Robust Conditional Independence maps of single-voxel Magnetic Resonance Spectra to elucidate associations between brain tumours and metabolites.

The aim of the paper is two-fold. First, we show that structure finding with the PC algorithm can be inherently unstable and requires further operational constraints in order to consistently obtain models that are faithful to the data. We propose a methodology to stabilise the structure finding process, minimising both false positive and false negative error rates. This is demonstrated with synthetic data. Second, to apply the proposed structure finding methodology to a data set comprising single-voxel Magnetic Resonance Spectra of normal brain and three classes of brain tumours, to elucidate the associations between brain tumour types and a range of observed metabolites that are known to be relevant for their characterisation. The data set is bootstrapped in order to maximise the robustness of feature selection for nominated target variables. Specifically, Conditional Independence maps (CI-maps) built from the data and their derived Bayesian networks have been used. A Directed Acyclic Graph (DAG) is built from CI-maps, being a major challenge the minimization of errors in the graph structure. This work presents empirical evidence on how to reduce false positive errors via the False Discovery Rate, and how to identify appropriate parameter settings to improve the False Negative Reduction. In addition, several node ordering policies are investigated that transform the graph into a DAG. The obtained results show that ordering nodes by strength of mutual information can recover a representative DAG in a reasonable time, although a more accurate graph can be recovered using a random order of samples at the expense of increasing the computation time.

Nursing judgement and decision-making using the Sedation Withdrawal Score (SWS) in children.

AIMS: The aim of the study was to evaluate registered children's nurses' approaches to the assessment and management of withdrawal syndrome in children. BACKGROUND: Assessment of withdrawal syndrome is undertaken following critical illness when the child's condition may be unstable with competing differential diagnoses. Assessment tools aim to standardize and improve recognition of withdrawal syndrome. Making the right decisions in complex clinical situations requires a degree of mental effort and it is not known how nurses make decisions when undertaking withdrawal assessments. DESIGN: Cognitive interviews with clinical vignettes. METHODS: Interviews were undertaken with 12 nurses to explore the cognitive processes they used when assessing children using the Sedation Withdrawal Score (SWS) tool. Interviews took place in Autumn 2013. FINDINGS: Each stage of decision-making-noticing, interpreting and responding-presented cognitive challenges for nurses. When defining withdrawal behaviours nurses tended to blur the boundaries between Sedation Withdrawal Score signs. Challenges in interpreting behaviours arose from not knowing if the patient's behaviour was a result of withdrawal or other co-morbidities. Nurses gave a range of diagnoses when interpreting the vignettes, despite being provided with identical information. Treatment responses corresponded to definite withdrawal diagnoses, but varied when nurses were unsure of the diagnosis. CONCLUSION: Cognitive interviews with vignettes provided insight into nurses' judgement and decision-making. The SWS does not standardize the assessment of withdrawal due to the complexity of the context where assessments take place and the difficulties of determining the cause of equivocal behaviours in children recovering from critical illness.

Match Physical Performance of Elite Female Soccer Players During International Competition.

Datson, N, Drust, B, Weston, M, Jarman, IH, Lisboa, P, and Gregson, W. Match physical performance of elite female soccer players during international competition. J Strength Cond Res 31(9): 2379-2387, 2017-The purpose of this study was to provide a detailed analysis of the physical demands of competitive international female soccer match play. A total of 148 individual match observations were undertaken on 107 outfield players competing in competitive international matches during the 2011-2012 and 2012-2013 seasons, using a computerized tracking system (Prozone Sports Ltd., Leeds, England). Total distance and total high-speed running distances were influenced by playing position, with central midfielders completing the highest (10,985 ± 706 m and 2,882 ± 500 m) and central defenders the lowest (9,489 ± 562 m and 1,901 ± 268 m) distances, respectively. Greater total very high-speed running distances were completed when a team was without (399 ± 143 m) compared to with (313 ± 210 m) possession of the ball. Most sprints were over short distances with 76% and 95% being less than 5 and 10 m, respectively. Between half reductions in physical performance were present for all variables, independent of playing position. This study provides novel findings regarding the physical demands of different playing positions in competitive international female match play and provides important insights for physical coaches preparing elite female players for competition.

Conditional independence mapping of DIGE data reveals PDIA3 protein species as key nodes associated with muscle aerobic capacity.

