SEARCH · PubMed Health

Results for “Predictive Learning Models”

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 1,567 records · Page 87Linked to original sources

PubMed2004

Missing information in multiple-cue probability learning.

In a multiple-cue probability learning task, participants learned to use six discrete symptoms (i.e., cues) to diagnose which of three possible flu strains a hypothetical patient suffered from. For some patients, information regarding the status of certain symptoms was not available. Various possible ways in which the missing cue information might be processed were distinguished and tested in a series of three experiments (Ns = 80, 109, and 61). The results suggest that the judged probability of the outcome variable (i.e., flu strain) was assessed by "filling in" the missing cue information with a mean value based on previous observations. The predictions of other methods of processing missing cue information are inconsistent with the data.

Cues↗

PubMedDate not supplied

Using surrogate modeling in the prediction of fibrinogen adsorption onto polymer surfaces.

We present a Surrogate (semiempirical) Model for prediction of protein adsorption onto the surfaces of biodegradable polymers that have been designed for tissue engineering applications. The protein used in these studies, fibrinogen, is known to play a key role in blood clotting. Therefore, fibrinogen adsorption dictates the performance of implants exposed to blood. The Surrogate Model combines molecular modeling, machine learning and an Artificial Neural Network. This novel approach includes an accounting for experimental error using a Monte Carlo analysis. Briefly, measurements of human fibrinogen adsorption were obtained for 45 polymers. A total of 106 molecular descriptors were generated for each polymer. Of these, 102 descriptors were computed using the Molecular Operating Environment (MOE) software based upon the polymer chemical structures, two represented different monomer types, and two were measured experimentally. The Surrogate Model was developed in two stages. In the first stage, the three descriptors with the highest correlation to adsorption were determined by calculating the information gain of each descriptor. Here a Monte Carlo approach enabled a direct assessment of the effect of the experimental uncertainty on the results. The three highest-ranking descriptors, defined as those with the highest information gain for the sample set, were then selected as the input variables for the second stage, an Artificial Neural Network (ANN) to predict fibrinogen adsorption. The ANN was trained using one-half of the experimental data set (the training set) selected at random. The effect of experimental error on predictive capability was again explored using a Monte Carlo analysis. The accuracy of the ANN was assessed by comparison of the predicted values for fibrinogen adsorption with the experimental data for the remaining polymers (the validation set). The mean value of the Pearson correlation coefficient for the validation data sets was 0.54 +/- 0.12. The average root-mean-square (relative) error in prediction for the validation data sets is 38%. This is an order of magnitude less than the range of experimental values (i.e., 366%) and compares favorably with the average percent relative standard deviation of the experimental measurements (i.e., 17.9%). The effects of each of the user-defined parameters in the ANN were explored. None were observed to have a significant effect on the results. Thus, the Surrogate Model can be used to accurately and unambiguously identify polymers whose fibrinogen absorption is at the limits of the range (i.e., low or high) which is an essential requirement for assessing polymers for regenerative tissue applications.

Adsorption↗

PubMed1983

Critical considerations in the assessment of health and environmental risks - what we have learned from the nuclear experience.

The radiological experience has produced some sophisticated approaches to estimating the environmental risks of anthropogenic chemicals, based on well-validated models for both health effects and exposure assessment. As to exposure assessment, site- and situation-specific data must be acquired for quantitative predictions. However, the requirements for quantitative estimation are often overlooked, even with the radiological models. Metabolism or other chemical processes, also, may more profoundly alter a chemical contaminant than they would a radioelement. Suitably developed models provide useful guidance in deciding what kinds of data to get and how extensive particular data bases need to be.

Air Pollutants, Occupational↗

PubMed2026

Comprehensive evaluation of AlphaFold/OpenFold prediction of experimentally unresolved proteins through novel metrics.

Predicting accurate protein structures is essential for understanding molecular mechanisms, interpreting the impact of sequence variation, and supporting translational applications ranging from drug discovery to clinical genomics. Recent advances in deep-learning-based predictors such as AlphaFold2, OpenFold, and AlphaFold3 have transformed structural biology, enabling routine in silico modeling even for challenging or previously uncharacterized proteins. However, systematic benchmarking of these tools-especially for novel targets and single amino acid variants-remains limited. Conventional global metrics often fail to capture biologically meaningful discrepancies. By evaluating multiple implementations of AlphaFold2 and OpenFold, together with ColabFold and the AlphaFold3 server, across 10 different proteins and 222 single amino acid protein variants encompassing a wide range of sizes, structures, and functions, we show that although widely used global indicators-like mean pLDDT, pTM-score, and RMSD-frequently suggest comparable performance, substantial local-level differences remain elusive. To address this gap, we introduce a comparative framework leveraging Bland-Altman agreement analysis, to evaluate per-residue Cα-confidence differences and Per-Residue profiles (PRPs), complemented by Uniform Manifold Approximation and Projection (UMAP). This approach reveals marked localized divergences, particularly within flexible or intrinsically disordered regions, where both predictor choice and single-residue substitutions trigger the largest conformational shifts. We further demonstrate that using reduced homology databases has minimal impact on predicted structural quality, offering computationally efficient alternatives. Collectively, our findings underscore the importance of integrating global and residue-specific evaluations to more accurately assess robustness, agreement, and practical usability across contemporary protein structure prediction methods.

