Biomedical subjects

Hans C van Houwelingen

Publications and source records attributed to Hans C van Houwelingen.

At least 19 recordsLinked to original sources

PubMed2007

Approaches in modelling long-term survival: an application to breast cancer.

Several modelling techniques have been proposed for non-proportional hazards. In this work we consider different models which can be classified into three wide categories: models with time-varying effects of the covariates; frailty models and cure rate models. We present those different extensions of the proportional hazards model on an application of 2433 breast cancer patients with a long follow-up. We comment on the differences and similarities among the models and evaluate their performance using survival and hazard plots, Brier scores and pseudo-observations.

Adult↗

PubMed2006

A relaxation of the gamma frailty (Burr) model.

Frailty models are used in univariate data to account for individual heterogeneity. In the popular gamma frailty model the marginal hazard has the form of a Burr model. Although the Burr model is very useful and can offer insight on the data, it is far from perfect. The estimation of the covariate effects is linked to the baseline hazard and this makes the model coefficients hard to interpret. At the same time, the frailties are assumed constant over time, while biological reasoning in some cases may indicate that frailties may be time dependent. In this paper we present a relaxation of the Burr model which is based on loosening the link between the estimation of the covariate effects and the baseline hazard. This can be achieved by replacing the cumulative baseline hazard in the Burr model by a set of time functions, and the frailty variance by a vector of coefficients directly estimated from the data using a partial likelihood. We illustrate the similarities of the model with the Burr model and a further extension of the latter, a model with an autoregressive stochastic process for the frailty. We compare the models on simulated data sets with constant and time-dependent frailties and show how the relaxed Burr models performs on two different real data sets. We show that the relaxed Burr model serves as a good approximation to the Burr model when the frailty is constant, and furthermore it gives better results when the frailty is time dependent.

Adolescent↗

PubMed2006

MR imaging: effectiveness and costs at triage of patients with nonacute knee symptoms.

PURPOSE: To prospectively evaluate the cost and effectiveness of magnetic resonance (MR) imaging performed to exclude the need for arthroscopy in patients with nonacute knee symptoms who are highly suspected clinically of having intraarticular knee abnormality. MATERIALS AND METHODS: The study was approved by the institutional review boards of three hospitals; informed patient consent was obtained. All 584 included patients (406 male, 178 female; mean age, 31.1 years+/-8.0 [standard deviation]) underwent MR imaging. Patients with an MR result positive for the diagnosis of intraarticular knee abnormality underwent arthroscopy (group A). Patients with a negative MR result were randomly assigned to undergo either conservative (group B) or arthroscopic (group C) treatment. Treatment was considered effective if the Noyes function score had increased 10% or more at 6 months. A cost analysis was performed from a societal perspective to compare the treatment strategy involving MR imaging with the strategy not involving MR imaging. RESULTS: Of the 584 patients, 294 (50.3%) were assigned to group A; 149 (25.5%), to group B; and 141 (24.1%), to group C. At 6 months, the number of patients effectively treated in group B (conservative treatment) was a mean of 5.1%+/-10.0 larger than the number of patients effectively treated in group C (arthroscopy). Owing to savings in productivity costs, total societal costs were lower with use of the strategy involving MR imaging by a mean of $153+/-488 (P=.54). CONCLUSION: MR imaging can be used without additional costs or disadvantageous effects on function to obviate arthroscopy in patients with nonacute knee symptoms who are highly suspected of having intraarticular knee abnormality.

Adolescent↗

PubMed2006

Assessing genetic effects in survival data by correlating martingale residuals with an application to age at onset of Huntington disease.

Genetic models for survival data are hard to formulate and hard to fit. For example, the popular gamma-frailty model for sib-pair data does not generalize easily to extended pedigrees and is not easy to fit. In this paper we show how martingale residuals from a (marginal) Cox model can be employed to estimate the presence of a genetic effect and to estimate genetic correlations depending on the genetic distance (kinship). The methodology is applied to age at onset of Huntington disease (HD) in carriers of the HD gene. The number of CAG repeats in the HD gene is a well-known predictor for age at onset of the disease. However, there is an indication that other genes might be involved as well; leading to unexplained familial clustering. Using our methodology, we found a clearly significant genetic association between the martingale residuals with correlations of about 0.6 for relatives that share 50 per cent of their genes (sib-pairs and parent-child) and about 0.3 for relatives that share 25 per cent of their genes (grandparent-grandchild, uncle/aunt-niece/nephew).

