PubMed Health⌕ Search

Biomedical subjects

A Tsodikov

Publications and source records attributed to A Tsodikov.

13 recordsLinked to original sources
PubMed2007

Profile information matrix for nonlinear transformation models.

For semiparametric models, interval estimation and hypothesis testing based on the information matrix for the full model is a challenge because of potentially unlimited dimension. Use of the profile information matrix for a small set of parameters of interest is an appealing alternative. Existing approaches for the estimation of the profile information matrix are either subject to the curse of dimensionality, or are ad-hoc and approximate and can be unstable and numerically inefficient. We propose a numerically stable and efficient algorithm that delivers an exact observed profile information matrix for regression coefficients for the class of Nonlinear Transformation Models [A. Tsodikov (2003) J R Statist Soc Ser B 65:759-774]. The algorithm deals with the curse of dimensionality and requires neither large matrix inverses nor explicit expressions for the profile surface.

Algorithms↗
PubMed2006

A population model of prostate cancer incidence.

Introduction of screening for prostate cancer using the prostate-specific antigen (PSA) marker of the disease led to remarkable dynamics of the incidence of the disease observed in the last two decades. A statistical model is used to provide a link between dissemination of PSA and the observed transient population responses. The model is used to estimate lead time, overdiagnosis and other relevant characteristics of prostate cancer screening.

Age of Onset↗
PubMed2002

Semi-parametric models of long- and short-term survival: an application to the analysis of breast cancer survival in Utah by age and stage.

A flexible class of semi-parametric survival models is proposed that takes account of long- and short-term covariate effects in cancer survival. The diversity of responses described by the models include non-proportional and crossing survival curves as well as a fraction of long-term survivors. Restricted non-parametric maximum likelihood estimation procedures (RNPMLE) are developed to provide point estimates, confidence intervals and tests for the models. Numerical algorithms to fit semi-parametric survival models are emphasized. The methods are applied to analyse post-treatment survival of breast cancer patients diagnosed in Utah by age and stage.

Adult↗
PubMed2002

Adjustments and measures of differential expression for microarray data.

MOTIVATION: Existing analyses of microarray data often incorporate an obscure data normalization procedure applied prior to data analysis. For example, ratios of microarray channels intensities are normalized to have common mean over the set of genes. We made an attempt to understand the meaning of such procedures from the modeling point of view, and to formulate the model assumptions that underlie them. Given a considerable diversity of data adjustment procedures, the question of their performance, comparison and ranking for various microarray experiments was of interest. RESULTS: A two-step statistical procedure is proposed: data transformation (adjustment for slide-specific effect) followed by a statistical test applied to transformed data. Various methods of analysis for differential expression are compared using simulations and real data on colon cancer cell lines. We found that robust categorical adjustments outperform the ones based on a precisely defined stochastic model, including some commonly used procedures.

Colonic Neoplasms↗
PubMed2001

Electron arc irradiation of the postmastectomy chest wall with CT treatment planning: 20-year experience.

PURPOSE: Since 1980, electron arc irradiation of the postmastectomy chest wall has been the preferred radiotherapy technique at the University of Utah for patients with advanced breast cancer. We report the results of this technique in 156 consecutive Stage IIA-IIIB patients treated from 1980 to 1998. METHODS: CT treatment planning was used in all patients to identify chest wall thickness and internal mammary lymph node depth. Computerized dosimetry was used to deliver total doses of 50 Gy in 5-1/2 weeks to the chest wall and the internal mammary lymph nodes with electron arc therapy. Patients were assessed for local, regional, and distant control of disease and for survival. Univariate and multivariate proportional hazards were modeled using a hierarchical nonproportional semiparametric model testing the following prognostic factors: age, stage, tumor size, number of positive lymph nodes, estrogen receptor status, and dose. End points evaluated included disease-free survival, cause-specific survival, and overall survival. RESULTS: Eighty-one percent of patients were at high risk for local-regional failure because of > T2 primary tumor or > 3 positive axillary lymph nodes. The median number of positive lymph nodes was 5, and the median tumor size was 3.5 cm. Actuarial 10-year local-regional control and overall survival were 95% and 52%, respectively. In multivariate analysis, the only factor prognostic for disease-free survival, cause-specific survival, and overall survival was the number of positive lymph nodes (p < 0.001). The 10-year rates of local-regional control for patients with 0, 1-3, 4-9, and > or = 10 involved lymph nodes were 100%, 98%, 93%, and 89%, respectively. The only rates of acute and chronic radiotherapy toxicity > or = 2 by RTOG/EORTC criteria were skin related and observed in 44% and 10% for acute and late reactions, respectively. CONCLUSION: These data demonstrate excellent local-regional control rates with electron arc therapy of the postmastectomy chest wall in patients with advanced breast cancer. Our 20-year experience with electron arc radiotherapy has demonstrated the safety and efficacy of this technique. The advantage of this technique is that the internal mammary lymph node chain can be easily encompassed while the dose to heart and lung is minimized; it also obviates match lines in areas of high risk.

Adult↗
PubMed2001

Modeling cancer detection: tumor size as a source of information on unobservable stages of carcinogenesis.

This paper is concerned with modern approaches to mechanistic modeling of the process of cancer detection. Measurements of tumor size at diagnosis represent a valuable source of information to enrich statistical inference on the processes underlying tumor latency. One possible way of utilizing this information is to model cancer detection as a quantal response variable. In doing so, one relates the chance of detecting a tumor to its current size. We present various theoretical results emerging from this approach and illustrate their usefulness with numerical examples and analyses of epidemiological data. An alternative approach based on a threshold type mechanism of tumor detection is briefly described.

