Search PubMed⌕ Search

Biomedical subjects

Torsten Hothorn

Publications and source records attributed to Torsten Hothorn.

12 recordsLinked to original sources
PubMed2006

Model-based boosting in high dimensions.

SUMMARY: The R add-on package mboost implements functional gradient descent algorithms (boosting) for optimizing general loss functions utilizing componentwise least squares, either of parametric linear form or smoothing splines, or regression trees as base learners for fitting generalized linear, additive and interaction models to potentially high-dimensional data. AVAILABILITY: Package mboost is available from the Comprehensive R Archive Network (http://CRAN.R-project.org) under the terms of the General Public Licence (GPL).

Algorithms↗
PubMed2005

Survival ensembles.

We propose a unified and flexible framework for ensemble learning in the presence of censoring. For right-censored data, we introduce a random forest algorithm and a generic gradient boosting algorithm for the construction of prognostic and diagnostic models. The methodology is utilized for predicting the survival time of patients suffering from acute myeloid leukemia based on clinical and genetic covariates. Furthermore, we compare the diagnostic capabilities of the proposed censored data random forest and boosting methods, applied to the recurrence-free survival time of node-positive breast cancer patients, with previously published findings.

Algorithms↗
PubMed2005

Improved prediction of body fat by measuring skinfold thickness, circumferences, and bone breadths.

OBJECTIVE: To develop improved predictive regression equations for body fat content derived from common anthropometric measurements. RESEARCH METHODS AND PROCEDURES: 117 healthy German subjects, 46 men and 71 women, 26 to 67 years of age, from two different studies were assigned to a validation and a cross-validation group. Common anthropometric measurements and body composition by DXA were obtained. Equations using anthropometric measurements predicting body fat mass (BFM) with DXA as a reference method were developed using regression models. RESULTS: The final best predictive sex-specific equations combining skinfold thicknesses (SF), circumferences, and bone breadth measurements were as follows: BFM(New) (kg) for men = -40.750 + {(0.397 x waist circumference) + [6.568 x (log triceps SF + log subscapular SF + log abdominal SF)]} and BFM(New) (kg) for women = -75.231 + {(0.512 x hip circumference) + [8.889 x (log chin SF + log triceps SF + log subscapular SF)] + (1.905 x knee breadth)}. The estimates of BFM from both validation and cross-validation had an excellent correlation, showed excellent correspondence to the DXA estimates, and showed a negligible tendency to underestimate percent body fat in subjects with higher BFM compared with equations using a two-compartment (Durnin and Womersley) or a four-compartment (Peterson) model as the reference method. DISCUSSION: Combining skinfold thicknesses with circumference and/or bone breadth measures provide a more precise prediction of percent body fat in comparison with established SF equations. Our equations are recommended for use in clinical or epidemiological settings in populations with similar ethnic background.

Absorptiometry, Photon↗
PubMed2005

Increased uterine arterial pressure and contractility of perfused swine uterus after treatment with serum from pre-eclamptic women and endothelin-1.

The present study was designed to examine the effects of ET-1 (endothelin-1) and serum from PE (pre-eclamptic), HP (healthy pregnant) and HNP (healthy non-pregnant) women on uterine arterial perfusion pressure and uterine contractility. Swine uteri (n = 25) were perfused for a period of up to 11 h, with the aim being to preserve a viable organ. Various concentrations of ET-1 as well as serum from PE, HP and HNP women (n = 10 per group) were administered to the perfused swine uteri and IUP (intrauterine pressure) and IAP (intra-arterial pressure) were recorded. ET-1 produced dose-dependent increases in IUP and IAP. The ET-1 concentration in serum was higher in serum from PE women than in HP and HNP women (P > 0.05). Administration of all serum samples had a contractile effect on the swine uterus, with the greatest effect being seen in HNP women (12.8 +/- 5.3 mmHg), followed by PE (9.06 +/- 4.2 mmHg) and HP (6.1 +/- 4.1 mmHg) women. Statistically significant differences were observed between HNP and PE women (P = 0.048), and PE and HP women (P = 0.021). Increases in IAP following administration of serum from PE women (48.8 +/- 20.0 mmHg) were significantly higher (P = 0.024) compared with the effect of serum from HP women (28.4 +/- 13.7 mmHg). In conclusion, the findings show that serum from PE women has significant vasoconstrictive and oxytocic effects compared with serum from HP women. In pre-eclampsia, the balance between vasorelaxing and vasoactive substances is disturbed.

