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 829 records · Page 46Linked to original sources

PubMed2003

Application of physiologically based toxicokinetic modelling to study the impact of the exposure scenario on the toxicokinetics and the behavioural effects of toluene in rats.

The toxicity of inhalatory exposure to organic solvents may not only be related to the total external dose, but also to the pattern of exposure. In this study physiologically based toxicokinetic (PBTK) modelling has been used to study the impact of the exposure scenario on the toxicokinetics and the behavioural effects of the model solvent toluene in rats. After construction of the model with parameters from literature, toxicokinetic data were collected from rats exposed to either a constant concentration or fluctuating concentrations at total external dose levels of 20,000 and 10,000 ppm x h for model validation. At the same exposure conditions the effects on learned performance were evaluated in separate groups of rats using a visual discrimination task. In general, the PBTK model provided reliable predictions of the toxicokinetics of toluene at different exposure scenarios, but it also tended to underestimate the blood and brain concentrations in the descending parts of the tissue concentration-time curves. At these high dose levels the differences in toxicokinetics between the constant and the fluctuating exposure groups were relatively small. The visual discrimination experiments demonstrated a slowing of response speed and disinhibition of responding in all toluene-exposed groups. The results suggest that the brain concentration of toluene is one of the major determinants of its effect on disinhibition of responding.

Administration, Inhalation↗

PubMed2005

Competence and performance in causal learning.

The dominant theoretical approach to causal learning postulates the acquisition of associative weights between cues and outcomes. This reduction of causal induction to associative learning implies that learners are insensitive to important characteristics of causality, such as the inherent directionality between causes and effects. An ongoing debate centers on the question of whether causal learning is sensitive to causal directionality (as is postulated by causal-model theory) or whether it neglects this important feature of the physical world (as implied by associationist theories). Three experiments using different cue competition paradigms are reported that demonstrate the competence of human learners to differentiate between predictive and diagnostic learning. However, the experiments also show that this competence displays itself best in learning situations with few processing demands and with convincingly conveyed causal structures. The study provides evidence for the necessity to distinguish between competence and performance in causal learning.

Adult↗

PubMed2026

Biological Foundation Models for Complex Disease Research and Clinical Translation.

Complex diseases, including cancer, rare genetic disorders, neurodevelopmental and psychiatric conditions, and neurodegenerative diseases, arise from interactions among genetic variation, gene regulation, and cellular states that are difficult to capture using a single data type or biological scale. Biological foundation models address this challenge by treating nucleotides and genes as tokens and learning representations that can be transferred to downstream biomedical and clinical tasks. In this review, we examine two major model classes, genomic sequence foundation models and cell foundation models, and compare their tokenization strategies, model architectures, pretraining objectives, and adaptation methods. We summarize their emerging applications in regulatory variant interpretation, disease-associated cell-state analysis, drug-response prediction, and therapeutic target discovery across complex diseases. We distinguish applications supported by experimental or retrospective validation from those that remain primarily computational or conceptual. We further discuss key challenges to clinical translation, including multimodal data integration, model interpretability, benchmarking, patient-specific prediction, and privacy protection. We highlight future opportunities to integrate biological foundation models with emerging frameworks of medical digital twins, agentic AI, and federated learning. By linking model design to translational goals, this review provides a practical framework for evaluating biological foundation models and their readiness for complex disease research and clinical use.

biological foundation model↗

PubMed2006

Parent and child anxiety sensitivity: relationship to children's experimental pain responsivity.

UNLABELLED: Anxiety sensitivity (AS) or fear of anxiety sensations has been linked to childhood learning history for somatic symptoms, suggesting that parental AS may impact children's responses to pain. Using structural equation modeling, we tested a conceptual model in which parent AS predicted child AS, which in turn predicted a hypothesized latent construct consisting of children's pain intensity ratings for 3 laboratory pain tasks (cold pressor, thermal heat, and pressure). This conceptual model was tested in 211 nonclinical parent-child pairs (104 girls, 107 boys; mean age 12.4 years; 178 mothers, 33 fathers). Our model was supported in girls only, indicating that the sex of the child moderated the hypothesized relationships. Thus, parent AS was related to child laboratory pain intensity via its contribution to child AS in girls but not in boys. In girls, 42% of the effect of parent AS on laboratory pain intensity was explained via child AS. In boys, there was no clear link between parent AS and child AS, although child AS was predictive of experimental pain intensity across sex. Our results are consistent with the notion that parent AS may operate via healthy girls' own fear of anxiety symptoms to influence their responses to laboratory pain stimuli. PERSPECTIVE: The present study highlights sex differences in the links among parent and child anxiety sensitivity (fear of anxiety sensations) and children's experimental pain responses. Among girls, childhood learning history related to somatic symptoms may be a particularly salient factor in the development of anxiety sensitivity and pain responsivity.

