Handling varying amounts of missing data when classifying mental-health risk levels

One of the main challenges of classifying clinical data is determining how to handle missing features. Most research favours imputing of missing values or neglecting records that include missing data, both of which can degrade accuracy when missing values exceed a certain level. In this research we propose a methodology to handle data sets with a large percentage of missing values and with high variability in which particular data are missing. Feature selection is effected by picking variables sequentially in order of maximum correlation with the dependent variable and minimum correlation with variables already selected. Classification models are generated individually for each test case based on its particular feature set and the matching data values available in the training population. The method was applied to real patients' anonymous mental-health data where the task was to predict the suicide risk judgement clinicians would give for each patient's data, with eleven possible outcome classes: zero to ten, representing no risk to maximum risk. The results compare favourably with alternative methods and have the advantage of ensuring explanations of risk are based only on the data given, not imputed data. This is important for clinical decision support systems using human expertise for modelling and explaining predictions.

Evaluating Misclassification Probability Using Empirical Risk

* The work is supported by RFBR, grant 04-01-00858-a

Risk Factors of Central Venous Catheter Related Infections in Intensive Care Patients

2002 Mathematics Subject Classification: 62P10.

Risk Measures for Classical and Perturbed Risk Processes - a Survey

2000 Mathematics Subject Classification: 60B10, 60G17, 60G51, 62P05.

Sensitivity Analysis of the Risk of Forecasting for Autoregressive Time Series with Missing Values

2000 Mathematics Subject Classification: 62M20, 62M10, 62-07.

A Modified Model of Risk Business

2000 Mathematics Subject Classification: 60K10, 62P05

On the Lp-Norm Regression Models for Estimating Value-at-Risk

Analysis of risk measures associated with price series data movements and its predictions are of strategic importance in the financial markets as well as to policy makers in particular for short- and longterm planning for setting up economic growth targets. For example, oilprice risk-management focuses primarily on when and how an organization can best prevent the costly exposure to price risk. Value-at-Risk (VaR) is the commonly practised instrument to measure risk and is evaluated by analysing the negative/positive tail of the probability distributions of the returns (profit or loss). In modelling applications, least-squares estimation (LSE)-based linear regression models are often employed for modeling and analyzing correlated data. These linear models are optimal and perform relatively well under conditions such as errors following normal or approximately normal distributions, being free of large size outliers and satisfying the Gauss-Markov assumptions. However, often in practical situations, the LSE-based linear regression models fail to provide optimal results, for instance, in non-Gaussian situations especially when the errors follow distributions with fat tails and error terms possess a finite variance. This is the situation in case of risk analysis which involves analyzing tail distributions. Thus, applications of the LSE-based regression models may be questioned for appropriateness and may have limited applicability. We have carried out the risk analysis of Iranian crude oil price data based on the Lp-norm regression models and have noted that the LSE-based models do not always perform the best. We discuss results from the L1, L2 and L∞-norm based linear regression models. ACM Computing Classification System (1998): B.1.2, F.1.3, F.2.3, G.3, J.2.

Compound Compound Poisson Risk Model

2000 Mathematics Subject Classification: 60K10, 62P05.

Estimation of a Regression Function on a Point Process and its Application to Financial Ruin Risk Forecast

2000 Mathematics Subject Classification: Primary 60G55; secondary 60G25.

Requirement Risk Level Forecast Using Bayesian Networks Classifiers

Requirement engineering is a key issue in the development of a software project. Like any other development activity it is not without risks. This work is about the empirical study of risks of requirements by applying machine learning techniques, specifically Bayesian networks classifiers. We have defined several models to predict the risk level for a given requirement using three dataset that collect metrics taken from the requirement specifications of different projects. The classification accuracy of the Bayesian models obtained is evaluated and compared using several classification performance measures. The results of the experiments show that the Bayesians networks allow obtaining valid predictors. Specifically, a tree augmented network structure shows a competitive experimental performance in all datasets. Besides, the relations established between the variables collected to determine the level of risk in a requirement, match with those set by requirement engineers. We show that Bayesian networks are valid tools for the automation of risks assessment in requirement engineering.

