In this work, we introduce an entirely data-driven and automated approach to reveal disease-associated biomarker and risk factor networks from heterogeneous and high-dimensional healthcare data. Our workflow is based on Bayesian networks, which are a popular tool for analyzing the interplay of biomarkers. Usually, data require extensive manual preprocessing and dimension reduction to allow for effective learning of Bayesian networks. For heterogeneous data, this preprocessing is hard to automatize and typically requires domain-specific prior knowledge. We here combine Bayesian network learning with hierarchical variable clustering in order to detect groups of similar features and learn interactions between them entirely automated. We present an optimization algorithm for the adaptive refinement of such group Bayesian networks to account for a specific target variable, like a disease. The combination of Bayesian networks, clustering, and refinement yields low-dimensional but disease-specific interaction networks. These networks provide easily interpretable, yet accurate models of biomarker interdependencies. We test our method extensively on simulated data, as well as on data from the Study of Health in Pomerania (SHIP-TREND), and demonstrate its effectiveness using non-alcoholic fatty liver disease and hypertension as examples. We show that the group network models outperform available biomarker scores, while at the same time, they provide an easily interpretable interaction network.

Abstract Attrition or dropout is the most severe missingness problem in longitudinal cohort study data where some participants do not show up for follow‐up examinations. Dropouts result in biased data and cause the reduction of 1ata set size. Moreover, they limit the power of statistical analysis and the validity of study findings. Visualization can play a strong role in analysing and displaying the missingness patterns. In this work, we present VIVID, a framework for the visual analysis of missing values in cohort study data. VIVID is inspired by discussions with epidemiologists and adds visual components to their current statistics‐based approaches. VIVID provides functions for exploration, imputation and validity check of imputations. The main focus of this paper is multiple imputation to fix the missing data.

Epidemiological population-based studies collect hundreds of socio-demographic, lifestyle-related, and health related variables for thousands of individuals in order to better characterize health and disease in a defined population. To understand the relations between the variables in the study data, we employ Bayesian Networks, as they not only represent associations between variables but also assign probabilities to these associations. The probabilistic associations allow us to draw inference for unknown events in question, based on the provided evidence. In our work, we induce a Bayesian Network from the data of the population-based epidemiological Study of Health in Pomerania (SHIP), to identify variables related to the outcome "fatty liver". We report on Bayesian Network structure learning, identification of variables associated with the outcome, and the strong associations identified among the variables.

Subgroup discovery (SD) exploits its full value in applications where the goal is to generate understandable models. Epidemiologists search for statistically significant relationships between risk factors and outcome in large and heterogeneous datasets encompassing information about the participants health status gathered from questionnaires, medical examinations and image acquisition. SD algorithms can help epidemiologists by automatically detecting such relationships presented as comprehensible rules, aiming to ultimately improve prevention, diagnosis and treatment of diseases. However, SD algorithms often produce large and overlapping rule sets requiring the expert to conduct a manual post-filtering step that is time-consuming and tedious. In this work, we propose a clustering-based algorithm that hierarchically reorganizes rule sets and summarizes all important concepts while maintaining diversity between the rule clusters. For each cluster, a representative rule is selected and then displayed to the expert who in turn can drill-down to other cluster members. We evaluate our algorithm on two cohort study datasets where the diseases hepatic steatosis and goiter serve as target variable, respectively. We report on our findings with respect to effectiveness of our algorithm and we present selected subpopulations.

Personalized medicine benefits from the identification of subpopulations that exhibit higher prevalence of a disease than the general population: such subpopulations can become the target of more intensive investigations to identify risk factors and to develop dedicated therapies. Classification rule discovery algorithms are an appropriate tool for discovering such subpopulations: they scale well, even for multi-dimensional data and deliver comprehensible patterns. However, they may generate hundreds of rules and thus call for exploration methods. In this study, we extend the tool Interactive Medical Miner for the discovery of classification rules, into the Interactive Classification rule Explorer ICE, which offers functionalities for rule exploration, grouping, rule visualization and statistics. We report on our first results for the classification of cohort data on goiter, a disorder of the thyroid gland.

The identification of predictive features associated with distinct medical outcomes is a key requirement for meaningful clinical decision support. Usually, their discovery is based on sets of labeled examples and an analysis of the inherent information of the features w. r. t. the target variable. However, obtaining large sets of labeled examples may be not feasible and the sole label consideration could even dilute characteristics unique to distinct subgroups. In such cases, instead of considering the value of the target variable, expert knowledge on the similarity between examples could be utilized. In this work we propose a new algorithm for the "Discovery of Relevant Example-constrained Subspaces" (DRESS) which uses constraints on the similarity between examples to discover feature sets that describe a target concept. DRESS exploits the density of clusters and the distance-behavior between constrained examples to evaluate the quality of a feature set without requiring explicit information about the target variable. We evaluate DRESS against classical feature selection methods on cohort participants for the disorder "hepatic steatosis", and report on our findings on classifier performance and identified important features.