Adolescent↗

PubMed2004

Doing without schema hierarchies: a recurrent connectionist approach to normal and impaired routine sequential action.

In everyday tasks, selecting actions in the proper sequence requires a continuously updated representation of temporal context. Previous models have addressed this problem by positing a hierarchy of processing units, mirroring the roughly hierarchical structure of naturalistic tasks themselves. The present study considers an alternative framework, in which the representation of context depends on recurrent connections within a network mapping from environmental inputs to actions. The ability of this approach to account for human performance was evaluated by applying it, through simulation, to a specific everyday task. The resulting model learned to deal flexibly with a complex set of sequencing constraints, encoding contextual information at multiple time scales within a single, distributed internal representation. Degrading this representation led to errors resembling those observed both in everyday behavior and in apraxia. Analysis of the model's function yielded numerous predictions relevant to both normal and apraxic performance.

Cognition↗

PubMed2004

Inferring pathways and networks with a Bayesian framework.

Numerous mathematical methods have been adapted and developed to quantitatively reverse engineer biological networks, for example, signal transduction pathways, from experimental micro-array data. Compared with stochastic methods, such as Boolean networks, and deterministic methods, such as thermodynamic or differential equation-based models, Bayesian network analysis has the ability to assess, with scoring metrics, causal relations based on conditional probabilities and thus permit hypothesis testing. The goal of this paper is to illustrate the integration of several Bayesian based techniques into a unified Bayesian framework that can infer hepatocellular networks from metabolic data. Reverse engineering of pathways and networks provides a framework for predictive modeling and hypotheses testing to gain deeper insight into living organisms, disease mechanisms, and targeted therapeutics. Evaluating this methodology initially against the known biochemical network provides confidence in the networks that are uncovered from the experimental data using this framework. From the metabolic data we inferred the known sub-networks, such as the tricarboxylic acid (TCA) and urea cycles. In addition, we combined the relationships learned from the data and our current knowledge of the biological system to postulate several alternative metabolic sub-network models that can predict a particular cellular function, such as intracellular triglyceride accumulation.

Algorithms↗

PubMed2000

An investigation of current models of second language speech perception: the case of Japanese adults' perception of English consonants.

This study reports the results of two experiments with native speakers of Japanese. In experiment 1, near-monolingual Japanese listeners participated in a cross-language mapping experiment in which they identified English and Japanese consonants in terms of a Japanese category, then rated the identifications for goodness-of-fit to that Japanese category. Experiment 2 used the same set of stimuli in a categorial discrimination test. Three groups of Japanese speakers varying in English-language experience, and one group of native English speakers participated. Contrast pairs composed of two English consonants, two Japanese consonants, and one English and one Japanese consonant were tested. The results indicated that the perceived phonetic distance of second language (L2) consonants from the closest first language (L1) consonant predicted the discrimination of L2 sounds. In addition, this study investigated the role of experience in learning sounds in a second language. Some of the consonant contrasts tested showed evidence of learning (i.e., significantly higher scores for the experienced than the relatively inexperienced Japanese groups). The perceived phonetic distance of L1 and L2 sounds was found to predict learning effects in discrimination of L1 and L2 sounds in some cases. The results are discussed in terms of models of cross-language speech perception and L2 phonetic learning.

Adult↗

PubMed1991

Typicality in logically defined categories: exemplar-similarity versus rule instantiation.

A rule-instantiation model and a similarity-to-exemplars model were contrasted in terms of their predictions of typicality judgments and speeded classifications for members of logically defined categories. In Experiment 1, subjects learned a unidimensional rule based on the size of objects. It was assumed that items that maximally instantiated the rule were those farthest from the category boundary that separated small and large stimuli. In Experiment 2, subjects learned a disjunctive rule of the form "x or y or both". It was assumed that items that maximally instantiated the rule were those with both positive values (x and y). In both experiments, the frequency with which different exemplars were presented during classification learning was manipulated across conditions. These frequency manipulations exerted a major impact on subjects' postacquisition goodness-of-example judgments, and they also influenced reaction times in a speeded classification task. The results could not be predicted solely on the basis of the degree to which the rules were instantiated. The goodness judgments were predicted fairly well by a mixed exemplar model involving both relative-similarity and absolute-similarity components. It was concluded that even for logically defined concepts, stored exemplars may form a major component of the category representation.

