get expert data science (data engineering and analytics) help, will be a fundamental future skill for emergency physicians. This will maximise the good and minimise the harm of the easy availability of large patient datasets created by the introduction of EPRs.

COVID-19 vaccination uptake amongst ethnic minority communities in England: a linked study exploring the drivers of differential vaccination rates.

BACKGROUND: Despite generally high coronavirus disease 2019 (COVID-19) vaccination rates in the UK, vaccination hesitancy and lower take-up rates have been reported in certain ethnic minority communities. METHODS: We used vaccination data from the National Immunisation Management System (NIMS) linked to the 2011 Census and individual health records for subjects aged ≥40 years (n = 24 094 186). We estimated age-standardized vaccination rates, stratified by ethnic group and key sociodemographic characteristics, such as religious affiliation, deprivation, educational attainment, geography, living conditions, country of birth, language skills and health status. To understand the association of ethnicity with lower vaccination rates, we conducted a logistic regression model adjusting for differences in geographic, sociodemographic and health characteristics. ResultsAll ethnic groups had lower age-standardized rates of vaccination compared with the white British population, whose vaccination rate of at least one dose was 94% (95% CI: 94%-94%). Black communities had the lowest rates, with 75% (74-75%) of black African and 66% (66-67%) of black Caribbean individuals having received at least one dose. The drivers of these lower rates were partly explained by accounting for sociodemographic differences. However, modelled estimates showed significant differences remained for all minority ethnic groups, compared with white British individuals. CONCLUSIONS: Lower COVID-19 vaccination rates are consistently observed amongst all ethnic minorities.

Fibro-inflammatory recovery and type 2 diabetes remission following a low calorie diet but not exercise training: A secondary analysis of the DIASTOLIC randomised controlled trial.

AIMS: To investigate the relationship between fibro-inflammatory biomarkers and cardiovascular structure/function in people with Type 2 Diabetes (T2D) compared to healthy controls and the effect of two lifestyle interventions in T2D. METHODS: Data were derived from the DIASTOLIC randomised controlled trial (RCT) and includes a comparison between those with T2D and the matched healthy volunteers recruited at baseline. Adults with T2D without cardiovascular disease (CVD) were randomized to a 12-week intervention either: (1) exercise training, (2) a low-energy (∼810 kcal/day) meal-replacement plan (MRP) or (3) standard care. Principal Component and Fisher's linear discriminant analysis were used to investigate the relationships between MRI acquired cardiovascular outcomes and fibro-inflammatory biomarkers in cases versus controls and pre- and post-intervention in T2D. RESULTS: At baseline, 83 people with T2D (mean age 50.5 ± 6.4; 58% male) and 36 healthy controls (mean age 48.6 ± 6.2; 53% male) were compared and 76 people with T2D completed the RCT for pre- post-analysis. Compared to healthy controls, subjects with T2D had adverse cardiovascular remodelling and a fibro-inflammatory profile (20 differentially expressed biomarkers). The 3D data visualisations showed almost complete separation between healthy controls and those with T2D, and a marked shift towards healthy controls following the MRP (15 biomarkers significantly changed) but not exercise training. CONCLUSIONS: Fibro-inflammatory pathways and cardiovascular structure/function are adversely altered before the onset of symptomatic CVD in middle-aged adults with T2D. The MRP improved the fibro-inflammatory profile of people with T2D towards a more healthy status. Long-term studies are required to assess whether these changes lead to continued reverse cardiac remodelling and prevent CVD.

Domain Adaptation Principal Component Analysis: Base Linear Method for Learning with Out-of-Distribution Data.