Adolescent↗

PubMed2006

Cross-validated Cox regression on microarray gene expression data.

This paper describes how penalized Cox regression, in combination with cross-validated partial likelihood can be employed to obtain reliable survival prediction models for high dimensional microarray data. The suggested procedure is demonstrated on a breast cancer survival data set consisting of 295 tumours as collected in the National Cancer Institute in Amsterdam and previously reported in more general papers. The main aim of this paper it to show how generally accepted biostatistical procedures can be employed to analyse high-dimensional data.

Breast Neoplasms↗

PubMed2006

Reduced-rank hazard regression for modelling non-proportional hazards.

The Cox proportional hazards model is the most common method to analyse survival data. However, the proportional hazards assumption might not hold. The natural extension of the Cox model is to introduce time-varying effects of the covariates. For some covariates such as (surgical)treatment non-proportionality could be expected beforehand. For some other covariates the non-proportionality only becomes apparent if the follow-up is long enough. It is often observed that all covariates show similar decaying effects over time. Such behaviour could be explained by the popular (gamma-) frailty model. However, the (marginal) effects of covariates in frailty models are not easy to interpret. In this paper we propose the reduced-rank model for time-varying effects of covariates. Starting point is a Cox model with p covariates and time-varying effects modelled by q time functions (constant included), leading to a pxq structure matrix that contains the regression coefficients for all covariate by time function interactions. By reducing the rank of this structure matrix a whole range of models is introduced, from the very flexible full-rank model (identical to a Cox model with time-varying effects) to the very rigid rank one model that mimics the structure of a gamma-frailty model, but is easier to interpret. We illustrate these models with an application to ovarian cancer patients.

Biometry↗

PubMed2006

Combining risk estimates from observational studies with different exposure cutpoints: a meta-analysis on body mass index and diabetes type 2.

Studies on a dose-response relation often report separate relative risks for several risk classes compared with a referent class. When performing a meta-analysis of such studies, one has to convert these relative risks into an overall relative risk for a continuous effect. Apart from taking the dependence between separate relative risks into account, this implies assigning an exposure level to each risk factor class and allowing for the nonlinearity of the dose-response relation. The authors describe a relatively simple method solving these problems. As an illustration, they applied this method in a meta-analysis of the association between body mass index and diabetes type 2, restricted to results of follow-up studies (n=31). Results were compared with a more ad hoc method of assigning exposure levels and with a method in which the nonlinearity of the dose-response method was not taken into account. Differences with the ad hoc method were larger in studies with fewer categories. Not incorporating the nonlinearity of the dose response leads to an overestimation of the pooled relative risk, but this bias is relatively small.

Body Mass Index↗

PubMed2006

Patients with a favourable prognosis are equally palliated with single and multiple fraction radiotherapy: results on survival in the Dutch Bone Metastasis Study.

BACKGROUND AND PURPOSE: In the prospectively, randomized Dutch Bone Metastasis Study on the effect of a single fraction of 8 Gy versus 24 Gy in six fractions on painful bone metastases, 28% of the patients survived for more than 1 year. Purpose of the present study was to analyze the palliative effect of radiotherapy in long-term surviving patients, and to identify prognostic factors for survival. MATERIAL AND METHODS: Response rates were compared in all patients surviving>52 weeks. The Cox proportional hazards model stratified by primary tumour was used for multivariate (MV) analyses of prognostic factors for survival. RESULTS: In 320 patients surviving>52 weeks, responses were 87% after 8 Gy and 85% after 24 Gy (P=0.54). Duration of response and progression rates were similar. For all primary tumours, prognostic factors for survival were a good Karnofsky Performance Score, no visceral metastases, and non-opioid analgesics intake (all factors, MV P<0.001). CONCLUSIONS: Single fraction radiotherapy should be the standard dose schedule for all patients with painful bone metastases, including patients with an expected favourable survival. General prognosticators as the Karnofsky Performance Score and metastatic tumour load are useful in predicting survival.

