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 1,441 records · Page 80Linked to original sources

PubMed1990

Structure and stimulation in the ontogeny of spoken language.

Linguistic innateness is a fundamentally physical notion, which ultimately requires independent physical evidence. For spoken language, it is relevant to consider babbling, components of which are unaffected by ambient stimulation and are predicted by models of vocal tract function. Links between babbling and speech point to innate factors in the ontogeny of spoken language and invite attention to central control mechanisms. These neural capabilities enable oral language learning by providing children with control over an initial stock of speech-like movements and by directing their attention to salient linguistic patterns. Dispositions to attend to some cues are so strong that little stimulation is required. In other cases, predispositions are weak, and acquisition requires correspondingly more experience. To understand the ontogeny of language, we need to learn which cases are which and to know how these interactions occur and change over the course of acquisition.

Animals↗

PubMed2005

Computational modeling of dendrites.

Computational methods have been part of neuroscience for many years. For example, models developed with these methods have provided a theory that helps explain the action potential. More recently, as experimental patch-electrode techniques have revealed new biophysics related to dendritic function and synaptic integration, computational models of dendrites have been developed to explain and further illuminate these results, and to predict possible additional behavior. Here, a collection of computational models of dendrites is reviewed. The goal is to help explain how such computational techniques work, some of their limitations, and what one can hope to learn about dendrites by modeling them.

Action Potentials↗

PubMed1996

Application of the fuzzy ARTMAP neural network model to medical pattern classification tasks.

This paper presents research into the application of the fuzzy ARTMAP neural network model to medical pattern classification tasks. A number of domains, both diagnostic and prognostic, are considered. Each such domain highlights a particularly useful aspect of the model. The first coronary care patient prognosis, demonstrates the ARTMAP voting strategy involving 'pooled' decision-making using a number of networks, each of which has learned a slightly different mapping of input features to pattern classes. The second domain, breast cancer diagnosis, demonstrates the model's symbolic rule extraction capabilities which support the validation and explanation of a network's predictions. The final domain, diagnosis of acute myocardial infarction, demonstrates a novel category pruning technique allowing the performance of a trained network to be altered so as to favour predictions of one class over another (e.g. trading sensitivity for specificity or vice versa). It also introduces a 'cascaded' variant of the voting strategy intended to allow identification of a subset of cases which the network has a very high certainty of classifying correctly.

Artificial Intelligence↗

PubMed2026

Genome-wide association, polygenic risk scores, and machine learning for chronic post-surgical pain risk stratification: A UK biobank study.

Chronic post-surgical pain is a prevalent and debilitating complication following surgery, representing a clinical challenge. Despite the established heritability of pain phenotypes, large-scale genetic studies remain limited. This study aimed to identify genetic variants associated with chronic post-surgical pain, develop polygenic risk scores, and integrate these with clinical features for risk prediction. UK Biobank data from 47,836 participants (2490 cases and 45,346 controls) were split into training (80%; n = 38,268) and validation (20%; n = 9568) sets prior to analysis. A genome-wide association study was conducted on the training set only, across 19 million variants, and polygenic risk scores were constructed and integrated with clinical features in a logistic regression framework. Two close, rare, imputed signals crossed the genome-wide significance threshold but lacked local linkage-disequilibrium support, while 220 variants crossed the suggestive threshold. In the held-out validation set, cases had higher mean polygenic risk scores than controls (0.138 vs. -0.021; Cohen's d = 0.16, p < 0.001). A logistic regression model integrating clinical features and polygenic risk scores achieved an area under the curve of 0.639 (95% CI: 0.583-0.693), higher than models using either feature set alone. The polygenic risk score for chronic post-surgical pain was among the most important predictors. Risk stratification revealed the top quartile had 3.84-fold higher odds of chronic post-surgical pain than the bottom quartile (95% CI: 2.00-7.37). These findings suggest a possible modest genetic contribution to chronic post-surgical pain. Polygenic risk scores may complement clinical factors in surgical risk stratification. PERSPECTIVE: Chronic post-surgical pain may have a modest genetic contribution. This UK Biobank study identified over 220 variants at suggestive significance and constructed a polygenic risk score that was significantly elevated in cases. A combined clinical-genomic model achieved a 3.84-fold difference in odds across predicted-risk quartiles.

