PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “Models, Statistical”

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 1,207 records · Page 67Linked to original sources
PubMedDate not supplied

Estimating the accident potential of an Ontario driver.

To run a "demerit point" program, one uses routinely available information about drivers to identify those who are most likely to have an accident in the near future. On the basis of a four-year record for a large sample of Ontario drivers, we have examined several tools for the identification of such drivers and investigated how they perform. Each driver is thought to have an expected number of accidents, m. In a group of drivers with common traits (such as age, gender, record of convictions and accidents) the ms have a mean E(m) and a variance VAR(m). Estimates of E(m) and VAR(m) for all combinations of traits can be obtained within the framework of a multivariate statistical model. The same estimates can then be used to judge how well a model identifies drivers who have a large m. In such a multivariate model it is important to use data about previous accidents and convictions. However, the accuracy with which the m of a driver can be estimated is not improved much by distinguishing between offence type or between accidents as being "at fault" or "not at fault". Without much loss in estimation accuracy, one may attach a weight 1 to a conviction and 2 to an accident. Model performance is described in tangible terms: how many accidents are recorded by the drivers identified by a model, what proportion of identified drivers are "false positives," how many drivers with high m remain unidentified. We conclude that by using a multivariate statistical model one can do substantially better than by using a demerit point scheme in which points are assigned to offenses on the basis of their perceived seriousness. However, even when the best model is used to identify a large group of drivers, many will be false positives.

Accidents, Traffic↗
PubMed1999

Interday variation in vertical ground reaction force in clinically normal Greyhounds at the trot.

OBJECTIVE: To determine the effect of interday variation on vertical ground reaction force variables in dogs. ANIMALS: 52 clinically normal Greyhounds of either sex weighing between 22 and 35 kg. PROCEDURE: Dogs were led at a trot across a floor-mounted force platform to determine vertical ground reaction force variables (peak [PFz] and impulse [IFz]) from hind limbs. Data were collected from each dog on 3 consecutive days. Variance components were estimated, using maximal likelihood to evaluate contributions of interday variation within dogs and variation attributable to dogs and repetitions. An ANOVA was used to test significance of interday variation within dogs and day within dog interactions. RESULTS: PFz, IFz, or both differed significantly from day to day for 29 of 52 dogs. Only PFz differed significantly among days for 16 dogs, and only IFz differed among days for 5 dogs. The PFz and IFz differed significantly from day to day in 8 dogs. Using ANOVA, the difference for PFz and IFz among days within dogs was significant. CONCLUSIONS: Effect of day within dog variation (interaction) should be considered as a component in statistical models in which data from 1 day are evaluated against data from the same subject on another day. We propose a statistical model that incorporates an accommodation for interday variation. Investigators should determine the factors that affect their studies, including the extent of interday variation, and compensate for the variation attributable to each factor in the statistical models used to analyze their data.

Analysis of Variance↗
PubMed1999

Characterisation of side-chain conformational preferences in a biologically active but unfolded protein.

A combination of experimental NMR 3J alpha beta coupling constant measurements and theoretical predictions from a statistical model for a random coil have been used to characterise the conformations of amino acid side-chains in an unfolded fibronectin binding protein. The statistical model uses the distribution of torsion angles in a data base of native folded protein structures to provide a description of the torsion angle populations of each residue in a random coil. For all but three of the residues studied a close agreement is observed between the experimental 3J alpha beta data and the model predictions (correlation coefficient 0.90; RMSD 0.70 Hz). In these cases the populations about the chi 1 torsion angles in the conformational ensemble defining the fibronectin binding protein are well described by those present in the protein data base. For Phe 69, Asp 92 and Asp 105 however significant deviations are observed between the predictions and experimental data. Each of these side-chains is found to be involved in persistent non-random structural features arising from clustering of hydrophobic groups or interactions between charged side-chains. The analysis demonstrates the detailed insight that can be provided into conformationally disordered states by combining experimental and theoretical approaches.

Adhesins, Bacterial↗
PubMed2006

Linear regression modeling to compare fluoride release profiles of various restorative materials.