Attention↗

PubMed1995

A multiscale dynamic routing circuit for forming size- and position-invariant object representations.

We describe a neural model for forming size- and position-invariant representations of visual objects. The model is based on a previously proposed dynamic routing circuit that remaps selected portions of an input array into an object-centered reference frame. Here, we show how a multiscale representation may be incorporated at the input stage of the model, and we describe the control architecture and dynamics for a hierarchical, multistage routing circuit. Specific neurobiological substrates and mechanisms for the model are proposed, and a number of testable predictions are described.

Attention↗

PubMed2003

Distinguishing enzyme structures from non-enzymes without alignments.

The ability to predict protein function from structure is becoming increasingly important as the number of structures resolved is growing more rapidly than our capacity to study function. Current methods for predicting protein function are mostly reliant on identifying a similar protein of known function. For proteins that are highly dissimilar or are only similar to proteins also lacking functional annotations, these methods fail. Here, we show that protein function can be predicted as enzymatic or not without resorting to alignments. We describe 1178 high-resolution proteins in a structurally non-redundant subset of the Protein Data Bank using simple features such as secondary-structure content, amino acid propensities, surface properties and ligands. The subset is split into two functional groupings, enzymes and non-enzymes. We use the support vector machine-learning algorithm to develop models that are capable of assigning the protein class. Validation of the method shows that the function can be predicted to an accuracy of 77% using 52 features to describe each protein. An adaptive search of possible subsets of features produces a simplified model based on 36 features that predicts at an accuracy of 80%. We compare the method to sequence-based methods that also avoid calculating alignments and predict a recently released set of unrelated proteins. The most useful features for distinguishing enzymes from non-enzymes are secondary-structure content, amino acid frequencies, number of disulphide bonds and size of the largest cleft. This method is applicable to any structure as it does not require the identification of sequence or structural similarity to a protein of known function.

Algorithms↗

PubMed1996

Memory for places: a navigational model in support of Marr's theory of hippocampal function.

In this report we describe a model that applies Marr's theory of hippocampal function to the problem of map-based navigation. Like many others we attribute a spatial memory function to the hippocampus, but we suggest that the additional functional components required for map-based navigation are located elsewhere in the brain. One of the key functional components in this model is an egocentric map of space, located in the neocortex, that is continuously updated using ideothetic (self-motion) information. The hippocampus stores snapshots of this egocentric map. The modeled activity pattern of head direction cells is used to set the best egocentric map rotation to match the snapshots stored in the hippocampus, resulting in place cells with a nondirectional firing pattern. We describe an evaluation of this model using a mobile robot and demonstrate that with this model the robot can recognize an environment and find a hidden goal. This model is discussed in the context of prior experiments that were designed to discover the map-based spatial processing of animals. We also predict the results of further experiments.

Animals↗

PubMed2005

Accurate quantitative structure-property relationship model to predict the solubility of C60 in various solvents based on a novel approach using a least-squares support vector machine.

A least-squares support vector machine (LSSVM) was used for the first time as a novel machine-learning technique for the prediction of the solubility of C60 in a large number of diverse solvents using calculated molecular descriptors from the molecular structure alone and on the basis of the software CODESSA as inputs. The heuristic method of CODESSA was used to select the correlated descriptors and build the linear model. Both the linear and the nonlinear models can give very satisfactory prediction results: the square of the correlation coefficient R(2) was 0.892 and 0.903, and the root-mean-square error was 0.126 and 0.116, respectively, for the whole data set. The prediction result of the LSSVM model is better than that obtained by the heuristic method and the reference, which proved LSSVM was a useful tool in the prediction of the solubility of C60. In addition, this paper provided a new and effective method for predicting the solubility of C60 from its structures and gave some insight into the structural features related to the solubility of C60 in different solvents.

Electrochemistry↗

PubMed2001

Slow down, you move too fast: emotional intelligence remains an "elusive" intelligence.

Commentators on the R. D. Roberts, M. Zeidner, and G. Matthews (2001) article on the measurement of emotional intelligence (EI) made various pertinent observations that confirm the growing interest in this topic. This rejoinder finds general agreement on some key issues: learning from the history of ability testing, developing more sophisticated structural models of ability, studying emotional abilities across the life span, and establishing predictive and construct validity. However, scoring methods for tests of EI remain problematic. This rejoinder acknowledges recent improvements in convergence between different scoring methods but discusses further difficulties related to (a) neglect of group differences in normative social behaviors, (b) segregation of separate domains of knowledge linked to cognitive and emotional intelligences, (c) potential confounding of competence with learned skills and cultural factors, and (d) lack of specification of adaptive functions of EI. Empirical studies have not yet established that the Multi-Factor Emotional Intelligence Scale and related tests assess a broad EI factor of real-world significance.