Chronic post-surgical pain↗

PubMed2001

Prediction of enthalpy of alkanes by the use of radial basis function neural networks.

A new method for the prediction of enthalpy of alkanes between C6 and C10 from molecular structures has been proposed. Thirty five calculated descriptors were selected for the description of molecular structures. The first four scores of Principle Component Analysis on the calculated descriptors were used as inputs to predict the enthalpy of alkanes. Models relating relationships between molecular structure descriptors and enthalpy of alkanes were constructed by means of radial basis function neural networks. To get the best prediction results, some strategies were also employed to optimise the learning parameters of the radial basis function neural networks. For the test set, a predictive correlation coefficient of R = 0.9913 and root mean squared error of 0.5876 were obtained.

Journal Article↗

PubMedDate not supplied

Introducing the consensus modeling concept in genetic algorithms: application to interpretable discriminant analysis.

An evolutionary statistical learning method was applied to classify drugs according to their biological target and also to discriminate between a compilation of oral and nonoral drugs. The emphasis was placed not only on how well the models predict but also on their interpretability. In an enhancement to previous studies, the consistency of the model weights over several runs of the genetic algorithm was considered with the goal of producing comprehensible models. Via this approach, the descriptors and their ranges that contribute most to class discrimination were identified. Selecting a bin step size that enables the average descriptor properties of the class being trained to be captured improves the interpretability and discriminatory power of a model. The performance, consistency, and robustness of such models were further enhanced by using two novel approaches that reduce the variability between individual solutions: consensus and splice modeling. Finally, the ability of the genetic algorithm to discriminate between activity classes was compared with a similarity searching method, while naïve Bayes classifiers and support vector machines were applied in discriminating the oral and nonoral drugs.

Algorithms↗

PubMed2001

Predictors of pain catastrophizing in women with rheumatoid arthritis.

Catastrophizing has been conceptualized as an appraisal, a cognitive distortion, and a coping mechanism in the psychosocial literature. Regardless of its conceptualization, catastrophizing has been associated with negative psychological and physical outcomes in numerous studies, including our intervention study with 90 women with rheumatoid arthritis. Because of catastrophizing's robust relationship with negative outcomes, predictors of catastrophizing as a pain coping behavior were investigated in this sample, using data collected from two points in time before the intervention. Using Lazarus and Folkman's stress and coping theoretical framework to guide the analyses, variables with a proximal relationship to catastrophizing in the framework were examined for significant associations with pain catastrophizing using correlational analyses. Subsequent stepwise regression involving all variables from Time 1 with significant associations resulted in a model that explained 63% of the variance in Time 2 pain catastrophizing scores. The four predictors in this model were dispositional pessimism, passive pain coping, venting (as a pain coping behavior), and arthritis helplessness. Potential clinical implications related to these predictors are also discussed. Knowledge about predictors of catastrophizing may enhance efforts to address this maladaptive pattern through educational and therapeutic approaches.

Adaptation, Psychological↗

PubMed2000

Population pharmacokinetic analysis of netilmicin in neonates and infants with use of a nonparametric method.

BACKGROUND: Although the therapeutic and toxic effects of netilmicin are related to its plasma concentration, its pharmacokinetics in neonates and infants and the influence of clinical and biological variables have been only partially assessed. METHODS: Therapeutic drug monitoring data collected from 186 neonates and 95 infants receiving netilmicin were analyzed with a nonparametric population approach. The influence of gestational and postnatal age, weight, Apgar score, and creatinine and urea plasma concentrations on the pharmacokinetic parameters was assessed. The neonate and infant groups were each randomly divided into a learning sample and a validation sample. The population analysis was performed on each learning subgroup with the nonparametric maximum likelihood (NPML) method. In the validation group, the data were used to assess the concentration predictability. Because there is no specific netilmicin formulation for neonates and infants, an error model was proposed to account for errors attributable to dilution processes when preparing the infusion. RESULTS: In neonates, the covariates that reduced expected variance of plasma clearance by more than 10% were postnatal age, body weight, and plasma creatinine, as well as plasma urea and creatinine in infants. Body weight and sex played a significant role in explaining the variability of the volume of distribution. The accuracy of the concentration predictability assessed in the validation samples was satisfactory, and no significant bias was found. CONCLUSION: These findings help explain the large interindividual variability of the pharmacokinetics of netilmicin and the influence of the clinical and laboratory covariates in neonates and infants.