Domain adaptation is a popular paradigm in modern machine learning which aims at tackling the problem of divergence (or shift) between the labeled training and validation datasets (source domain) and a potentially large unlabeled dataset (target domain). The task is to embed both datasets into a common space in which the source dataset is informative for training while the divergence between source and target is minimized. The most popular domain adaptation solutions are based on training neural networks that combine classification and adversarial learning modules, frequently making them both data-hungry and difficult to train. We present a method called Domain Adaptation Principal Component Analysis (DAPCA) that identifies a linear reduced data representation useful for solving the domain adaptation task. DAPCA algorithm introduces positive and negative weights between pairs of data points, and generalizes the supervised extension of principal component analysis. DAPCA is an iterative algorithm that solves a simple quadratic optimization problem at each iteration. The convergence of the algorithm is guaranteed, and the number of iterations is small in practice. We validate the suggested algorithm on previously proposed benchmarks for solving the domain adaptation task. We also show the benefit of using DAPCA in analyzing single-cell omics datasets in biomedical applications. Overall, DAPCA can serve as a practical preprocessing step in many machine learning applications leading to reduced dataset representations, taking into account possible divergence between source and target domains.

CNN-Based Spectral Super-Resolution of Panchromatic Night-Time Light Imagery: City-Size-Associated Neighborhood Effects.

Data on artificial night-time light (NTL), emitted from the areas, and captured by satellites, are available at a global scale in panchromatic format. In the meantime, data on spectral properties of NTL give more information for further analysis. Such data, however, are available locally or on a commercial basis only. In our recent work, we examined several machine learning techniques, such as linear regression, kernel regression, random forest, and elastic map models, to convert the panchromatic NTL images into colored ones. We compared red, green, and blue light levels for eight geographical areas all over the world with panchromatic light intensities and characteristics of built-up extent from spatially corresponding pixels and their nearest neighbors. In the meantime, information from more distant neighboring pixels might improve the predictive power of models. In the present study, we explore this neighborhood effect using convolutional neural networks (CNN). The main outcome of our analysis is that the neighborhood effect goes in line with the geographical extent of metropolitan areas under analysis: For smaller areas, optimal input image size is smaller than for bigger ones. At that, for relatively large cities, the optimal input image size tends to differ for different colors, being on average higher for red and lower for blue lights. Compared to other machine learning techniques, CNN models emerged comparable in terms of Pearson's correlation but showed performed better in terms of WMSE, especially for testing datasets.

Social stress drives the multi-wave dynamics of COVID-19 outbreaks.

The dynamics of epidemics depend on how people's behavior changes during an outbreak. At the beginning of the epidemic, people do not know about the virus, then, after the outbreak of epidemics and alarm, they begin to comply with the restrictions and the spreading of epidemics may decline. Over time, some people get tired/frustrated by the restrictions and stop following them (exhaustion), especially if the number of new cases drops down. After resting for a while, they can follow the restrictions again. But during this pause the second wave can come and become even stronger then the first one. Studies based on SIR models do not predict the observed quick exit from the first wave of epidemics. Social dynamics should be considered. The appearance of the second wave also depends on social factors. Many generalizations of the SIR model have been developed that take into account the weakening of immunity over time, the evolution of the virus, vaccination and other medical and biological details. However, these more sophisticated models do not explain the apparent differences in outbreak profiles between countries with different intrinsic socio-cultural features. In our work, a system of models of the COVID-19 pandemic is proposed, combining the dynamics of social stress with classical epidemic models. Social stress is described by the tools of sociophysics. The combination of a dynamic SIR-type model with the classical triad of stages of the general adaptation syndrome, alarm-resistance-exhaustion, makes it possible to describe with high accuracy the available statistical data for 13 countries. The sets of kinetic constants corresponding to optimal fit of model to data were found. These constants characterize the ability of society to mobilize efforts against epidemics and maintain this concentration over time and can further help in the development of management strategies specific to a particular society.

Scikit-Dimension: A Python Package for Intrinsic Dimension Estimation.

