Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “probabilistic modelling”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

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

At least 55 records · Page 3Linked to original sources
PubMed1991

Probabilistic diagnosis using a reformulation of the INTERNIST-1/QMR knowledge base. I. The probabilistic model and inference algorithms.

In Part I of this two-part series, we report the design of a probabilistic reformulation of the Quick Medical Reference (QMR) diagnostic decision-support tool. We describe a two-level multiply connected belief-network representation of the QMR knowledge base of internal medicine. In the belief-network representation of the QMR knowledge base, we use probabilities derived from the QMR disease profiles, from QMR imports of findings, and from National Center for Health Statistics hospital-discharge statistics. We use a stochastic simulation algorithm for inference on the belief network. This algorithm computes estimates of the posterior marginal probabilities of diseases given a set of findings. In Part II of the series, we compare the performance of QMR to that of our probabilistic system on cases abstracted from continuing medical education materials from Scientific American Medicine. In addition, we analyze empirically several components of the probabilistic model and simulation algorithm.

Algorithms↗
PubMed2005

Probabilistic model for estimating field mortality of target and non-target bird populations when simultaneously exposed to avicide bait.

A probabilistic model was developed to estimate target and non-target avian mortality associated with the application of the avicide CPTH (3-chloro-p-toluidine hydrochloride) to minimize sprouting rice damage in the southern USA. CPTH exposures for individual birds were predicted by random sampling from species-specific non-parametric distributions of bait seed consumption and CPTH residues detected on individual bait seeds. Mortality was predicted from the species-specific exposure versus mortality relationship. Individual variations in this response were captured in the model by Monte Carlo sampling from species-specific distributions of slopes and median toxicity values (LD50) for each bird. The model was used to simultaneously predict mortality (percentage of exposed population and number of birds killed/weight of consumed bait) for a target (blackbird) and non-target (mourning dove) species feeding on bait sites for up to five consecutive days.

Animals↗
PubMed2006

A probabilistic model for the MRMC method, part 1: theoretical development.

RATIONALE AND OBJECTIVES: Current approaches to receiver operating characteristic (ROC) analysis use the MRMC (multiple-reader, multiple-case) paradigm in which several readers read each case and their ratings (or scores) are used to construct an estimate of the area under the ROC curve or some other ROC-related parameter. Standard practice is to decompose the parameter of interest according to a linear model into terms that depend in various ways on the readers, cases, and modalities. Though the methodologic aspects of MRMC analysis have been studied in detail, the literature on the probabilistic basis of the individual terms is sparse. In particular, few articles state what probability law applies to each term and what underlying assumptions are needed for the assumed independence. When probability distributions are specified for these terms, these distributions are assumed to be Gaussians. MATERIALS AND METHODS: This article approaches the MRMC problem from a mechanistic perspective. For a single modality, three sources of randomness are included: the images, the reader skill, and the reader uncertainty. The probability law on the reader scores is written in terms of three nested conditional probabilities, and random variables associated with this probability are referred to as triply stochastic. RESULTS: In this article, we present the probabilistic MRMC model and apply this model to the Wilcoxon statistic. The result is a seven-term expansion for the variance of the figure of merit. CONCLUSION: We relate the terms in this expansion to those in the standard, linear MRMC model. Finally, we use the probabilistic model to derive constraints on the coefficients in the seven-term expansion.

Analysis of Variance↗
PubMed2003

Validation and sensitivity analysis of a probabilistic model for dietary exposure assessment to pesticide residues with a Basque Country duplicate diet study.

The 'fitness for purpose' of a probabilistic model designed to assess dietary exposure to pesticides was validated. The model had to meet two prerequisites. First, it should provide more realistic estimates of intake than conservative methods. Second, it should not underestimate 'true' intakes. True intakes were estimated using a duplicate diet study. Three approaches were used to check the prerequisites: visual comparison, a statistical test of a high percentile, and a comparison for each infant of the duplicate diet, conservative and model intake values. Compliance with the prerequisites was met for the six pesticides selected, in the three approaches. Model outcome distributions reduced the uncertainty, considered as the difference between conservative and duplicate diet intakes, by 75-98% for high percentiles, depending on the pesticides. A sensitivity analysis of the model based on analysis of variance for selected factors was conducted for three pesticides. The factors included concentration and food consumption input data presentations, values assigned to pesticide-food commodities without analysis, values assigned to samples with results below the limit of reporting, unit-to-unit variability and processing factors. Their significance and relevance were studied. Assigning values to pesticide-food commodities without analysis and processing factors, when available, were the most relevant factors in this study.

