Using secondary knowledge to support decision tree classification of retrospective clinical data

Retrospective clinical data presents many challenges for data mining and machine learning. The transcription of patient records from paper charts and subsequent manipulation of data often results in high volumes of noise as well as a loss of other important information. In addition, such datasets often fail to represent expert medical knowledge and reasoning in any explicit manner. In this research we describe applying data mining methods to retrospective clinical data to build a prediction model for asthma exacerbation severity for pediatric patients in the emergency department. Difficulties in building such a model forced us to investigate alternative strategies for analyzing and processing retrospective data. This paper describes this process together with an approach to mining retrospective clinical data by incorporating formalized external expert knowledge (secondary knowledge sources) into the classification task. This knowledge is used to partition the data into a number of coherent sets, where each set is explicitly described in terms of the secondary knowledge source. Instances from each set are then classified in a manner appropriate for the characteristics of the particular set. We present our methodology and outline a set of experiential results that demonstrate some advantages and some limitations of our approach. © 2008 Springer-Verlag Berlin Heidelberg.

The integration of multi-source data to improve the classification of remotely sensed images

The number of remote sensing platforms and sensors rises almost every year, yet much work on the interpretation of land cover is still carried out using either single images or images from the same source taken at different dates. Two questions could be asked of this proliferation of images: can the information contained in different scenes be used to improve the classification accuracy and, what is the best way to combine the different imagery? Two of these multiple image sources are MODIS on the Terra platform and ETM+ on board Landsat7, which are suitably complementary. Daily MODIS images with 36 spectral bands in 250-1000 m spatial resolution and seven spectral bands of ETM+ with 30m and 16 days spatial and temporal resolution respectively are available. In the UK, cloud cover may mean that only a few ETM+ scenes may be available for any particular year and these may not be at the time of year of most interest. The MODIS data may provide information on land cover over the growing season, such as harvest dates, that is not present in the ETM+ data. Therefore, the primary objective of this work is to develop a methodology for the integration of medium spatial resolution Landsat ETM+ image, with multi-temporal, multi-spectral, low-resolution MODIS \Terra images, with the aim of improving the classification of agricultural land. Additionally other data may also be incorporated such as field boundaries from existing maps. When classifying agricultural land cover of the type seen in the UK, where crops are largely sown in homogenous fields with clear and often mapped boundaries, the classification is greatly improved using the mapped polygons and utilising the classification of the polygon as a whole as an apriori probability in classifying each individual pixel using a Bayesian approach. When dealing with multiple images from different platforms and dates it is highly unlikely that the pixels will be exactly co-registered and these pixels will contain a mixture of different real world land covers. Similarly the different atmospheric conditions prevailing during the different days will mean that the same emission from the ground will give rise to different sensor reception. Therefore, a method is presented with a model of the instantaneous field of view and atmospheric effects to enable different remote sensed data sources to be integrated.

The use of context in the classification of urban aerial imagery

Urban regions present some of the most challenging areas for the remote sensing community. Many different types of land cover have similar spectral responses, making them difficult to distinguish from one another. Traditional per-pixel classification techniques suffer particularly badly because they only use these spectral properties to determine a class, and no other properties of the image, such as context. This project presents the results of the classification of a deeply urban area of Dudley, West Midlands, using 4 methods: Supervised Maximum Likelihood, SMAP, ECHO and Unsupervised Maximum Likelihood. An accuracy assessment method is then developed to allow a fair representation of each procedure and a direct comparison between them. Subsequently, a classification procedure is developed that makes use of the context in the image, though a per-polygon classification. The imagery is broken up into a series of polygons extracted from the Marr-Hildreth zero-crossing edge detector. These polygons are then refined using a region-growing algorithm, and then classified according to the mean class of the fine polygons. The imagery produced by this technique is shown to be of better quality and of a higher accuracy than that of other conventional methods. Further refinements are suggested and examined to improve the aesthetic appearance of the imagery. Finally a comparison with the results produced from a previous study of the James Bridge catchment, in Darleston, West Midlands, is made, showing that the Polygon classified ATM imagery performs significantly better than the Maximum Likelihood classified videography used in the initial study, despite the presence of geometric correction errors.

The application of methods of uncertain reasoning to the biological classification of river water quality

This thesis presents an investigation into the application of methods of uncertain reasoning to the biological classification of river water quality. Existing biological methods for reporting river water quality are critically evaluated, and the adoption of a discrete biological classification scheme advocated. Reasoning methods for managing uncertainty are explained, in which the Bayesian and Dempster-Shafer calculi are cited as primary numerical schemes. Elicitation of qualitative knowledge on benthic invertebrates is described. The specificity of benthic response to changes in water quality leads to the adoption of a sensor model of data interpretation, in which a reference set of taxa provide probabilistic support for the biological classes. The significance of sensor states, including that of absence, is shown. Novel techniques of directly eliciting the required uncertainty measures are presented. Bayesian and Dempster-Shafer calculi were used to combine the evidence provided by the sensors. The performance of these automatic classifiers was compared with the expert's own discrete classification of sampled sites. Variations of sensor data weighting, combination order and belief representation were examined for their effect on classification performance. The behaviour of the calculi under evidential conflict and alternative combination rules was investigated. Small variations in evidential weight and the inclusion of evidence from sensors absent from a sample improved classification performance of Bayesian belief and support for singleton hypotheses. For simple support, inclusion of absent evidence decreased classification rate. The performance of Dempster-Shafer classification using consonant belief functions was comparable to Bayesian and singleton belief. Recommendations are made for further work in biological classification using uncertain reasoning methods, including the combination of multiple-expert opinion, the use of Bayesian networks, and the integration of classification software within a decision support system for water quality assessment.

