The Feasibility of Semi-Continuous and Multi-Frequency Thoracic Bioimpedance Measurements by a Wearable Device during Fluid Changes in Hemodialysis Patients.

Repeated single-point measurements of thoracic bioimpedance at a single (low) frequency are strongly related to fluid changes during hemodialysis. Extension to semi-continuous measurements may provide longitudinal details in the time pattern of the bioimpedance signal, and multi-frequency measurements may add in-depth information on the distribution between intra- and extracellular fluid. This study aimed to investigate the feasibility of semi-continuous multi-frequency thoracic bioimpedance measurements by a wearable device in hemodialysis patients. Therefore, thoracic bioimpedance was recorded semi-continuously (i.e., every ten minutes) at nine frequencies (8-160 kHz) in 68 patients during two consecutive hemodialysis sessions, complemented by a single-point measurement at home in-between both sessions. On average, the resistance signals increased during both hemodialysis sessions and decreased during the interdialytic interval. The increase during dialysis was larger at 8 kHz (∆ 32.6 Ω during session 1 and ∆ 10 Ω during session 2), compared to 160 kHz (∆ 29.5 Ω during session 1 and ∆ 5.1 Ω during session 2). Whereas the resistance at 8 kHz showed a linear time pattern, the evolution of the resistance at 160 kHz was significantly different (p < 0.0001). Measuring bioimpedance semi-continuously and with a multi-frequency current is a major step forward in the understanding of fluid dynamics in hemodialysis patients. This study paves the road towards remote fluid monitoring.

Spatiochemical Characterization of the Pancreas Using Mass Spectrometry Imaging and Topological Data Analysis.

Mass Spectrometry Imaging (MSI) is a technique used to identify the spatial distribution of molecules in tissues. An MSI experiment results in large amounts of high dimensional data, so efficient computational methods are needed to analyze the output. Topological Data Analysis (TDA) has proven to be effective in all kinds of applications. TDA focuses on the topology of the data in high dimensional space. Looking at the shape in a high dimensional data set can lead to new or different insights. In this work, we investigate the use of Mapper, a form of TDA, applied on MSI data. Mapper is used to find data clusters inside two healthy mouse pancreas data sets. The results are compared to previous work using UMAP for MSI data analysis on the same data sets. This work finds that the proposed technique discovers the same clusters in the data as UMAP and is also able to uncover new clusters, such as an additional ring structure inside the pancreatic islets and a better defined cluster containing blood vessels. The technique can be used for a large variety of data types and sizes and can be optimized for specific applications. It is also computationally similar to UMAP for clustering. Mapper is a very interesting method, especially its use in biomedical applications.

Data-Driven Chronic Allograft Phenotypes: A Novel and Validated Complement for Histologic Assessment of Kidney Transplant Biopsies.

BACKGROUND: No validated system currently exists to realistically characterize the chronic pathology of kidney transplants that represents the dynamic disease process and spectrum of disease severity. We sought to develop and validate a tool to describe chronicity and severity of renal allograft disease and integrate it with the evaluation of disease activity. METHODS: The training cohort included 3549 kidney transplant biopsies from an observational cohort of 937 recipients. We reweighted the chronic histologic lesions according to their time-dependent association with graft failure, and performed consensus k-means clustering analysis. Total chronicity was calculated as the sum of the weighted chronic lesion scores, scaled to the unit interval. RESULTS: We identified four chronic clusters associated with graft outcome, based on the proportion of ambiguous clustering. The two clusters with the worst survival outcome were determined by interstitial fibrosis and tubular atrophy (IFTA) and by transplant glomerulopathy. The chronic clusters partially overlapped with the existing Banff IFTA classification (adjusted Rand index, 0.35) and were distributed independently of the acute lesions. Total chronicity strongly associated with graft failure (hazard ratio [HR], 8.33; 95% confidence interval [CI], 5.94 to 10.88; P<0.001), independent of the total activity scores (HR, 5.01; 95% CI, 2.83 to 7.00; P<0.001). These results were validated on an external cohort of 4031 biopsies from 2054 kidney transplant recipients. CONCLUSIONS: The evaluation of total chronicity provides information on kidney transplant pathology that complements the estimation of disease activity from acute lesion scores. Use of the data-driven algorithm used in this study, called RejectClass, may provide a holistic and quantitative assessment of kidney transplant injury phenotypes and severity.