Age Factors↗

PubMed2025

Predicting emergent phenotypes from single cell populations using CELLECTION.

Biological systems exhibit emergent phenotypes that arise from the collective behavior of individual components, such as whole-organ functions that arise from the coordinated activity of its individual cells, or organism-level phenotypes that result from the functional interplay of collections of genes in the genome. We present CELLECTION, a deep learning framework that learns to associate subgroups of instances with different emergent phenotypes. We show CELLECTION enables interpretable predictions for heterogeneous tasks, including disease classification, identification of disease-associated cell subtypes, alignment of developmental stages between human model systems, and even predicting relative hand-wing indices across the avian lineage. CELLECTION therefore provides a scalable and flexible framework for identifying key cellular or genetic signatures underlying complex traits in development, disease, and evolution.

Journal Article↗

PubMed2004

Lessons learned from perinatal exposure to diethylstilbestrol.

The synthetic estrogen diethylstilbestrol (DES) is well documented to be a perinatal carcinogen in both humans and experimental animals. Exposure to DES during critical periods of differentiation permanently alters the programming of estrogen target tissues resulting in benign and malignant abnormalities in the reproductive tract later in life. Using the perinatal DES-exposed rodent model, cellular and molecular mechanisms have been identified that play a role in these carcinogenic effects. Although DES is a potent estrogenic chemical, effects of low doses of the compound are being used to predict health risks of weaker environmental estrogens. Therefore, it is of particular interest that developmental exposure to very low doses of DES has been found to adversely affect fertility and to increase tumor incidence in murine reproductive tract tissues. These adverse effects are seen at environmentally relevant estrogen dose levels. New studies from our lab verify that DES effects are not unique; when numerous environmental chemicals with weak estrogenic activity are tested in the experimental neonatal mouse model, developmental exposure results in an increased incidence of benign and malignant tumors including uterine leiomyomas and adenocarcinomas that are similar to those shown following DES exposure. Finally, growing evidence in experimental animals suggests that some adverse effects can be passed on to subsequent generations, although the mechanisms involved in these trans-generational events remain unknown. Although the complete spectrum of risks to DES-exposed humans are uncertain at this time, the scientific community continues to learn more about cellular and molecular mechanisms by which perinatal carcinogenesis occurs. These advances in knowledge of both genetic and epigenetic mechanisms will be significant in ultimately predicting risks to other environmental estrogens and understanding more about the role of estrogens in normal and abnormal development.

Adult↗

PubMed1997

Academic goals and emotions: results of a structural equation model and a cluster analysis.

BACKGROUND: Motivational researchers have suggested that the environment plays a key role in students' goal formation. However, some recent work (Seifert, 1996) suggests that students' emotions may play a role in goal formation. AIM: This study examined the relationship between environment, emotions, and goals. Do emotions and perceptions of teachers both contribute to goal orientation, or do emotions mediate the influence of perceptions of teachers on goal orientation? SAMPLE: 559 Grade 10 students in Newfoundland and Labrador. METHOD: Two structural equations were postulated: one in which students' affect mediated the influence of perceptions of teachers on goal orientation and one in which students' affect contributed to goal formation in addition to perceptions of teachers. A cluster analysis of affect scores was performed followed by between-group and within-group contrasts of goal orientation scores. RESULTS: The structural equation model in which emotions mediate the influence of perceptions of teachers on goal orientation fit the data better than the model in which perceptions of teachers directly predicted goal orientation. The cluster analysis showed that groups with different profiles of affect pursued different goals. CONCLUSIONS: Emotions seem to be directly linked to goal orientation. Teachers who are perceived as nurturing will foster feelings of self-assuredness and control in students which will lead to a learning orientation.

Adolescent↗

PubMed1992

The learning curve and the cost of heart transplantation.

