Statistical aspects of prognostic factor studies in oncology
British Journal of CancerPublished 1 June 1994Open access
Richard Simon, DG Altman
Citations593
SJR quartileQ1
SJR score3.14
SNIP1.83
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
Some of the statistical problems common to prognostic factor studies are considered as a step towards the development of broadly acceptable principles that might guide their conduct and reporting.
Keywords
Immunology and MicrobiologyMedicine
Statistics in MedicineFlexible regression models with cubic splines
2,696 Citations1989Sylvain Durrleman, Richard Simon
JNCI Journal of the National Cancer InstitutePostoperative Adjuvant Chemotherapy or Radiation Therapy for Rectal Cancer: Results From NSABP Protocol R-011
1,047 Citations1988B. Fisher, Norman Wolmark +16 more
Investigation of stratification variables employed in this study indicated that sex, and to a lesser extent age and Dukes stage, made individual contributions to the disease-free survival and the survival benefit from chemotherapy.
BiometricsTesting for Qualitative Interactions between Treatment Effects and Patient Subsets
646 Citations1985Mitchell H. Gail, Richard Simon
A likelihood ratio test is developed to test for qualitative interactions and a non-crossover interaction arises when there is variation in the magnitude, but not in the direction, of treatment effects among subsets.
PubMedRegression models for prognostic prediction: advantages, problems, and suggested solutions.
566 Citations1985Harrell Fe, Lee Kl +2 more
Regression models can make more accurate predictions than other methods such as stratification and recursive partitioning, when model assumptions are thoroughly examined; steps are taken when assumptions are violated; and the method of model formulation does not result in overfitting the data.
ScienceSome Thoughts on Clinical Trials, Especially Problems of Multiplicity
482 Citations1977John W. Tukey
Problems of statistical and conceptual design of experiments are exacerberated by ethical issues in many, if not most, clinical trials.
BiometrikaThe asymptotic properties of nonparametric tests for comparing survival distributions
471 Citations1981David Schoenfeld
Annals of Internal MedicineConfidence Intervals for Reporting Results of Clinical Trials
421 Citations1986Richard Simon
Statistics in MedicineBootstrap investigation of the stability of a cox regression model
309 Citations1989Douglas G. Altman, Per Kragh Andersen
A bootstrap investigation of the stability of a Cox proportional hazards regression model resulting from the analysis of a clinical trial of azathioprine versus placebo in patients with primary biliary cirrhosis shows graphically that these intervals are markedly wider than those obtained from the original model.
New England Journal of MedicineThe Relation between Estrogen Receptors and Response Rate to Cytotoxic Chemotherapy in Metastatic Breast Cancer
284 Citations1978Marc E. Lippman, Joseph C. Allegra +8 more
It is concluded that estrogen-receptor values are an important predictor of response to cytotoxic chemotherapy in metastatic breast cancer.
JNCI Journal of the National Cancer InstituteEvaluating the Potential Usefulness of New Prognostic and Predictive Indicators on Node-Negative Breast Cancer Patients
246 Citations1993Giampietro Gasparini, F. Pozza +1 more
The ultimate goals are to facilitate the understanding of node-negative breast cancer prognostic markers among clinicians, to help them select the most appropriate indicator for specific situations, and to recommend methodology for future research.
British Journal of CancerAn overview of prognostic factors in small cell lung cancer
205 Citations1990NSB Rawson, J Peto
It is recommended that performance status, disease stage, AlkP, Na, AST and LDH should be measured in all future SCLC studies to assist comparisons between studies and possibly the selection of patients for different treatment strategies.
Statistics in MedicineMeasures of explained variation for survival data
194 Citations1990Edward L. Korn, Richard Simon
The importance of quantifying the predictive power of a prognostic model is discussed, and measures of explained variation as a possible quantification are suggested.
British Journal of CancerHead and neck sarcomas: prognostic factors and implications for treatment
174 Citations1993Rosalind A. Eeles, Cyril Fisher +6 more
The addition of radiotherapy to surgery may result in longer local recurrence-free survival, and patients in the combined modality and single treatment modality groups were well balanced for T stage, grade and tumour site.
Breast Cancer Research and TreatmentWhy do so many prognostic factors fail to pan out?
137 Citations1992Susan G. Hilsenbeck, Gary M. Clark +1 more
It is recommended that exploratory analyses of prognostic factors formally employ some method of adjusting for increased Type I errors, such as independent validation sets, ad hoc adjustment factors, or other statistical methods of estimating the true risk.
British Journal of Clinical PharmacologyPatient subsets and variation in therapeutic efficacy.
132 Citations1982Richard Simon
In order to obtain the degree of reliability usually demanded of clinical therapeutic evaluations, "statistically significant' interactions between relative treatment efficacy and subsets should be demonstrated.
British Journal of CancerCategorising continuous variables
116 Citations1991DG Altman
Sir Sigurdsson et al. (1990) presented a method for dividing the values of a continuous prognostic variables into categories for the purpose of prediction in a Cox multiple regression model, but there are some serious problems with this approach, especially the fact that the choice of cut-off is derived from the data.