The application of artificial neural networks to the interpretation and classification of freshwater benthic invertebrate communities

This thesis presents a thorough and principled investigation into the application of artificial neural networks to the biological monitoring of freshwater. It contains original ideas on the classification and interpretation of benthic macroinvertebrates, and aims to demonstrate their superiority over the biotic systems currently used in the UK to report river water quality. The conceptual basis of a new biological classification system is described, and a full review and analysis of a number of river data sets is presented. The biological classification is compared to the common biotic systems using data from the Upper Trent catchment. This data contained 292 expertly classified invertebrate samples identified to mixed taxonomic levels. The neural network experimental work concentrates on the classification of the invertebrate samples into biological class, where only a subset of the sample is used to form the classification. Other experimentation is conducted into the identification of novel input samples, the classification of samples from different biotopes and the use of prior information in the neural network models. The biological classification is shown to provide an intuitive interpretation of a graphical representation, generated without reference to the class labels, of the Upper Trent data. The selection of key indicator taxa is considered using three different approaches; one novel, one from information theory and one from classical statistical methods. Good indicators of quality class based on these analyses are found to be in good agreement with those chosen by a domain expert. The change in information associated with different levels of identification and enumeration of taxa is quantified. The feasibility of using neural network classifiers and predictors to develop numeric criteria for the biological assessment of sediment contamination in the Great Lakes is also investigated.

A smart sensing platform for the classification of ambulatory patterns

This paper describes an innovative sensing approach allowing capture, discrimination, and classification of transients automatically in gait. A walking platform is described, which offers an alternative design to that of standard force plates with advantages that include mechanical simplicity and less restriction on dimensions. The scope of the work is to investigate as an experiment the sensitivity of the distributive tactile sensing method with the potential to address flexibility on gait assessment, including patient targeting and the extension to a variety of ambulatory applications. Using infrared sensors to measure plate deflection, gait patterns are compared with stored templates using a pattern recognition algorithm. This information is input into a neural network to classify normal and affected walking events, with a classification accuracy of just under 90 per cent achieved. The system developed has potential applications in gait analysis and rehabilitation, whereby it can be used as a tool for early diagnosis of walking disorders or to determine changes between pre- and post-operative gait.

Classification of bacterial strains based on DNA profiles

The analysis of bacterial genomes for epidemiological purposes often results in the production of a banding profile of DNA fragments characteristic of the genome under investigation. These may be produced using various methods, many of which involve the cutting or amplification of DNA into defined and reproducible characteristic fragments. It is frequently of interest to enquire whether the bacterial isolates are naturally classifiable into distinct groups based on their DNA profiles. A major problem with this approach is whether classification or clustering of the data is even appropriate. It is always possible to classify such data but it does not follow that the strains they represent are ‘actually’ classifiable into well-defined separate parts. Hence, the act of classification does not in itself answer the question: do the strains consist of a number of different distinct groups or species or do they merge imperceptibly into one another because DNA profiles vary continuously? Nevertheless, we may still wish to classify the data for ‘convenience’ even though strains may vary continuously, and such a classification has been called a ‘dissection’. This Statnote discusses the use of classificatory methods in analyzing the DNA profiles from a sample of bacterial isolates.

Hierarchical classification of G-protein-coupled receptors with data-driven selection of attributes and classifiers

We address the important bioinformatics problem of predicting protein function from a protein's primary sequence. We consider the functional classification of G-Protein-Coupled Receptors (GPCRs), whose functions are specified in a class hierarchy. We tackle this task using a novel top-down hierarchical classification system where, for each node in the class hierarchy, the predictor attributes to be used in that node and the classifier to be applied to the selected attributes are chosen in a data-driven manner. Compared with a previous hierarchical classification system selecting classifiers only, our new system significantly reduced processing time without significantly sacrificing predictive accuracy.

A unified classification of manufacturing strategies and design processes

This article categorises manufacturing strategy design processes and presents the characteristics of resulting strategies. This work will therefore assist practitioners to appreciate the implications of planning activities. The article presents a framework for classifying manufacturing strategy processes and the resulting strategies. Each process and respective strategy is then considered in detail. In this consideration the preferred approach is presented for formulating a world class manufacturing strategy. Finally, conclusions and recommendations for further work are given.

On the 'classification' of neurodegenerative disorders:discrete entities, overlap or continuum?