Data-driven Derivation and Validation of Novel Phenotypes for Acute Kidney Transplant Rejection using Semi-supervised Clustering.

BACKGROUND: Over the past decades, an international group of experts iteratively developed a consensus classification of kidney transplant rejection phenotypes, known as the Banff classification. Data-driven clustering of kidney transplant histologic data could simplify the complex and discretionary rules of the Banff classification, while improving the association with graft failure. METHODS: The data consisted of a training set of 3510 kidney-transplant biopsies from an observational cohort of 936 recipients. Independent validation of the results was performed on an external set of 3835 biopsies from 1989 patients. On the basis of acute histologic lesion scores and the presence of donor-specific HLA antibodies, stable clustering was achieved on the basis of a consensus of 400 different clustering partitions. Additional information on kidney-transplant failure was introduced with a weighted Euclidean distance. RESULTS: Based on the proportion of ambiguous clustering, six clinically meaningful cluster phenotypes were identified. There was significant overlap with the existing Banff classification (adjusted rand index, 0.48). However, the data-driven approach eliminated intermediate and mixed phenotypes and created acute rejection clusters that are each significantly associated with graft failure. Finally, a novel visualization tool presents disease phenotypes and severity in a continuous manner, as a complement to the discrete clusters. CONCLUSIONS: A semisupervised clustering approach for the identification of clinically meaningful novel phenotypes of kidney transplant rejection has been developed and validated. The approach has the potential to offer a more quantitative evaluation of rejection subtypes and severity, especially in situations in which the current histologic categorization is ambiguous.

Correspondence-Aware Manifold Learning for Microscopic and Spatial Omics Imaging: A Novel Data Fusion Method Bringing Mass Spectrometry Imaging to a Cellular Resolution.

High-dimensional molecular measurements are transforming the field of pathology into a data-driven discipline. While hematoxylin and eosin (H&E) stainings are still the gold standard to diagnose diseases, the integration of microscopic and molecular information is becoming crucial to advance our understanding of tissue heterogeneity. To this end, we propose a data fusion method that integrates spatial omics and microscopic data obtained from the same tissue slide. Through correspondence-aware manifold learning, we can visualize the biological trends observed in the high-dimensional omics data at microscopic resolution. While data fusion enables the detection of elements that would not be detected taking into account the separate data modalities individually, out-of-sample prediction makes it possible to predict molecular trends outside of the measured tissue area. The proposed dimensionality reduction-based data fusion paradigm will therefore be helpful in deciphering molecular heterogeneity by bringing molecular measurements such as mass spectrometry imaging (MSI) to the cellular resolution.

A mathematical comparison of non-negative matrix factorization related methods with practical implications for the analysis of mass spectrometry imaging data.

RATIONALE: Non-negative matrix factorization (NMF) has been used extensively for the analysis of mass spectrometry imaging (MSI) data, visualizing simultaneously the spatial and spectral distributions present in a slice of tissue. The statistical framework offers two related NMF methods: probabilistic latent semantic analysis (PLSA) and latent Dirichlet allocation (LDA), which is a generative model. This work offers a mathematical comparison between NMF, PLSA, and LDA, and includes a detailed evaluation of Kullback-Leibler NMF (KL-NMF) for MSI for the first time. We will inspect the results for MSI data analysis as these different mathematical approaches impose different characteristics on the data and the resulting decomposition. METHODS: The four methods (NMF, KL-NMF, PLSA, and LDA) are compared on seven different samples: three originated from mice pancreas and four from human-lymph-node tissues, all obtained using matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS). RESULTS: Where matrix factorization methods are often used for the analysis of MSI data, we find that each method has different implications on the exactness and interpretability of the results. We have discovered promising results using KL-NMF, which has only rarely been used for MSI so far, improving both NMF and PLSA, and have shown that the hitherto stated equivalent KL-NMF and PLSA algorithms do differ in the case of MSI data analysis. LDA, assumed to be the better method in the field of text mining, is shown to be outperformed by PLSA in the setting of MALDI-MSI. Additionally, the molecular results of the human-lymph-node data have been thoroughly analyzed for better assessment of the methods under investigation. CONCLUSIONS: We present an in-depth comparison of multiple NMF-related factorization methods for MSI. We aim to provide fellow researchers in the field of MSI a clear understanding of the mathematical implications using each of these analytical techniques, which might affect the exactness and interpretation of the results.