Dealing with uncertainty in applications of machine learning to real-life data critically depends on the knowledge of intrinsic dimensionality (ID). A number of methods have been suggested for the purpose of estimating ID, but no standard package to easily apply them one by one or all at once has been implemented in Python. This technical note introduces scikit-dimension, an open-source Python package for intrinsic dimension estimation. The scikit-dimension package provides a uniform implementation of most of the known ID estimators based on the scikit-learn application programming interface to evaluate the global and local intrinsic dimension, as well as generators of synthetic toy and benchmark datasets widespread in the literature. The package is developed with tools assessing the code quality, coverage, unit testing and continuous integration. We briefly describe the package and demonstrate its use in a large-scale (more than 500 datasets) benchmarking of methods for ID estimation for real-life and synthetic data.

Learning from Scarce Information: Using Synthetic Data to Classify Roman Fine Ware Pottery.

In this article, we consider a version of the challenging problem of learning from datasets whose size is too limited to allow generalisation beyond the training set. To address the challenge, we propose to use a transfer learning approach whereby the model is first trained on a synthetic dataset replicating features of the original objects. In this study, the objects were smartphone photographs of near-complete Roman terra sigillata pottery vessels from the collection of the Museum of London. Taking the replicated features from published profile drawings of pottery forms allowed the integration of expert knowledge into the process through our synthetic data generator. After this first initial training the model was fine-tuned with data from photographs of real vessels. We show, through exhaustive experiments across several popular deep learning architectures, different test priors, and considering the impact of the photograph viewpoint and excessive damage to the vessels, that the proposed hybrid approach enables the creation of classifiers with appropriate generalisation performance. This performance is significantly better than that of classifiers trained exclusively on the original data, which shows the promise of the approach to alleviate the fundamental issue of learning from small datasets.

Feature selection for unsupervised machine learning of accelerometer data physical activity clusters - A systematic review.

BACKGROUND: Identifying clusters of physical activity (PA) from accelerometer data is important to identify levels of sedentary behaviour and physical activity associated with risks of serious health conditions and time spent engaging in healthy PA. Unsupervised machine learning models can capture PA in everyday free-living activity without the need for labelled data. However, there is scant research addressing the selection of features from accelerometer data. The aim of this systematic review is to summarise feature selection techniques applied in studies concerned with unsupervised machine learning of accelerometer-based device obtained physical activity, and to identify commonly used features identified through these techniques. Feature selection methods can reduce the complexity and computational burden of these models by removing less important features and assist in understanding the relative importance of feature sets and individual features in clustering. METHOD: We conducted a systematic search of Pubmed, Medline, Google Scholar, Scopus, Arxiv and Web of Science databases to identify studies published before January 2021 which used feature selection methods to derive PA clusters using unsupervised machine learning models. RESULTS: A total of 13 studies were eligible for inclusion within the review. The most popular feature selection techniques were Principal Component Analysis (PCA) and correlation-based methods, with k-means frequently used in clustering accelerometer data. Cluster quality evaluation methods were diverse, including both external (e.g. cluster purity) or internal evaluation measures (silhouette score most frequently). Only four of the 13 studies had more than 25 participants and only four studies included two or more datasets. CONCLUSION: There is a need to assess multiple feature selection methods upon large cohort data consisting of multiple (3 or more) PA datasets. The cut-off criteria e.g. number of components, pairwise correlation value, explained variance ratio for PCA, etc. should be expressly stated along with any hyperparameters used in clustering.

High-Dimensional Separability for One- and Few-Shot Learning.