Adult↗

PubMed2006

A fast routine for fitting Cox models with time varying effects of the covariates.

The S-plus and R statistical packages have implemented a counting process setup to estimate Cox models with time varying effects of the covariates. The data set has to be re-arranged in a repeated measurement setting: the time is divided into small time intervals where a single event occurs and for each time interval, the covariate values and outcome in the interval for each subject still under observation are stacked to a large data set. This is the known (Tstart,Tstop] algorithm implemented in Therneau's Survival library (S-plus), which has been ported into an R package by Thomas Lumley. However, the expansion of a data set leads to a larger set, which can be hard to handle even with fast modern computers. We propose the use of a fast and efficient algorithm, written in R, which works on the original data without the use of an expansion. The computations are done on the original data set, with significant less memory resources used. This improves the computational time by orders of magnitude. The algorithm can also fit reduced rank Cox models with time varying effects. We illustrate the method on a large data set of 2433 breast cancer patients, a smaller study of 358 ovarian cancer patients, and compare the computational times on simulated data of up to 10,000 cases with SAS proc phreg and survival package in R. For larger data sets our algorithm was several times faster, and was able to handle larger data sets then SAS and R.

Algorithms↗

PubMed2006

Travel-related venous thrombosis: results from a large population-based case control study (MEGA study).

BACKGROUND: Recent studies have indicated an increased risk of venous thrombosis after air travel. Nevertheless, questions on the magnitude of risk, the underlying mechanism, and modifying factors remain unanswered. METHODS AND FINDINGS: We studied the effect of various modes and duration of travel on the risk of venous thrombosis in a large ongoing case-control study on risk factors for venous thrombosis in an unselected population (MEGA study). We also assessed the combined effect of travel and prothrombotic mutations, body mass index, height, and oral contraceptive use. Since March 1999, consecutive patients younger than 70 y with a first venous thrombosis have been invited to participate in the study, with their partners serving as matched control individuals. Information has been collected on acquired and genetic risk factors for venous thrombosis. Of 1,906 patients, 233 had traveled for more than 4 h in the 8 wk preceding the event. Traveling in general was found to increase the risk of venous thrombosis 2-fold (odds ratio [OR] 2.1; 95% confidence interval [CI] 1.5-3.0). The risk of flying was similar to the risks of traveling by car, bus, or train. The risk was highest in the first week after traveling. Travel by car, bus, or train led to a high relative risk of thrombosis in individuals with factor V Leiden (OR 8.1; 95% CI 2.7-24.7), in those who had a body mass index of more than 30 kg/m(2) (OR 9.9; 95% CI 3.6-27.6), in those who were more than 1.90 m tall (OR 4.7; 95% CI 1.4-15.4), and in those who used oral contraceptives (estimated OR > 20). For air travel these synergistic findings were more apparent, while people shorter than 1.60 m had an increased risk of thrombosis after air travel (OR 4.9; 95% CI 0.9-25.6) as well. CONCLUSIONS: The risk of venous thrombosis after travel is moderately increased for all modes of travel. Subgroups exist in which the risk is highly increased.

Adult↗

PubMed2005

How to quantify information loss due to phase ambiguity in haplotype case-control studies.

Assigning haplotypes in a case-control study is a challenging problem. We proposed a method to quantify the information loss due to missing phase information. We determined which individuals were responsible for the information loss, and calculated how much information could be gained when the ambiguous individuals could be resolved by adding additional parental information.

Case-Control Studies↗

PubMed2005

Interim analysis on survival data: its potential bias and how to repair it.

We consider interim analyses in clinical trials or observational studies with a time-to-event outcome variable where the survival curves are compared using the hazard ratio resulting from a proportional hazards (PH) model or tested with the logrank test or another two-sample test. We show and illustrate with an example that if the PH assumption is violated, the results of interim analyses can be heavily biased. This is due to the fact that the censoring pattern in interim analyses can be completely different from the final analysis. We argue that, when the PH assumption is violated, interim analyses are only sensible if a fixed time horizon for the final analysis is specified, and at the time of the interim analysis sufficient information is available over the whole time interval up to the horizon. We show how the bias can then be remedied by introducing in the estimation and testing procedures an appropriate weighting that reflects the weights to be expected in the final analysis. The consequences for design and analysis are discussed and some practical recommendations are given.