Spatially aware clustering of ion images in mass spectrometry imaging data using deep learning.

Computational analysis is crucial to capitalize on the wealth of spatio-molecular information generated by mass spectrometry imaging (MSI) experiments. Currently, the spatial information available in MSI data is often under-utilized, due to the challenges of in-depth spatial pattern extraction. The advent of deep learning has greatly facilitated such complex spatial analysis. In this work, we use a pre-trained neural network to extract high-level features from ion images in MSI data, and test whether this improves downstream data analysis. The resulting neural network interpretation of ion images, coined neural ion images, is used to cluster ion images based on spatial expressions. We evaluate the impact of neural ion images on two ion image clustering pipelines, namely DBSCAN clustering, combined with UMAP-based dimensionality reduction, and k-means clustering. In both pipelines, we compare regular and neural ion images from two different MSI datasets. All tested pipelines could extract underlying spatial patterns, but the neural network-based pipelines provided better assignment of ion images, with more fine-grained clusters, and greater consistency in the spatial structures assigned to individual clusters. Additionally, we introduce the relative isotope ratio metric to quantitatively evaluate clustering quality. The resulting scores show that isotopical m/z values are more often clustered together in the neural network-based pipeline, indicating improved clustering outcomes. The usefulness of neural ion images extends beyond clustering towards a generic framework to incorporate spatial information into any MSI-focused machine learning pipeline, both supervised and unsupervised.

An automated data cleaning method for Electronic Health Records by incorporating clinical knowledge.

BACKGROUND: The use of Electronic Health Records (EHR) data in clinical research is incredibly increasing, but the abundancy of data resources raises the challenge of data cleaning. It can save time if the data cleaning can be done automatically. In addition, the automated data cleaning tools for data in other domains often process all variables uniformly, meaning that they cannot serve well for clinical data, as there is variable-specific information that needs to be considered. This paper proposes an automated data cleaning method for EHR data with clinical knowledge taken into consideration. METHODS: We used EHR data collected from primary care in Flanders, Belgium during 1994-2015. We constructed a Clinical Knowledge Database to store all the variable-specific information that is necessary for data cleaning. We applied Fuzzy search to automatically detect and replace the wrongly spelled units, and performed the unit conversion following the variable-specific conversion formula. Then the numeric values were corrected and outliers were detected considering the clinical knowledge. In total, 52 clinical variables were cleaned, and the percentage of missing values (completeness) and percentage of values within the normal range (correctness) before and after the cleaning process were compared. RESULTS: All variables were 100% complete before data cleaning. 42 variables had a drop of less than 1% in the percentage of missing values and 9 variables declined by 1-10%. Only 1 variable experienced large decline in completeness (13.36%). All variables had more than 50% values within the normal range after cleaning, of which 43 variables had a percentage higher than 70%. CONCLUSIONS: We propose a general method for clinical variables, which achieves high automation and is capable to deal with large-scale data. This method largely improved the efficiency to clean the data and removed the technical barriers for non-technical people.

An ensemble-based feature selection framework to select risk factors of childhood obesity for policy decision making.

