Search PubMed⌕ Search

Biomedical subjects

B De Moor

Publications and source records attributed to B De Moor.

At least 19 recordsLinked to original sources
PubMed2006

An adaptive input-output modeling approach for predicting the glycemia of critically ill patients.

In this paper we apply system identification techniques in order to build a model suitable for the prediction of glycemia levels of critically ill patients admitted to the intensive care unit. These patients typically show increased glycemia levels, and it has been shown that glycemia control by means of insulin therapy significantly reduces morbidity and mortality. Based on a real-life dataset from 15 critically ill patients, an initial input-output model is estimated which captures the insulin effect on glycemia under different settings. To incorporate patient-specific features, an adaptive modeling strategy is also proposed in which the model is re-estimated at each time step (i.e., every hour). Both one-hour-ahead predictions and four-hours-ahead simulations are executed. The optimized adaptive modeling technique outperforms the general initial model. To avoid data selection bias, 500 permutations, in which the patients are randomly selected, are considered. The results are satisfactory both in terms of forecasting ability and in the clinical interpretation of the estimated coefficients.

Aged↗
PubMed2006

Predicting the outcome of pregnancies of unknown location: Bayesian networks with expert prior information compared to logistic regression.

BACKGROUND: As women present at earlier gestations to early pregnancy units (EPUs), the number of women diagnosed with a pregnancy of unknown location (PUL) increases. Some of these women will have an ectopic pregnancy (EP), and it is this group in the PUL population that poses the greatest concern. The aim of this study was to develop Bayesian networks to predict EPs in the PUL population. METHODS: Data were gathered in a single EPU from all women with a PUL. This data set was divided into a model-building (599 women with 44 EPs) and a validation (257 women with 22 EPs) data set and consisted of the following variables: vaginal bleeding, fluid in the pouch of Douglas, midline echo, lower abdominal pain, age, endometrial thickness, gestation days, the ratio of HCG at 48 and 0 h, progesterone levels (0 and 48 h) and the clinical outcome of the PUL. We developed Bayesian networks with expert information using this data set to predict EPs. RESULTS: The best Bayesian network used the gestational age, HCG ratio and the progesterone level at 48 h and had an area under the receiver operator characteristic curve (AUC) of 0.88 for predicting EPs when tested prospectively. CONCLUSIONS: Discrete-valued Bayesian networks are more complex to build than, for example, logistic regression. Nevertheless, we have demonstrated that such models can be used to predict EPs in a PUL population. Prospective interventional multicentre studies are needed to validate the use of such models in clinical practice.

Adolescent↗
PubMed2006

Emerging patterns of cryptic chromosomal imbalance in patients with idiopathic mental retardation and multiple congenital anomalies: a new series of 140 patients and review of published reports.

BACKGROUND: Chromosomal abnormalities are a major cause of mental retardation and multiple congenital anomalies (MCA/MR). Screening for these chromosomal imbalances has mainly been done by standard karyotyping. Previous array CGH studies on selected patients with chromosomal phenotypes and normal karyotypes suggested an incidence of 10-15% of previously unnoticed de novo chromosomal imbalances. OBJECTIVE: To report array CGH screening of a series of 140 patients (the largest published so far) with idiopathic MCA/MR but normal karyotype. RESULTS: Submicroscopic chromosomal imbalances were detected in 28 of the 140 patients (20%) and included 18 deletions, seven duplications, and three unbalanced translocations. Seventeen of 24 imbalances were confirmed de novo and 19 were assumed to be causal. Excluding subtelomeric imbalances, our study identified 11 clinically relevant interstitial submicroscopic imbalances (8%). Taking this and previously reported studies into consideration, array CGH screening with a resolution of at least 1 Mb has been undertaken on 432 patients with MCA/MR. Most imbalances are non-recurrent and spread across the genome. In at least 8.8% of these patients (38 of 432) de novo intrachromosomal alterations have been identified. CONCLUSIONS: Array CGH should be considered an essential aspect of the genetic analysis of patients with MCA/MR. In addition, in the present study three patients were mosaic for a structural chromosome rearrangement. One of these patients had monosomy 7 in as few as 8% of the cells, showing that array CGH allows detection of low grade mosaicisims.

Abnormalities, Multiple↗
PubMed2006

Three-dimensional ultrasound assessment of the cervix for predicting time to spontaneous onset of labor and time to delivery in prolonged pregnancy.

