Subclassification and Individual Survival Time Prediction from Gene Expression Data of Neuroblastoma Patients by Using CASPAR

Oberthuer, Andreacute; Kaderali, Lars; Kahlert, Yvonne; Hero, Barbara; Westermann, Frank; Berthold, Frank; Brors, Benedikt; Eils, Roland; Fischer, Matthias

doi:10.1158/1078-0432.ccr-07-4377

Cited by 22 publications

(17 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[33] and consists of 362 patients suffering from neuroblastoma. For each patient, we have information on their risk group according to the current German neuroblastoma trial (NB2004, levels low/intermediate/high) as well as 9978 microarray gene expression values and its (possibly) censored survival time.…”

Section: Resultsmentioning

confidence: 99%

“…Median follow-up time for the patients are 3.8 years, and out of the 362 patients 21% died from the disease. The patients were introduced in [33] as two different sets; one "training set" of 256 patients and one "test set" of 120 patients. We merged the two, and the 9978 microarray gene expression measurements are from probes shared by both sets.…”

Section: Resultsmentioning

confidence: 99%

“…Also, 14 patients were omitted from our study due to missing clinical information. For more information on the data, consult [33]. …”

Section: Resultsmentioning

confidence: 99%

See 2 more Smart Citations

Survival prediction from clinico-genomic models - a comparative study

2009

View full text Add to dashboard Cite

BackgroundSurvival prediction from high-dimensional genomic data is an active field in today's medical research. Most of the proposed prediction methods make use of genomic data alone without considering established clinical covariates that often are available and known to have predictive value. Recent studies suggest that combining clinical and genomic information may improve predictions, but there is a lack of systematic studies on the topic. Also, for the widely used Cox regression model, it is not obvious how to handle such combined models.ResultsWe propose a way to combine classical clinical covariates with genomic data in a clinico-genomic prediction model based on the Cox regression model. The prediction model is obtained by a simultaneous use of both types of covariates, but applying dimension reduction only to the high-dimensional genomic variables. We describe how this can be done for seven well-known prediction methods: variable selection, unsupervised and supervised principal components regression and partial least squares regression, ridge regression, and the lasso. We further perform a systematic comparison of the performance of prediction models using clinical covariates only, genomic data only, or a combination of the two. The comparison is done using three survival data sets containing both clinical information and microarray gene expression data. Matlab code for the clinico-genomic prediction methods is available at http://www.med.uio.no/imb/stat/bmms/software/clinico-genomic/.ConclusionsBased on our three data sets, the comparison shows that established clinical covariates will often lead to better predictions than what can be obtained from genomic data alone. In the cases where the genomic models are better than the clinical, ridge regression is used for dimension reduction. We also find that the clinico-genomic models tend to outperform the models based on only genomic data. Further, clinico-genomic models and the use of ridge regression gives for all three data sets better predictions than models based on the clinical covariates alone.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Survival prediction from clinico-genomic models - a comparative study

2009

View full text Add to dashboard Cite

show abstract

“…Although risk stratification schemes have so far integrated molecular data based on only few chromosome loci (Cohn et al , 2009), more recent reports suggest that pangenomic data could further improve pre-therapeutic risk estimation (Ambros et al , 2009; Janoueix-Lerosey et al , 2009; Caren et al , 2010). As high-risk NBs nearly always demonstrate SCA, future therapeutic strategies for these cases might rather rely on gene expression or other molecular data (Oberthuer et al , 2008; Vermeulen et al , 2009; Ambros et al , 2011). However, pangenomic data might prove to be especially informative for treatment stratification in the clinically defined low- and intermediate-risk groups (Janoueix-Lerosey et al , 2009; Schleiermacher et al , 2010).…”

mentioning

confidence: 99%

Segmental chromosomal alterations lead to a higher risk of relapse in infants with MYCN-non-amplified localised unresectable/disseminated neuroblastoma (a SIOPEN collaborative study)

et al. 2011

View full text Add to dashboard Cite

Background:In neuroblastoma (NB), the presence of segmental chromosome alterations (SCAs) is associated with a higher risk of relapse.Methods:In order to analyse the role of SCAs in infants with localised unresectable/disseminated NB without MYCN amplification, we have performed an array CGH analysis of tumours from infants enroled in the prospective European INES trials.Results:Tumour samples from 218 out of 300 enroled patients could be analysed. Segmental chromosome alterations were observed in 11%, 20% and 59% of infants enroled in trials INES99.1 (localised unresectable NB), INES99.2 (stage 4s) and INES99.3 (stage 4) (P<0.0001). Progression-free survival was poorer in patients whose tumours harboured SCA, in the whole population and in trials INES99.1 and INES99.2, in the absence of clinical symptoms (log-rank test, P=0.0001, P=0.04 and P=0.0003, respectively). In multivariate analysis, a SCA genomic profile was the strongest predictor of poorer progression-free survival.Conclusion:In infants with stage 4s MYCN-non-amplified NB, a SCA genomic profile identifies patients who will require upfront treatment even in the absence of other clinical indication for therapy, whereas in infants with localised unresectable NB, a genomic profile characterised by the absence of SCA identifies patients in whom treatment reduction might be possible. These findings will be implemented in a future international trial.

show abstract

“…A further real-world example is related to the microarray data set of Oberthuer et al [89]. It consists of n =276 patients suffering from neuroblastoma.…”

Section: Resultsmentioning

confidence: 99%

Combining techniques for screening and evaluating interaction terms on high-dimensional time-to-event data

2014

View full text Add to dashboard Cite

BackgroundMolecular data, e.g. arising from microarray technology, is often used for predicting survival probabilities of patients. For multivariate risk prediction models on such high-dimensional data, there are established techniques that combine parameter estimation and variable selection. One big challenge is to incorporate interactions into such prediction models. In this feasibility study, we present building blocks for evaluating and incorporating interactions terms in high-dimensional time-to-event settings, especially for settings in which it is computationally too expensive to check all possible interactions.ResultsWe use a boosting technique for estimation of effects and the following building blocks for pre-selecting interactions: (1) resampling, (2) random forests and (3) orthogonalization as a data pre-processing step. In a simulation study, the strategy that uses all building blocks is able to detect true main effects and interactions with high sensitivity in different kinds of scenarios. The main challenge are interactions composed of variables that do not represent main effects, but our findings are also promising in this regard. Results on real world data illustrate that effect sizes of interactions frequently may not be large enough to improve prediction performance, even though the interactions are potentially of biological relevance.ConclusionScreening interactions through random forests is feasible and useful, when one is interested in finding relevant two-way interactions. The other building blocks also contribute considerably to an enhanced pre-selection of interactions. We determined the limits of interaction detection in terms of necessary effect sizes. Our study emphasizes the importance of making full use of existing methods in addition to establishing new ones.

show abstract

Subclassification and Individual Survival Time Prediction from Gene Expression Data of Neuroblastoma Patients by Using CASPAR

Cited by 22 publications

References 50 publications

Survival prediction from clinico-genomic models - a comparative study

Survival prediction from clinico-genomic models - a comparative study

Segmental chromosomal alterations lead to a higher risk of relapse in infants with MYCN-non-amplified localised unresectable/disseminated neuroblastoma (a SIOPEN collaborative study)

Combining techniques for screening and evaluating interaction terms on high-dimensional time-to-event data

Contact Info

Product

Resources

About