OBJECTIVES: The aim of this study was to compare the released fluoride profiles of various restorative materials by using linear regression analysis. METHODS: Specimens were prepared using a cylindrical Teflon mold with a height of 2 mm and a radius of 8 mm. After being prepared, specimens were immediately placed into artificial saliva which was replaced at various times during 6 weeks. These released intrinsic fluoride amounts were measured by using an ion selective electrode. Then, data obtained cumulatively were statistically analyzed, and the released profiles were compared. RESULTS: It was observed that the materials released fluoride at different levels of concentration and the largest fluoride release was obtained from the conventional glass ionomer cement. This was followed by resin modified glass ionomer cement, polyacid modified composite resin, and fluoride releasing composite resin, respectively. Although the released fluoride amounts of the materials were different, their release profiles were found to be similar in that the release was initially fast and then it became steady as time passed. SIGNIFICANCE: The statistical modeling of the release profiles helps to compare the fluoride release behavior of materials and also to predict fluoride release amounts for the future. In literature, for these purposes, separate nonlinear statistical models have extensively been utilized. However, the single linear statistical modeling approach has numerous advantages such as providing estimators having good statistical properties, exact results, precise inference and simplicity in calculation. Therefore, this study was conducted to introduce the use of single linear regression modeling to compare release profiles statistically.

Compomers↗
PubMed2005

Statistical thermodynamics models for polyatomic adsorbates: application to adsorption of n-paraffins in 5A zeolite.

Experimental adsorption isotherms of five n-paraffins (ethane, propane, butane, pentane, and hexane) in 5A zeolite were described by means of a statistical thermodynamics model for linear adsorbates (MLA) developed by Ramirez-Pastor et al. (1999) and compared with the well-known multisite Langmuir model (MSL) of Nitta et al. (1984). The experimental data, obtained by different authors in a wide range of temperatures and pressures, were correlated by using an algorithm of multiple fitting. Two main conclusions were drawn from the analysis of experimental data: (i) for small molecules (ethane, propane), MLA is the more accurate model, validating the hypothesis of the linear rigid character of the adsorbate and reinforcing previous results obtained from the analysis of computational experiments developed for dimers and linear trimers; (ii) for large molecules (n-butane, n-pentane, n-hexane), the better performance of the MSL model suggests that the admolecules adsorb in a nonlinear structure. The isosteric heat of adsorption dependence on the number of carbons obtained from our study, ranging between 23.84 kJ/mol for ethane and 59.26 kJ/mol for hexane, showed a very good agreement with previous results reported in the literature, confirming the consistency of our analysis.

Journal Article↗
PubMed2004

Cost-effectiveness of duplex ultrasound surveillance in spinal cord injury.

OBJECTIVE: To determine cost-effectiveness of surveillance with duplex ultrasound for thromboembolic disease in individuals with acute traumatic spinal cord injury at admission to rehabilitation. DESIGN: In this retrospective sequential case series study, individuals with traumatic spinal cord injury admitted to our rehabilitation facility between July 1, 1988, and December 31, 1998, were identified. Cost at our institution for treatment of thromboembolic disease was tabulated in 2001-2002 dollar amounts. Using this cost information, in a statistical model founded on available medical evidence, analysis for cost-effectiveness was then performed. RESULTS: A total of 369 subjects met inclusion criteria. Based on the statistical model, the cost and estimated mortality from thromboembolic disease per subject when performing admission duplex ultrasounds was $449.28 and 0.016%, respectively. The estimated total cost per subject when not performing admission duplex ultrasounds was $136.29, with predicted mortality of 0.524% due to thromboembolic disease. Therefore, cost of one life saved when performing admission duplex ultrasound surveillance is calculated to be $61,542, with cost per life year gained between $1193 and $9050, depending on age at time of injury and severity of injury. CONCLUSION: Duplex ultrasound is a cost-effective tool for deep venous thrombosis surveillance in individuals with acute traumatic spinal cord injury admitted to rehabilitation programs.

Cost-Benefit Analysis↗
PubMed1994

Risk stratification for long-term outcome after elective coronary angioplasty: a multivariate analysis of 5,000 patients.

OBJECTIVES: We attempted to develop a statistical model to facilitate risk stratification for long-term outcome after elective coronary angioplasty. BACKGROUND: Our understanding of factors related to long-term outcome after coronary angioplasty is limited. Adequate assessment of risk indexes could potentially lead to more appropriate use of percutaneous revascularization. METHODS: We studied 5,000 consecutive patients and assessed 19 clinical and anatomic variables as predictors of long-term event-free survival. Events were defined as death of any cause, myocardial infarction, bypass surgery or repeat percutaneous transluminal coronary angioplasty. Cox proportional hazards models were used to develop an equation for predicting event-free survival in a subset of 4,000 patients. The equation was validated with the remaining 1,000 patients. Variables that were significantly associated with an adverse outcome in the multivariate model included age > 60 years, extent of disease, Canadian Cardiovascular Society functional class, previous coronary angioplasty, male gender, history of diabetes mellitus, history of hypertension and history of congestive heart failure. RESULTS: The statistical model was used to develop a simplified scoring system, and the patients were assigned to three risk subgroups. Event-free survival curves for the three groups were significantly different (p = 0.0001). High risk patients had worse outcomes for each of the end points compared with low and moderate risk patients (p < 0.02). CONCLUSIONS: We demonstrated that clinical and anatomic variables can be used to risk-stratify long-term outcome after angioplasty, that a simplified scoring system can be used for risk stratification and that high risk patients have a low event-free survival.