This work is driven by a practical question: corrections of Artificial Intelligence (AI) errors. These corrections should be quick and non-iterative. To solve this problem without modification of a legacy AI system, we propose special 'external' devices, correctors. Elementary correctors consist of two parts, a classifier that separates the situations with high risk of error from the situations in which the legacy AI system works well and a new decision that should be recommended for situations with potential errors. Input signals for the correctors can be the inputs of the legacy AI system, its internal signals, and outputs. If the intrinsic dimensionality of data is high enough then the classifiers for correction of small number of errors can be very simple. According to the blessing of dimensionality effects, even simple and robust Fisher's discriminants can be used for one-shot learning of AI correctors. Stochastic separation theorems provide the mathematical basis for this one-short learning. However, as the number of correctors needed grows, the cluster structure of data becomes important and a new family of stochastic separation theorems is required. We refuse the classical hypothesis of the regularity of the data distribution and assume that the data can have a rich fine-grained structure with many clusters and corresponding peaks in the probability density. New stochastic separation theorems for data with fine-grained structure are formulated and proved. On the basis of these theorems, the multi-correctors for granular data are proposed. The advantages of the multi-corrector technology were demonstrated by examples of correcting errors and learning new classes of objects by a deep convolutional neural network on the CIFAR-10 dataset. The key problems of the non-classical high-dimensional data analysis are reviewed together with the basic preprocessing steps including the correlation transformation, supervised Principal Component Analysis (PCA), semi-supervised PCA, transfer component analysis, and new domain adaptation PCA.

Universal Gorban's Entropies: Geometric Case Study.

Recently, A.N. Gorban presented a rich family of universal Lyapunov functions for any linear or non-linear reaction network with detailed or complex balance. Two main elements of the construction algorithm are partial equilibria of reactions and convex envelopes of families of functions. These new functions aimed to resolve "the mystery" about the difference between the rich family of Lyapunov functions (f-divergences) for linear kinetics and a limited collection of Lyapunov functions for non-linear networks in thermodynamic conditions. The lack of examples did not allow to evaluate the difference between Gorban's entropies and the classical Boltzmann-Gibbs-Shannon entropy despite obvious difference in their construction. In this paper, Gorban's results are briefly reviewed, and these functions are analysed and compared for several mechanisms of chemical reactions. The level sets and dynamics along the kinetic trajectories are analysed. The most pronounced difference between the new and classical thermodynamic Lyapunov functions was found far from the partial equilibria, whereas when some fast elementary reactions became close to equilibrium then this difference decreased and vanished in partial equilibria.

Fractional Norms and Quasinorms Do Not Help to Overcome the Curse of Dimensionality.

The curse of dimensionality causes the well-known and widely discussed problems for machine learning methods. There is a hypothesis that using the Manhattan distance and even fractional lp quasinorms (for p less than 1) can help to overcome the curse of dimensionality in classification problems. In this study, we systematically test this hypothesis. It is illustrated that fractional quasinorms have a greater relative contrast and coefficient of variation than the Euclidean norm l2, but it is shown that this difference decays with increasing space dimension. It has been demonstrated that the concentration of distances shows qualitatively the same behaviour for all tested norms and quasinorms. It is shown that a greater relative contrast does not mean a better classification quality. It was revealed that for different databases the best (worst) performance was achieved under different norms (quasinorms). A systematic comparison shows that the difference in the performance of kNN classifiers for lp at p = 0.5, 1, and 2 is statistically insignificant. Analysis of curse and blessing of dimensionality requires careful definition of data dimensionality that rarely coincides with the number of attributes. We systematically examined several intrinsic dimensions of the data.

Trajectories, bifurcations, and pseudo-time in large clinical datasets: applications to myocardial infarction and diabetes data.

BACKGROUND: Large observational clinical datasets are becoming increasingly available for mining associations between various disease traits and administered therapy. These datasets can be considered as representations of the landscape of all possible disease conditions, in which a concrete disease state develops through stereotypical routes, characterized by "points of no return" and "final states" (such as lethal or recovery states). Extracting this information directly from the data remains challenging, especially in the case of synchronic (with a short-term follow-up) observations. RESULTS: Here we suggest a semi-supervised methodology for the analysis of large clinical datasets, characterized by mixed data types and missing values, through modeling the geometrical data structure as a bouquet of bifurcating clinical trajectories. The methodology is based on application of elastic principal graphs, which can address simultaneously the tasks of dimensionality reduction, data visualization, clustering, feature selection, and quantifying the geodesic distances (pseudo-time) in partially ordered sequences of observations. The methodology allows a patient to be positioned on a particular clinical trajectory (pathological scenario) and the degree of progression along it to be characterized with a qualitative estimate of the uncertainty of the prognosis. We developed a tool ClinTrajan for clinical trajectory analysis implemented in the Python programming language. We test the methodology in 2 large publicly available datasets: myocardial infarction complications and readmission of diabetic patients data. CONCLUSIONS: Our pseudo-time quantification-based approach makes it possible to apply the methods developed for dynamical disease phenotyping and illness trajectory analysis (diachronic data analysis) to synchronic observational data.

