PubMed Health⌕ Search

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 1,711 records · Page 95Linked to original sources

Phonological processing and oral language abilities in fourth-grade poor readers.

UNLABELLED: This study investigated the contribution of phonological processing and oral language skills to reading abilities (word attack, word recognition, and comprehension) in 17 fourth graders identified as poor readers. Participants were assessed in the areas of phonological awareness, verbal working memory, and rapid naming, in addition to oral language abilities as predictors of poor reading skills. Results indicated that the strongest predictors of word attack skills were phonological awareness and grammaticality judgment. The combination of phonological awareness, grammaticality judgment, phoneme manipulation, and rapid naming of digits accounted for more than half of the variance in word recognition. Furthermore, the amount of discrepancy between IQ scores and reading achievement did not distinguish groups of poor readers. The results support the importance of metalinguistic skills to support reading ability. Phonological processing and oral language abilities may vary in children with poor reading skills as processing demands change with age and task. LEARNING OUTCOMES: As a result of this activity, the reader will be able to: (1) identify phonological processing and oral language skills that are most predictive of specific reading skills in poor readers; (2) describe further evidence of the lack of utility of the discrepancy model to define reading disorders in children.

Awareness↗

Effects of cholinesterase inhibitors on a two-component chained schedule performance in rats.

The acetylcholinesterase (AChE) inhibitors physostigmine (PHY), tacrine (THA), and heptylphysostigmine (HEP) have been evaluated as potential therapeutics for treatment of Alzheimer's disease (AD) and as prophylactics against organophosphate (OP) poisoning. The above medical applications are based upon the neurochemical principles of elevation of transient levels of acetylcholine (ACh) in brain and reversible inhibition of AChE in blood and brain, respectively. The present study was undertaken to evaluate the effects of these drugs on performance of a two-component chained schedule of differential-reinforcement-of-high-rate (DRH) reward/differential-reinforcement-of-low-rate (DRL) nonreward contingencies, for water reinforcement in 2-h experimental sessions in rats. Both PHY (0.031-0.25 mg/kg, SC) and HEP (0.625-10.0 mg/kg, SC) decreased overall reinforcement rate and nonreinforced response in a dose-related and parallel manner, whereas THA (0.625-5.0 mg/kg) decreased the overall reinforcement rate in a dose-related manner, but did not significantly affect nonreinforced response. The least significant doses of PHY (0.625 mg/kg), THA (1.25 mg/kg), and HEP (1. 25 mg/kg) on the behavioral performance were associated with oral movements and/or muscle fasciculation. Moderate to high doses of these drugs (i.e., PHY >/= 0.624, THA >/= 1.25, and HEP >/= 1.25 mg/kg) produced behavioral suppression, which resulted mostly from the cessation of responding in the presence of cholinergic adverse events. The ED(50) values of the behavioral disruption (as documented by overall reinforcer loss) for PHY, THA, and HEP were 0. 081, 3.87, and 2.89 mg/kg, respectively, and the behavioral-deficit-free (BDF) doses were 0.031, 0.625, and 0.625 mg/kg, respectively. Preclinical data revealed that the BDF doses of both PHY and HEP have moderate inhibition of AChE, which leads to an efficacious elevation of ACh level in the brain, whereas the BDF dose of THA shows no significant AChE inhibition or elevation of brain ACh level; however, they all have cognition enhancing effects at their respective safety doses. The above data suggest that the BDF doses of PHY and HEP may have prophylactic efficacy against OP poisoning, whereas THA may not. The BDF doses of these three drugs are comparable to the maximum tolerated doses in clinical practice, suggesting that the present rat model may have potential value in predicting the clinical safety of AChE inhibitors developed for therapy of AD and prophylaxis against OP poisoning as well.

Animals↗

Environmental correlates of child copula verb growth.

