Biomedical subjects

Berthold Lausen

Publications and source records attributed to Berthold Lausen.

5 recordsLinked to original sources

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

Results and complications of hydrophobic acrylic vs PMMA posterior chamber lenses in children under 17 years of age.

PURPOSE: To compare results and complications of implantation of hydrophobic acrylic foldable intraocular lenses in children with those of polymethylmethacrylate (PMMA) intraocular lenses. METHODS: In a retrospective study, we analyzed results of cataract surgery with posterior chamber lens implantation in 30 eyes of 30 patients aged 1-16 years. In 10 eyes, acrylic (Alcon AcrySof) intraocular lenses, and in 20 eyes, single-piece PMMA posterior chamber lenses were implanted. Indications for cataract surgery (blunt or penetrating trauma, zonular cataract, cataracta polaris posterior, posterior lenticonus) and mean age at implantation were comparable in the two groups. Mean patient age at surgery was 8.6+/-4.6 years (range 3-16 years) for the acrylic vs 6.3+/-4.3 years (range 1-16 years) for the PMMA group. Mean follow-up was 1.0+/-0.7 years (range 0.1-2.2 years) in the acrylic group and 1.8+/-1.5 years (range 0.1-5.7 years) in the PMMA group. Primary anterior vitrectomy was performed in 7 eyes in the PMMA group and in 3 eyes in the acrylic group. In addition, one additional posterior capsulorhexis without anterior vitrectomy was performed in each group. Primary outcome measure was the occurrence of postoperative "complications" (fibrin, synechiae, posterior capsular opacification). For statistical evaluation, the Fisher exact test was used. RESULTS: When evaluating all complications together (at least one complication vs no complication), there were significantly less complications in the acrylic group (2 of 10 vs 15 of 20; p=0.007. For early complications (postoperative fibrin, synechiae) the difference was also significant (1 of 10 in the acrylic vs 11 of 20 in the PMMA group; p=0.02). The rate of posterior capsular opacification necessitating YAG capsulotomy was lower in the acrylic group (1 of 10 eyes) than in the PMMA group (7 of 20 eyes), but the difference did not reach statistical significance ( p=0.67). The postoperative time point of YAG capsulotomy was 21 months in the acrylic group and 19+/-10 months (range 6-33 months) in the PMMA group. IOL dislocation was not observed in any of the patients. Postoperative visual acuity was comparable in the two groups: 0.57+/-0.35 (0.03-1.0) in the acrylic vs 0.39+/-0.34 (0.001-0.9) in the PMMA group ( p=0.83). CONCLUSIONS: Implantation of hydrophobic acrylic intraocular lenses in the capsular bag in children may be associated with less postoperative complications compared with implantation of PMMA lenses. This appears also to be true in children under age 6 years. The visual results seem comparable and correspond mainly to the underlying ocular pathology.

Acrylates↗

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↗

PubMed2002

[Comparison of precision of the TonoPenXL with the Goldmann and Draeger applanation tonometer in a sitting and recumbent position of the patients -- a clinical study on 251 eyes].

PURPOSE: Comparison of precise intraocular pressure (IOP) measurement with TonoPenXL, Goldmann and Draeger applanation tonometer in a sitting and recumbent position. MATERIAL AND METHODS: The IOP of 251 eyes of 127 consecutive patients (SFB 539) was measured prospectively in a sitting position (1 x Goldmann, 3 x TonoPenXL) and in recumbent position (1 x Draeger, 3 x TonoPen). The mean of three TonoPenXL measurements was only accepted in a 5 % interval. Additionally, corneal ultrasonic pachymetry (Tomey, AL-2000), central corneal power, refractive error, gender and age were registered. RESULTS: The IOP measured with the TonoPenXL was in 92 % in a range of 2 mm Hg from the Goldmann standard. In a vertical position, the IOP TonoPenXL (16.7 +/- 4.5 mm Hg) was 0.2 mm Hg lower than the IOP Goldmann (16.9 +/- 5.1 mm Hg; regression analysis: IOP TonoPenXL = 1.78 + 0.88 IOP Goldmann). In a horizontal position, the IOP TonoPenXL (17.5 +/- 5.0 mm Hg) was 0.5 mm Hg higher as the IOP Draeger (17.0 +/- 5.3 mm Hg; regression analysis: IOP TonoPen = 0.34 + 1.016 IOP Draeger). Using the TonoPenXL, the IOP was 0.8 mm Hg higher in recumbent position than in a sitting position (regression analysis: IOP TonoPen recumbent position = - 2.27 + 1.19 IOP TonoPen sitting position). We found no relationship found between central corneal power, central corneal thickness and IOD measured with the TonoPenXL. CONCLUSIONS: The TonoPenXL is useful for IOP measurement in a sitting and recumbent position. The results are reproducible in 92% with the Goldmann-applanation tonometer. The ophthalmologist has a comfortable measurement and screening tool for consultations or IOP investigation under general anaesthesia.

Adult↗