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 1,495 records · Page 83Linked to original sources

PubMed1999

Language acquisition in the absence of explicit negative evidence: how important is starting small?

It is commonly assumed that innate linguistic constraints are necessary to learn a natural language, based on the apparent lack of explicit negative evidence provided to children and on Gold's proof that, under assumptions of virtually arbitrary positive presentation, most interesting classes of languages are not learnable. However, Gold's results do not apply under the rather common assumption that language presentation may be modeled as a stochastic process. Indeed, Elman (Elman, J.L., 1993. Learning and development in neural networks: the importance of starting small. Cognition 48, 71-99) demonstrated that a simple recurrent connectionist network could learn an artificial grammar with some of the complexities of English, including embedded clauses, based on performing a word prediction task within a stochastic environment. However, the network was successful only when either embedded sentences were initially withheld and only later introduced gradually, or when the network itself was given initially limited memory which only gradually improved. This finding has been taken as support for Newport's 'less is more' proposal, that child language acquisition may be aided rather than hindered by limited cognitive resources. The current article reports on connectionist simulations which indicate, to the contrary, that starting with simplified inputs or limited memory is not necessary in training recurrent networks to learn pseudonatural languages; in fact, such restrictions hinder acquisition as the languages are made more English-like by the introduction of semantic as well as syntactic constraints. We suggest that, under a statistical model of the language environment, Gold's theorem and the possible lack of explicit negative evidence do not implicate innate, linguistic-specific mechanisms. Furthermore, our simulations indicate that special teaching methods or maturational constraints may be unnecessary in learning the structure of natural language.

Artificial Intelligence↗

PubMed1999

A behavioral stages model of classical (Pavlovian) conditioning: application to cognitive aging.

In the present article, it is argued that a five-stage sequential model of the behavioral and neurophysiological events that occur when organisms are exposed to signals predicting significant events suggests that classical conditioning produces multiple memory traces involving both excitatory and inhibitory processes. Further, these multiple brain structures and associated neurophysiological mechanisms are beginning to be understood; thus, using Pavlovian conditioning techniques to study aging and cognitive functions may provide insights into which brain structures or mechanisms are responsible for more general age-related declines in associative learning and memory. The evidence for this model is briefly reviewed and studies suggesting age-related effects on classical conditioning of various response systems are described within the context of the brain structures implicated by the model.

Aging↗

PubMed2003

Brain injury and neurofunctional deficit in neonatal mice with hypoxic-ischemic encephalopathy.

Birth asphyxia accounts for the majority of developmental motor and cognitive deficits. Studies were undertaken to develop a reproducible murine model of perinatal hypoxic-ischemic encephalopathy (HIE) which would permit both anatomic and neurofunctional quantification of injury. Short-term neurofunctional outcomes consisted of three developmental reflexes (righting, cliff aversion and geotaxis) assessed in 7-day-old mouse pups 24 h after unilateral carotid artery ligation followed by inhalation of 8% oxygen. Cerebral infarct volume was dependent on duration of hypoxia, being approximately 2.5-fold greater with longer (60 min) versus shorter (30 min) hypoxia exposure (P=0.001). All three sensorimotor neonatal reflexes assessed at 24 h after HIE injury correlated significantly with long-term neurofunction evaluated using a water-maze test of navigational learning and memory assessed 8 weeks later in the same animals. Cerebral atrophy, a delayed consequence of HIE in this model, also correlated strongly with water-maze performance (r=0.86, P=0.002). These data demonstrate for the first time that murine neonatal sensorimotor reflex performance can be rigorously quantified in the acute phase of perinatal HIE and has strong predictive value not only for anatomic extent of cerebral injury, but also for long-term neurofunctional outcome.

Animals↗

PubMed2004

Interventions to improve follow-up of abnormal findings in cancer screening.