A recurring result from studies which relate the frequency of input variables to rate of language development, is the link between auxiliary verb growth and yes-no questions addressed to children. Explanations for this relationship usually concentrate on the advantages of hearing stressed and non-contracted auxiliary forms in sentence-initial position over hearing unstressed, contracted forms in medial position in declaratives. If such accounts are correct, then it can be predicted that yes-no questions which place forms of COPULA be in initial position will also increase the rate of growth of children's COPULA verb development. This prediction was tested using a sample of 33 children, carefully matched for stage of language development at 1;9 and 2;0 years; rate of copula verb growth was then measured over the succeeding nine months. Analyses include an examination of the contribution of sub-categories of yes-no question, tag questions, and utterances containing sentence-final copulas to the growth of contracted and full copulas. Results confirm that the frequency of inverted copulas in yes-no questions predicts children's copula development. Nevertheless, caution is urged before interpreting the relationship in terms of a direct causal model.

Acoustic Stimulation↗

Attributional style and the type A coronary-prone behavior pattern.

The present two studies examined the attributional styles of Type A and B individuals. Past research suggests that Type A's exhibit greater performance deficits than Type B's following exposure to extended, salient uncontrollable stimuli. The reformulated learned helplessness model suggests that individuals most prone to such performance deficits should exhibit an attributional style characterized by internal, stable, and global attributions for negative outcomes, but external, unstable, and specific attributions for positive outcomes. However, a self-esteem protection explanation of learned helplessness findings predicts an opposite, self-serving attributional style. Results from both studies indicated that Type A's are more self-serving than Type B's in their attributions for positive and negative outcomes.

Achievement↗

A constructive-associative model of the contextual dependence of unidimensional similarity.

Conditions under which pairwise dissimilarity ratings should reflect manipulations of the stimulus distribution were outlined by a model that proposed these effects. These conditions arise from either a context dependent process for constructing implicit scale values or a process that uses previously established stimulus-response associates. Consistent with the model, results from 3 experiments using unidimensional psychophysical stimuli demonstrated disordinal context effects on pairwise dissimilarity ratings when (a) there was a 3-s delay between presentation of pair members or (b) a unidimensional rating task preceded the pairwise dissimilarity ratings. Global effects of density were fit well by a model that extended A. Parducci's (1983) range-frequency theory to dissimilarity ratings. Local density effects were generally consistent with predictions from C.L.Krumhansl's (1978) distance-density theory.

Association Learning↗

Associative control of tolerance to the sedative effects of a short-acting benzodiazepine.

The role of Pavlovian conditioning in tolerance to the depressant effect of a benzodiazepine (midazolam) on the ambulatory activity of rats was examined. The depression of activity by low doses (1.0 and 4.0 mg/kg, ip) of midazolam diminished quickly over repeated doses given at 48-hr intervals (Experiment 1). Equivalent tolerance was observed in groups measured at 2 min and 30 min after drug injection. When challenged with saline, however, drug-tolerant animals tested immediately after injection were hyperactive in comparison with nontolerant controls, whereas equivalent groups tested 30 min after injection were not. A second context was designed, and its discriminability from the original was established by assessing context-specific suppression of activity following exposure to mild electric shock (Experiment 2). In Experiment 3A, although tolerant animals tested in the drug-associated context remained fully tolerant, a second group demonstrated a complete loss of tolerance when given the drug in a saline-associated context. Both groups were fully tolerant when tested again in the drug-associated context after 14 drug-free days. In Experiment 3B, tolerance was significantly reduced by 14 extinction exposures to the drug-associated environment without the drug. These results are uniquely predicted by associative models of drug tolerance and may have implications for the clinical use of this class of drugs.

Animals↗

Predicting thermal displacements in modular tool systems.