OBJECTIVES: To determine whether three-dimensional (3D) ultrasound including power Doppler examination of the cervix is useful for predicting time to spontaneous onset of labor or time to delivery in prolonged pregnancy. METHODS: A prospective study was conducted in 60 women who went into spontaneous labor. All underwent transvaginal 3D power Doppler ultrasound examination of the cervix immediately before a prolonged-pregnancy check-up at > or = 41 + 5 gestational weeks. Univariate and multivariate logistic regression analysis was used to determine which of the following variables predicted spontaneous onset of labor > 24 h and > 48 h and vaginal delivery > 48 h and > 60 h: length, anteroposterior (AP) diameter and width of the cervix and of any cervical funneling; cervical volume (cm3); vascularization index (VI); flow index (FI); vascularization flow index (VFI); parity; and Bishop score. Multivariate logistic regression analysis was carried out both with and without Bishop score as a predictive variable. Receiver-operating characteristics (ROC) curves were used to describe the diagnostic performance of the tests. RESULTS: The areas under the ROC curves for Bishop score, cervical length, and logistic regression models did not differ significantly (areas ranging from 0.72 to 0.82). If Bishop score was not included in the logistic regression model, cervical length, VI and FI independently predicted delivery > 48 h, the likelihood increasing with increasing cervical length, decreasing VI and increasing FI. CONCLUSIONS: In prolonged pregnancy cervical vascularization as estimated by 3D power Doppler ultrasound is related to time to delivery > 48 h, but the likelihood of delivery > 48 h can be predicted equally well using Bishop score alone or sonographic cervical length alone.

Adult↗
PubMed2006

New models to predict depth of infiltration in endometrial carcinoma based on transvaginal sonography.

OBJECTIVES: Preoperative knowledge of the depth of myometrial infiltration is important in patients with endometrial carcinoma. This study aimed at assessing the value of histopathological parameters obtained from an endometrial biopsy (Pipelle de Cornier; results available preoperatively) and ultrasound measurements obtained after transvaginal sonography with color Doppler imaging in the preoperative prediction of the depth of myometrial invasion, as determined by the final histopathological examination of the hysterectomy specimen (the gold standard). METHODS: We first collected ultrasound and histopathological data from 97 consecutive women with endometrial carcinoma and divided them into two groups according to surgical stage (Stages Ia and Ib vs. Stages Ic and higher). The areas (AUC) under the receiver-operating characteristics curves of the subjective assessment of depth of invasion by an experienced gynecologist and of the individual ultrasound parameters were calculated. Subsequently, we used these variables to train a logistic regression model and least squares support vector machines (LS-SVM) with linear and RBF (radial basis function) kernels. Finally, these models were validated prospectively on data from 76 new patients in order to make a preoperative prediction of the depth of invasion. RESULTS: Of all ultrasound parameters, the ratio of the endometrial and uterine volumes had the largest AUC (78%), while that of the subjective assessment was 79%. The AUCs of the blood flow indices were low (range, 51-64%). Stepwise logistic regression selected the degree of differentiation, the number of fibroids, the endometrial thickness and the volume of the tumor. Compared with the AUC of the subjective assessment (72%), prospective evaluation of the mathematical models resulted in a higher AUC for the LS-SVM model with an RBF kernel (77%), but this difference was not significant. CONCLUSIONS: Single morphological parameters do not improve the predictive power when compared with the subjective assessment of depth of myometrial invasion of endometrial cancer, and blood flow indices do not contribute to the prediction of stage. In this study an LS-SVM model with an RBF kernel gave the best prediction; while this might be more reliable than subjective assessment, confirmation by larger prospective studies is required.

Aged↗
PubMed2005

Diagnostic accuracy of varying discriminatory zones for the prediction of ectopic pregnancy in women with a pregnancy of unknown location.

