SEARCH · PubMed Health

Results for “Likelihood Functions”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 829 records · Page 46Linked to original sources

PubMed2003

Unsupervised robust nonparametric estimation of the hemodynamic response function for any fMRI experiment.

This paper deals with the estimation of the blood oxygen level-dependent response to a stimulus, as measured in functional magnetic resonance imaging (fMRI) data. A precise estimation is essential for a better understanding of cerebral activations. The most recent works have used a nonparametric framework for this estimation, considering each brain region as a system characterized by its impulse response, the so-called hemodynamic response function (HRF). However, the use of these techniques has remained limited since they are not well-adapted to real fMRI data. Here, we develop a threefold extension to previous works. We consider asynchronous event-related paradigms, account for different trial types and integrate several fMRI sessions into the estimation. These generalizations are simultaneously addressed through a badly conditioned observation model. Bayesian formalism is used to model temporal prior information of the underlying physiological process of the brain hemodynamic response. By this way, the HRF estimate results from a tradeoff between information brought by the data and by our prior knowledge. This tradeoff is modeled with hyperparameters that are set to the maximum-likelihood estimate using an expectation conditional maximization algorithm. The proposed unsupervised approach is validated on both synthetic and real fMRI data, the latter originating from a speech perception experiment.

Algorithms↗

PubMed2001

A survey of validity and utility of electronic patient records in a general practice.

OBJECTIVE: To develop methods of measuring the validity and utility of electronic patient records in general practice. DESIGN: A survey of the main functional areas of a practice and use of independent criteria to measure the validity of the practice database. SETTING: A fully computerised general practice in Skipton, north Yorkshire. SUBJECTS: The records of all registered practice patients. MAIN OUTCOME MEASURES: Validity of the main functional areas of the practice clinical system. Measures of the completeness, accuracy, validity, and utility of the morbidity data for 15 clinical diagnoses using recognised diagnostic standards to confirm diagnoses and identify further cases. Development of a method and statistical toolkit to validate clinical databases in general practice. RESULTS: The practice electronic patient records were valid, complete, and accurate for prescribed items (99.7%), consultations (98.1%), laboratory tests (100%), hospital episodes (100%), and childhood immunisations (97%). The morbidity data for 15 clinical diagnoses were complete (mean sensitivity=87%) and accurate (mean positive predictive value=96%). The presence of the Read codes for the 15 diagnoses was strongly indicative of the true presence of those conditions (mean likelihood ratio=3917). New interpretations of descriptive statistics are described that can be used to estimate both the number of true cases that are unrecorded and quantify the benefits of validating a clinical database for coded entries. CONCLUSION: This study has developed a method and toolkit for measuring the validity and utility of general practice electronic patient records.

Databases, Factual↗

PubMed2002

Diuretics, mortality, and nonrecovery of renal function in acute renal failure.

CONTEXT: Acute renal failure is associated with high mortality and morbidity. Diuretic agents continue to be used in this setting despite a lack of evidence supporting their benefit. OBJECTIVE: To determine whether the use of diuretics is associated with adverse or favorable outcomes in critically ill patients with acute renal failure. DESIGN: Cohort study conducted from October 1989 to September 1995. PATIENTS AND SETTING: A total of 552 patients with acute renal failure in intensive care units at 4 academic medical centers affiliated with the University of California. Patients were categorized by the use of diuretics on the day of nephrology consultation and, in companion analyses, by diuretic use at any time during the first week following consultation. MAIN OUTCOME MEASURES: All-cause hospital mortality, nonrecovery of renal function, and the combined outcome of death or nonrecovery. RESULTS: Diuretics were used in 326 patients (59%) at the time of nephrology consultation. Patients treated with diuretics on or before the day of consultation were older and more likely to have a history of congestive heart failure, nephrotoxic (rather than ischemic or multifactorial) origin of acute renal failure, acute respiratory failure, and lower serum urea nitrogen concentrations. With adjustment for relevant covariates and propensity scores, diuretic use was associated with a significant increase in the risk of death or nonrecovery of renal function (odds ratio, 1.77; 95% confidence interval, 1.14-2.76). The risk was magnified (odds ratio, 3.12; 95% confidence interval, 1.73-5.62) when patients who died within the first week following consultation were excluded. The increased risk was borne largely by patients who were relatively unresponsive to diuretics. CONCLUSIONS: The use of diuretics in critically ill patients with acute renal failure was associated with an increased risk of death and nonrecovery of renal function. Although observational data prohibit causal inference, it is unlikely that diuretics afford any material benefit in this clinical setting. In the absence of compelling contradictory data from a randomized, blinded clinical trial, the widespread use of diuretics in critically ill patients with acute renal failure should be discouraged.