In the last decade, there has been an increasing interest in compensating thermally induced errors to improve the manufacturing accuracy of modular tool systems. These modular tool systems are interfaces between spindle and workpiece and consist of several complicatedly formed parts. Their thermal behavior is dominated by nonlinearities, delay and hysteresis effects even in tools with simpler geometry and it is difficult to describe it theoretically. Due to the dominant nonlinear nature of this behavior the so far used linear regression between the temperatures and the displacements is insufficient. Therefore, in this study we test the hypothesis whether we can reliably predict such thermal displacements via nonlinear temperature-displacement regression functions. These functions are estimated first from learning measurements using the alternating conditional expectation (ACE) algorithm and then tested on independent data sets. First, we analyze data that were generated by a finite element spindle model. We find that our approach is a powerful tool to describe the relation between temperatures and displacements for simulated data. Next, we analyze the temperature-displacement relationship in a silent real experimental setup, where the tool system is thermally forced. Again, the ACE algorithm is powerful to estimate the deformation with high precision. The corresponding errors obtained by using the nonlinear regression approach are 10-fold lower in comparison to multiple linear regression analysis. Finally, we investigate the thermal behavior of a modular tool system in a working milling machine and again get promising results. The thermally induced errors can be estimated with 1-2 microm accuracy using this nonlinear regression analysis. Therefore, this approach seems to be very useful for the development of new modular tool systems.

Computer Simulation↗

Processing and storage in working memory span.

Two experiments are reported that address theoretical assumptions as to the nature of working memory involved in working memory span tasks (Daneman & Carpenter, 1980). Experiment 1 used a version of the sentence span task, and Experiment 2 combined arithmetic verification with recall of presented words. In each experiment, working memory processing span was assessed independently of temporary storage span prior to their combination. Combined task performance under high demand for each component resulted in substantial residual performance for both task elements, particularly in Experiment 2. The results do not challenge the utility of the sentence span task as a measure of on-line cognition, but they raise concerns as to how resource might be allocated to processing and storage elements of the task within a single flexible resource pool, or between different resources of a multiple component working memory system. Although both models lack predictive power regarding resource allocation in these tasks, the multiple resource model appears to offer the better account.

Adult↗

Modular DAG-RNN architectures for assembling coarse protein structures.

We develop and test machine learning methods for the prediction of coarse 3D protein structures, where a protein is represented by a set of rigid rods associated with its secondary structure elements (alpha-helices and beta-strands). First, we employ cascades of recursive neural networks derived from graphical models to predict the relative placements of segments. These are represented as discretized distance and angle maps, and the discretization levels are statistically inferred from a large and curated dataset. Coarse 3D folds of proteins are then assembled starting from topological information predicted in the first stage. Reconstruction is carried out by minimizing a cost function taking the form of a purely geometrical potential. We show that the proposed architecture outperforms simpler alternatives and can accurately predict binary and multiclass coarse maps. The reconstruction procedure proves to be fast and often leads to topologically correct coarse structures that could be exploited as a starting point for various protein modeling strategies. The fully integrated rod-shaped protein builder (predictor of contact maps + reconstruction algorithm) can be accessed at http://distill.ucd.ie/.

Algorithms↗

Learning driver-response relationships from synchronization patterns.

We test recent claims that causal (driver-response) relationships can be deduced from interdependencies between simultaneously measured time series. We apply two recently proposed interdependence measures that should give results similar to cross predictabilities used by previous authors. The systems that we study are asymmetrically coupled simple models (Lorenz, Roessler, and Hénon models), the couplings being such that they lead to generalized synchronization. If the data were perfect (noise-free, infinitely long), we should be able to detect, at least in some cases, which of the coupled systems is the driver and which the response. This might no longer be true if the time series has finite length. Instead, estimated interdependencies depend strongly on which of the systems has a higher effective dimension at the typical neighborhood sizes used to estimate them, and causal relationships are more difficult to detect. We also show that slightly different variants of the interdependence measure can have quite different sensitivities.

Electroencephalography↗

Relative effectiveness of concurrent forward/backward versus simple forward and simple backward Pavlovian conditioning procedures.