Proteins↗

PubMed2003

Towards a theory of the laminar architecture of cerebral cortex: computational clues from the visual system.

One of the most exciting and open research frontiers in neuroscience is that of seeking to understand the functional roles of the layers of cerebral cortex. New experimental techniques for probing the laminar circuitry of cortex have recently been developed, opening up novel opportunities for investigating how its six-layered architecture contributes to perception and cognition. The task of trying to interpret this complex structure can be facilitated by theoretical analyses of the types of computations that cortex is carrying out, and of how these might be implemented in specific cortical circuits. We have recently developed a detailed neural model of how the parvocellular stream of the visual cortex utilizes its feedforward, feedback and horizontal interactions for purposes of visual filtering, attention and perceptual grouping. This model, called LAMINART, shows how these perceptual processes relate to the mechanisms that ensure the stable development of cortical circuits in the infant, and to the continued stability of learning in the adult. The present article reviews this laminar theory of visual cortex, considers how it may be generalized towards a more comprehensive theory that encompasses other cortical areas and cognitive processes, and shows how its laminar framework generates a variety of testable predictions.

Adaptation, Physiological↗

PubMed2005

Alpha phase synchronization predicts P1 and N1 latency and amplitude size.

The oscillatory phase-resetting model predicts that event-related potential (ERP) components are generated by a superposition of evoked oscillations with different frequencies. We investigate this question in a memory task in which human subjects had to retrieve a verbal label in response to the presentation of a picture. The results show that (i) evoked oscillations in the delta, theta, alpha and beta range undergo a significant phase resetting and (ii) become synchronized in absolute phase during small time windows that (iii) coincide with the latencies of the P1-N1 complex. Our conclusion is that the latencies of ERP components can be predicted at least in part by phase synchronization between frequencies.

Adult↗

PubMed1990

A taste aversion model of drug discrimination learning: training drug and condition influence rate of learning, sensitivity and drug specificity.

A model of drug discrimination based on a lithium chloride (LiCl) flavour aversion was described and examined. Mildly thirsty rats were presented daily with 4 ml of a distinctly flavoured solution which was followed on 50% of the days by an IP injection of LiCl. Prior to the flavour presentation, the rats were injection SC with saline or a training drug (0.04 mg/kg fentanyl or 20 mg/kg pentobarbital) to signal whether LiCl would follow. Almost all rats eventually exhibited stable behaviour that involved drinking most or all of the fluid when it was not to be followed by LiCl and little or no drinking when it was. Such discrimination occurred regardless of whether drug predicted LiCl (learned-discomfort) or predicted no LiCl (learned-safety). However, with fentanyl there were clear differences between rats trained with drug under learned-safety and under learned-discomfort conditions for 1) the rate of acquisition of stable performance as a function of LiCl dose, 2) generalization of the training dose to a test dose that was lower, and 3) elicitation of fentanyl responses by pentobarbital. These findings, together with indications that such effects did not always occur with pentobarbital as the training drug, were discussed from theoretical and practical perspectives.

Animals↗

PubMed1989

Attributional style and depressive mood reactions.

According to the reformulated learned helplessness model of depression, individuals who characteristically attribute negative events to internal-stable-global causes become depressed when confronted with negative life events. This proposition was tested in a field and a laboratory study in settings with an interpersonal, socially relevant character. In the field study, the attributional style of 86 female college students was investigated before Christmas, and their mood was recorded both before and after Christmas. The laboratory study recorded the mood of 46 female students before and after either success or failure. In both studies changes in depressive mood were predicted by the Attribution X Outcome interaction. The direction and form of the interaction were in line with the diathesis-stress model. In the field study, but not the laboratory study, outcome was a significant predictor of changes in depressive mood.

Adult↗

PubMed2006

A mouse model of posttraumatic stress disorder that distinguishes between conditioned and sensitised fear.