OBJECTIVES: Various serum human chorionic gonadotropin (hCG) discriminatory zones are currently used for evaluating the likelihood of an ectopic pregnancy in women classified as having a pregnancy of unknown location (PUL) following a transvaginal ultrasound examination. We evaluated the diagnostic accuracy of discriminatory zones for serum hCG levels of > 1000 IU/L, 1500 IU/L and 2000 IU/L for the detection of ectopic pregnancy in such women. METHODS: This was a prospective observational study of women who were assessed in a specialized transvaginal scanning unit. All women with a PUL had serum hCG measured at presentation. Expectant management of PULs was adopted. These women were followed up with transvaginal ultrasound, monitoring of serum hormone levels and laparoscopy until a final diagnosis was established: a failing PUL, an intrauterine pregnancy (IUP), an ectopic pregnancy or a persisting PUL. The persisting PULs probably represented ectopic pregnancies which had been missed on ultrasound and these were incorporated into the ectopic pregnancy group. Three different discriminatory zones (1000 IU/L, 1500 IU/L and 2000 IU/L) were evaluated for predicting ectopic pregnancy in this PUL population. RESULTS: A total of 5544 consecutive women presented to the early pregnancy unit between 25 June 2001 and 14 April 2003. Of these, 569 (10.3%) women were classified as having a PUL, 42 of which were lost to follow up. Of the 527 (9.5%) cases with PUL analyzed, there were 300 (56.9%) failing PULs, 181 (34.3%) IUPs and 46 (8.7%) ectopic pregnancies. Overall, 74.6% were symptomatic and 25.4% were asymptomatic (P = 8.825E-07). The sensitivity and specificity of an hCG level of > 1000 IU/L to detect ectopic pregnancy were 21.7% (10/46) and 87.3% (420/481), respectively; for an hCG level of > 1500 IU/L these values were 15.2% (7/46) and 93.4% (449/481), respectively, and for an hCG level of > 2000 IU/L they were 10.9% (5/46) and 95.2% (458/481), respectively. CONCLUSIONS: Varying the discriminatory zone does not significantly improve the detection of ectopic pregnancy in a PUL population. A single measurement of serum hCG is not only potentially falsely reassuring but also unhelpful in excluding the presence of an ectopic pregnancy.

Biomarkers↗
PubMed2004

Balancing false positives and false negatives for the detection of differential expression in malignancies.

A basic problem of microarray data analysis is to identify genes whose expression is affected by the distinction between malignancies with different properties. These genes are said to be differentially expressed. Differential expression can be detected by selecting the genes with P-values (derived using an appropriate hypothesis test) below a certain rejection level. This selection, however, is not possible without accepting some false positives and negatives since the two sets of P-values, associated with the genes whose expression is and is not affected by the distinction between the different malignancies, overlap. We describe a procedure for the study of differential expression in microarray data based on receiver-operating characteristic curves. This approach can be useful to select a rejection level that balances the number of false positives and negatives and to assess the degree of overlap between the two sets of P-values. Since this degree of overlap characterises the balance that can be reached between the number of false positives and negatives, this quantity can be seen as a quality measure of microarray data with respect to the detection of differential expression. As an example, we apply our method to data sets studying acute leukaemia.

False Negative Reactions↗
PubMed2003

Evaluation of the vector space representation in text-based gene clustering.

Thanks to its increasing availability, electronic literature can now be a major source of information when developing complex statistical models where data is scarce or contains much noise. This raises the question of how to deeply integrate information from domain literature with experimental data. Evaluating what kind of statistical text representations can integrate literature knowledge in clustering still remains an unsufficiently explored topic. In this work we discuss how the bag-of-words representation can be used successfully to represent genetic annotation and free-text information coming from different databases. We demonstrate the effect of various weighting schemes and information sources in a functional clustering setup. As a quantitative evaluation, we contrast for different parameter settings the functional groupings obtained from text with those obtained from expert assessments and link each of the results to a biological discussion.

Artificial Intelligence↗
PubMed2003

Probabilistic graphical models for computational biomedicine.

BACKGROUND: As genomics becomes increasingly relevant to medicine, medical informatics and bioinformatics are gradually converging into a larger field that we call computational biomedicine. OBJECTIVES: Developing a computational framework that is common to the different disciplines that compose computational biomedicine will be a major enabler of the further development and integration of this research domain. METHODS: Probabilistic graphical models such as Hidden Markov Models, belief networks, and missing-data models together with computational methods such as dynamic programming, Expectation-Maximization, data-augmentation Gibbs sampling, and the Metropolis-Hastings algorithm provide the tools for an integrated probabilistic approach to computational biomedicine. RESULTS AND CONCLUSIONS: We show how graphical models have already found a broad application in different fields composing computational biomedicine. We also indicate several challenges that lie at the interface between medical informatics, statistical genomics, and bioinformatics. We also argue that graphical models offer a unified framework making it possible to integrate in a statistically meaningful way multiple models ranging from the molecular level to cellular and to clinical levels. Because of their versatility and firm statistical underpinning, we assert that probabilistic graphical models can serve as the lingua franca for many computationally intensive approaches to biology and medicine. As such, graphical models should be a foundation of the curriculum of students in these fields. From such a foundation, students could then build towards specific computational methods in medical informatics, medical image analysis, statistical genetics, or bioinformatics while keeping the communication open between these areas.

Computational Biology↗
PubMed2002

An algorithm including results of gray-scale and power Doppler ultrasound examination to predict endometrial malignancy in women with postmenopausal bleeding.