BACKGROUND: The increasing prevalence of childhood obesity makes it essential to study the risk factors with a sample representative of the population covering more health topics for better preventive policies and interventions. It is aimed to develop an ensemble feature selection framework for large-scale data to identify risk factors of childhood obesity with good interpretability and clinical relevance. METHODS: We analyzed the data collected from 426,813 children under 18 during 2000-2019. A BMI above the 90th percentile for the children of the same age and gender was defined as overweight. An ensemble feature selection framework, Bagging-based Feature Selection framework integrating MapReduce (BFSMR), was proposed to identify risk factors. The framework comprises 5 models (filter with mutual information/SVM-RFE/Lasso/Ridge/Random Forest) from filter, wrapper, and embedded feature selection methods. Each feature selection model identified 10 variables based on variable importance. Considering accuracy, F-score, and model characteristics, the models were classified into 3 levels with different weights: Lasso/Ridge, Filter/SVM-RFE, and Random Forest. The voting strategy was applied to aggregate the selected features, with both feature weights and model weights taken into consideration. We compared our voting strategy with another two for selecting top-ranked features in terms of 6 dimensions of interpretability. RESULTS: Our method performed the best to select the features with good interpretability and clinical relevance. The top 10 features selected by BFSMR are age, sex, birth year, breastfeeding type, smoking habit and diet-related knowledge of both children and mothers, exercise, and Mother's systolic blood pressure. CONCLUSION: Our framework provides a solution for identifying a diverse and interpretable feature set without model bias from large-scale data, which can help identify risk factors of childhood obesity and potentially some other diseases for future interventions or policies.

Prioritization of m/z-Values in Mass Spectrometry Imaging Profiles Obtained Using Uniform Manifold Approximation and Projection for Dimensionality Reduction.

Mass spectrometry imaging (MSI) is a promising technique to assess the spatial distribution of molecules in a tissue sample. Nonlinear dimensionality reduction methods such as Uniform Manifold Approximation and Projection (UMAP) can be very valuable for the visualization of the massive data sets produced by MSI. These visualizations can offer us good initial insights regarding the heterogeneity and variety of molecular patterns present in the data, but they do not discern which molecules might be driving these observations. To prioritize the m/z-values associated with these biochemical profiles, we apply a bidirectional dimensionality reduction approach taking into account both the spectral and spatial information. The results show that both sources of information are instrumental to get a more comprehensive view on the relevant m/z-values and can support the reliability of the results obtained using UMAP. We illustrate our approach on heterogeneous pancreas tissues obtained from healthy mice.

Exercise intervention in hospitalized heart failure patients, with emphasis on congestion-related complications: a review.

The importance of physical activity has become evident since a sedentary lifestyle drives cardiovascular disease progression and is associated with increased morbidity and mortality. The favorable effects of exercise training in chronic heart failure (HF) and chronic kidney disease (CKD) are widely recognized and exercise training is recommended by European and American guidelines. However, the application of exercise intervention in HF patients hospitalized for acute decompensation or acute worsening in cardiac function has not been explored extensively and, as a result, knowledge about the effects of exercise training in the inpatient setting of acute HF is limited. Acute HF is often accompanied by signs and symptoms of congestion, termed acute decompensated heart failure (ADHF), which leads to worsening renal function (WRF) and eventually negatively affects both thoracic and abdominal organs. Therefore, we first provide a comprehensive overview of the impact of exercise training in hospitalized patients demonstrating acute decompensating HF. In the second part, we will focus on the effects of exercise training on congestion in a setting of ADHF complicated by renal dysfunction. This review suggests that exercise intervention is beneficial in the inpatient setting of acute HF, but that more clinical studies focusing on the application of exercise training to counteract venous congestion are needed.

Evaluation of Distance Metrics and Spatial Autocorrelation in Uniform Manifold Approximation and Projection Applied to Mass Spectrometry Imaging Data.

In this work, uniform manifold approximation and projection (UMAP) is applied for nonlinear dimensionality reduction and visualization of mass spectrometry imaging (MSI) data. We evaluate the performance of the UMAP algorithm on MSI data sets acquired in mouse pancreas and human lymphoma samples and compare it to those of principal component analysis (PCA), t-distributed stochastic neighbor embedding (t-SNE), and the Barnes-Hut (BH) approximation of t-SNE. Furthermore, we compare different distance metrics in (BH) t-SNE and UMAP and propose the use of spatial autocorrelation as a means of comparing the resulting low-dimensional embeddings. The results indicate that UMAP is competitive with t-SNE in terms of visualization and is well-suited for the dimensionality reduction of large (>100 000 pixels) MSI data sets. With an almost fourfold decrease in runtime, it is more scalable in comparison with the current state-of-the-art: t-SNE or the Barnes-Hut approximation of t-SNE. In what seems to be the first application of UMAP to MSI data, we assess the value of applying alternative distance metrics, such as the correlation, cosine, and the Chebyshev metric, in contrast to the traditionally used Euclidean distance metric. Furthermore, we propose "histomatch" as an additional custom distance metric for the analysis of MSI data.