The potential reduction in morbidity and mortality through cancer screening cannot be realized without receipt of appropriate follow-up care for abnormalities identified via screening. In this paper, the authors critically examine the existing literature on correlates of receipt of appropriate follow-up care for screen-detected abnormalities, as well as the literature on interventions designed to increase rates of receipt of follow-up care. Lessons learned describe what is known and not known about factors that are related to or predict receipt of follow-up care. Similarly, effective interventions to increase follow-up are described and gaps identified. A conceptual model is developed that categorizes the health care system in the United States as comprising four levels: policy, practice, provider, and patient. Some patient-level factors that influence follow-up receipt are identified, but the lack of data severely limit the understanding of provider, practice, and policy-level correlates. The majority of intervention studies to increase follow-up receipt have focused on patient-level factors and have targeted follow-up of abnormal Papanicolaou smears. Insufficient information is available regarding the effectiveness of provider, practice, or policy-level interventions. Standard definitions of what constitutes appropriate follow-up are lacking, which severely limit comparability of findings across studies. The validity of various methods of obtaining outcome data has not been clearly established. More research is needed on interventions targeting provider, system, and policy-level factors, particularly interventions focusing on follow-up of colorectal and breast abnormalities. Standardization of definitions and measures is needed to facilitate comparisons across studies.

Continuity of Patient Care↗

PubMed2004

Advances in the prediction of protein targeting signals.

Enlarged sets of reference data and special machine learning approaches have improved the accuracy of the prediction of protein subcellular localization. Recent approaches report over 95% correct predictions with low fractions of false-positives for secretory proteins. A clear trend is to develop specifically tailored organism- and organelle-specific prediction tools rather than using one general method. Focus of the review is on machine learning systems, highlighting four concepts: the artificial neural feed-forward network, the self-organizing map (SOM), the Hidden-Markov-Model (HMM), and the support vector machine (SVM).

Animals↗

PubMed1996

Family process and child anxiety and aggression: an observational analysis.

Barrett, Rapee, Dadds, and Ryan (1996) described a phenomenon whereby family discussions magnified the style of children's problem solving in a way characteristic of their particular clinical diagnosis. That is, anxious children became more avoidant, aggressive children more aggressive, and nonclinic children more prosocial, after discussing ambiguous hypothetical situations with their parents. This study examined specific sequences of communications exchanged between parents and children hypothesized to underlie this family exacerbation of child cognitive style. Family discussions were videotaped and categorized for groups of anxious, aggressive, and nonclinic children and their parents. Results revealed differences between groups of parents in frequency of agreeing with and listening to their child and the frequency of pointing out positive consequences. Conditional probability analyses showed that parents of anxious children were more likely to reciprocate avoidance, while parents of nonclinic children were more likely to agree with and listen to prosocial plans from their child. Differences in parent behaviors observed during the family discussions were reliably associated with the child's response to the ambiguous situation proposed after the family discussion. Results support a model of developmental anxiety and aggression that emphasizes the interaction of family processes and social-cognitive development in the child.

Adolescent↗

PubMed2005

Involving the pharmaceutical and biotech communities in medication development for substance abuse.

Pharmacotherapy as adjunctive treatment is an integral part of the strategy for treating substance abuse. Although there are several approved drugs for the treatment of opioid, alcohol, and nicotine dependence, the pharmaceutical industry, for a variety of reasons, has been reluctant to enter this area to develop medications for substance abuse indications. Therefore, in 1990, a Medication Development Program was established by NIDA to carry out and assist in stimulating development of new pharmacotherapies. It is vital for NIDA to provide clear leadership and establish a collaborative working relationship with the pharmaceutical industry, providing scientific, development, and financial assistance, depending on the size, resources, and expertise of the company. An important NIDA role in this effort is setting standards, such as establishing Target Product Profiles (TPPs), predictive decision trees for selection of clinical candidates, and animal models to evaluate safety and potential effectiveness prior to human studies. NIDA can further establish standards for clinical studies, including Proof of Concept (PoC), Phase 2 (or Learning) trials to establish initial proof of safety and effectiveness, and Phase 3 (or Confirming) trials to validate Phase 2 findings. NIDA and other government agencies need to work to improve industry incentives to participate in medication development for substance abuse. Specific incentives, such as market exclusivity and patent extension, as provided in BioShield and pediatric drug legislation, should be strongly considered. NIDA can further assist industry to navigate the regulatory and, if needed, controlled substance scheduling processes, by establishing a true Federal partnership between NIDA, FDA, and DEA.