Diet↗
PubMed2006

How prior reward experience biases exploratory movements: a probabilistic model.

Animals return to rewarded locations. An example of this is conditioned place preference (CPP), which is widely used in studies of drug reward. Although CPP is expressed as increased time spent in a previously rewarded location, the behavioral strategy underlying this change is unknown. We continuously monitored rats (n = 22) in a three-room in-line configuration, before and after morphine conditioning in one end room. Although sequential room visit durations were variable, their probability distribution was exponential, indicating that the processes controlling visit durations can be modeled by instantaneous room exit probabilities. Further analysis of room transitions and computer simulations of probabilistic models revealed that the exploratory bias toward the morphine room is best explained by an increase in the probability of a subset of rapid, direct transitions from the saline- to the morphine-paired room by the central room. This finding sharply delineates and constrains possible neural mechanisms for a class of self-initiated, goal-directed behaviors toward previously rewarded locations.

Analgesics, Opioid↗
PubMed2005

Corpus callosum subdivision based on a probabilistic model of inter-hemispheric connectivity.

Statistical shape analysis has become of increasing interest to the neuroimaging community due to its potential to locate morphological changes. In this paper, we present the a novel combination of shape analysis and Diffusion Tensor Image (DTI) Tractography to the computation of a probabilistic, model based corpus callosum (CC) subdivision. The probabilistic subdivision is based on the distances of arc-length parameterized corpus callosum contour points to trans-callosal DTI fibers associated with an automatic lobe subdivision. Our proposed subdivision method is automatic and reproducible, Its results are more stable than the Witelson subdivision scheme or other commonly applied schemes based on the CC bounding box. We present the application of our subdivision method to a small scale study of regional CC area growth in healthy subjects from age 2 to 4 years.

Algorithms↗
PubMedDate not supplied

A simple probabilistic model for standard air dives that is focused on total decompression time.

A statistical fit of an algorithm to "calibration data" gives parameter values for a "probabilistic decompression model." Our objective is to prepare a simple model that will estimate risk of decompression sickness (DCS) in air dives. We develop a logistic regression model using calibration data from carefully controlled experimental dives recorded in the U.S. Navy Decompression Database. We exclude saturation dives, which can have very long decompression times. For most depths, our model's prescriptions for 2% probability of DCS avoid the experimental DCS cases without mandating excessive time at decompression stops. Our model indicates that the long decompression times prescribed by some previous probabilistic models are not necessary. Our model cannot be used operationally because it cannot calculate depths and times at decompression stops; however, there is general concurrence between our model and prescriptions of a deterministic model known as the VVal-18 Algorithm; this supports the adoption of theVVal-18 Algorithm for operational use on decompression dives.

Air↗
PubMed2003

A probabilistic model for identifying protein names and their name boundaries.

This paper proposes a method for identifying protein names in biomedical texts with an emphasis on detecting protein name boundaries. We use a probabilistic model which exploits several surface clues characterizing protein names and incorporates word classes for generalization. In contrast to previously proposed methods, our approach does not rely on natural language processing tools such as part-of-speech taggers and syntactic parsers, so as to reduce processing overhead and the potential number of probabilistic parameters to be estimated. A notion of certainty is also proposed to improve precision for identification. We implemented a protein name identification system based on our proposed method, and evaluated the system on real-world biomedical texts in conjunction with the previous work. The results showed that overall our system performs comparably to the state-of-the-art protein name identification system and that higher performance is achieved for compound names. In addition, it is demonstrated that our system can further improve precision by restricting the system output to those names with high certainties.

Artificial Intelligence↗
PubMed1978

A probabilistic model of intensive designs.

Without internal validity, experimental data are uninterpretable. With intensive designs, most methods presented to quantify a design's internal validity have been subject to criticism. A probabilistic model of intensive designs is presented that demonstrates the high degree of internal validity of these designs without relying on adaptations from traditional inferential statistics. Where the experimenter is able to conform to the restrictions of the model, the equations provide an estimation of internal validity for either reversal or multiple-baseline designs. More importantly, the model provides mathematical bases for some of the common recommendations and design considerations in intensive research (such as the desirability of within-subject replications and of four or more multiple baselines).