Profiling of protein species is important because gene polymorphisms, splice variations and post-translational modifications may combine and give rise to multiple protein species that have different effects on cellular function. Two-dimensional gel electrophoresis is one of the most robust methods for differential analysis of protein species, but bioinformatic interrogation is challenging because the consequences of changes in the abundance of individual protein species on cell function are unknown and cannot be predicted. We conducted DIGE of soleus muscle from male and female rats artificially selected as either high- or low-capacity runners (HCR and LCR, respectively). In total 696 protein species were resolved and LC-MS/MS identified proteins in 337 spots. Forty protein species were differentially (P<0.05, FDR<10%) expressed between HCR and LCR and conditional independence mapping found distinct networks within these data, which brought insight beyond that achieved by functional annotation. Protein disulphide isomerase A3 emerged as a key node segregating with differences in aerobic capacity and unsupervised bibliometric analysis highlighted further links to signal transducer and activator of transcription 3, which were confirmed by western blotting. Thus, conditional independence mapping is a useful technique for interrogating DIGE data that is capable of highlighting latent features. BIOLOGICAL SIGNIFICANCE: Quantitative proteome profiling revealed that there is little or no sexual dimorphism in the skeletal muscle response to artificial selection on running capacity. Instead we found that noncanonical STAT3 signalling may be associated with low exercise capacity and skeletal muscle insulin resistance. Importantly, this discovery was made using unsupervised multivariate association mapping and bibliometric network analyses. This allowed our interpretation of the findings to be guided by patterns within the data rather than our preconceptions about which proteins or processes are of greatest interest. Moreover, we demonstrate that this novel approach can be applied to 2D gel analysis, which is unsurpassed in its ability to profile protein species but currently has few dedicated bioinformatic tools.

A novel semi-supervised methodology for extracting tumor type-specific MRS sources in human brain data.

BACKGROUND: The clinical investigation of human brain tumors often starts with a non-invasive imaging study, providing information about the tumor extent and location, but little insight into the biochemistry of the analyzed tissue. Magnetic Resonance Spectroscopy can complement imaging by supplying a metabolic fingerprint of the tissue. This study analyzes single-voxel magnetic resonance spectra, which represent signal information in the frequency domain. Given that a single voxel may contain a heterogeneous mix of tissues, signal source identification is a relevant challenge for the problem of tumor type classification from the spectroscopic signal. METHODOLOGY/PRINCIPAL FINDINGS: Non-negative matrix factorization techniques have recently shown their potential for the identification of meaningful sources from brain tissue spectroscopy data. In this study, we use a convex variant of these methods that is capable of handling negatively-valued data and generating sources that can be interpreted as tumor class prototypes. A novel approach to convex non-negative matrix factorization is proposed, in which prior knowledge about class information is utilized in model optimization. Class-specific information is integrated into this semi-supervised process by setting the metric of a latent variable space where the matrix factorization is carried out. The reported experimental study comprises 196 cases from different tumor types drawn from two international, multi-center databases. The results indicate that the proposed approach outperforms a purely unsupervised process by achieving near perfect correlation of the extracted sources with the mean spectra of the tumor types. It also improves tissue type classification. CONCLUSIONS/SIGNIFICANCE: We show that source extraction by unsupervised matrix factorization benefits from the integration of the available class information, so operating in a semi-supervised learning manner, for discriminative source identification and brain tumor labeling from single-voxel spectroscopy data. We are confident that the proposed methodology has wider applicability for biomedical signal processing.

Finding reproducible cluster partitions for the k-means algorithm.

K-means clustering is widely used for exploratory data analysis. While its dependence on initialisation is well-known, it is common practice to assume that the partition with lowest sum-of-squares (SSQ) total i.e. within cluster variance, is both reproducible under repeated initialisations and also the closest that k-means can provide to true structure, when applied to synthetic data. We show that this is generally the case for small numbers of clusters, but for values of k that are still of theoretical and practical interest, similar values of SSQ can correspond to markedly different cluster partitions. This paper extends stability measures previously presented in the context of finding optimal values of cluster number, into a component of a 2-d map of the local minima found by the k-means algorithm, from which not only can values of k be identified for further analysis but, more importantly, it is made clear whether the best SSQ is a suitable solution or whether obtaining a consistently good partition requires further application of the stability index. The proposed method is illustrated by application to five synthetic datasets replicating a real world breast cancer dataset with varying data density, and a large bioinformatics dataset.

The effects of deprivation and relative deprivation on self-reported morbidity in England: an area-level ecological study.

BACKGROUND: Socioeconomic status gradients in health outcomes are well recognised and may operate in part through the psychological effect of observing disparities in affluence. At an area-level, we explored whether the deprivation differential between neighbouring areas influenced self-reported morbidity over and above the known effect of the deprivation of the area itself. METHODS: Deprivation differentials between small areas (population size approximately 1,500) and their immediate neighbours were derived (from the Index of Multiple Deprivation (IMD)) for Lower Super Output Area (LSOA) in the whole of England (n=32482). Outcome variables were self-reported from the 2001 UK Census: the proportion of the population suffering Limiting Long-Term Illness (LLTI) and 'not good health'. Linear regression was used to identify the effect of the deprivation differential on morbidity in different segments of the population, controlling for the absolute deprivation. The population was segmented using IMD tertiles and P2 People and Places geodemographic classification. P2 is a commercial market segmentation tool, which classifies small areas according to the characteristics of the population. The classifications range in deprivation, with the most affluent type being 'Mature Oaks' and the least being 'Urban Challenge'. RESULTS: Areas that were deprived compared to their immediate neighbours suffered higher rates of 'not good health' (ß=0.312, p<0.001) and LLTI (ß=0.278, p<0.001), after controlling for the deprivation of the area itself ('not good health'-ß=0.655, p<0.001; LLTI-ß=0.548, p<0.001). The effect of the deprivation differential relative to the effect of deprivation was strongest in least deprived segments (e.g., for 'not good health', P2 segments 'Mature Oaks'-ß=0.638; 'Rooted Households'-ß=0.555). CONCLUSIONS: Living in an area that is surrounded by areas of greater affluence has a negative impact on health in England. A possible explanation for this phenomenon is that negative social comparisons between areas cause ill-health. This 'psychosocial effect' is greater still in least deprived segments of the population, supporting the notion that psychosocial effects become more important when material (absolute) deprivation is less relevant.

