Learning Bayesian networks for clinical time series analysis.

INTRODUCTION: Autonomous chronic disease management requires models that are able to interpret time series data from patients. However, construction of such models by means of machine learning requires the availability of costly health-care data, often resulting in small samples. We analysed data from chronic obstructive pulmonary disease (COPD) patients with the goal of constructing a model to predict the occurrence of exacerbation events, i.e., episodes of decreased pulmonary health status. METHODS: Data from 10 COPD patients, gathered with our home monitoring system, were used for temporal Bayesian network learning, combined with bootstrapping methods for data analysis of small data samples. For comparison a temporal variant of augmented naive Bayes models and a temporal nodes Bayesian network (TNBN) were constructed. The performances of the methods were first tested with synthetic data. Subsequently, different COPD models were compared to each other using an external validation data set. RESULTS: The model learning methods are capable of finding good predictive models for our COPD data. Model averaging over models based on bootstrap replications is able to find a good balance between true and false positive rates on predicting COPD exacerbation events. Temporal naive Bayes offers an alternative that trades some performance for a reduction in computation time and easier interpretation.

Using local context information to improve automatic mammographic mass detection.

Despite their promising application, current Computer-Aided Detection (CAD) systems face difficulties, especially in the detection of malignant masses -a major mammographic sign for breast cancer. One of the main problems is the large number of false positives prompted, which is a critical issue in screening programs where the number of normal cases is considerably large. A crucial determinant for this problem is the dependence of the CAD output on the single pixel-based locations initially detected. To refine the initial detection step, in this paper, we propose a novel approach by considering the context information between the neighbouring pixel features and classes for every initially detected suspicious location. Our modelling scheme is based on the Conditional Random Field technique and the mammographic features extracted by image processing techniques. In experimental study, we demonstrated the practical application of the approach and we compared its performance to that of a previously developed CAD system. The results demonstrated the superiority of the context modelling in terms of significantly improved accuracy without increase in computation efforts.

Improved mammographic CAD performance using multi-view information: a Bayesian network framework.

Mammographic reading by radiologists requires the comparison of at least two breast projections (views) for the detection and the diagnosis of breast abnormalities. Despite their reported potential to support radiologists, most mammographic computer-aided detection (CAD) systems have a major limitation: as opposed to the radiologist's practice, computerized systems analyze each view independently. To tackle this problem, in this paper, we propose a Bayesian network framework for multi-view mammographic analysis, with main focus on breast cancer detection at a patient level. We use causal-independence models and context modeling over the whole breast represented as links between the regions detected by a single-view CAD system in the two breast projections. The proposed approach is implemented and tested with screening mammograms for 1063 cases of whom 385 had breast cancer. The single-view CAD system is used as a benchmark method for comparison. The results show that our multi-view modeling leads to significantly better performance in discriminating between normal and cancerous patients. We also demonstrate the potential of our multi-view system for selecting the most suspicious cases.

Smartphone-based analysis of biochemical tests for health monitoring support at home.

In the context of home-based healthcare monitoring systems, it is desirable that the results obtained from biochemical tests - tests of various body fluids such as blood and urine - are objective and automatically generated to reduce the number of man-made errors. The authors present the StripTest reader - an innovative smartphone-based interpreter of biochemical tests based on paper-based strip colour using image processing techniques. The working principles of the reader include image acquisition of the colour strip pads using the camera phone, analysing the images within the phone and comparing them with reference colours provided by the manufacturer to obtain the test result. The detection of kidney damage was used as a scenario to illustrate the application of, and test, the StripTest reader. An extensive evaluation using laboratory and human urine samples demonstrates the reader's accuracy and precision of detection, indicating the successful development of a cheap, mobile and smart reader for home-monitoring of kidney functioning, which can facilitate the early detection of health problems and a timely treatment intervention.

On the interplay of machine learning and background knowledge in image interpretation by Bayesian networks.

OBJECTIVES: To obtain a balanced view on the role and place of expert knowledge and learning methods in building Bayesian networks for medical image interpretation. METHODS AND MATERIALS: The interpretation of mammograms was selected as the example medical image interpretation problem. Medical image interpretation has its own common standards and procedures. The impact of these on two complementary methods for Bayesian network construction was explored. Firstly, methods for the discretisation of continuous features were investigated, yielding multinomial distributions that were compared to the original Gaussian probabilistic parameters of the network. Secondly, the structure of a manually constructed Bayesian network was tested by structure learning from image data. The image data used for the research came from screening mammographic examinations of 795 patients, of whom 344 were cancerous. RESULTS: The experimental results show that there is an interesting interplay of machine learning results and background knowledge in medical image interpretation. Networks with discretised data lead to better classification performance (increase in the detected cancers of up to 11.7%), easier interpretation, and a better fit to the data in comparison to the expert-based Bayesian network with Gaussian probabilistic parameters. Gaussian probability distributions are often used in medical image interpretation because of the continuous nature of many of the image features. The structures learnt supported many of the expert-originated relationships but also revealed some novel relationships between the mammographic features. Using discretised features and performing structure learning on the mammographic data has further improved the cancer detection performance of up to 17% compared to the manually constructed Bayesian network model. CONCLUSION: Finding the right balance between expert knowledge and data-derived knowledge, both at the level of network structure and parameters, is key to using Bayesian networks for medical image interpretation. A balanced approach to building Bayesian networks for image interpretation yields more accurate and understandable Bayesian network models.

A probabilistic framework for image information fusion with an application to mammographic analysis.

The recent increased interest in information fusion methods for solving complex problem, such as in image analysis, is motivated by the wish to better exploit the multitude of information, available from different sources, to enhance decision-making. In this paper, we propose a novel method, that advances the state of the art of fusing image information from different views, based on a special class of probabilistic graphical models, called causal independence models. The strength of this method is its ability to systematically and naturally capture uncertain domain knowledge, while performing information fusion in a computationally efficient way. We examine the value of the method for mammographic analysis and demonstrate its advantages in terms of explicit knowledge representation and accuracy (increase of at least 6.3% and 5.2% of true positive detection rates at 5% and 10% false positive rates) in comparison with previous single-view and multi-view systems, and benchmark fusion methods such as naïve Bayes and logistic regression.

Monotone and partially monotone neural networks.

In many classification and prediction problems it is known that the response variable depends on certain explanatory variables. Monotone neural networks can be used as powerful tools to build monotone models with better accuracy and lower variance compared to ordinary nonmonotone models. Monotonicity is usually obtained by putting constraints on the parameters of the network. In this paper, we will clarify some of the theoretical results on monotone neural networks with positive weights, issues that are sometimes misunderstood in the neural network literature. Furthermore, we will generalize some of the results obtained by Sill for the so-called min-max networks to the case of partially monotone problems. The method is illustrated in practical case studies.

Comparison of universal approximators incorporating partial monotonicity by structure.

Neural networks applied in control loops and safety-critical domains have to meet more requirements than just the overall best function approximation. On the one hand, a small approximation error is required; on the other hand, the smoothness and the monotonicity of selected input-output relations have to be guaranteed. Otherwise, the stability of most of the control laws is lost. In this article we compare two neural network-based approaches incorporating partial monotonicity by structure, namely the Monotonic Multi-Layer Perceptron (MONMLP) network and the Monotonic MIN-MAX (MONMM) network. We show the universal approximation capabilities of both types of network for partially monotone functions. On a number of datasets, we investigate the advantages and disadvantages of these approaches related to approximation performance, training of the model and convergence.