Animals↗
PubMed2004

Multiplanar functional imaging of the larynx and hypopharynx with multislice spiral CT.

The purpose of this study is to evaluate multislice spiral CT (MSCT) in multiplanar functional imaging of the larynx and hypopharynx and to define the optimal image planes for the delineation of the tumor and specific anatomical structures. Forty patients with suspected tumors of the larynx or hypopharynx were examined with MSCT during quiet breathing (QB), E-phonation (EP) and modified Valsalva maneuver (VM). Images were read in the axial, coronal and sagittal planes. Overall image quality, delineation of the tumor and anatomic structures for different conditions and orientations were graded using a three-point scale; the conditional permutation test was applied to detect quality differences. Differences between image types were statistically significant. The axial plane was superior in overall image quality and the delineation of the tumor, pyriform sinus, vocal cords and fat within the parapharyngeal/visceral space. The coronal plane was best for delineating the ventricle and the paraglottic space, the sagittal plane for the retropharyngeal and the preepiglottic space. For tumor detection, sensitivity, specificity and accuracy were 0.92, 1.0 and 0.93 for QB.ax, 0.94, 0.8 and 0.92 for EP.ax and 0.85, 1.0 and 0.87 for VM.ax, respectively. Examination during QB should be the standard procedure; additional scanning with EP improved tumor assessment.

Female↗
PubMed2004

Bioconductor: open software development for computational biology and bioinformatics.

The Bioconductor project is an initiative for the collaborative creation of extensible software for computational biology and bioinformatics. The goals of the project include: fostering collaborative development and widespread use of innovative software, reducing barriers to entry into interdisciplinary scientific research, and promoting the achievement of remote reproducibility of research results. We describe details of our aims and methods, identify current challenges, compare Bioconductor to other open bioinformatics projects, and provide working examples.

Computational Biology↗
PubMed2004

Bagging survival trees.

Predicted survival probability functions of censored event free survival are improved by bagging survival trees. We suggest a new method to aggregate survival trees in order to obtain better predictions for breast cancer and lymphoma patients. A set of survival trees based on B bootstrap samples is computed. We define the aggregated Kaplan-Meier curve of a new observation by the Kaplan-Meier curve of all observations identified by the B leaves containing the new observation. The integrated Brier score is used for the evaluation of predictive models. We analyse data of a large trial on node positive breast cancer patients conducted by the German Breast Cancer Study Group and a smaller 'pilot' study on diffuse large B-cell lymphoma, where prognostic factors are derived from microarray expression values. In addition, simulation experiments underline the predictive power of our proposal.

Breast Neoplasms↗
PubMed2003

Bagging tree classifiers for laser scanning images: a data- and simulation-based strategy.

Diagnosis based on medical image data is common in medical decision making and clinical routine. We discuss a strategy to derive a classifier with good performance on clinical image data and to justify the properties of the classifier by an adapted simulation model of image data. We focus on the problem of classifying eyes as normal or glaucomatous based on 62 routine explanatory variables derived from laser scanning images of the optic nerve head. As learning sample we use a case-control study of 98 normal and 98 glaucomatous subjects matched by age and sex. Aggregating multiple unstable classifiers allows substantial reduction of misclassification error in many applications and bench mark problems. We investigate the performance of various classifiers for the clinical learning sample as well as for a simulation model of eye morphologies. Bagged classification trees (bagged-CTREE) are compared to single classification trees and linear discriminant analysis (LDA). We additionally compare three estimators of misclassification error: 10-fold cross-validation, the 0.632+ bootstrap and the out-of-bag estimate. In summary, the application of our strategy of a knowledge-based decision support shows that bagged classification trees perform best for glaucoma classification.

Case-Control Studies↗
PubMed2003

New glaucoma classification method based on standard Heidelberg Retina Tomograph parameters by bagging classification trees.