FilterK: A new outlier detection method for k-means clustering of physical activity.

In this paper, a new algorithm denoted as FilterK is proposed for improving the purity of k-means derived physical activity clusters by reducing outlier influence. We applied it to physical activity data obtained with body-worn accelerometers and clustered using k-means. We compared its performance with three existing outlier detection methods: Local Outlier Factor, Isolation Forests and KNN using the ground truth (class labels), average cluster and event purity (ACEP). FilterK provided comparable gains in ACEP (0.581 â†’ 0.596 compared to 0.580-0.617) whilst removing a lower number of outliers than the other methods (4% total dataset size vs 10% to achieve this ACEP). The main focus of our new outlier detection method is to improve the cluster purities of physical activity accelerometer data, but we also suggest it may be potentially applied to other types of dataset captured by k-means clustering. We demonstrate our method using a k-means model trained on two independent accelerometer datasets (training n = 90) and re-applied to an independent dataset (test n = 41). Labelled physical activities include lying down, sitting, standing, household chores, walking (laboratory and non-laboratory based), stairs and running. This type of clustering algorithm could be used to assist with identifying optimal physical activity patterns for health.

Towards a Portable Model to Discriminate Activity Clusters from Accelerometer Data.

Few methods for classifying physical activity from accelerometer data have been tested using an independent dataset for cross-validation, and even fewer using multiple independent datasets. The aim of this study was to evaluate whether unsupervised machine learning was a viable approach for the development of a reusable clustering model that was generalisable to independent datasets. We used two labelled adult laboratory datasets to generate a k-means clustering model. To assess its generalised application, we applied the stored clustering model to three independent labelled datasets: two laboratory and one free-living. Based on the development labelled data, the ten clusters were collapsed into four activity categories: sedentary, standing/mixed/slow ambulatory, brisk ambulatory, and running. The percentages of each activity type contained in these categories were 89%, 83%, 78%, and 96%, respectively. In the laboratory independent datasets, the consistency of activity types within the clusters dropped, but remained above 70% for the sedentary clusters, and 85% for the running and ambulatory clusters. Acceleration features were similar within each cluster across samples. The clusters created reflected activity types known to be associated with health and were reasonably robust when applied to diverse independent datasets. This suggests that an unsupervised approach is potentially useful for analysing free-living accelerometer data.

Metallome of cerebrovascular endothelial cells infected with Toxoplasma gondii using µ-XRF imaging and inductively coupled plasma mass spectrometry.

In this study, we measured the levels of elements in human brain microvascular endothelial cells (ECs) infected with T. gondii. ECs were infected with tachyzoites of the RH strain, and at 6, 24, and 48 hours post infection (hpi), the intracellular concentrations of elements were determined using a synchrotron-microfocus X-ray fluorescence microscopy (µ-XRF) system. This method enabled the quantification of the concentrations of Zn and Ca in infected and uninfected (control) ECs at sub-micron spatial resolution. T. gondii-hosting ECs contained less Zn than uninfected cells only at 48 hpi (p < 0.01). The level of Ca was not significantly different between infected and control cells (p > 0.05). Inductively Coupled Plasma Mass Spectrometry (ICP-MS) analysis revealed infection-specific metallome profiles characterized by significant increases in the intracellular levels of Zn, Fe, Mn and Cu at 48 hpi (p < 0.01), and significant reductions in the extracellular concentrations of Co, Cu, Mo, V, and Ag at 24 hpi (p < 0.05) compared with control cells. Zn constituted the largest part (74%) of the total metal composition (metallome) of the parasite. Gene expression analysis showed infection-specific upregulation in the expression of five genes, MT1JP, MT1M, MT1E, MT1F, and MT1X, belonging to the metallothionein gene family. These results point to a possible correlation between T. gondii infection and increased expression of MT1 isoforms and altered intracellular levels of elements, especially Zn and Fe. Taken together, a combined µ-XRF and ICP-MS approach is promising for studies of the role of elements in mediating host-parasite interaction.