Concurrent forward/backward Pavlovian conditioning procedures were compared with simple forward and simple backward procedures for differential excitatory and inhibitory conditioning. Four groups of dogs each received 30 shocks while restrained in a Pavlovian harness. One group of dogs (CON) received concurrent conditioning with a clicker signaling shocks and with a tone following shocks. For another group of dogs (SF), a clicker signaled the shocks, whereas the tone was randomly related to shocks. For a third group (SB), the tone followed shock termination, whereas the clicker was randomly related to shocks. For a fourth group (TRC), both the clicker and the tone were randomly related to shocks. All stimuli were then superimposed on a temporally paced avoidance baseline and their associative properties were assessed relative to the TRC group. Differential excitatory-inhibitory conditioning was significantly reduced in the concurrent procedure relative to that which occurred in the simple conditioning procedures despite exactly equal CS + -US and US-CS-contingencies. These results were interpreted with reference to contextual conditioning effects predicted by the Rescorla-Wagner conditioning model and the theoretical issue of independence vs. interdependence of CS-US associative strengths.

Acoustic Stimulation↗

Machine learning can improve prediction of severity in acute pancreatitis using admission values of APACHE II score and C-reactive protein.

BACKGROUND: Acute pancreatitis (AP) has a variable course. Accurate early prediction of severity is essential to direct clinical care. Current assessment tools are inaccurate, and unable to adapt to new parameters. None of the current systems uses C-reactive protein (CRP). Modern machine-learning tools can address these issues. METHODS: 370 patients admitted with AP in a 5-year period were retrospectively assessed; after exclusions, 265 patients were studied. First recorded values for physical examination and blood tests, aetiology, severity and complications were recorded. A kernel logistic regression model was used to remove redundant features, and identify the relationships between relevant features and outcome. Bootstrapping was used to make the best use of data and obtain confidence estimates on the parameters of the model. RESULTS: A model containing 8 variables (age, CRP, respiratory rate, pO2 on air, arterial pH, serum creatinine, white cell count and GCS) predicted a severe attack with an area under the receiver-operating characteristic curve (AUC) of 0.82 (SD 0.01). The optimum cut-off value for predicting severity gave sensitivity and specificity of 0.87 and 0.71 respectively. The predictions were significantly better (p = 0.0036) than admission APACHE II scores in the same patients (AUC 0.74) and better than historical admission APACHE II data (AUC 0.68-0.75). CONCLUSIONS: This system for the first time combines admission values of selected components of APACHE II and CRP for prediction of severe AP. The score is simple to use, and is more accurate than admission APACHE II alone. It is adaptable and would allow incorporation of new predictive factors.

APACHE↗

Natural reward-related learning in rats with neonatal ventral hippocampal lesions and prior cocaine exposure.

RATIONALE: Psychostimulant injections in rats have been shown to alter future performance in natural reward conditioning. These effects may represent a persistent impact of drugs on neurocircuits that interface cognitive and motivational processes, which may be further altered in neuropsychiatric conditions that entail increased addiction vulnerability. OBJECTIVE: This study investigated whether a rat model of schizophrenia with cocaine addiction vulnerability shows altered natural reward conditioning with or without prior cocaine exposure. METHODS: Adult rats with SHAM or neonatal ventral hippocampal lesions were given cocaine (15 mg/kg per day for 5 days) or saline injections, followed 7 days later by natural reward-conditioned learning. Over ten daily sessions, water-restricted rats were assessed for durations of head entries into a magazine during random water presentations, a conditioning stimulus phase predictive of the water reward, and an "inappropriate" phase when conditioning stimuli were absent and reward presentation would be delayed. RESULTS: Over repeated sessions, lesioned and SHAM rats showed similar reductions in total magazine entry durations, with similar increases in the allocations of entry times during the water presentation. However, lesioned rats, especially those exposed to cocaine, demonstrated reduced allocations of magazine entry times during the conditioning stimulus phase, and increased allocations during the inappropriate phase. CONCLUSIONS: Intact natural reward motivation accompanied by deficient learning of complex contingencies to guide efficient reward approach may represent a form of impulsivity as an addiction vulnerability trait marker in an animal model of schizophrenia.

Animals↗

Psychobiology of the acute stress response and its relationship to the psychobiology of post-traumatic stress disorder.