Partial logistic artificial neural network for competing risks regularized with automatic relevance determination.

Time-to-event analysis is important in a wide range of applications from clinical prognosis to risk modeling for credit scoring and insurance. In risk modeling, it is sometimes required to make a simultaneous assessment of the hazard arising from two or more mutually exclusive factors. This paper applies to an existing neural network model for competing risks (PLANNCR), a Bayesian regularization with the standard approximation of the evidence to implement automatic relevance determination (PLANNCR-ARD). The theoretical framework for the model is described and its application is illustrated with reference to local and distal recurrence of breast cancer, using the data set of Veronesi (1995).

An integrated framework for risk profiling of breast cancer patients following surgery.

OBJECTIVE: An integrated decision support framework is proposed for clinical oncologists making prognostic assessments of patients with operable breast cancer. The framework may be delivered over a web interface. It comprises a triangulation of prognostic modelling, visualisation of historical patient data and an explanatory facility to interpret risk group assignments using empirically derived Boolean rules expressed directly in clinical terms. METHODS AND MATERIALS: The prognostic inferences in the interface are validated in a multicentre longitudinal cohort study by modelling retrospective data from 917 patients recruited at Christie Hospital, Wilmslow between 1983 and 1989 and predicting for 931 patients recruited in the same centre during 1990-1993. There were also 291 patients recruited between 1984 and 1998 at the Clatterbridge Centre for Oncology and the Linda McCartney Centre, Liverpool, UK. RESULTS AND CONCLUSIONS: There are three novel contributions relating this paper to breast cancer cases. First, the widely used Nottingham prognostic index (NPI) is enhanced with additional clinical features from which prognostic assessments can be made more specific for patients in need of adjuvant treatment. This is shown with a cross matching of the NPI and a new prognostic index which also provides a two-dimensional visualisation of the complete patient database by risk of negative outcome. Second, a principled rule-extraction method, orthogonal search rule extraction, generates readily interpretable explanations of risk group allocations derived from a partial logistic artificial neural network with automatic relevance determination (PLANN-ARD). Third, 95% confidence intervals for individual predictions of survival are obtained by Monte Carlo sampling from the PLANN-ARD model.

Time-to-event analysis with artificial neural networks: an integrated analytical and rule-based study for breast cancer.

This paper presents an analysis of censored survival data for breast cancer specific mortality and disease-free survival. There are three stages to the process, namely time-to-event modelling, risk stratification by predicted outcome and model interpretation using rule extraction. Model selection was carried out using the benchmark linear model, Cox regression but risk staging was derived with Cox regression and with Partial Logistic Regression Artificial Neural Networks regularised with Automatic Relevance Determination (PLANN-ARD). This analysis compares the two approaches showing the benefit of using the neural network framework especially for patients at high risk. The neural network model also has results in a smooth model of the hazard without the need for limiting assumptions of proportionality. The model predictions were verified using out-of-sample testing with the mortality model also compared with two other prognostic models called TNG and the NPI rule model. Further verification was carried out by comparing marginal estimates of the predicted and actual cumulative hazards. It was also observed that doctors seem to treat mortality and disease-free models as equivalent, so a further analysis was performed to observe if this was the case. The analysis was extended with automatic rule generation using Orthogonal Search Rule Extraction (OSRE). This methodology translates analytical risk scores into the language of the clinical domain, enabling direct validation of the operation of the Cox or neural network model. This paper extends the existing OSRE methodology to data sets that include continuous-valued variables.

Development of a rule based prognostic tool for HER 2 positive breast cancer patients.

A three stage development process for the production of a hierarchical rule based prognosis tool is described. The application for this tool is specific to breast cancer patients that have a positive expression of the HER 2 gene. The first stage is the development of a Bayesian classification neural network to classify for cancer specific mortality. Secondly, low-order Boolean rules are extracted form this model using an Orthogonal Search based Rule Extraction (OSRE) algorithm. Further to these rules additional information is gathered from the Kaplan-Meier survival estimates of the population, stratified by the categorizations of the input variables. Finally, expert knowledge is used to further simplify the rules and to rank them hierarchically in the form of a decision tree. The resulting decision tree groups all observations into specific categories by clinical profile and by event rate. The practical clinical value of this decision support tool will in future be tested by external validation with additional data from other clinical centres.