PURPOSE: In this article we propose and evaluate nonparametric tree classifiers that can handle non-normal data and a large number of possible predictors using the full set of standard Heidelberg Retina Tomograph measurements for classifying glaucoma. METHODS: The classifiers were trained and tested using standard Heidelberg Retina Tomograph parameters from examinations of 98 subjects with glaucoma and 98 normal subjects of the Erlangen Glaucoma Registry. All patients and control subjects were evaluated by 15 degrees -optic disc stereographs, Heidelberg Retina Tomograph measurements, standard computerized white-in-white perimetry, and 24-hour-intraocular pressure profiles. The subjects were matched by age and sex. Standard classification trees as well as bagged classification trees were used. The classification outcome of the trees was compared with the classification by two published linear discriminant functions based on Heidelberg Retina Tomograph variables with respect to their cross-validated misclassification error. RESULTS: The bagged classification tree had the lowest misclassification error estimate of 14.8% with a sensitivity of 81.6% at a specificity of 88.8%. The cross-validated error rates of the two linear discriminant function procedures were 20.4% (sensitivity 82.6%, specificity 76.7%) and 20.6% (sensitivity 81.4%, specificity 77.3%) for our set of observations. Bagged classification trees were able to reduce the misclassification error of glaucoma classification. CONCLUSIONS: Bagged classification trees promise to be a new and efficient approach for glaucoma classification using morphometric 2- and 3-dimensional data derived from the Heidelberg Retina Tomograph, taking into account all given variables.

Case-Control Studies↗
PubMed2003

The role of control groups in mutagenicity studies: matching biological and statistical relevance.

The statistical test of the conventional hypothesis of "no treatment effect" is commonly used in the evaluation of mutagenicity experiments. Failing to reject the hypothesis often leads to the conclusion in favour of safety. The major drawback of this indirect approach is that what is controlled by a prespecified level alpha is the probability of erroneously concluding hazard (producer risk). However, the primary concern of safety assessment is the control of the consumer risk, i.e. limiting the probability of erroneously concluding that a product is safe. In order to restrict this risk, safety has to be formulated as the alternative, and hazard, i.e. the opposite, has to be formulated as the hypothesis. The direct safety approach is examined for the case when the corresponding threshold value is expressed either as a fraction of the population mean for the negative control, or as a fraction of the difference between the positive and negative controls.

Animal Testing Alternatives↗
PubMed2002

Longitudinal concentrations of vitamin B(12) and vitamin B(12)-binding proteins during uncomplicated pregnancy.

BACKGROUND: Because reference values for vitamin B(12) concentrations and vitamin B(12)-binding capacities for pregnant women have not been established, the reference values for nonpregnant women are often applied to assess vitamin B(12) status. The aim of the present study was to describe ranges of biochemical indices of vitamin B(12) status, including red blood cell (RBC) vitamin B(12), saturated and unsaturated cobalamin-binding proteins, and binding capacities in all trimesters of uncomplicated pregnancy. METHODS: A total of 39 healthy pregnant women with long-term daily intake of vitamin B(12) >2.6 microg/day and uncomplicated pregnancies participated in the study throughout their pregnancies. RBCs and serum vitamin B(12), holo-haptocorrin, unsaturated cobalamin-binding proteins, unsaturated and total vitamin B(12)-binding capacities, total homocysteine (tHcy), and RBC count were assessed in weeks 9-12, 20-22, and 36-38 of gestation. RESULTS: Significant changes in vitamin B(12) status occurred in the course of pregnancy. Serum vitamin B(12) concentrations and percentage of saturation of vitamin B(12)-binding proteins decreased steadily throughout pregnancy. In the third trimester, 35% of the participants had serum vitamin B(12) concentrations <150 pmol/L and 68.6% had <15% saturation of total vitamin B(12)-binding capacities, but no women had RBC vitamin B(12) concentrations <148 pmol/L. However, the decrease in these indices was not associated with reduced hemoglobin concentrations or RBC count or with increased tHcy concentrations. CONCLUSIONS: Our findings suggest that the reference values for vitamin B(12) status in nonpregnant women may not be applicable to pregnant women.

Diet↗