Acute Kidney Injury↗

PubMed1993

A predictive index for functional decline in hospitalized elderly medical patients.

OBJECTIVE: To prospectively develop and validate a predictive index to identify on admission elderly hospitalized medical patients at risk for functional decline. DESIGN: Two prospective cohort studies, in tandem. The predictive model developed in the initial cohort was subsequently validated in a separate cohort. SETTING: General medical wards of a university teaching hospital. PATIENTS: For the development cohort, 188 hospitalized general medical patients aged > or = 70 years. For the validation cohort, 142 comparable patients. MEASUREMENT AND MAIN RESULTS: The subjects and their nurses were interviewed twice weekly using standardized, validated instruments. Functional decline occurred among 51/188 (27%) patients in the development cohort. Four independent baseline risk factors (RFs) for functional decline were identified: decubitus ulcer (adjusted relative risk [RR] 2.7; 95% confidence interval [CI] 1.4, 5.2); cognitive impairment (RR 1.7; CI 0.9, 3.1); functional impairment (RR 1.8; CI 1.0, 3.3); and low social activity level (RR 2.4; CI 1.2, 5.1). A risk-stratification system was developed by adding the numbers of RFs. Rates of functional decline for the low- (0 RF), intermediate- (1-2 RFs), and high- (3-4 RFs) risk groups were 8%, 28%, and 63%, respectively (p < 0.0001). The corresponding rates in the validation cohort, of whom 34/142 (24%) developed functional decline, were 6%, 29%, and 83% (p < 0.0001). The rates of death or nursing home placement, clinical outcomes associated with functional decline in the hospital, were 6%, 19%, and 41% (p < 0.002) in the development cohort and 10%, 32%, and 67% (p < 0.001) in the validation cohort, respectively, for the three risk groups. CONCLUSIONS: Functional decline among hospitalized elderly patients is common, and a simple predictive model based on four risk factors can be used on admission to identify elderly persons at greatest risk.

Activities of Daily Living↗

PubMed2004

Semiparametric estimation of time-dependent ROC curves for longitudinal marker data.

One approach to evaluating the strength of association between a longitudinal marker process and a key clinical event time is through predictive regression methods such as a time-dependent covariate hazard model. For example, a Cox model with time-varying covariates specifies the instantaneous risk of the event as a function of the time-varying marker and additional covariates. In this manuscript we explore a second complementary approach which characterizes the distribution of the marker as a function of both the measurement time and the ultimate event time. Our goal is to extend the standard diagnostic accuracy concepts of sensitivity and specificity so as to recognize explicitly both the timing of the marker measurement and the timing of disease. The accuracy of a longitudinal marker can be fully characterized using time-dependent receiver operating characteristic (ROC) curves. We detail a semiparametric estimation method for time-dependent ROC curves that adopts a regression quantile approach for longitudinal data introduced by Heagerty and Pepe (1999, Applied Statistics, 48, 533-551). We extend the work of Heagerty and Pepe (1999, Applied Statistics, 48, 533-551) by developing asymptotic distribution theory for the ROC estimators where the distributional shape for the marker is allowed to depend on covariates. To illustrate our method, we analyze pulmonary function measurements among cystic fibrosis subjects and estimate ROC curves that assess how well the pulmonary function measurement can distinguish subjects that progress to death from subjects that remain alive. Comparing the results from our semiparametric analysis to a fully parametric method discussed by Etzioni et al. (1999, Medical Decision Making, 19, 242-251) suggests that the ability to relax distributional assumptions may be important in practice.

Adolescent↗

PubMed1995

Trees and splines in survival analysis.

During the past few years several nonparametric alternatives to the Cox proportional hazards model have appeared in the literature. These methods extend techniques that are well known from regression analysis to the analysis of censored survival data. In this paper we discuss methods based on (partition) trees and (polynomial) splines, analyse two datasets using both Survival Trees and HARE, and compare the strengths and weaknesses of the two methods. One of the strengths of HARE is that its model fitting procedure has an implicit check for proportionality of the underlying hazards model. It also provides an explicit model for the conditional hazards function, which makes it very convenient to obtain graphical summaries. On the other hand, the tree-based methods automatically partition a dataset into groups of cases that are similar in survival history. Results obtained by survival trees and HARE are often complementary. Trees and splines in survival analysis should provide the data analyst with two useful tools when analysing survival data.