Current animal models for the study of congestion in heart failure: an overview.

Congestion (i.e., backward failure) is an important culprit mechanism driving disease progression in heart failure. Nevertheless, congestion remains often underappreciated and clinicians underestimate the importance of congestion on the pathophysiology of decompensation in heart failure. In patients, it is however difficult to study how isolated congestion contributes to organ dysfunction, since heart failure and chronic kidney disease very often coexist in the so-called cardiorenal syndrome. Here, we review the existing relevant and suitable backward heart failure animal models to induce congestion, induced in the left- (i.e., myocardial infarction, rapid ventricular pacing) or right-sided heart (i.e., aorta-caval shunt, mitral valve regurgitation, and monocrotaline), and more specific animal models of congestion, induced by saline infusion or inferior vena cava constriction. Next, we examine critically how representative they are for the clinical situation. After all, a relevant animal model of isolated congestion offers the unique possibility of studying the effects of congestion in heart failure and the cardiorenal syndrome, separately from forward failure (i.e., impaired cardiac output). In this respect, new treatment options can be discovered.

Software-guided versus nurse-directed blood glucose control in critically ill patients: the LOGIC-2 multicenter randomized controlled clinical trial.

BACKGROUND: Blood glucose control in the intensive care unit (ICU) has the potential to save lives. However, maintaining blood glucose concentrations within a chosen target range is difficult in clinical practice and holds risk of potentially harmful hypoglycemia. Clinically validated computer algorithms to guide insulin dosing by nurses have been advocated for better and safer blood glucose control. METHODS: We conducted an international, multicenter, randomized controlled trial involving 1550 adult, medical and surgical critically ill patients, requiring blood glucose control. Patients were randomly assigned to algorithm-guided blood glucose control (LOGIC-C, n = 777) or blood glucose control by trained nurses (Nurse-C, n = 773) during ICU stay, according to the local target range (80-110 mg/dL or 90-145 mg/dL). The primary outcome measure was the quality of blood glucose control, assessed by the glycemic penalty index (GPI), a measure that penalizes hypoglycemic and hyperglycemic deviations from the chosen target range. Incidence of severe hypoglycemia (<40 mg/dL) was the main safety outcome measure. New infections in ICU, duration of hospital stay, landmark 90-day mortality and quality of life were clinical safety outcome measures. RESULTS: The median GPI was lower in the LOGIC-C (10.8 IQR 6.2-16.1) than in the Nurse-C group (17.1 IQR 10.6-26.2) (P < 0.001). Mean blood glucose was 111 mg/dL (SD 15) in LOCIC-C versus 119 mg/dL (SD 21) in Nurse-C, whereas the median time-in-target range was 67.0% (IQR 52.1-80.1) in LOGIC-C versus 47.1% (IQR 28.1-65.0) in the Nurse-C group (both P < 0.001). The fraction of patients with severe hypoglycemia did not differ between LOGIC-C (0.9%) and Nurse-C (1.2%) (P = 0.6). The clinical safety outcomes did not differ between groups. The sampling interval was 2.3 h (SD 0.5) in the LOGIC-C group versus 3.0 h (SD 0.8) in the Nurse-C group (P < 0.001). CONCLUSIONS: In a randomized controlled trial of a mixed critically ill patient population, the use of the LOGIC-Insulin blood glucose control algorithm, compared with blood glucose control by expert nurses, improved the quality of blood glucose control without increasing hypoglycemia. TRIAL REGISTRATION: ClinicalTrials.gov, NCT02056353 . Registered on 4 February 2014.

eXtasy: variant prioritization by genomic data fusion.