The pathomechanisms of posttraumatic stress disorder (PTSD) are still unknown, but both fear conditioning and stress sensitisation are supposed to play a crucial role. Hence, valid animal models that model both associative and non-associative components of fear will facilitate elucidation of the biological substrates of the illness, and to develop novel and specific approaches for its prevention and therapy. Here we applied a single electric footshock to C57BL/6N (B6N) and C57BL/6JOla (B6JOla) mice and recorded the conditioned response to contextual trauma reminders (associative fear), the sensitised reaction to a neutral tone in a novel environment (non-associative fear, hyperarousal), social interaction and various emotional behaviours using Modified Holeboard, Test for Novelty-Induced Suppression of Feeding and Forced Swimming Test, after different incubation times (1, 14, 28 days). Freezing generally increased as a function of shock intensity. In B6N mice, sensitised fear was maximal 28 days after trauma and was accompanied by signs of emotional blunting and social withdrawal. B6JOla mice, in contrast, were less susceptible to develop PTSD-like symptoms. The phenotype of B6N exhibited high behavioural variance, allowing distinction between vulnerable and resilient individuals. Only in vulnerable B6N mice, chronic fluoxetine treatment - initiated after an incubation period of 28 days - ameliorated sensitised fear. This new mouse model fulfils common criteria for face and predictive validity and can be used to investigate the biological correlates of individual fear susceptibility, as well as the impact and interrelationship of associative and non-associative fear components in the development and maintenance of PTSD.

Administration, Oral↗

PubMed1995

Implicit and explicit memory bias in anxiety: a conceptual replication.

Williams, Watts, MacLeod and Mathews' (1988) [Cognitive psychology and the emotional disorders. Chichester, Wiley] model of anxiety and cognition leads to the prediction that anxious subjects will show an implicit, but not an explicit, memory advantage for threat-related information. Mathews, Mogg, May and Eysenck (1989) [Journal of Abnormal Psychology, 98, 401-407] obtained marginally significant support for this prediction in an experiment that tested memory using word stem completion tasks following a self-referent encoding procedure. However, neither the reliability nor generality of these findings have been established. The current experiment was designed to provide a conceptual replication of Mathews et al.'s study, using different tests of implicit memory (i.e. tachistoscopic identification) and explicit memory (i.e. recognition) and an alternative type of encoding task (i.e. colour naming stimulus words). 16 generalised anxiety disorder patients, and 16 non-anxious control subjects were tested. As predicted, the anxiety patients showed a relative implicit memory advantage for threat-related stimulus words, while the two subject groups did not differ in their pattern of explicit memory performance. These results support the predictions generated by Williams et al.'s model of anxiety and cognition.

Adult↗

PubMed2003

Lexical access without attention? Explorations using dichotic priming.

The authors used lexical decision in a dichotic listening situation and measured identity priming across channels to explore whether unattended stimuli can be processed lexically. In 6 experiments, temporal synchronization of prime and target words was manipulated, and acoustic saliency of the unattended prime was varied by embedding it in a carrier sentence or in babble speech. When the prime was acoustically salient, a cross-channel priming effect emerged, and participants were aware of the prime. When the prime was less salient, no identity priming was found, and participants failed to notice the prime. Saliency was manipulated in ways that did not degrade the prime. Results are inconsistent with models of late filtering, which predict equal priming irrespective of prime saliency.

Analysis of Variance↗

PubMed1990

Comparing scores on the Stanford-Binet, Fourth Edition with the WISC-R for exceptional children.

The purpose of the present study was to examine the performance of a sample of 19 exceptional children on both the Stanford-Binet Intelligence Scale, Fourth Edition (Stanford-Binet IV) and the WISC-R. Construct validity studies of the Stanford-Binet IV with the WISC-R have yielded results which provide only partial support for predictions derived from the theoretical model underlying this new measure. The results obtained for the naturally occurring sample of exceptional children indicate nonsignificant differences in performance between Stanford-Binet IV and WISC-R Full Scale IQ. As with prior studies, results provide only partial support for the predictions derived from the theoretical model. Explanatory hypotheses for the observed discrepancies are discussed.

Adolescent↗

PubMed1990

On the waterfront: predictive and reactive regulatory descriptions of thirst and sodium appetite.

The concepts of homeostasis and regulation are discussed and examples are given in which current regulatory models of ingestive behavior inadequately predict or explain the observed phenomena. The implications of this for the choice of experimental paradigms, and the interpretation of neurobiological data obtained therein, are discussed. Paradigms that allow the expression of behavioral strategies and learned responses may be biologically more relevant than the more popular but highly constrained "physiologic" paradigms.

Animals↗

PubMed2005

Structure-based classification of active and inactive estrogenic compounds by decision tree, LVQ and kNN methods.