A national coastal erosion risk assessment for Scotland

The geography of Scotland, with a highly undulating hinterland, long and indented coastline, together with a large number of islands, means that much social and economic activity is largely located at the coast. The importance of the coast is further highlighted by the large number of ecosystem services derived from the coast. The threat posed by climate change, particularly current and future sea level rise, is of considerable concern and the associated coastal erosion and coastal flooding has the potential to have a substantial effect on the socioeconomic activity of the whole country. Currently, the knowledge base of coastal erosion is poor, which serves to hinder the current and future management of the coast. This research reported here aimed to establish four key aspects of coastal erosion within Scotland: the physical susceptibility of the coast to erosion; the assets exposed to coastal erosion; the vulnerability of communities to coastal erosion; and the coastal erosion risk to those communities. Coastal erosion susceptibility was modelled here within a GIS, using data for ground elevation, rockhead elevation, wave exposure and proximity to the open coast. Combining these data produced the Underlying Physical Susceptibility Model (UPSM), in the form of a 50 m2 raster of national coverage. The Coastal Erosion Susceptibility Model (CESM) was produced with the addition of sediment supply and coastal defence data, which then moderates the outputs of the UPSM. Asset data for dwellings, key assets, transport infrastructure, historic assets, and natural assets were used along with the UPSM and CESM to assess their degree of exposure to coastal erosion. A Coastal Erosion Vulnerability Model (CEVM) was produced using Experian Mosaic Scotland (a geodemographic classification which identifies 44 different social groups within Scotland) to classify populations based upon 11 vulnerability variables. Dwellings were assigned a CESM and CEVM score in order to establish their coastal erosion risk. This research demonstrated that the issue of coastal erosion will impact on a relatively low number of properties compared to those impacted by flooding (both coastal and fluvial) as many dwellings are already protected by coastal defences. There is therefore, a considerable future liability, and great pressure for coastal defences to be maintained and upgraded in their current form. The use of the CEVM is a novel inclusion within a coastal erosion assessment for Scotland. Use of the CEVM established that coastal erosion risk is not distributed equally amongst the Scottish coastal population and highlighted that risk can be reduced by either reducing exposure or reducing vulnerability. Thus far in Scotland, reducing exposure has been the primary management approach, which has a number of implications with regards social justice. This research identified the existing data gaps that should be addressed by future research in order to further improve coastal management in Scotland. Future research should focus on assessing historical coastal change rates on a national scale, improve modelling of national scale wave exposure, enhance the information held about current coastal defences and, determine the direct and indirect economic cost associated with the loss of different asset types. It is also necessary to clarify the social justice implications of using adaptation approaches to manage coastal erosion as well as establishing a method to communicate the susceptibility, exposure, vulnerability and risk aspects whilst minimising the potential negative impacts (e.g. property blight) of releasing such information.

Abundance of Lutzomyia longipalpis in urban households as risk factor of transmission of visceral leishmaniasis

Urban occurrence of human and canine visceral leishmaniasis (VL) is linked to households with characteristics conducive to the presence of sand flies. This study proposes an ad hoc classification of households according to the environmental characteristics of receptivity to phlebotominae and an entomological study to validate the proposal. Here we describe the phlebotominae population found in intra- and peridomiciliary environments and analyse the spatiotemporal distribution of the VL vector Lutzomyia longipalpis of households receptive to VL. In the region, 153 households were classified into levels of receptivity to VL followed by entomological surveys in 40 of those properties. Kruskal-Wallis verified the relationship between the households’ classification and sand fly abundance and Kernel analysis evaluated L. longipalpis spatial distribution: of the 740 sand flies were captured, 91% were L. longipalpis; 82% were found peridomiciliary whilst the remaining 18% were found intradomiciliary. No statistically significant association was found between sandflies and households levels. L. longipalpis counts were concentrated in areas of high vulnerability and some specific households were responsible for the persistence of the infestation. L. longipalpis prevails over other sand fly species for urban VL transmission. The entomological study may help target the surveillance and vector control strategies to domiciles initiating and/or maintaining VL outbreaks.

An Integrated Soft Computing Approach to Hughes Syndrome Risk Assessment

The AntiPhospholipid Syndrome (APS) is an acquired autoimmune disorder induced by high levels of antiphospholipid antibodies that cause arterial and veins thrombosis, as well as pregnancy-related complications and morbidity, as clinical manifestations. This autoimmune hypercoagulable state, usually known as Hughes syndrome, has severe consequences for the patients, being one of the main causes of thrombotic disorders and death. Therefore, it is required to be preventive; being aware of how probable is to have that kind of syndrome. Despite the updated of antiphospholipid syndrome classification, the diagnosis remains difficult to establish. Additional research on clinically relevant antibodies and standardization of their quantification are required in order to improve the antiphospholipid syndrome risk assessment. Thus, this work will focus on the development of a diagnosis decision support system in terms of a formal agenda built on a Logic Programming approach to knowledge representation and reasoning, complemented with a computational framework based on Artificial Neural Networks. The proposed model allows for improving the diagnosis, classifying properly the patients that really presented this pathology (sensitivity higher than 85%), as well as classifying the absence of APS (specificity close to 95%).