Animals↗

PubMed2004

Visual awareness and the cerebellum: possible role of decorrelation control.

The two roles in awareness most often suggested for the cerebellum are (i) keeping the details of motor skills away from forebrain computation, and (ii) signaling to the forebrain when a sensory event is not predictable from prior motor commands. However, it is unclear how current models of the cerebellum could carry out these roles. Their architecture, based on the seminal ideas of Marr and Albus, appears to need 'motor error' to learn correct motor commands. However, since motor error is the difference between the actual motor command and what the command should have been, it is a signal unavailable to the organism in principle. We propose a possible solution to this problem, termed decorrelation control, in which the cerebellum learns to decorrelate the motor command sent to the muscles from the sensory consequences of motor error. This method was tested in a linear model of oculomotor plant compensation in the vestibulo-ocular reflex. A copy of the eye-movement command was sent as mossy-fiber input to the flocculus, represented as a simple adaptive filter version of the Marr-Albus architecture. The sensory consequences of motor error were retinal slip, delivered as climbing fiber input to the flocculus. A standard anti-Hebbian learning rule was used to decorrelate the two. Simulations of the linearized problem showed the method to be effective and robust for plant compensation. Decorrelation control is thus a candidate algorithm for the basic cerebellar microcircuit, indicating how it could achieve motor learning using only signals available to the system. Such learning might then enable the cerebellum to free up visual awareness, and also, by providing a sensory signal decorrelated from motor command, supply awareness with crucial information about the external world.

Algorithms↗

PubMed2001

Exemplar accounts of blending and distinctiveness effects in perceptual old-new recognition.

Recent findings from the perceptual old-new recognition literature indicate that observers have extremely high false-alarm rates to new items that are "blends" of old ones. In addition, evidence suggests that "distinctive" old items--that is, those located in isolated regions of the similarity space--are recognized with higher probability than are typical old items. Both types of phenomena challenge the predictions of global-familiarity exemplar models of perceptual old-new recognition, which posit that the probability that an observer judges an item as old is based on its summed similarity to previously presented exemplars. In the present research the authors pursued these blending and distinctiveness effects by testing paradigms in which similarity relations among objects are highly controlled and in which the variables of blending and distinctiveness are not confounded with other properties associated with the individual objects themselves. In contrast to previous results, the authors found effects of blending and distinctiveness that are compatible with the predictions of a pure summed-similarity exemplar model.

Adult↗

PubMed1990

Postsynaptic NMDA receptor-mediated calcium accumulation in hippocampal CA1 pyramidal cell dendrites.

In the CA1 hippocampal region, intracellular calcium is a putative second messenger for the induction of long-term potentiation (LTP), a persistent increase of synaptic transmission produced by high frequency afferent fibre stimulation. Because LTP in this region is blocked by the NMDA (N-methyl-D-aspartate) receptor antagonist AP5 (DL-2-amino-5-phosphonovaleric acid) and the calcium permeability of NMDA receptors is controlled by a voltage-dependent magnesium block, a model has emerged that suggests that the calcium permeability of NMDA receptor-coupled ion channels is the biophysical basis for LTP induction. We have performed microfluorometric measurements in individual CA1 pyramidal cells during stimulus trains that induce LTP. In addition to a widespread component of postsynaptic calcium accumulation previously described, we now report that brief high frequency stimulus trains produce a transient component spatially localized to dendritic areas near activated afferents. This localized component is blocked by the NMDA receptor antagonist AP5. The results directly confirm the calcium rise predicted by NMDA receptor models of LTP induction.

2-Amino-5-phosphonovalerate↗

PubMed2000

Learning chaotic attractors by neural networks.