BiometricsEvaluating Serial Cancer Marker Studies in Patients at Risk of Recurrent Disease
101 Citations1981Mitchell H. Gail
The proportional hazards model of Cox, with a time-dependent covariate, is used to analyze serial cancer marker data, showing that high levels of the cancer marker carcinoembryonic antigen (CEA) are associated with increased risk of death in patients with resected colorectal cancer.
British Journal of CancerThe prognostic value of serum β 2 microglobulin compared with other presentation features in myelomatosis
86 Citations1985Jack Cuzick, E.H. Cooper +1 more
Journal of Clinical OncologyWhen is a prognostic factor useful? A guide for the perplexed.
66 Citations1991Mark N. Levine, George P. Browman +3 more
The aim of a prognostic test in breast cancer is to predict which patients are destined to develop a recurrence of cancer and those who are not, and the prognostic usefulness of a test can be expressed in terms of relative risk.
Statistics in MedicineBayesian subset analysis in a colorectal cancer clinical trial
63 Citations1992Dennis O. Dixon, Richard Simon
This work presents Bayesian point and interval estimates under the assumption that the interaction terms are exchangeable and the prior distributions for the other regression parameters are locally uniform, and produces a shrinking of the estimated interaction effects towards zero, thereby discounting them and dealing in a natural way with multiplicity.
Controlled Clinical TrialsAnalysis of clinical trial outcomes: Some comments on subgroup analyses
63 Citations1989Marc E. Buyse
The various ways in which prognostic information can be included in the analysis of treatment effect in clinical trials are discussed, which are an informative and needed complement to an analysis of overall treatment effect.
British Journal of CancerPrognosis after resection of residual masses following chemotherapy for metastatic nonseminomatous testicular cancer: a multivariate analysis
53 Citations1993Ewout W. Steyerberg, H.J. Keizer +5 more
The histology found at resection was not associated with the risk of relapse, which might be explained by the effectiveness of postresection chemotherapy, which in the majority of these patients was a salvage regimen rather than two further cycles of the initial cytostatics.
American Journal of EpidemiologyCAUSALITY INFERENCE IN OBSERVATIONAL VS. EXPERIMENTAL STUDIES
51 Citations1988Katherine Gray‐Donald, Michael S. Kramer
International Journal of Gynecological CancerThe prognostic value of serum CA 125 in patients with advanced ovarian carcinoma: an analysis of 573 patients by the Medical Research Council Working Party on Gynaecological Cancer
51 Citations1993Peter Fayers, Gordon Rustin +11 more
It is concluded that prognostic information based upon CA 125 measurements up to the start of the third course of initial chemotherapy is not accurate enough to be used to manage individual patients.
Statistics in MedicineA proposal for examining and reporting stepwise regressions
50 Citations1991Walter W. Hauck, Rei Miike
A simple table is proposed as an aid in examining and reporting stepwise regression analyses that recognition of 'close alternatives', that is, those variables excluded from selection by the inclusion of another variable.
British Journal of CancerA score at diagnosis for predicting length of remission in childhood acute lymphoblastic leukaemia
47 Citations1980M K Palmer, Ian Hann +2 more
Application of the risk score improves the prediction of the outcome of treatment, and the clinical trials, allows more accurate stratification, less extensive data collection and simpler analysis.
Wiley StatsRef: Statistics Reference OnlineCategorizing Continuous Variables
47 Citations2014Douglas G. Altman
British Journal of CancerMultivariate analysis of prognostic factors in patients with non HIV-related primary cerebral lymphoma. A proposal for a prognostic scoring
41 Citations1993Jean‐Yves Blay, Christine Lasset +9 more
PCL is an heterogeneous disease in terms of the prognostic in which three subgroups with discriminant survival can be identified, and a prognostic index which allowed us to distinguish three risk groups whose theoretical median survival is 4, 20 and 54, months respectively in patients with non HIV related PCL.
Statistics in MedicineComparison of the cox model and the regression tree procedure in analysing a randomized clinical trial
40 Citations1993Claudia Schmoor, Kurt Ulm +1 more
Breast Cancer Research and TreatmentFlexible covariate effects in the proportional hazards model
35 Citations1992Trevor Hastie, Lynn A. Sleeper +1 more
A class of semiparametric models is outlined that allows one to model prognostic factors nonlinearly, and have the data suggest the form of their effect.
British Journal of CancerPrognostic value of continuous variables in breast cancer and head and neck cancer. Dependence on the cut-off level
30 Citations1988A. Courdi, Michel Héry +4 more
Prognostic value of continuous variables in breast cancer and head and neck cancer and prognosis on the cut-off level are compared.
BiometrikaThe Asymptotic Properties of Nonparametric Tests for Comparing Survival Distributions
24 Citations1981David Schoenfeld
British Journal of CancerAdjusting survival curves for imbalances in prognostic factors
19 Citations1988Walter M. Gregory
A new method for comparing the survival of two or more groups of patients adjusting for factors distributed unevenly between the groups is presented, and provides a graphical counterpart to Mantel's adjusted chi-square statistic.
PubMed CentralAdjusting survival curves for imbalances in prognostic factors.
1 Citations1988Gregory, W. M.