The effect of learning on hospital outcomes such as mortality or adverse events (the so-called "practice makes perfect" hypothesis) has been studied by numerous investigators. The effect of learning on hospital cost, however, has received much less attention. This article reports the results of a multiple regression model demonstrating a nonlinear, decreasing trend in operative and postoperative hospital costs over time in a consecutive series of 71 heart transplant patients, all treated in the same institution. The cost trend is shown to persist even after controlling for various preoperative demographic and clinical risk factors and the specific experience of individual surgeons. Using a reference case, the model predicts a cost of $81,297 for the first heart transplant procedure performed at the hospital. If this same patient had been the tenth case rather than the first, with the hospital having benefited from the experience gained in nine previous cases, the model predicts the cost would now be only $48,431, or approximately 60 percent of the cost of the first case. Had this patient been the twenty-fifth case, the predicted cost would be $35,352 (43 percent of the original cost), and had this been the fiftieth case, the cost would be $25,458 (31 percent of the original cost). The longitudinal study design used in this analysis greatly reduces the likelihood that the observed cost reduction is due to economies of scale rather than learning. The results have implications for a policy of regionalization as a tactic for containing hospital cost. Whereas others have pointed to a volume-cost relationship as an argument for the regionalization of expensive and complex hospital procedures, the present data isolate a learning-cost relationship as a separate argument for regionalization.

Adult↗

PubMed1981

Effects of bromocriptine in developing rat pups after 6-hydroxydopamine.

The effects of low (0.5 mg/kg) and high (2.0 mg/kg) doses of bromocriptine (BCR) on activity and escape performance were examined during the first month of postnatal life in normal developing rat pups and littermates treated at 5 days of age with a combination of desmethylimipramine and 6-hydroxydopamine (6-OHDA). Such a procedure resulted in significant reductions in brain dopamine to concentrations 10-20% of vehicle controls while norepinephrine was unaffected. BCR increased general motor activity in vehicle pups at 13 and 19 days but had little effect on more mature animals. Pups who had not received BCR exhibited a decline in activity over the hour long observation period (habituation of activity) but this decline was abolished by both low (0.5 mg/kg) and high (2.0 mg/kg) doses of the agent. Stereotyped activity, particularly at 19 days was increased by BCR in 6-OHDA pups but not in vehicle animals, an effect suggesting denervation supersensitivity. Head dips in a hole box at 30 days of age were not influenced by BCR in vehicle pups but significantly reduced by BCR in 6-OHDA pups, suggesting that BCR might be acting to stimulate inhibitory dopaminergic mechanisms. Escape learning in a T-maze at 20 days and shuttle box at 28 days was disrupted by high doses of BCR in vehicle pups and both doses of BCR in 6-OHDA animals. The similarity with the behaviors observed in the clinical syndrome of attention deficit disorder with hyperactivity prompted a number of investigative groups including our own to suggest that the 6-OHDA model might serve as a useful and convenient paradigm to evaluate pharmacological agents that offer potential in the treatment of this most common disorder. From this perspective we would predict that BCR would have little clinical utility since it both failed to attenuate 6-OHDA induced hyperactivity and tended to disrupt performance in an avoidance learning task.

Animals↗

PubMed2000

[Column efficiency prediction of two dimensional chromatography by artificial neural network].

This paper used artificial neural network (ANN) modeling method to study the relationship between the column efficiency and the operating conditions. This method solved the problem that it is not easy to establish a quantitative model between the column efficiency and its main effecting factors using those traditional modeling methods, as the relationship is usually quite complex and non-linear in fact. The varied-pace BP (back-propagation) learning algorithm was adopted, and a three-layer weight-connected ANN model for a typical dual column system was established. The effective plate number representing the column efficiency acted as the output vectors, while the temperature of the pre-column, the temperature of the main column, the pressure difference between the columns and the vent rate acted as the input vectors. Then the model acquired was used to predict column efficiency (characterized by "effective plate number") under different operating conditions. The results showed that the model predicting value was in consistent with the value found. This work proved that ANN modeling method was suitable for the study on the relationship between the column efficiency of two-dimensional column chromatography system and the operating conditions.