Epidemiological studies comprise heterogeneous data about a subject group to define disease-specific risk factors. These data contain information (features) about a subject's lifestyle, medical status as well as medical image data. Statistical regression analysis is used to evaluate these features and to identify feature combinations indicating a disease (the target feature). We propose an analysis approach of epidemiological data sets by incorporating all features in an exhaustive regression-based analysis. This approach combines all independent features w.r.t. a target feature. It provides a visualization that reveals insights into the data by highlighting relationships. The 3D Regression Heat Map, a novel 3D visual encoding, acts as an overview of the whole data set. It shows all combinations of two to three independent features with a specific target disease. Slicing through the 3D Regression Heat Map allows for the detailed analysis of the underlying relationships. Expert knowledge about disease-specific hypotheses can be included into the analysis by adjusting the regression model formulas. Furthermore, the influences of features can be assessed using a difference view comparing different calculation results. We applied our 3D Regression Heat Map method to a hepatic steatosis data set to reproduce results from a data mining-driven analysis. A qualitative analysis was conducted on a breast density data set. We were able to derive new hypotheses about relations between breast density and breast lesions with breast cancer. With the 3D Regression Heat Map, we present a visual overview of epidemiological data that allows for the first time an interactive regression-based analysis of large feature sets with respect to a disease.

Medical research can greatly benefit from advances in data mining. We propose a mining approach for cohort analysis in a longitudinal population-based epidemiological study, and show that modelling and exploiting the evolution of cohort participants over time improves classification quality towards an outcome (a disease). Our mining workflow encompasses steps for tracing the evolution of the cohort participants and for using evolution features in classification. We show that our approach separates better between classes and that change in the values of variables is predictive. We report on results for the liver disorder hepatic steatosis (high fat accumulation in the liver), but our approach is appropriate for classification of longitudinal epidemiological data on further disorders.

Clinical decision support relies on the findings of epidemiological (longitudinal and cross-sectional) studies on predictive features and risk factors for diseases. Such features flow into the diagnostic procedures. Personalized medicine, which aims to optimize clinical decision making by taking individual characteristics of the patients into account, relies on the findings of epidemiology on groups of cohort participants that have common risk factors and exhibit the outcome under study. The identification of such groups requires modeling and exploiting similarity among individuals described through medical tests. In this work, we study how similarity measures for complex objects contribute to class separation for a multifactorial disorder. We present a data preparation, partitioning and classification workflow on cohort participants for the disorder "hepatic steatosis", and report on our findings on classifier performance and identified important features.

Epidemiological population studies impose information about a set of subjects (a cohort) to characterize disease-specific risk factors. Cohort studies comprise heterogenous variables describing the medical condition as well as demographic and lifestyle factors and, more recently, medical image data. We propose an Interactive Visual Analysis (IVA) approach that enables epidemiologists to rapidly investigate the entire data pool for hypothesis validation and generation. We incorporate image data, which involves shape-based object detection and the derivation of attributes describing the object shape. The concurrent investigation of image-based and non-image data is realized in a web-based multiple coordinated view system, comprising standard views from information visualization and epidemiological data representations such as pivot tables. The views are equipped with brushing facilities and augmented by 3D shape renderings of the segmented objects, e.g., each bar in a histogram is overlaid with a mean shape of the associated subgroup of the cohort. We integrate an overview visualization, clustering of variables and object shape for data-driven subgroup definition and statistical key figures for measuring the association between variables. We demonstrate the IVA approach by validating and generating hypotheses related to lower back pain as part of a qualitative evaluation.

Fully automatic 3-D segmentation techniques for clinical applications or epidemiological studies have proven to be a very challenging task in the domain of medical image analysis. 3-D organ segmentation on magnetic resonance (MR) datasets requires a well-designed segmentation strategy due to imaging artifacts, partial volume effects, and similar tissue properties of adjacent tissues. We developed a 3-D segmentation framework for fully automatic kidney parenchyma volumetry that uses Bayesian concepts for probability map generation. The probability map quality is improved in a multistep refinement approach. An extended prior shape level set segmentation method is then applied on the refined probability maps. The segmentation quality is improved by incorporating an exterior cortex edge alignment technique using cortex probability maps. In contrast to previous approaches, we combine several relevant kidney parenchyma features in a sequence of segmentation techniques for successful parenchyma delineation on native MR datasets. Furthermore, the proposed method is able to recognize and exclude parenchymal cysts from the parenchymal volume. We analyzed four different quality measures showing better results for right parenchymal tissue than for left parenchymal tissue due to an incorporated liver part removal in the segmentation framework. The results show that the outer cortex edge alignment approach successfully improves the quality measures.