Journal Article↗
PubMed2001

Adaptive and self-averaging Thouless-Anderson-Palmer mean-field theory for probabilistic modeling.

We develop a generalization of the Thouless-Anderson-Palmer (TAP) mean-field approach of disorder physics, which makes the method applicable to the computation of approximate averages in probabilistic models for real data. In contrast to the conventional TAP approach, where the knowledge of the distribution of couplings between the random variables is required, our method adapts to the concrete set of couplings. We show the significance of the approach in two ways: Our approach reproduces replica symmetric results for a wide class of toy models (assuming a nonglassy phase) with given disorder distributions in the thermodynamic limit. On the other hand, simulations on a real data model demonstrate that the method achieves more accurate predictions as compared to conventional TAP approaches.

Journal Article↗
PubMed2005

Population-based continuous optimization, probabilistic modelling and mean shift.

Evolutionary algorithms perform optimization using a population of sample solution points. An interesting development has been to view population-based optimization as the process of evolving an explicit, probabilistic model of the search space. This paper investigates a formal basis for continuous, population-based optimization in terms of a stochastic gradient descent on the Kullback-Leibler divergence between the model probability density and the objective function, represented as an unknown density of assumed form. This leads to an update rule that is related and compared with previous theoretical work, a continuous version of the population-based incremental learning algorithm, and the generalized mean shift clustering framework. Experimental results are presented that demonstrate the dynamics of the new algorithm on a set of simple test problems.

Algorithms↗
PubMed1998

A Probabilistic Model of Criticality in a Sequential Public Good Dilemma.

A public good (PG) is a commodity or service made available to all members of a group: its provision depends on the voluntary contribution of its members. Once provided, all members can enjoy the benefits of the PG, regardless of whether they contributed or not; hence, there is a temptation to "free-ride" in the hope that others will contribute. Rapoport (1987) showed that an important factor that affects cooperation (contribution) in a PG dilemma is the extent to which a group member is critical in providing it. Erev and Rapoport (1990) tested a game-theoretic model that yields deterministic predictions about the effects of criticality on cooperation in public good dilemmas. Based on research by Chen, Au, and Komorita (1996), we propose a probabilistic model of criticality. The model is tested and found to fit empirical data. Extensions of the model to situations with uncertain group size or provision point are discussed. Copyright 1998 Academic Press.

Journal Article↗
PubMed2003

Chronic nephropathies: individual risk for progression to end-stage renal failure as predicted by an integrated probabilistic model.

BACKGROUND/AIMS: To predict risk of end-stage renal disease (ESRD) in individual patients with chronic nephropathy. METHODS: Sequential use of univariate analyses and Cox regression to identify risk factors, artificial neural network to quantify their relative importance and Bayesian analysis to address uncertainty of relationships and incorporate ESRD prevalence information in 344 patients with chronic nephropathy enrolled in the Ramipril Efficacy In Nephropathy study. RESULTS: Serum creatinine (SC), 24-hour urinary protein excretion (UPE) and calcium-phosphorus (Ca*P) product were, in this order, the strongest time-adjusted ESRD predictors. Individual risk of ESRD ranged from near zero when SC and UPE were <1.66 mg/dl and <3 g/24 h, to 69% when SC, UPE and Ca*P were > or =2.41 mg/dl, > or =3 g/24 h and > or =32.64 mg2/dl2, respectively. Receiver operating characteristic curves showed that within lowest, middle and highest tertiles of basal SC (0.90-1.65, 1.66-2.40 and 2.41-6.30 mg/dl, respectively) the model accurately predicted ESRD (AUC = 0.80, 0.72 and 0.65; p = 0.0003, 0.0001 and 0.0022, respectively), quality of life or treatment costs. CONCLUSION: Integrated use of regression analysis and probabilistic models allows computation of individual risk of progression to ESRD and related utilities. This may help in optimizing care and costs in nephrology and other medical areas and designing trials in high-risk patients.

Analysis of Variance↗
PubMed2004

Probabilistic model of decompression sickness based on stochastic models of bubbling in tissues.