Massively parallel sequencing greatly facilitates the discovery of novel disease genes causing Mendelian and oligogenic disorders. However, many mutations are present in any individual genome, and identifying which ones are disease causing remains a largely open problem. We introduce eXtasy, an approach to prioritize nonsynonymous single-nucleotide variants (nSNVs) that substantially improves prediction of disease-causing variants in exome sequencing data by integrating variant impact prediction, haploinsufficiency prediction and phenotype-specific gene prioritization.

External Validation of a risk stratification model to assist shared decision making for patients starting renal replacement therapy.

BACKGROUND: Shared decision making is nowadays acknowledged as an essential step when deciding on starting renal replacement therapy. Valid risk stratification of prognosis is, besides discussing quality of life, crucial in this regard. We intended to validate a recently published risk stratification model in a large cohort of incident patients starting renal replacement therapy in Flanders. METHODS: During 3 years (2001-2003), the data set collected for the Nederlandstalige Belgische Vereniging voor Nefrologie (NBVN) registry was expanded with parameters of comorbidity. For all incident patients, the abbreviated REIN score(aREIN), being the REIN score without the parameter "mobility", was calculated, and prognostication of mortality at 3, 6 and 12 month after start of renal replacement therapy (RRT) was evaluated. RESULTS: Three thousand four hundred seventy-two patients started RRT in Flanders during the observation period (mean age 67.6 ± 14.3, 56.7 % men, 33.6 % diabetes). The mean aREIN score was 4.1 ± 2.8, and 56.8, 23.1, 12.6 and 7.4 % of patients had a score of ≤4, 5-6, 7-8 or ≥9 respectively. Mortality at 3, 6 and 12 months was 8.6, 14.1 and 19.6 % in the overall and 13.2, 21.5 and 31.9 % in the group with age >75 respectively. In RoC analysis, the aREIN score had an AUC of 0.74 for prediction of survival at 3, 6 and 12 months. There was an incremental increase in mortality with the aREIN score from 5.6 to 45.8 % mortality at 6 months for those with a score ≤4 or ≥9 respectively. CONCLUSION: The aREIN score is a useful tool to predict short term prognosis of patients starting renal replacement therapy as based on comorbidity and age, and delivers meaningful discrimination between low and high risk populations. As such, it can be a useful instrument to be incorporated in shared decision making on whether or not start of dialysis is worthwhile.

Problems with the nested granularity of feature domains in bioinformatics: the eXtasy case.

BACKGROUND: Data from biomedical domains often have an inherit hierarchical structure. As this structure is usually implicit, its existence can be overlooked by practitioners interested in constructing and evaluating predictive models from such data. Ignoring these constructs leads to potentially problematic and the routinely unrecognized bias in the models and results. In this work, we discuss this bias in detail and propose a simple, sampling-based solution for it. Next, we explore its sources and extent on synthetic data. Finally, we demonstrate how the state-of-the-art variant prioritization framework, eXtasy, benefits from using the described approach in its Random forest-based core classification model. RESULTS AND CONCLUSIONS: The conducted simulations clearly indicate that the heterogeneous granularity of feature domains poses significant problems for both the standard Random forest classifier and a modification that relies on stratified bootstrapping. Conversely, using the proposed sampling scheme when training the classifier mitigates the described bias. Furthermore, when applied to the eXtasy data under a realistic class distribution scenario, a Random forest learned using the proposed sampling scheme displays much better precision that its standard version, without degrading recall. Moreover, the largest performance gains are achieved in the most important part of the operating range: the top of prioritized gene list.

New bandwidth selection criterion for Kernel PCA: approach to dimensionality reduction and classification problems.