Adaptation, Psychological↗

PubMed2004

A model of antipsychotic action in conditioned avoidance: a computational approach.

The selective ability of antipsychotic drugs (APDs) to attenuate conditioned avoidance responding (CAR) has been recognized for over 50 years. However, most efforts to account for this finding have been either neurochemically oriented (focusing on the neuromodulator dopamine) or behavioral, with little effort invested in uniting the two within a computational model. In this paper we propose a computational model, based on concepts from formal reinforcement learning theory, which accounts for the basic finding that noncataleptic doses of APDs disrupt avoidance without disrupting escape. The model formally separates out sensory, motor, and reward processes, and makes novel predictions pertaining to the dose- and time-dependent effects of APDs on response latencies--predictions which we verified in experimental studies using four different APDs (haloperidol, chlorpromazine, risperidone, and clozapine). The APD action in this model is most consistent with an effect on 'expected future reward'--an idea closely linked to motivational drives and consistent with several leading theories of dopamine action.

Animals↗

PubMed1995

Associative learning in acutely ill and recovered schizophrenic patients.

Eight acutely ill deluded schizophrenic patients were compared with eight matched recovered patients on an associative learning task. Ten word pair associations were presented over five trials. Subsequently the subjects were presented with ten novel pairings over three trials, one word from the first pair associated with a new partner. Recovered patients performed better than acutely ill patients on both stages of the task. This result does not support the neuropsychological model of Gray et al. (1991) which predicts that acute schizophrenia is characterised by a weakening of the effect of previous experience on new learning.

Acute Disease↗

PubMed2004

Modeling the effects of prior knowledge on learning incongruent features of category members.

The authors conducted 3 experiments addressing the issue of how observations and multiple sources of prior knowledge are put together in category learning. In Experiments 1 and 2, learning was faster for critical features, which were predictable on the basis of prior knowledge, than for filler features, and this advantage increased as more observations were made. In addition, learning was fastest for incongruent features that could only be predicted using knowledge from other domains. In Experiment 3, presenting contradictory features that violated prior knowledge led to rote learning rather than use of prior knowledge. The results were simulated with the Baywatch model, which addresses how observations of category members lead to recruitment and selection of sources of prior knowledge.

Cognition↗

PubMed1997

Retrieving cases for treatment advice in nursing using text representation and structured text retrieval.

A nursing database which records patient details and treatments as fields in a standard database format is transformed into a collection, in text form, of patient case days with history. Each case is represented as text strings encoding the patient details, the current problems, treatments and their associated history. The cosine measure of similarity is used to compute a whole case similarity between a text query and the cases in text form. This standard text retrieval technique is used and compared to a simple rule base. In case-based reasoning, the similarity of cases is often computed by combining similarities of the case features involved. In this work the standard text retrieval function is modified to incorporate this case structure by combining individual matches of case components based on the cosine measure. The combination is based on a linear regression model for learning the weights assigned to the components of this retrieval function. For the 1355 records two tasks were tried: predicting the treatment for a new problem and predicting the treatment for a continuing problem when a change of treatment is required. Simple text retrieval was better than the rule base for one task and case structured retrieval was at least 18% better on both tasks. Further techniques are discussed.

Age Factors↗

PubMed2003

Learning to control a brain-machine interface for reaching and grasping by primates.

Reaching and grasping in primates depend on the coordination of neural activity in large frontoparietal ensembles. Here we demonstrate that primates can learn to reach and grasp virtual objects by controlling a robot arm through a closed-loop brain-machine interface (BMIc) that uses multiple mathematical models to extract several motor parameters (i.e., hand position, velocity, gripping force, and the EMGs of multiple arm muscles) from the electrical activity of frontoparietal neuronal ensembles. As single neurons typically contribute to the encoding of several motor parameters, we observed that high BMIc accuracy required recording from large neuronal ensembles. Continuous BMIc operation by monkeys led to significant improvements in both model predictions and behavioral performance. Using visual feedback, monkeys succeeded in producing robot reach-and-grasp movements even when their arms did not move. Learning to operate the BMIc was paralleled by functional reorganization in multiple cortical areas, suggesting that the dynamic properties of the BMIc were incorporated into motor and sensory cortical representations.

Animals↗