Bias↗

PubMed2005

Results of the Dutch National study of the palliative effect of irradiation using two different treatment schemes for non-small-cell lung cancer.

PURPOSE: A national multicenter randomized study compared the efficacy of 2 x 8 Gy versus our standard 10 x 3 Gy in patients with inoperable stage IIIA/B (with an Eastern Cooperative Oncology Group score of 3 to 4 and/or substantial weight loss) and stage IV non-small-cell lung cancer. PATIENTS AND METHODS: Between January 1999 and June 2002, 297 patients were eligible and randomized to receive either 10 x 3 Gy or 2 x 8 Gy by external-beam irradiation. The primary end point was a patient-assessed score of treatment effect on seven thoracic symptoms using an adapted Rotterdam Symptom Checklist. Study sample size was determined based on an average total symptom score difference of more than one point over the initial 39 weeks post-treatment. The time course of symptom scores were also evaluated, and other secondary end points were toxicity and survival. RESULTS: Both treatment arms were equally effective, as the average total symptom score over the initial 39 weeks did not differ. However, the pattern in time of these scores differed significantly (P < .001). Palliation in the 10 x 3-Gy arm was more prolonged (until week 22) with less worsening symptoms than in 2 x 8-Gy. Survival in the 10 x 3-Gy arm was significantly (P = .03) better than in the 2 x 8-Gy arm with 1-year survival of 19.6% (95%CI, 14.1% to 27.3%) v 10.9% (95%CI, 6.9% to 17.3%). CONCLUSION: The 10 x 3-Gy radiotherapy schedule is preferred over the 2 x 8-Gy schedule for palliative treatment, as it improves survival and results in a longer duration of the palliative response.

Aged↗

PubMed2005

Prolonged conservative treatment or 'early' surgery in sciatica caused by a lumbar disc herniation: rationale and design of a randomized trial [ISRCT 26872154].

BACKGROUND: The design of a randomized multicenter trial is presented on the effectiveness of a prolonged conservative treatment strategy compared with surgery in patients with persisting intense sciatica (lumbosacral radicular syndrome). METHODS/DESIGN: Patients presenting themselves to their general practitioner with disabling sciatica lasting less than twelve weeks are referred to the neurology outpatient department of one of the participating hospitals. After confirmation of the diagnosis and surgical indication MRI scanning is performed. If a distinct disc herniation is discerned which in addition covers the clinically expected site the patient is eligible for randomization. Depending on the outcome of the randomization scheme the patient will either be submitted to prolonged conservative care or surgery. Surgery will be carried out according to the guidelines and between six and twelve weeks after onset of complaints. The experimental therapy consists of a prolonged conservative treatment under supervision of the general practitioner, which may be followed by surgical intervention in case of persisting or progressive disability. The main primary outcome measure is the disease specific disability of daily functioning. Other primary outcome measures are perceived recovery and intensity of legpain. Secondary outcome measures encompass severity of complaints, quality of life, medical consumption, absenteeism, costs and preference. The main research question will be answered at 12 months after randomization. The total follow-up period covers two years. DISCUSSION: Evidence is lacking concerning the optimal treatment of lumbar disc induced sciatica. This pragmatic randomized trial, focusses on the 'timing' of intervention, and will contribute to the decision of the general practictioner and neurologist, regarding referral of patients for surgery.

Humans↗

PubMed2005

Testing association of a pathway with survival using gene expression data.

MOTIVATION: A recent surge of interest in survival as the primary clinical endpoint of microarray studies has called for an extension of the Global Test methodology to survival. RESULTS: We present a score test for association of the expression profile of one or more groups of genes with a (possibly censored) survival time. Groups of genes may be pathways, areas of the genome, clusters from a cluster analysis or all genes on a chip. The test allows one to test hypotheses about the influence of these groups of genes on survival directly, without the intermediary of single gene testing. The test is based on the Cox proportional hazards model and is calculated using martingale residuals. It is possible to adjust the test for the presence of covariates. We also present a diagnostic graph to assist in the interpretation of the test result, visualizing the influence of genes. The test is applied to a tumor dataset, revealing pathways from the gene ontology database that are associated with survival of patients. AVAILABILITY: The Global Test for survival has been incorporated into the R-package globaltest (version 3.0), available at http://www.bioconductor.org

Biomarkers, Tumor↗

PubMed2005

Translation, adaptation and validation of the Shoulder Rating Questionnaire (SRQ) into the Dutch language.