BACKGROUND: DNA microarrays are potentially powerful technology for improving diagnostic classification, treatment selection, and prognostic assessment. The use of this technology to predict cancer outcome has a history of almost a decade. Disease class predictors can be designed for known disease cases and provide diagnostic confirmation or clarify abnormal cases. The main input to this class predictors are high dimensional data with many variables and few observations. Dimensionality reduction of these features set significantly speeds up the prediction task. Feature selection and feature transformation methods are well known preprocessing steps in the field of bioinformatics. Several prediction tools are available based on these techniques. RESULTS: Studies show that a well tuned Kernel PCA (KPCA) is an efficient preprocessing step for dimensionality reduction, but the available bandwidth selection method for KPCA was computationally expensive. In this paper, we propose a new data-driven bandwidth selection criterion for KPCA, which is related to least squares cross-validation for kernel density estimation. We propose a new prediction model with a well tuned KPCA and Least Squares Support Vector Machine (LS-SVM). We estimate the accuracy of the newly proposed model based on 9 case studies. Then, we compare its performances (in terms of test set Area Under the ROC Curve (AUC) and computational time) with other well known techniques such as whole data set + LS-SVM, PCA + LS-SVM, t-test + LS-SVM, Prediction Analysis of Microarrays (PAM) and Least Absolute Shrinkage and Selection Operator (Lasso). Finally, we assess the performance of the proposed strategy with an existing KPCA parameter tuning algorithm by means of two additional case studies. CONCLUSION: We propose, evaluate, and compare several mathematical/statistical techniques, which apply feature transformation/selection for subsequent classification, and consider its application in medical diagnostics. Both feature selection and feature transformation perform well on classification tasks. Due to the dynamic selection property of feature selection, it is hard to define significant features for the classifier, which predicts classes of future samples. Moreover, the proposed strategy enjoys a distinctive advantage with its relatively lesser time complexity.

Predicting breast cancer using an expression values weighted clinical classifier.

BACKGROUND: Clinical data, such as patient history, laboratory analysis, ultrasound parameters-which are the basis of day-to-day clinical decision support-are often used to guide the clinical management of cancer in the presence of microarray data. Several data fusion techniques are available to integrate genomics or proteomics data, but only a few studies have created a single prediction model using both gene expression and clinical data. These studies often remain inconclusive regarding an obtained improvement in prediction performance. To improve clinical management, these data should be fully exploited. This requires efficient algorithms to integrate these data sets and design a final classifier. LS-SVM classifiers and generalized eigenvalue/singular value decompositions are successfully used in many bioinformatics applications for prediction tasks. While bringing up the benefits of these two techniques, we propose a machine learning approach, a weighted LS-SVM classifier to integrate two data sources: microarray and clinical parameters. RESULTS: We compared and evaluated the proposed methods on five breast cancer case studies. Compared to LS-SVM classifier on individual data sets, generalized eigenvalue decomposition (GEVD) and kernel GEVD, the proposed weighted LS-SVM classifier offers good prediction performance, in terms of test area under ROC Curve (AUC), on all breast cancer case studies. CONCLUSIONS: Thus a clinical classifier weighted with microarray data set results in significantly improved diagnosis, prognosis and prediction responses to therapy. The proposed model has been shown as a promising mathematical framework in both data fusion and non-linear classification problems.

Automated anatomical interpretation of ion distributions in tissue: linking imaging mass spectrometry to curated atlases.

Imaging mass spectrometry (IMS) has become a prime tool for studying the distribution of biomolecules in tissue. Although IMS data sets can become very large, computational methods have made it practically feasible to search these experiments for relevant findings. However, these methods lack access to an important source of information that many human interpretations rely upon: anatomical insight. In this work, we address this need by (1) integrating a curated anatomical data source with an empirically acquired IMS data source, establishing an algorithm-accessible link between them and (2) demonstrating the potential of such an IMS-anatomical atlas link by applying it toward automated anatomical interpretation of ion distributions in tissue. The concept is demonstrated in mouse brain tissue, using the Allen Mouse Brain Atlas as the curated anatomical data source that is linked to MALDI-based IMS experiments. We first develop a method to spatially map the anatomical atlas to the IMS data sets using nonrigid registration techniques. Once a mapping is established, a second computational method, called correlation-based querying, gives an elementary demonstration of the link by delivering basic insight into relationships between ion images and anatomical structures. Finally, a third algorithm moves further beyond both registration and correlation by providing automated anatomical interpretation of ion images. This task is approached as an optimization problem that deconstructs ion distributions as combinations of known anatomical structures. We demonstrate that establishing a link between an IMS experiment and an anatomical atlas enables automated anatomical annotation, which can serve as an important accelerator both for human and machine-guided exploration of IMS experiments.