Algorithms↗

PubMed2003

Development under extreme conditions: forensic bioinformatics in the wake of the World Trade Center disaster.

The terrorist attacks of September 11, 2001 resulted in death and devastation in three locations, and extraordinary efforts have been exerted to identify the remains of all victims. As mass fatalities go, this one has been unusual at a policy level because the goal has been not merely to identify remains for every decedent, but to identify every bit of remains found so that even small pieces of tissue can be returned to families for burial. While the human impact at the Pentagon and Shanksville, PA was horrific, the World Trade Center site presented a particularly complex challenge for forensic DNA matching and data handling. A complete and definitive list of all those killed is still elusive, and human remains were crushed and co-mingled by the falling towers. Software tools had never been considered for a problem of this scale and scope. New data handling systems had to be created under extreme software development conditions characterized by incomplete requirements specifications, chaotically changing priorities, truly impossible deadlines and rapidly rolling production releases. Partly because of the company's experience with mtDNA tools built for the Armed Forces DNA Identification Lab starting in 1997, the New York City Office of Chief Medical Examiner [OCME] contacted Gene Codes Corporation in late September as existing data-handling tools began to fail. We began work on the project in mid-October, 2001. Our approach to the problem included: Extreme Programming [XP] methodology for functional software development, On-site time and motion analysis at the OCME for user interface design, Evidentiary references between STR, SNP and mtDNA analysis results, and Separate data Quality Control [QC] and software Quality Assurance [QA] initiatives. A substantial software suite was developed called M-FISys, an acronym for Mass-Fatality Identification System.

Computational Biology↗

PubMed1995

Real-time functional magnetic resonance imaging.

A recursive algorithm suitable for functional magnetic resonance imaging (FMRI) calculations is presented. The correlation coefficient of a time course of images with a reference time series, with the mean and any linear trend projected out, may be computed with 22 operations per voxel, per image; the storage overhead is four numbers per voxel. A statistical model for the FMRI signal is presented, and thresholds for the correlation coefficient are derived from it. Selected images from the first real-time functional neuroimaging experiment (at 3 Tesla) are presented. Using a 50-MHz workstation equipped with a 14-bit analog-to-digital converter, each echo planar image was acquired, reconstructed, correlated, thresholded, and displayed in pseudocolor (highlighting active regions in the brain) within 500 ms of the RF pulse.

Algorithms↗

PubMed1993

Forecasts of active life expectancy: policy and fiscal implications.

Age-related changes in functional status can be summarized by active life expectancy (ALE) measures. ALE is useful in assessing efforts to improve function and in determining a population's service needs. ALE disaggregates total life expectancy (TLE) into components representing degree and type of impairment. We illustrate the calculation of two ALE measures and their relations to health inputs and service use. First, scores are calculated from 27 measures of function for persons 65 and over, as reported in the National Long Term Care Survey (NLTCS). The scores are then used to calculate the two ALE measures. Results are compared to ALE calculated from the 1982, 1984, and 1989 NLTCS.

Activities of Daily Living↗

PubMed2005

Adaptive evolution in GroEL from distantly related endosymbiotic bacteria of insects.

Many symbioses between bacteria and insects resulted from ancient infections followed by strict vertical transmission within host lineages. The strong bottlenecks under which this transmission occurs promote the neutral fixation of slightly deleterious mutations by genetic drift. As predicted by Muller's ratchet, this fixation will drive endosymbiotic bacteria through an irreversible dynamics of fitness loss. The chaperonin GroEL has been proposed as a compensatory mechanism whereby endosymbiotic bacteria of aphids persist. Here, we show that endosymbiotic bacteria of insects from two phylogenetically very distant bacterial phyla have fixed amino acid substitutions by positive selection in functionally important GroEL regions involved in either GroES/peptide binding or in the en bloc movement of the GroEL apical domain. These results, together with the high levels of constitutive expression of GroEL in these endosymbionts, provide valuable insights into the evolution of a molecular mechanism responsible for the maintenance of the symbiotic lifestyle.

Adaptation, Biological↗

PubMed2004

Quantitative imaging of lymphocyte membrane protein reorganization and signaling.