Algorithms↗

PubMed2001

What can we learn about protein folding from Ising-like models?

Ising-like models have been remarkably successful in reproducing all the experimental data available on the equilibrium and kinetics of secondary structure formation in short peptides. Over the past two years, very similar models have been used to predict the folding of complete proteins, with encouraging results. Although Ising-like models are probably too simple to describe all aspects of protein folding, the results obtained so far indicate that they can play a critical role in the study of protein folding by bridging the gap between experiment and more detailed theoretical approaches.

Models, Molecular↗

PubMed2026

MetaFX: feature extraction from whole-genome metagenomic sequencing data.

MOTIVATION: Microbial communities consist of thousands of microorganisms and viruses and have a tight connection with an environment, such as gut microbiota modulation of host body metabolism. However, the direct relationship between the presence of certain microorganism and the host state often remains unknown. Toolkits using reference-based approaches are limited to microbes present in databases. Reference-free methods often require enormous resources for metagenomic assembly or results in many poorly interpretable features based on k-mers. RESULTS: Here we present MetaFX-an open-source library for feature extraction from whole-genome metagenomic sequencing data and classification of groups of samples. Using a large volume of metagenomic samples deposited in databases, MetaFX compares samples grouped by metadata criteria (e.g. disease, treatment, etc.) and constructs genomic features distinct for certain types of communities. Features constructed based on statistical k-mer analysis and de Bruijn graphs partition. Those features are used in machine learning models for classification of novel samples. Extracted features can be visualized on de Bruijn graphs and annotated for providing biological insights. We demonstrate the utility of MetaFX by building classification models for 590 human gut samples with inflammatory bowel disease. Our results outperform the previous research disease prediction accuracy up to 17%, and improves classification results compared to taxonomic analysis by 9±10% on average. AVAILABILITY AND IMPLEMENTATION: MetaFX is a feature extraction toolkit applicable for metagenomic datasets analysis and samples classification. The source code, test data, and relevant information for MetaFX are freely accessible at https://github.com/ctlab/metafx under the MIT License. Alternatively, MetaFX can be obtained via http://doi.org/10.5281/zenodo.16949369.

Metagenomics↗

PubMed2005

From the lexicon to expectations about kinds: a role for associative learning.

In the novel noun generalization task, 2 1/2-year-old children display generalized expectations about how solid and nonsolid things are named, extending names for never-before-encountered solids by shape and for never-before-encountered nonsolids by material. This distinction between solids and nonsolids has been interpreted in terms of an ontological distinction between objects and substances. Nine simulations and behavioral experiments tested the hypothesis that these expectations arise from the correlations characterizing early learned noun categories. In the simulation studies, connectionist networks were trained on noun vocabularies modeled after those of children. These networks formed generalized expectations about solids and nonsolids that match children's performances in the novel noun generalization task in the very different languages of English and Japanese. The simulations also generate new predictions supported by new experiments with children. Implications are discussed in terms of children's development of distinctions between kinds of categories and in terms of the nature of this knowledge.

Association Learning↗

PubMed1996

Artificial neural networks as a novel approach to integrated pharmacokinetic-pharmacodynamic analysis.

A novel model-independent approach to analyze pharmacokinetic (PK)-pharmacodynamic (PD) data using artificial neural networks (ANNs) is presented. ANNs are versatile computational tools that possess the attributes of adaptive learning and self-organization. The emulative ability of neural networks is evaluated with simulated PK-PD data, and the power of ANNs to extrapolate the acquired knowledge is investigated. ANNs of one architecture are shown to be flexible enough to accurately predict PD profiles for a wide variety of PK-PD relationships (e.g., effect compartment linked to the central or peripheral compartment and indirect response models). Also, an example is given of the ability of ANNs to accurately predict PD profiles without requiring any information regarding the active metabolite. Because structural details are not required, ANNs exhibit a clear advantage over conventional model-dependent methods. ANNs are proved to be robust toward error in the data and perturbations in the initial estimates. Moreover, ANNs were shown to handle sparse data well. Neural networks are emerging as promising tools in the field of drug discovery and development.

Mathematical Computing↗