OBJECTIVE: To determine if power Doppler ultrasound examination of the endometrium can contribute to a correct diagnosis of endometrial malignancy in women with postmenopausal bleeding and endometrium > or = 5 mm. METHODS: Eighty-three women with postmenopausal bleeding and endometrium > or = 5 mm underwent gray-scale and power Doppler ultrasound examination using predetermined, standardized settings. Suspicion of endometrial malignancy at gray-scale ultrasound examination (endometrial morphology) was noted, and the color content of the endometrium at power Doppler examination was estimated subjectively (endometrial color score). Computer analysis of the most vascularized area of the endometrium was done off-line in a standardized manner. Stepwise multivariate logistic regression analysis was carried out to determine which subjective and objective ultrasound and power Doppler variables satisfied the criteria to be included in a model to calculate the probability of endometrial malignancy. RESULTS: Endometrial thickness, vascularity index (vascularized area/endometrial area), and use of hormone replacement therapy (HRT) satisfied the criteria to be included in the model used to calculate the 'objective probability of endometrial malignancy'. Endometrial morphology, endometrial color score and HRT use satisfied the criteria to be included in the model to calculate the 'subjective probability of malignancy'. Endometrial thickness > or = 10.5 mm had a sensitivity with regard to endometrial cancer of 0.88 and a specificity of 0.61. At a fixed sensitivity of 0.88, the specificity of the 'objective probability of malignancy' (0.81) was superior to all other ultrasound and power Doppler variables (P = 0.001-0.02). The 'objective probability of malignancy' detected more malignancies at endometrium 5-15 mm than endometrial morphology (5/7 vs. 1/7, i.e. 0.71 vs. 0.14; P = 0.125) with a similar specificity (49/57 vs. 51/57, i.e. 0.86 vs. 0.89). CONCLUSION: Power Doppler ultrasound can contribute to a correct diagnosis of endometrial malignancy, especially if the endometrium measures 5-15 mm. The use of regression models including power Doppler results to estimate the risk of endometrial cancer deserves further development.

Aged↗
PubMed2002

Bayesian framework for least-squares support vector machine classifiers, gaussian processes, and kernel Fisher discriminant analysis.

The Bayesian evidence framework has been successfully applied to the design of multilayer perceptrons (MLPs) in the work of MacKay. Nevertheless, the training of MLPs suffers from drawbacks like the nonconvex optimization problem and the choice of the number of hidden units. In support vector machines (SVMs) for classification, as introduced by Vapnik, a nonlinear decision boundary is obtained by mapping the input vector first in a nonlinear way to a high-dimensional kernel-induced feature space in which a linear large margin classifier is constructed. Practical expressions are formulated in the dual space in terms of the related kernel function, and the solution follows from a (convex) quadratic programming (QP) problem. In least-squares SVMs (LS-SVMs), the SVM problem formulation is modified by introducing a least-squares cost function and equality instead of inequality constraints, and the solution follows from a linear system in the dual space. Implicitly, the least-squares formulation corresponds to a regression formulation and is also related to kernel Fisher discriminant analysis. The least-squares regression formulation has advantages for deriving analytic expressions in a Bayesian evidence framework, in contrast to the classification formulations used, for example, in gaussian processes (GPs). The LS-SVM formulation has clear primal-dual interpretations, and without the bias term, one explicitly constructs a model that yields the same expressions as have been obtained with GPs for regression. In this article, the Bayesian evidence framework is combined with the LS-SVM classifier formulation. Starting from the feature space formulation, analytic expressions are obtained in the dual space on the different levels of Bayesian inference, while posterior class probabilities are obtained by marginalizing over the model parameters. Empirical results obtained on 10 public domain data sets show that the LS-SVM classifier designed within the Bayesian evidence framework consistently yields good generalization performances.

Artificial Intelligence↗
PubMed2001

Asymptotic relative entropy of entanglement.

We present an analytical formula for the asymptotic relative entropy of entanglement with respect to positive partial transpose states for Werner states of arbitrary dimension. We then demonstrate its validity using methods from convex optimization. This is the first case in which the asymptotic value of a subadditive entanglement measure has been calculated.

Journal Article↗
PubMed2001

Optimal control by least squares support vector machines.