OBJECTIVE: To translate and adapt the original English version of the Shoulder Rating Questionnaire (SRQ) into the Dutch language (SRQ-DLV) and evaluate its internal consistency, reliability, validity and responsiveness to clinical changes. DESIGN: Prospective study. SETTING: Outpatient departments of orthopaedics, radiology and physical therapy of an academic and a non-academic hospital. SUBJECTS: One hundred and seven patients treated for unilateral shoulder disorder (adhesive capsulitis 68, calcifying tendinitis 22, impingement syndrome or rotator cuff tear 17). METHODS: The original SRQ was translated and adapted following international guidelines. The SRQ-DLV was used among other measures of body function and structure, activities and societal participation in order to determine reliability, internal consistency, validity and responsiveness. Assessments were done at baseline and three months after treatment, with the SRQ-DLV being re-administered within one week before the baseline measurement and the start of the treatment for testing reliability. RESULTS: Cronbach's alpha for internal consistency was 0.89 for the total questionnaire and 0.81, 0.80, 0.72 and 0.84 for the domains pain, daily activities, sports/recreational activities and work, respectively. Test-retest reliability of the SRQ-DLV and its subscales ranged from 0.63 to 0.86. The summary score of the SRQ-DLV correlated with measures of shoulder function, daily activities and quality of life. Except for the work subscale of the SRQ-DLV, large effect sizes, reflecting its responsiveness to clinical changes after treatment, were found for both the summary and the subscales scores. CONCLUSIONS: Empirical data support that the SRQ-DLV is a reliable, valid and responsive measure to be used in clinical trials including Dutch patients with various shoulder disorders.

Disability Evaluation↗

PubMed2004

Validation and updating of predictive logistic regression models: a study on sample size and shrinkage.

A logistic regression model may be used to provide predictions of outcome for individual patients at another centre than where the model was developed. When empirical data are available from this centre, the validity of predictions can be assessed by comparing observed outcomes and predicted probabilities. Subsequently, the model may be updated to improve predictions for future patients. As an example, we analysed 30-day mortality after acute myocardial infarction in a large data set (GUSTO-I, n = 40 830). We validated and updated a previously published model from another study (TIMI-II, n = 3339) in validation samples ranging from small (200 patients, 14 deaths) to large (10,000 patients, 700 deaths). Updated models were tested on independent patients. Updating methods included re-calibration (re-estimation of the intercept or slope of the linear predictor) and more structural model revisions (re-estimation of some or all regression coefficients, model extension with more predictors). We applied heuristic shrinkage approaches in the model revision methods, such that regression coefficients were shrunken towards their re-calibrated values. Parsimonious updating methods were found preferable to more extensive model revisions, which should only be attempted with relatively large validation samples in combination with shrinkage.

Computer Simulation↗

PubMed2004

A global test for groups of genes: testing association with a clinical outcome.

MOTIVATION: This paper presents a global test to be used for the analysis of microarray data. Using this test it can be determined whether the global expression pattern of a group of genes is significantly related to some clinical outcome of interest. Groups of genes may be any size from a single gene to all genes on the chip (e.g. known pathways, specific areas of the genome or clusters from a cluster analysis). RESULT: The test allows groups of genes of different size to be compared, because the test gives one p-value for the group, not a p-value for each gene. Researchers can use the test to investigate hypotheses based on theory or past research or to mine gene ontology databases for interesting pathways. Multiple testing problems do not occur unless many groups are tested. Special attention is given to visualizations of the test result, focussing on the associations between samples and showing the impact of individual genes on the test result. AVAILABILITY: An R-package globaltest is available from http://www.bioconductor.org

Algorithms↗