BACKGROUND: Decompression sickness (DCS) is caused by gas bubbles formed from pre-existing and new microscopic gas nuclei in blood and tissues. Assuming a random pattern of bubbling processes in living tissues, we developed a probabilistic model of DCS. We hypothesized that symptoms of DCS in an individual exposed to decompression appear when the total volume of bubbles in a unit volume of any tissue, w(t), exceeds the critical specific volume of a free gas phase, wcr. Therefore, one may consider the expectation of w(t)/wcr as a measure of the dynamic risk of gas bubble lesion of a given tissue segment. METHODS: Using the standard approach to estimation of various risks and the sum rule of probabilities of joint events, we defined the cumulative probability of DCS onset by the equation Pcum(t) = 1 - exp[Fcum(t)], where Fcum(t) = sigmaVnQnMnc(t), Qn = 1/wncr, where Vn is the volume of a tissue n. The function Mnc(t) coincides with the function Mn(t), defining a time history of the expectation of wn(t) until it achieves its maximum and then becomes a constant. Evaluating Pcum(t) for particular altitude decompressions, we identified the additive cumulative risk function of development of any DCS symptoms, Fcum-tot(t), with the function defining the cumulative risk of any bubble lesion of the "worst" virtual tissue (WVT) of Type A. On the other hand, we identified the additive cumulative risk function of development of intolerable DCS symptoms, Fcum-int(t), with the function defining the cumulative risk of acute bubble lesion of the WVT of Type phi. RESULTS: We found parameters of the curves Pcum-tot(t) and Pcum-int(t) that fit the known empirical curves for the cumulative probability of DCS onset. For men performing mild exercise at 30 kPa after preoxygenation, our estimated parameters for curves Pcum-tot(t) indicate that the WVTs of Type A have nitrogen washout half-times of 260 and 290 min for preoxygenation times of 75 and 135 min, respectively. On the other hand, the parameters of curves Pcum-int(t) show that the WVTs of Type phi in men performing mild exercise at 20-40 kPa after preoxygenation during 0-6 h are virtual tissues with nitrogen washout half-times of 400 to 615 min. CONCLUSION: Our model provides a new approach to predicting DCS risk for various decompression profiles. By demonstrating the dependence of DCS risk on body tissue parameters, the model explains why resistance to DCS in mammals increases with a lower body mass and greater specific blood flow in tissues.

Decompression Sickness↗
PubMed2005

Fuzzy-probabilistic model for risk assessment of radioactive material railway transportation.

Transportation of radioactive materials is obviously accompanied by a certain risk. A model for risk assessment of emergency situations and terrorist attacks may be useful for choosing possible routes and for comparing the various defence strategies. In particular, risk assessment is crucial for safe transportation of excess weapons-grade plutonium arising from the removal of plutonium from military employment. A fuzzy-probabilistic model for risk assessment of railway transportation has been developed taking into account the different natures of risk-affecting parameters (probabilistic and not probabilistic but fuzzy). Fuzzy set theory methods as well as standard methods of probability theory have been used for quantitative risk assessment. Information-preserving transformations are applied to realise the correct aggregation of probabilistic and fuzzy parameters. Estimations have also been made of the inhalation doses resulting from possible accidents during plutonium transportation. The obtained data show the scale of possible consequences that may arise from plutonium transportation accidents.

Body Burden↗
PubMed1986

A probabilistic model for fitting MWC polynomials in protein-ligand binding.

Given a binding polynomial in Adair form, A(x) = 1 + beta 1 x + ... + beta n x n, beta i greater than or equal to 0, a basic problem is to determine a method of fitting a model polynomial to A(x) and a quantitative measure of the goodness of fit. This paper presents such a method for fitting Monod-Wyman-Changeux (MWC) model polynomials when A(x) is of degree three or four. The method of fitting is based on the property that the zeros of an MWC polynomial of any degree lie on a circle in the complex plane. The parameters in the MWC model are determined so that if possible this circle coincides with the circle on which lie the zeros of A(x). The measure of goodness of fit is provided by a probabilistic model which gives the probability that a binding polynomial has its zeros on a circle on which lie the zeros of an MWC polynomial and if so, the probability that the juxtaposition of the two sets of zeros can occur by chance alone.

Kinetics↗
PubMed2005

Probabilistic models for food-borne disease risk assessment.

Risk assessment is a tool used by manufacturers, governmental, or regulatory bodies to evaluate the safety of food production systems and decide on strategies to protect consumers. This article presents a general approach to the use of probabilistic models to assess the risk related to specific hazards in some categories of food. It discusses their value in organising and analysing the scientific knowledge about the factors that most affect risk along the food production chain, but also highlights the data gaps that currently hamper accurate risk assessment.

Animals↗