Aged↗
PubMed1998

Predicting probabilities of pregnancy and multiple gestation from in vitro fertilization--a new model.

OBJECTIVE: To develop a statistical model that adjusts for variation between patients and adequately predicts the observed distribution of pregnancies among singletons and multiple gestations of various orders. METHODS: All in vitro fertilization (IVF) cycles from the inception of the IVF program at Women and Infants' Hospital on May 26, 1988, until December 31, 1993, were evaluated using logistic regression in selected subsets. RESULTS: A new cycle-one specific model uses three different probabilities: P1, the probability of pregnancy (predicted by age and total embryo score); P2/P1, the conditional probability of finding a second implantation in those who had become pregnant with at least one (predicted by total embryo score); and P3/P2, the conditional probability of finding a third implantation in those who had become pregnant with at least two (with no significant predictors). This is the first model to use these three adjusted probabilities. CONCLUSION: P1 increases with increasing total embryo score but decreases with increasing age. P2/P1 increases with increasing total embryo score but does not depend on age. Embryo scoring is useful because the total embryo score is a better predictor of P1 and P2/P1 than the number of embryos alone. By using patient-specific information (age and total embryo score) and cycle-specific tables, an estimate of the probability of pregnancy and multiple gestation can be provided before embryo transfer.

Adult↗
PubMed2000

Variational learning for switching state-space models.

We introduce a new statistical model for time series that iteratively segments data into regimes with approximately linear dynamics and learnsthe parameters of each of these linear regimes. This model combines and generalizes two of the most widely used stochastic time-series models -- hidden Markov models and linear dynamical systems -- and is closely related to models that are widely used in the control and econometrics literatures. It can also be derived by extending the mixture of experts neural network (Jacobs, Jordan, Nowlan, & Hinton, 1991) to its fully dynamical version, in which both expert and gating networks are recurrent. Inferring the posterior probabilities of the hidden states of this model is computationally intractable, and therefore the exact expectation maximization (EM) algorithm cannot be applied. However, we present a variational approximation that maximizes a lower bound on the log-likelihood and makes use of both the forward and backward recursions for hidden Markov models and the Kalman filter recursions for linear dynamical systems. We tested the algorithm on artificial data sets and a natural data set of respiration force from a patient with sleep apnea. The results suggest that variational approximations are a viable method for inference and learning in switching state-space models.

Algorithms↗
PubMed1998

[Epidemiologic and statistical interaction models and consequences for regression analysis].

Different ways to define interaction between exposition factors in epidemiological studies as well as the choice between additive and multiplicative no interaction leads frequently to confusion during data analysis. In their standard form methods of event data analysis such as Poisson or logistic regression assume a multiplicative parameterization of no interaction. However, evidence from empirical investigations as well as causal models of disease etiology, e.g. the simple independent action model of Finney or the sufficient-component-causes model of Rothman, suggest additive or other kinds of non-multiplicative concepts of no interaction. For additive structured data we illustrate the asymptotic bias ("interaction-bias") of main effect estimates which are based on inappropriate data analysis using multiplicative models and omitting significant or non-significant interaction terms. We show that both the epidemiological study design as well as the underlying causal model are determinants of the interaction structure of the data and should be considered in the model selection process. The definition of interaction should distinguish between risk, rate and odds if risks are not very small. Using generalized linear models with parametrical link functions we are able to analyze non-multiplicative interaction structures.

Adult↗
PubMedDate not supplied

CT attenuation value and shockwave fragmentation.