Computer Simulation↗
PubMed1999

A random walk model of oligodendrocyte generation in vitro and associated estimation problems.

A branching stochastic process proposed earlier to model oligodendrocyte generation by O-2A progenitor cells under in vitro conditions does not allow invoking the maximum likelihood techniques for estimation purposes. To overcome this difficulty, we propose a partial likelihood function based on an embedded random walk model of clonal growth and differentiation of O-2A progenitor cells. Under certain conditions, the partial likelihood function yields consistent estimates of model parameters. The usefulness of this approach is illustrated with computer simulations and data analyses.

Algorithms↗
PubMed1999

Deficiency of platelet-activating factor acetylhydrolase is a severity factor for asthma.

Asthma, a family of airway disorders characterized by airway inflammation, has an increasing incidence worldwide. Platelet-activating factor (PAF) may play a role in the pathophysiology of asthma. Its proinflammatory actions are antagonized by PAF acetylhydrolase. A missense mutation (V279F) in the PAF acetylhydrolase gene results in the complete loss of activity, which occurs in 4% of the Japanese population. We asked if PAF acetylhydrolase deficiency correlates with the incidence and severity of asthma in Japan. We found that the prevalence of PAF acetylhydrolase deficiency is higher in Japanese asthmatics than healthy subjects and that the severity of this syndrome is highest in homozygous-deficient subjects. We conclude that the PAF acetylhydrolase gene is a modulating locus for the severity of asthma.

1-Alkyl-2-acetylglycerophosphocholine Esterase↗
PubMed1998

Regression with bounded outcome score: evaluation of power by bootstrap and simulation in a chronic myelogenous leukaemia clinical trial.

Evaluation of the treatment effect on cytogenetic ordered categorical response is considered in patients treated for chronic myelogenous leukaemia (CML) in a clinical trial initiated by the East German Group for Hematology and Oncology. A simulation model for the cytogenetic response (per cent of Philadelphia chromosome positive metaphases) serially measured in CML patients was constructed to describe roughly the sparse information available in medical literature. The model was used to construct a summary measure of response and to formulate the treatment effect as a regression with U-shape distributed ordered categorical data. Two simple models (vertical shift model and pooled conditional response model) were specifically designed to model the treatment effect 'observed' in a simulated 'pilot' data set. The powers were contrasted with the traditional proportional odds and binary models. The comparison was based both on repeated sampling from the simulated model and on bootstrap of 'given' pilot data set. We show that the specific models that address the treatment effect directly (as anticipated from pilot data) can gain in power as compared to the traditional proportional odds model when evaluated by bootstrap. However, the proportional odds model appears to be better with repeated sampling from the simulation model. To explain this discrepancy we generated 'pilot data sets' repeatedly from the simulation model and showed that the ordering of the bootstrap power estimates is unstable with reasonably complex models dependent on the random fall of the pilot data sets. This phenomenon clearly limits the usefulness of subtle modelling the form of the treatment difference observed in a small pilot data set.

Antineoplastic Combined Chemotherapy Protocols↗
PubMed1998

A cure model with time-changing risk factor: an application to the analysis of secondary leukaemia. A report from the International Database on Hodgkin's Disease.

A parametric model is used to investigate the latency time of leukaemia observed in patients treated for Hodgkin's disease. In specifying the treatment effect on leukaemia-free survival, account was taken of a fraction of long-term survivors and of time-changing risk associated with the relapse of the primary disease. The model is applied to data collected in the International Database on Hodgkin's Disease. It permits estimation of the contributions of primary and of relapse treatment to the overall risk of induced leukaemia. Baseline hazards appear to be identical after primary and relapse treatments supporting the concept that induced leukaemia have common origin. The probability to induce leukaemia by MOPP chemotherapy is the same, regardless whether used as primary or relapse treatment.

Acute Disease↗
PubMed1998

Modeling carcinogenesis under a time-changing exposure.

A model of carcinogenesis for fractionated and continuous exposure is developed. The model is discussed from two points of view. First a "surface" statistical model is introduced by making assumptions about the hazard function for the time of tumor latency. Later it is shown that the model can be interpreted in a mechanistic sense as a discrete and a mixed discrete/continuous counterpart of a model of carcinogenesis recently proposed by Yakovlev and Polig [A. Yakovlev, E. Polig, Math. Biosci. 132 (1996) 1]. Two counteracting effects are combined: a protective multiplicative effect of the exposure on the hazard function along with an additive effect of cancer induction responsible for an additional hazard. The model is used to revisit the analysis by Yakovlev et al. [A. Yakovlev, W. Müller. L. Pavlova, E. Polig, Math. Biosci. 142 (1997) 107] of lymphoma-free survival in irradiated mice under acute and fractionated exposure.

Animals↗
PubMed1998

A proportional hazards model taking account of long-term survivors.

A proportional hazards (PH) model is modified to take account of long-term survivors by assuming the cumulative hazard to be bounded but otherwise unspecified to yield an improper survival function. A marginal likelihood is derived under the restriction for type I censoring patterns. For a PH model with cure, the marginal and the partial likelihood are not the same. In the absence of covariate information, the estimate of the cure rate based on the marginal likelihood reduces to the value of the Kaplan-Meier estimate at the end of the study. An example of low asymptotic efficiency of the partial likelihood as compared to the marginal, profile, and parametric likelihoods is given. An algorithm is suggested to fit the full PH model with cure.

Algorithms↗