Clustered intergenic region sequences as predictors of factor H Binding Protein expression patterns and for assessing Neisseria meningitidis strain coverage by meningococcal vaccines.

Factor H binding protein (fHbp) is a major protective antigen in 4C-MenB (Bexsero®) and Trumenba®, two serogroup B meningococcal vaccines, wherein expression level is a determinant of protection. Examination of promoter-containing intergenic region (IGR) sequences indicated that nine fHbp IGR alleles covered 92% of 1,032 invasive meningococcal strains with variant 1 fHbp alleles. Relative expression values for fHbp were determined for 79 meningococcal isolates covering ten IGR alleles by quantitative reverse transcriptase polymerase chain reaction (qRT PCR). Derivation of expression clusters of IGR sequences by linear regression identified five expression clusters with five nucleotides and one insertion showing statistically associations with differences in expression level. Sequence analysis of 273 isolates examined by the Meningococcal Antigen Typing Scheme, a sandwich ELISA, found that coverage depended on the IGR expression cluster and vaccine peptide homology combination. Specific fHbp peptide-IGR expression cluster combinations were designated as 'at risk' for coverage by 4C-MenB and were detected in multiple invasive meningococcal disease cases confirmed by PCR alone and occurring in partially-vaccinated infants. We conclude that sequence-based analysis of IGR sequences is informative for assessing protein expression and has utility for culture-independent assessments of strain coverage by protein-based vaccines.

Accelerometer-assessed Physical Activity in Epidemiology: Are Monitors Equivalent?

PURPOSE: Accelerometers are increasingly being used to assess physical activity in large-scale surveys. Establishing whether key physical activity outcomes can be considered equivalent between three widely used accelerometer brands would be a significant step toward capitalizing on the increasing availability of accelerometry data for epidemiological research. METHODS: Twenty participants wore a GENEActiv, an Axivity AX3, and an ActiGraph GT9X on their nondominant wrist and were observed for 2 h in a simulated living space. Participants undertook a series of seated and upright light/active behaviors at their own pace. All accelerometer data were processed identically using open-source software (GGIR) to generate physical activity outcomes (including average dynamic acceleration (ACC) and time within intensity cut points). Data were analyzed using pairwise 95% equivalence tests (±10% equivalence zone), intraclass correlation coefficients (ICC) and limits of agreement. RESULTS: The GENEActiv and Axivity could be considered equivalent for ACC (ICC = 0.95, 95% confidence interval (CI), 0.87-0.98), but ACC measured by the ActiGraph was approximately 10% lower (GENEActiv/ActiGraph: ICC = 0.86; 95% CI, 0.56-0.95; Axivity/ActiGraph: ICC = 0.82; 95% CI, 0.50-0.94). For time spent within intensity cut points, all three accelerometers could be considered equivalent to each other for more than 85% of outcomes (ICC ≥0.69, lower 95% CI ≥0.36), with the GENEActiv and Axivity equivalent for 100% of outcomes (ICC ≥0.95, lower 95% CI ≥0.86). CONCLUSIONS: GENEActiv and Axivity data processed in GGIR are largely equivalent. If GENEActiv or Axivity is compared with the ActiGraph, time spent within intensity cut points has good agreement. These findings can be used to inform selection of appropriate outcomes if outputs from these accelerometer brands are compared.