PURPOSE: To evaluate whether, in principle, the mean CT attenuation values of kidney stones could predict fragmentation by shockwaves. MATERIALS AND METHODS: Four types of artificial kidney stones having different CT attenuation values were tested. Artificial stones were weighed and exposed to 700 shockwaves at 21 kV at the focus of an electrohydraulic lithotripter. Fragments were strained through meshes with 2x2-mm and 3.1x3.1-mm openings. The material left on the meshes after shockwave exposure was dried and weighed on a precision scale. Half of all artificial stones were saturated by immersing them in water several days before fragmentation. Fragmentation coefficients (i.e., percent weight loss) were associated with CT attenuation values using a statistical model. RESULTS: Higher CT numbers resulted in lower fragmentation coefficients. Artificial stone weight was inversely proportional to the percent weight loss. Larger fragments were obtained at lower fragmentation coefficients. Statistical analysis revealed that fragmentation can be predicted knowing the weight and the CT number of a stone before shockwave application. CONCLUSION: Prediction of the number of shockwaves necessary for successful SWL could be possible. Our statistical model proved to fit in vitro fragmentation of artificial stones; however, clinical application requires further research.

Humans↗
PubMed2002

Optimizing higher throughput methods to assess drug-drug interactions for CYP1A2, CYP2C9, CYP2C19, CYP2D6, rCYP2D6, and CYP3A4 in vitro using a single point IC(50).

Drug-drug interactions involving cytochrome P(450) (CYP) are an important factor in whether a new chemical entity will survive through to the development stage. Therefore, the identification of this potential as early as possible in vitro could save considerable future unnecessary investment. In vitro CYP interaction screening data generated for CYP2C9, CYP2D6, and CYP3A4 were initially analyzed to determine the correlation of IC(50) from 10- and 3-point determinations. A high correlation (r = 0.99) prompted the further assessment of predicting the IC(50) by a single value of percent inhibition at either 10, 3, or 1 microM. Statistical analysis of the initial proprietary compounds showed that there was a strong linear relationship between log IC(50) and percent inhibition at 3 microM, and that it was possible to predict a compound's IC(50) by the percent inhibition value obtained at 3 microM. Additional data for CYP1A2, CYP2C19, and the recombinant CYP2D6 were later obtained and used together with the initial data to demonstrate that a single statistical model could be applicable across different CYPs and different in vitro microsomal systems. Ultimately, the data for all five CYPs and the recombinant CYP2D6 were used to build a statistical model for predicting the IC(50) with a single point. The 95% prediction boundary for the region of interest was about +/- 0.37 on log(10) scale, comparable to the variability of in vitro determinations for positive control IC(50) data. The use of a single inhibitor concentration would enable determination of more IC(50) values on a 96-well plate and result in more economical use of compounds, human liver or expressed enzyme microsomes, substrates, and reagents. This approach would offer the opportunity to increase screening for CYP-mediated drug-drug interactions, which may be important given the challenges provided by the generation of orders of magnitude more new chemical entities in the field of combinatorial chemistry. In addition, the algorithmic approach we propose would obviously be applicable for other in vitro bioactivity and therapeutic target enzyme and receptor screens.

Algorithms↗
PubMed2002

Using chaos theory: the implications for nursing.

AIMS OF THE PAPER: The purpose of this paper is to review chaos theory and to examine the role that it may have in the discipline of nursing. BACKGROUND: In this paper, the fundamental ingredients of chaotic thinking are outlined. The earlier days of chaos thinking were characterized by an almost exclusively physiological focus. By the 21st century, nurse theorists were applying its principles to the organization and evaluation of care delivery with varying levels of success. Whilst the biological use of chaos has focused on pragmatic approaches to knowledge enhancement, nursing has often focused on the mystical aspects of chaos as a concept. CONCLUSIONS: The contention that chaos theory has yet to find a niche within nursing theory and practice is examined. The application of chaotic thinking across nursing practice, nursing research and statistical modelling is reviewed. The use of chaos theory as a way of identifying the attractor state of specific systems is considered and the suggestion is made that it is within statistical modelling of services that chaos theory is most effective.

Humans↗
PubMed2006

Joint spatial analysis of gastrointestinal infectious diseases.

A major obstacle in the spatial analysis of infectious disease surveillance data is the problem of under-reporting. This article investigates the possibility of inferring reporting rates through joint statistical modelling of several infectious diseases with different aetiologies. Once variation in under-reporting can be estimated, geographic risk patterns for infections associated with specific food vehicles may be discerned. We adopt the shared component model, proposed by Knorr-Held and Best for two chronic diseases and further extended by (Held L, Natario I, Fenton S, Rue H, Becker N. Towards joint disease mapping. Statistical Methods in Medical Research 2005b; 14: 61-82) for more than two chronic diseases to the infectious disease setting. Our goal is to estimate a shared component, common to all diseases, which may be interpreted as representing the spatial variation in reporting rates. Additional components are introduced to describe the real spatial variation of the different diseases. Of course, this interpretation is only allowed under specific assumptions, in particular, the geographical variation in under-reporting should be similar for the diseases considered. In addition, it is vital that the data do not contain large local outbreaks, so adjustment based on a time series method recently proposed by (Held L, Höhle M, Hofmann M. A statistical framework for the analysis of multivariate infectious disease surveillance data. Statistical Modelling 2005a; 5: 187-99) is made at a preliminary stage. We will illustrate our approach through the analysis of gastrointestinal diseases notification data obtained from the German infectious disease surveillance system, administered by the Robert Koch Institute in Berlin.