The literature to date that examines the biology of the acute stress reactions suggests that relatively lower baseline cortisol is associated with the development of PTSD. This is particularly informative because of the ongoing controversy surrounding baseline cortisol in PTSD. Studies have found low baseline cortisol, normal range, and elevated baseline cortisol in chronic PTSD, and it has been unclear whether this reflects methodologic differences across studies or true heterogeneity within the disorder. Thus, the few studies to date support the finding of low-normal baseline cortisol in chronic PTSD and suggest that it is a pre-existing functional trait. Whether it plays an etiologic role or is an epiphenomenon of some other process is unclear. What does seem clear, however, is that this characteristic is relatively nonspecific to PTSD, given the fact that low cortisol has been observed in multiple subject populations, including normal individuals under chronic stress as well as chronic medical conditions (for review see [23]). For example, it is possible that reduced baseline cortisol reflects the net result of input to the hypothalamus from cortical and subcortical regions of the brain linked to increased vigilance, sensitization to trauma because of prior traumatic experiences, or genetic factors. For example, primate studies have demonstrated persistent alterations in HPA axis functioning in animals reared by mothers living in moderately stressful conditions [24]. The development of PTSD is associated with sensitization of the startle response. Because the neurobiology of startle is well characterized, this finding implicates a role for specific neurocircuitry in PTSD [25]. Non-habituation of the startle response in PTSD appears related to sensitization specifically to contextual cues (i.e., the environment) that signal the presence of potential threat of danger-related fears [26]. This may be the neurobiological correlate to the over-generalization seen in PTSD that distinguishes the disorder from a simple trauma-induced phobia. The bed nucleus of the stria terminalis (BNST) is specifically implicated from preclinical research in the mediation of context-dependent cues [1]. Treatments that result in down-regulation of the BNST are therefore of particular interest in therapeutic models of prevention after trauma. The fact that a number of vulnerability factors associated with increased risk for developing PTSD are also likely to be biologically based (e.g., a genetic component, prior psychiatric history, prior family of history of psychiatric disorder), provides further evidence in support of a role for psychobiological factors in producing PTSD. Nevertheless, the considerable overlap on these measures between those who will develop PTSD, and those who eventually recover spontaneously, belies any attempt to identify any single or pathognomonic biological marker for risk. For now, the standard of care in predicting level of symptomatology and prognosis in the acute setting continues to be based on careful, informed, serial assessments of symptoms and functioning. Because the capacity to learn from and adapt to adverse conditions are essential to the survival of any species, understanding the neurobiological pathways that mediate learning from traumatic experiences in an adaptive way is as important as understanding the etiology of PTSD and other trauma-related maladaptive consequences. Biological models that trace the causal cascade of post-traumatic events in the brain and neuroendocrine systems may offer a multiplicity of possibilities for intervention. It is well established that conditioned responses are robust and persistent. Moreover, the primary mechanism of habituation is overlearning rather than extinction. Interventions that promote overlearning may therefore prove to be the most powerful and efficient preventative treatments. The therapeutics literature supports this hypothesis, in that brief psychosocial interventions based on sophisticated cognitive-behavioral models have proven effective in reducing suffering, symptom severity, and chronicity in individuals presenting with acute PTSD symptoms [27-29]. No acutely administered pharmacologic treatment to date has been shown effective in accelerating the process of recovery or in preventing the development of chronic PTSD. However, pharmacologic interventions that would prevent sensitization of circuits related to context-dependent threat perception, dysregulation of affect, and/or dysregulation of normal circadian rhythms are of theoretical interest and deserve further study.

Acute Disease↗

Predicting gene function in Saccharomyces cerevisiae.