Changes in membrane protein localization are critical to establishing cell polarity and regulating cell signaling. Fluorescence microscopy of labeled proteins allows visualization of these changes, but quantitative analysis is needed to study this aspect of cell signaling in full mechanistic detail. We have developed a novel approach for quantitative assessment of membrane protein redistribution based on four-dimensional video microscopy of fluorescently labeled proteins. Our analytic system provides robust automated methods for cell surface reconstruction, cell shape tracking, cell-surface distance measurement, and cluster formation analysis. These methods permit statistical analyses and testing of mechanistic hypotheses regarding cell signaling. We have used this approach to measure antigen-dependent clustering of signaling molecules in CD4+ T lymphocytes, obtaining clustering velocities consistent with single-particle tracking data. Our system captures quantitative differences in clustering between signaling proteins with distinct biological functions. Our methods can be generalized to a range of cell-signaling phenomena and enable novel applications not feasible with single-particle studies, such as analysis of subcellular protein localization in live organ culture.

Algorithms↗

PubMed1998

Breast cancer risk assessment: use of complete pedigree information and the effect of misspecified ages at diagnosis of affected relatives.

Reliable risk estimates for hereditary breast cancer are important for the genetic counseling of women who have one or more first- and/or second-degree relatives affected by the disease. If no mutation analysis of known high-penetrance breast cancer genes is performed, risk estimation is often based on published reference tables. These tables express a woman's age-specific risk of breast cancer as a function of the ages at diagnosis of one or two affected relatives with different degrees of relationship to the counselee. However, unaffected relatives are not taken into account when these estimates are derived. We report here the extent to which risk estimation is influenced by the number and ages of any unaffected relatives and by the exact genealogical relationship between the proband and affected relative rather than merely the degree. Additionally, we describe the sensitivity of risk estimates when ages at diagnosis of affected relatives are misspecified because of inaccurate information supplied by the counselee. We determined a proband's probability of being a carrier of a highly penetrant breast cancer susceptibility gene, such as BRCA1 or BRCA2, by likelihood calculations that take into account information from the entire pedigree. This genetic risk was used to estimate a phenotypic lifetime breast cancer risk, which was compared with the risks derived from the published reference tables. We demonstrate numerically that the tabulated values tend to over-estimate the probands risk and that the extent of over-estimation depends greatly on the number and ages of unaffected relatives. The validity of the relatives ages at diagnosis can affect risk predictions considerably in small families with two or three affected relatives. Furthermore, the magnitude of the estimated breast cancer risks depends upon the assumed genetic model and can therefore vary appreciably when different penetrance estimates are used.

Adult↗

PubMed1995

Gender differences in cystic fibrosis: Pseudomonas aeruginosa infection.

The median survival age for females with cystic fibrosis (CF) is approximately 3 years younger than for males. We tested whether earlier acquisition of Pseudomonas aeruginosa (PA) by female CF patients or the greater impact of this organism on their lung disease, or both, contribute to their poorer survival. PA infection status, survival, pulmonary function tests, and chest X-ray scores from patients who were followed at our center for at least 2 years with a minimum of three respiratory cultures per year were analyzed (n = 848). The median age of chronic infection with mucoid PA was 1.7 years earlier in females than in males. Patients infected with mucoid PA had poorer survival, chest X-ray scores, and pulmonary function tests than patients who had either no Pseudomonas species or only the nonmucoid phenotype. Acquisition of mucoid PA was associated with an accelerated rate of decline in pulmonary function. However, the rate of change of pulmonary function after mucoid PA infection was similar for males and females. Moreover, even among patients who had only the mucoid form or only the nonmucoid form, males had better percent predicted forced expiratory volume in 1 sec and better survival. Therefore, factors in addition to earlier acquisition of mucoid PA may contribute to the poorer survival of female CF patients.

Adolescent↗

PubMed2003

Utility of the peripheral blood white blood cell count for identifying sick young infants who need lumbar puncture.