Adolescent↗
PubMed2004

Combining mathematical models and statistical methods to understand and predict the dynamics of antibiotic-sensitive mutants in a population of resistant bacteria during experimental evolution.

Temporarily discontinuing the use of antibiotics has been proposed as a means to eliminate resistant bacteria by allowing sensitive clones to sweep through the population. In this study, we monitored a tetracycline-sensitive subpopulation that emerged during experimental evolution of E. coli K12 MG1655 carrying the multiresistance plasmid pB10 in the absence of antibiotics. The fraction of tetracycline-sensitive mutants increased slowly over 500 generations from 0.1 to 7%, and loss of resistance could be attributed to a recombination event that caused deletion of the tet operon. To help understand the population dynamics of these mutants, three mathematical models were developed that took into consideration recurrent mutations, increased host fitness (selection), or a combination of both mechanisms (full model). The data were best explained by the full model, which estimated a high mutation frequency (lambda = 3.11 x 10(-5)) and a significant but small selection coefficient (sigma = 0.007). This study emphasized the combined use of experimental data, mathematical models, and statistical methods to better understand and predict the dynamics of evolving bacterial populations, more specifically the possible consequences of discontinuing the use of antibiotics.

Anti-Bacterial Agents↗
PubMed2005

Automated identification of a physician's primary patients.

OBJECTIVE: To develop and validate an automated method for determining the set of patients for whom a given primary care physician holds overall clinical responsibility. DESIGN: The study included all adult patients (16,185) seen at least once in an ambulatory setting during a three-year period by 18 primary care physicians in ten practices. The physicians indicated whether they considered themselves to be the physician primarily responsible for the overall clinical care of each visiting patient. Statistical models were constructed to predict the physicians' designations using predictor variables derived from electronically available appointment schedules and demographic information. MEASUREMENTS: Predictive accuracy was assessed primarily using the area under the receiver-operating characteristic curve (AUC), and secondarily using positive predictive value (PPV) and sensitivity. RESULTS: A minimal set of six variables was identified as predictive of the physicians' designations. The constructed model had a median AUC for individual physicians of 0.92 (interquartile interval: 0.90-0.96), a PPV of 0.94 (interquartile interval: 0.87-0.95), and a sensitivity of 0.95 (interquartile interval: 0.87-0.97). CONCLUSION: A statistical model using a minimal set of commonly available electronic data can accurately predict the set of patients for whom a physician holds primary clinical responsibility. Further research examining the generalization of the model to other settings would be valuable.

Adult↗
PubMed2003

Alternative approaches to predicting methane emissions from dairy cows.

Previous attempts to apply statistical models, which correlate nutrient intake with methane production, have been of limited value where predictions are obtained for nutrient intakes and diet types outside those used in model construction. Dynamic mechanistic models have proved more suitable for extrapolation, but they remain computationally expensive and are not applied easily in practical situations. The first objective of this research focused on employing conventional techniques to generate statistical models of methane production appropriate to United Kingdom dairy systems. The second objective was to evaluate these models and a model published previously using both United Kingdom and North American data sets. Thirdly, nonlinear models were considered as alternatives to the conventional linear regressions. The United Kingdom calorimetry data used to construct the linear models also were used to develop the three nonlinear alternatives that were all of modified Mitscherlich (monomolecular) form. Of the linear models tested, an equation from the literature proved most reliable across the full range of evaluation data (root mean square prediction error = 21.3%). However, the Mitscherlich models demonstrated the greatest degree of adaptability across diet types and intake level. The most successful model for simulating the independent data was a modified Mitscherlich equation with the steepness parameter set to represent dietary starch-to-ADF ratio (root mean square prediction error = 20.6%). However, when such data were unavailable, simpler Mitscherlich forms relating dry matter or metabolizable energy intake to methane production remained better alternatives relative to their linear counterparts.

Animal Feed↗