Support vector machines have been very successful in pattern recognition and function estimation problems. In this paper we introduce the use of least squares support vector machines (LS-SVM's) for the optimal control of nonlinear systems. Linear and neural full static state feedback controllers are considered. The problem is formulated in such a way that it incorporates the N-stage optimal control problem as well as a least squares support vector machine approach for mapping the state space into the action space. The solution is characterized by a set of nonlinear equations. An alternative formulation as a constrained nonlinear optimization problem in less unknowns is given, together with a method for imposing local stability in the LS-SVM control scheme. The results are discussed for support vector machines with radial basis function kernel. Advantages of LS-SVM control are that no number of hidden units has to be determined for the controller and that no centers have to be specified for the Gaussian kernels when applying Mercer's condition. The curse of dimensionality is avoided in comparison with defining a regular grid for the centers in classical radial basis function networks. This is at the expense of taking the trajectory of state variables as additional unknowns in the optimization problem, while classical neural network approaches typically lead to parametric optimization problems. In the SVM methodology the number of unknowns equals the number of training data, while in the primal space the number of unknowns can be infinite dimensional. The method is illustrated both on stabilization and tracking problems including examples on swinging up an inverted pendulum with local stabilization at the endpoint and a tracking problem for a ball and beam system.

Feedback↗
PubMed2001

A higher-order background model improves the detection of promoter regulatory elements by Gibbs sampling.

MOTIVATION: Transcriptome analysis allows detection and clustering of genes that are coexpressed under various biological circumstances. Under the assumption that coregulated genes share cis-acting regulatory elements, it is important to investigate the upstream sequences controlling the transcription of these genes. To improve the robustness of the Gibbs sampling algorithm to noisy data sets we propose an extension of this algorithm for motif finding with a higher-order background model. RESULTS: Simulated data and real biological data sets with well-described regulatory elements are used to test the influence of the different background models on the performance of the motif detection algorithm. We show that the use of a higher-order model considerably enhances the performance of our motif finding algorithm in the presence of noisy data. For Arabidopsis thaliana, a reliable background model based on a set of carefully selected intergenic sequences was constructed. AVAILABILITY: Our implementation of the Gibbs sampler called the Motif Sampler can be used through a web interface: http://www.esat.kuleuven.ac.be/~thijs/Work/MotifSampler.html. CONTACT: gert.thijs@esat.kuleuven.ac.be; yves.moreau@esat.kuleuven.ac.be

Algorithms↗
PubMed2001

Improved long-term temperature prediction by chaining of neural networks.

When an artificial neural network (ANN) is trained to predict signals p steps ahead, the quality of the prediction typically decreases for large values of p. In this paper, we compare two methods for prediction with ANNs: the classical recursion of one-step ahead predictors and a new kind of chain structure. When applying both techniques to the prediction of the temperature at the end of a blast furnace, we conclude that the chaining approach leads to an improved prediction of the temperature and avoidance of instabilities, since the chained networks gradually take the prediction of their predecessors in the chain as an extra input. It is observed that instabilities might occur in the iterative case, which does not happen with the chaining approach. To select relevant inputs and decrease the number of weights in this approach, Automatic Relevance Determination (ARD) for multilayer perceptrons is applied.

Bayes Theorem↗
PubMed2000

Fetal electrocardiogram extraction by blind source subspace separation.

In this paper, we propose the emerging technique of independent component analysis, also known as blind source separation, as an interesting tool for the extraction of the antepartum fetal electrocardiogram from multilead cutaneous potential recordings. The technique is illustrated by means of a real-life example.

Algorithms↗
PubMed1999

Artificial neural network models for the preoperative discrimination between malignant and benign adnexal masses.

OBJECTIVE: The aim of this study was to generate and evaluate artificial neural network (ANN) models from simple clinical and ultrasound-derived criteria to predict whether or not an adnexal mass will have histological evidence of malignancy. DESIGN: The data were collected prospectively from 173 consecutive patients who were scheduled to undergo surgical investigations at the University Hospitals, Leuven, between August 1994 and August 1996. The outcome measure was the histological classification of excised tissues as malignant (including borderline) or benign. METHODS: Age, menopausal status and serum CA 125 levels and sonographic features of the adnexal mass were encoded as variables. The ANNs were trained on a randomly selected set of 116 patient records and tested on the remainder (n = 57). The performance of each model was evaluated using receiver operating characteristic (ROC) curves and compared with corresponding data from an established risk of malignancy index (RMI) and a logistic regression model. RESULTS: There were 124 benign masses, five of borderline malignancy and 44 invasive cancers (of which 29% were metastatic); 37% of patients with a malignant or borderline tumor had stage I disease. The best ANN gave an area under the ROC curve of 0.979 for the whole dataset, a sensitivity of 95.9% and specificity of 93.5%. The corresponding values for the RMI were 0.882, 67.3% and 91.1%, and for the logistic regression model 0.956, 95.9% and 85.5%, respectively. CONCLUSION: An ANN can be trained to provide clinically accurate information, on whether or not an adnexal mass is malignant, from the patient's menopausal status, serum CA 125 levels, and some simple ultrasonographic criteria.

Adnexal Diseases↗