STUDY OBJECTIVE: We assess the utility of the peripheral blood WBC count as a screen for lumbar puncture among young infants evaluated for serious bacterial infections. METHODS: We performed logistic regression modeling and receiver operating characteristic curve analysis of peripheral blood WBC count and cerebrospinal fluid WBC count for results obtained from 3- to 89-day-old infants undergoing a full sepsis evaluation. RESULTS: Twenty-two of 5,353 (4.1 per 1,000) infants had acute bacterial meningitis. For diagnosing acute bacterial meningitis, the peripheral blood WBC count was poorly discriminating and significantly inferior to the cerebrospinal fluid WBC count. This was true both when the odds of meningitis were modeled to vary linearly and as a U-shaped function of the peripheral blood WBC count. When relying on single and interval-based high-risk thresholds of peripheral blood WBC counts alone, the majority of infants with acute bacterial meningitis would have been missed. CONCLUSION: Decisions to perform or withhold lumbar puncture should not be based on prevailing interpretations of the total peripheral blood WBC counts to maximize detection of bacterial meningitis in young infants.

Humans↗

PubMed2005

Subtree power analysis and species selection for comparative genomics.

Sequence comparison across multiple organisms aids in the detection of regions under selection. However, resource limitations require a prioritization of genomes to be sequenced. This prioritization should be grounded in two considerations: the lineal scope encompassing the biological phenomena of interest, and the optimal species within that scope for detecting functional elements. We introduce a statistical framework for optimal species subset selection, based on maximizing power to detect conserved sites. Analysis of a phylogenetic star topology shows theoretically that the optimal species subset is not in general the most evolutionarily diverged subset. We then demonstrate this finding empirically in a study of vertebrate species. Our results suggest that marsupials are prime sequencing candidates.

Animals↗

PubMed2002

Functional mixed effects models.

In this article, a new class of functional models in which smoothing splines are used to model fixed effects as well as random effects is introduced. The linear mixed effects models are extended to nonparametric mixed effects models by introducing functional random effects, which are modeled as realizations of zero-mean stochastic processes. The fixed functional effects and the random functional effects are modeled in the same functional space, which guarantee the population-average and subject-specific curves have the same smoothness property. These models inherit the flexibility of the linear mixed effects models in handling complex designs and correlation structures, can include continuous covariates as well as dummy factors in both the fixed or random design matrices, and include the nested curves models as special cases. Two estimation procedures are proposed. The first estimation procedure exploits the connection between linear mixed effects models and smoothing splines and can be fitted using existing software. The second procedure is a sequential estimation procedure using Kalman filtering. This algorithm avoids inversion of large dimensional matrices and therefore can be applied to large data sets. A generalized maximum likelihood (GML) ratio test is proposed for inference and model selection. An application to comparison of cortisol profiles is used as an illustration.

Bayes Theorem↗

PubMed2005

Gene expression profiling of muscle tissue in Brahman steers during nutritional restriction.

Expression profiling using microarrays allows for the detailed characterization of the gene networks that regulate an animal's response to environmental stresses. During nutritional restriction, processes such as protein turnover, connective tissue remodeling, and muscle atrophy take place in the skeletal muscle of the animal. These processes and their regulation are of interest in the context of managing livestock for optimal production efficiency and product quality. Here we expand on recent research applying complementary DNA (cDNA) microarray technology to the study of the effect of nutritional restriction on bovine skeletal muscle. Using a custom cDNA microarray of 9,274 probes from cattle muscle and s.c. fat libraries, we examined the differential gene expression profile of the LM from 10 Brahman steers under three different dietary treatments. The statistical approach was based on mixed-model ANOVA and model-based clustering of the BLUP solutions for the gene x diet interaction effect. From the results, we defined a transcript profile of 156 differentially expressed array elements between the weight loss and weight gain diet substrates. After sequence and annotation analyses, the 57 upregulated elements represented 29 unique genes, and the 99 downregulated elements represented 28 unique genes. Most of these co-regulated genes cluster into groups with distinct biological function related to protein turnover and cytoskeletal metabolism and contribute to our mechanistic understanding of the processes associated with remodeling of muscle tissue in response to nutritional stress.

Analysis of Variance↗

PubMed2007

Testing the proportional odds model for interval-censored data.

This paper discusses the goodness-of-fit test for the proportional odds model for K-sample interval-censored failure time data, which frequently occur in, for example, periodic follow-up survival studies. The proportional odds model has a feature that allows the ratio of two hazard functions to be monotonic and converge to one and provides an important tool for the modeling of survival data. To test the model, a procedure is proposed, which is a generalization of the method given in Dauxois and Kirmani [Dauxois JY, Kirmani SNUA (2003) Biometrika 90:913-922]. The asymptotic distribution of the procedure is established and its properties are evaluated by simulation studies

Biometry↗