The traditional method of classifying neurodegenerative diseases is based on the original clinico-pathological concept supported by 'consensus' criteria and data from molecular pathological studies. This review discusses first, current problems in classification resulting from the coexistence of different classificatory schemes, the presence of disease heterogeneity and multiple pathologies, the use of 'signature' brain lesions in diagnosis, and the existence of pathological processes common to different diseases. Second, three models of neurodegenerative disease are proposed: (1) that distinct diseases exist ('discrete' model), (2) that relatively distinct diseases exist but exhibit overlapping features ('overlap' model), and (3) that distinct diseases do not exist and neurodegenerative disease is a 'continuum' in which there is continuous variation in clinical/pathological features from one case to another ('continuum' model). Third, to distinguish between models, the distribution of the most important molecular 'signature' lesions across the different diseases is reviewed. Such lesions often have poor 'fidelity', i.e., they are not unique to individual disorders but are distributed across many diseases consistent with the overlap or continuum models. Fourth, the question of whether the current classificatory system should be rejected is considered and three alternatives are proposed, viz., objective classification, classification for convenience (a 'dissection'), or analysis as a continuum.

Novel speech signal processing algorithms for high-accuracy classification of Parkinson's disease

There has been considerable recent research into the connection between Parkinson's disease (PD) and speech impairment. Recently, a wide range of speech signal processing algorithms (dysphonia measures) aiming to predict PD symptom severity using speech signals have been introduced. In this paper, we test how accurately these novel algorithms can be used to discriminate PD subjects from healthy controls. In total, we compute 132 dysphonia measures from sustained vowels. Then, we select four parsimonious subsets of these dysphonia measures using four feature selection algorithms, and map these feature subsets to a binary classification response using two statistical classifiers: random forests and support vector machines. We use an existing database consisting of 263 samples from 43 subjects, and demonstrate that these new dysphonia measures can outperform state-of-the-art results, reaching almost 99% overall classification accuracy using only ten dysphonia features. We find that some of the recently proposed dysphonia measures complement existing algorithms in maximizing the ability of the classifiers to discriminate healthy controls from PD subjects. We see these results as an important step toward noninvasive diagnostic decision support in PD.

The role of working memory in compulsive checking and OCD:a systematic classification of 58 experimental findings

Despite the large body of research regarding the role of memory in OCD, the results are described as mixed at best (Hermans et al., 2008). For example, inconsistent findings have been reported with respect to basic capacity, intact verbal, and generally affected visuospatial memory. We suggest that this is due to the traditional pursuit of OCD memory impairment as one of the general capacity and/or domain specificity (visuospatial vs. verbal). In contrast, we conclude from our experiments (i.e., Harkin & Kessler, 2009, 2011; Harkin, Rutherford, & Kessler, 2011) and recent literature (e.g., Greisberg & McKay, 2003) that OCD memory impairment is secondary to executive dysfunction, and more specifically we identify three common factors (EBL: Executive-functioning efficiency, Binding complexity, and memory Load) that we generalize to 58 experimental findings from 46 OCD memory studies. As a result we explain otherwise inconsistent research – e.g., intact vs. deficient verbal memory – that are difficult to reconcile within a capacity or domain specific perspective. We conclude by discussing the relationship between our account and others', which in most cases is complementary rather than contradictory.

On the hierarchical classification of G protein-coupled receptors

MOTIVATION: G protein-coupled receptors (GPCRs) play an important role in many physiological systems by transducing an extracellular signal into an intracellular response. Over 50% of all marketed drugs are targeted towards a GPCR. There is considerable interest in developing an algorithm that could effectively predict the function of a GPCR from its primary sequence. Such an algorithm is useful not only in identifying novel GPCR sequences but in characterizing the interrelationships between known GPCRs. RESULTS: An alignment-free approach to GPCR classification has been developed using techniques drawn from data mining and proteochemometrics. A dataset of over 8000 sequences was constructed to train the algorithm. This represents one of the largest GPCR datasets currently available. A predictive algorithm was developed based upon the simplest reasonable numerical representation of the protein's physicochemical properties. A selective top-down approach was developed, which used a hierarchical classifier to assign sequences to subdivisions within the GPCR hierarchy. The predictive performance of the algorithm was assessed against several standard data mining classifiers and further validated against Support Vector Machine-based GPCR prediction servers. The selective top-down approach achieves significantly higher accuracy than standard data mining methods in almost all cases.

The classification of HLA supertypes by GRID/CPCA and hierarchical clustering methods

Biological experiments often produce enormous amount of data, which are usually analyzed by data clustering. Cluster analysis refers to statistical methods that are used to assign data with similar properties into several smaller, more meaningful groups. Two commonly used clustering techniques are introduced in the following section: principal component analysis (PCA) and hierarchical clustering. PCA calculates the variance between variables and groups them into a few uncorrelated groups or principal components (PCs) that are orthogonal to each other. Hierarchical clustering is carried out by separating data into many clusters and merging similar clusters together. Here, we use an example of human leukocyte antigen (HLA) supertype classification to demonstrate the usage of the two methods. Two programs, Generating Optimal Linear Partial Least Square Estimations (GOLPE) and Sybyl, are used for PCA and hierarchical clustering, respectively. However, the reader should bear in mind that the methods have been incorporated into other software as well, such as SIMCA, statistiXL, and R.