The performance of decision tree (DT), learning vector quantization (LVQ), and k-nearest neighbour (kNN) methods classifying active and inactive estrogenic compounds in terms of their structure activity relationship (SAR) was evaluated. A set of 311 compounds was used for construction of the models, the predictive power of which was verified with separate training and test sets. Principal components derived from molecular descriptors calculated with DRAGON software were used as variables representing the structures of the compounds. Broadly, kNN had the best classification ability and DT the weakest, although the performance of each method was dependent on the group of compounds used for modelling. The best performance was obtained with kNN for the calf estrogen receptor data, averaging 98.3% of correctly classified compounds in the external tests. Overall, the results indicate that all the methods tested are suitable for the SAR classification of estrogenic compounds, producing models with a predictive power ranging from adequate to excellent.

Animals↗

PubMed2005

GMDH-based feature ranking and selection for improved classification of medical data.

Medical applications are often characterized by a large number of disease markers and a relatively small number of data records. We demonstrate that complete feature ranking followed by selection can lead to appreciable reductions in data dimensionality, with significant improvements in the implementation and performance of classifiers for medical diagnosis. We describe a novel approach for ranking all features according to their predictive quality using properties unique to learning algorithms based on the group method of data handling (GMDH). An abductive network training algorithm is repeatedly used to select groups of optimum predictors from the feature set at gradually increasing levels of model complexity specified by the user. Groups selected earlier are better predictors. The process is then repeated to rank features within individual groups. The resulting full feature ranking can be used to determine the optimum feature subset by starting at the top of the list and progressively including more features until the classification error rate on an out-of-sample evaluation set starts to increase due to overfitting. The approach is demonstrated on two medical diagnosis datasets (breast cancer and heart disease) and comparisons are made with other feature ranking and selection methods. Receiver operating characteristics (ROC) analysis is used to compare classifier performance. At default model complexity, dimensionality reduction of 22 and 54% could be achieved for the breast cancer and heart disease data, respectively, leading to improvements in the overall classification performance. For both datasets, considerable dimensionality reduction introduced no significant reduction in the area under the ROC curve. GMDH-based feature selection results have also proved effective with neural network classifiers.

Breast Neoplasms↗

PubMed2007

Within-category discontinuity interacts with verbal rule complexity in perceptual category learning.

A test of the predicted interaction between within-category discontinuity and verbal rule complexity on information-integration and rule-based category learning was conducted. Within-category discontinuity adversely affected information-integration category learning but not rule-based category learning. Model-based analyses suggested that some information-integration participants improved performance by recruiting more "units" in the discontinuous condition. Verbal rule complexity adversely affected rule-based category learning but not information-integration category learning. Model-based analyses suggested that the rule based effect was on both decision criterion learning and variability in decision criterion placement. These results suggest that within-category discontinuity and decision rule complexity differentially impact information-integration and rule-based category learning and provide information regarding the detailed processing characteristics of these two proposed category learning systems.

Concept Formation↗

PubMed1995

Hormonal control of rheumatoid inflammation.

As other contributors to this volume have discussed, the genetic basis of rheumatoid arthritis (RA) is multifactorial. One aim of this chapter is to propose that perhaps an additional, non-MHC genetic factor contributing to the pathogenesis of RA may reside in a defective response of the neuroendocrine system to inflammatory stimuli. This proposal is based on work carried out in patients with RA and on lessons learned from animal models of chronic inflammatory disease. This chapter will not consider the effect of sex hormones on the pathogenesis of RA because the data are often contradictory and have yet to crystallize into a coherent hypothesis with testable predictions.

Acute Disease↗

PubMed2006

Factorial coding of natural images: how effective are linear models in removing higher-order dependencies?

The performance of unsupervised learning models for natural images is evaluated quantitatively by means of information theory. We estimate the gain in statistical independence (the multi-information reduction) achieved with independent component analysis (ICA), principal component analysis (PCA), zero-phase whitening, and predictive coding. Predictive coding is translated into the transform coding framework, where it can be characterized by the constraint of a triangular filter matrix. A randomly sampled whitening basis and the Haar wavelet are included in the comparison as well. The comparison of all these methods is carried out for different patch sizes, ranging from 2x2 to 16x16 pixels. In spite of large differences in the shape of the basis functions, we find only small differences in the multi-information between all decorrelation transforms (5% or less) for all patch sizes. Among the second-order methods, PCA is optimal for small patch sizes and predictive coding performs best for large patch sizes. The extra gain achieved with ICA is always less than 2%. In conclusion, the edge filters found with ICA lead to only a surprisingly small improvement in terms of its actual objective.

Algorithms↗