Phylogenetics, Ancestral State Reconstruction, And A New Infrafamilial Classification Of The Pantropical Ochnaceae (medusagynaceae, Ochnaceae S.str., Quiinaceae) Based On Five Dna Regions.

Ochnaceae s.str. (Malpighiales) are a pantropical family of about 500 species and 27 genera of almost exclusively woody plants. Infrafamilial classification and relationships have been controversial partially due to the lack of a robust phylogenetic framework. Including all genera except Indosinia and Perissocarpa and DNA sequence data for five DNA regions (ITS, matK, ndhF, rbcL, trnL-F), we provide for the first time a nearly complete molecular phylogenetic analysis of Ochnaceae s.l. resolving most of the phylogenetic backbone of the family. Based on this, we present a new classification of Ochnaceae s.l., with Medusagynoideae and Quiinoideae included as subfamilies and the former subfamilies Ochnoideae and Sauvagesioideae recognized at the rank of tribe. Our data support a monophyletic Ochneae, but Sauvagesieae in the traditional circumscription is paraphyletic because Testulea emerges as sister to the rest of Ochnoideae, and the next clade shows Luxemburgia+Philacra as sister group to the remaining Ochnoideae. To avoid paraphyly, we classify Luxemburgieae and Testuleeae as new tribes. The African genus Lophira, which has switched between subfamilies (here tribes) in past classifications, emerges as sister to all other Ochneae. Thus, endosperm-free seeds and ovules with partly to completely united integuments (resulting in an apparently single integument) are characters that unite all members of that tribe. The relationships within its largest clade, Ochnineae (former Ochneae), are poorly resolved, but former Ochninae (Brackenridgea, Ochna) are polyphyletic. Within Sauvagesieae, the genus Sauvagesia in its broad circumscription is polyphyletic as Sauvagesia serrata is sister to a clade of Adenarake, Sauvagesia spp., and three other genera. Within Quiinoideae, in contrast to former phylogenetic hypotheses, Lacunaria and Touroulia form a clade that is sister to Quiina. Bayesian ancestral state reconstructions showed that zygomorphic flowers with adaptations to buzz-pollination (poricidal anthers), a syncarpous gynoecium (a near-apocarpous gynoecium evolved independently in Quiinoideae and Ochninae), numerous ovules, septicidal capsules, and winged seeds with endosperm are the ancestral condition in Ochnoideae. Although in some lineages poricidal anthers were lost secondarily, the evolution of poricidal superstructures secured the maintenance of buzz-pollination in some of these genera, indicating a strong selective pressure on keeping that specialized pollination system.

Advancing Bag-of-visual-words Representations For Lesion Classification In Retinal Images.

Diabetic Retinopathy (DR) is a complication of diabetes that can lead to blindness if not readily discovered. Automated screening algorithms have the potential to improve identification of patients who need further medical attention. However, the identification of lesions must be accurate to be useful for clinical application. The bag-of-visual-words (BoVW) algorithm employs a maximum-margin classifier in a flexible framework that is able to detect the most common DR-related lesions such as microaneurysms, cotton-wool spots and hard exudates. BoVW allows to bypass the need for pre- and post-processing of the retinographic images, as well as the need of specific ad hoc techniques for identification of each type of lesion. An extensive evaluation of the BoVW model, using three large retinograph datasets (DR1, DR2 and Messidor) with different resolution and collected by different healthcare personnel, was performed. The results demonstrate that the BoVW classification approach can identify different lesions within an image without having to utilize different algorithms for each lesion reducing processing time and providing a more flexible diagnostic system. Our BoVW scheme is based on sparse low-level feature detection with a Speeded-Up Robust Features (SURF) local descriptor, and mid-level features based on semi-soft coding with max pooling. The best BoVW representation for retinal image classification was an area under the receiver operating characteristic curve (AUC-ROC) of 97.8% (exudates) and 93.5% (red lesions), applying a cross-dataset validation protocol. To assess the accuracy for detecting cases that require referral within one year, the sparse extraction technique associated with semi-soft coding and max pooling obtained an AUC of 94.2 ± 2.0%, outperforming current methods. Those results indicate that, for retinal image classification tasks in clinical practice, BoVW is equal and, in some instances, surpasses results obtained using dense detection (widely believed to be the best choice in many vision problems) for the low-level descriptors.