MOTIVATION: S.cerevisiae is one of the most important model organisms, and has has been the focus of over a century of study. In spite of these efforts, 40% of its open reading frames (ORFs) remain classified as having unknown function (MIPS: Munich Information Center for Protein Sequences). We wished to make predictions for the function of these ORFs using data mining, as we have previously successfully done for the genomes of M.tuberculosis and E.coli. Applying this approach to the larger and eukaryotic S.cerevisiae genome involves modifying the machine learning and data mining algorithms, as this is a larger organism with more data available, and a more challenging functional classification. RESULTS: Novel extensions to the machine learning and data mining algorithms have been devised in order to deal with the challenges. Accurate rules have been learned and predictions have been made for many of the ORFs whose function is currently unknown. The rules are informative, agree with known biology and allow for scientific discovery. AVAILABILITY: All predictions are freely available from http://www.genepredictions.org, all datasets used in this study are freely available from http://www.aber.ac.uk/compsci/Research/bio/dss/yeastdataand software for relational data mining is available from http://www.aber.ac.uk/compsci/Research/bio/dss/polyfarm.

Chromosome Mapping↗

Predicting and understanding developmental delay of children of adolescent mothers: a multidimensional approach.

Divergent literatures on potential relationships among psychological, biological, and contextual factors that may contribute to mental retardation and other types of developmental delay in the children of adolescent mothers were reviewed. A linear model was proposed to describe the direct and indirect effects of learning ability, maternal health, social support, personal adjustment, cognitive readiness for parenting, and infant characteristics on adolescent parenting and child development. Because the validity of the model can be determined through the use of causal modeling (LISREL), it holds the potential for determining a unique set of risk factors that may produce developmental delay in children of adolescent mothers. These factors can serve as the targets in designing intervention programs for such mothers.

Adolescent↗

Cortico-hippocampal interaction and adaptive stimulus representation: a neurocomputational theory of associative learning and memory.

Computational models of the hippocampal region link psychological theories of associative learning with their underlying physiological and anatomical substrates. Our approach to theory development began with a broad description of the computations that depend on the hippocampal region in classical conditioning (Gluck and Myers, 1993 and Gluck and Myers, 2001). In this initial model, the hippocampal region was treated as an Information-processing system that transformed stimulus representations, compressing (making more similar) representations of inputs that co-occur or are otherwise redundant, while differentiating (or making less similar) representations of inputs that predict different future events. This model led to novel predictions for the behavioral consequences of hippocampal-region lesions in rodents and of brain damage in humans who have amnesia or are in the earliest stages of Alzheimer's disease. Many of these predictions have, since been confirmed by our lab and others. Functional brain imaging studies have provided further supporting evidence. In more recent computational modeling, we have shown how some aspects of this proposed information-processing function could emerge from known anatomical and physiological characteristics of the hippocampal region, including the entorhinal cortex and the septo-hippocampal cholinergic system. The modeling to date lays the groundwork for future directions that increase the depth of detail of the biological modeling, as well as the breadth of behavioral phenomena addressed. In particular, we are working now to reconcile these kinds of incremental associative learning models with other models of the hippocampal region that account for the rapid formation of declarative memories.

Animals↗

Mul-PheG2P: decoupled learning and prediction-space fusion enables robust and interpretable multi-phenotype genomic prediction.

Genomic prediction of multiple phenotypes is crucial in modern plant breeding; however, existing methods struggle with negative transfer and lack interpretability, particularly across high-dimensional small-sample data and diverse species. To address this, we propose Mul-PheG2P, a novel paradigm based on decoupled learning and predictive space fusion. It employs a two-stage design: first training phenotype-specific encoders using genetic data, then decoupling phenotype-specific learning from cross-phenotype aggregation via an interpretable prediction layer. Mul-PheG2P outperforms existing methods across diverse crop datasets, including maize (Zea mays), wheat (Triticum aestivum), and tomato (Solanum lycopersicum). It provides a multi-scale interpretability chain: at the macro level, it quantifies phenotypic contributions via attention-based weighting; at the micro level, Integrated Gradients reveal the genetic basis of predictions. Notably, the model successfully identified the CCT (CONSTANS, CO-like, and TOC) motif regulating photoperiodism and the SQUAMOSA (SQUAMOSA promoter binding protein) promoter for inflorescence development, confirming its ability to capture functional biological mechanisms. These results highlight the high performance and interpretability of Mul-PheG2P, showcasing its value for low-cost, large-scale screening to advance precision breeding.

Phenotype↗