An algorithm is introduced that trains a neural network to identify chaotic dynamics from a single measured time series. During training, the algorithm learns to short-term predict the time series. At the same time a criterion, developed by Diks, van Zwet, Takens, and de Goede (1996) is monitored that tests the hypothesis that the reconstructed attractors of model-generated and measured data are the same. Training is stopped when the prediction error is low and the model passes this test. Two other features of the algorithm are (1) the way the state of the system, consisting of delays from the time series, has its dimension reduced by weighted principal component analysis data reduction, and (2) the user-adjustable prediction horizon obtained by "error propagation"-partially propagating prediction errors to the next time step. The algorithm is first applied to data from an experimental-driven chaotic pendulum, of which two of the three state variables are known. This is a comprehensive example that shows how well the Diks test can distinguish between slightly different attractors. Second, the algorithm is applied to the same problem, but now one of the two known state variables is ignored. Finally, we present a model for the laser data from the Santa Fe time-series competition (set A). It is the first model for these data that is not only useful for short-term predictions but also generates time series with similar chaotic characteristics as the measured data.

Algorithms↗

PubMed2006

Differences in mnemonic processing by neurons in the human hippocampus and parahippocampal regions.

Different structures within the medial-temporal lobe likely make distinct contributions to declarative memory. In particular, several current psychological and computational models of memory predict that the hippocampus and parahippocampal regions play different roles in the formation and retrieval of declarative memories [e.g., Norman, K. A., & O'Reilly, R. C. Modeling hippocampal and neocortical contributions to recognition memory: A complementary-learning systems approach. Psychological Review, 110, 611-646, 2003]. Here, we examined the neuronal firing patterns in these two regions during recognition memory. Recording directly from neurons in humans, we find that cells in both regions respond to novel stimuli with an increase in firing (excitation). However, already on the second presentation of a stimulus, neurons in these regions show very different firing patterns. In the parahippocampal region there is dramatic decrease in the number of cells responding to the stimuli, whereas in the hippocampus there is recruitment of a large subset of neurons showing inhibitory (decrease from baseline firing) responses. These results suggest that inhibition is a mechanism used by cells in the human hippocampus to support sparse coding in mnemonic processing. The findings also provide further evidence for the division of labor in the medial-temporal lobe with respect to declarative memory processes.

Cell Differentiation↗

PubMed2005

Probabilities and predictions: modeling the development of scientific problem-solving skills.

The IMMEX (Interactive Multi-Media Exercises) Web-based problem set platform enables the online delivery of complex, multimedia simulations, the rapid collection of student performance data, and has already been used in several genetic simulations. The next step is the use of these data to understand and improve student learning in a formative manner. This article describes the development of probabilistic models of undergraduate student problem solving in molecular genetics that detailed the spectrum of strategies students used when problem solving, and how the strategic approaches evolved with experience. The actions of 776 university sophomore biology majors from three molecular biology lecture courses were recorded and analyzed. Each of six simulations were first grouped by artificial neural network clustering to provide individual performance measures, and then sequences of these performances were probabilistically modeled by hidden Markov modeling to provide measures of progress. The models showed that students with different initial problem-solving abilities choose different strategies. Initial and final strategies varied across different sections of the same course and were not strongly correlated with other achievement measures. In contrast to previous studies, we observed no significant gender differences. We suggest that instructor interventions based on early student performances with these simulations may assist students to recognize effective and efficient problem-solving strategies and enhance learning.

Aptitude↗

PubMed2026

Topologically distinct intratumoral heterogeneity scores for predicting high-risk pathological grades in invasive lung adenocarcinoma: A multicenter study across four institutions.

High-risk subtypes of invasive lung adenocarcinoma (IAC), particularly micropapillary- or solid-predominant patterns, are closely associated with poor prognosis. This multicenter retrospective study developed and validated a predictive model for the preoperative identification of these high-risk subtypes using topologically distinct intratumoral heterogeneity (ITH) scores derived from CT images. The study included 1,051 patients with IAC. Two complementary ITH scores were developed: a two-dimensional ITH score, which integrated local radiomics features with global pixel distribution patterns on the largest cross-sectional CT slice, and a three-dimensional ITH score, which extended this quantification across the entire tumor volume. Clinicoradiological features and ITH scores were incorporated as model inputs to construct six base machine learning classifiers and a final stacking ensemble classifier. Model interpretability and robustness were evaluated using SHapley Additive exPlanations (SHAP)-based ablation analyses. An independent dataset from The Cancer Imaging Archive (TCIA) was used for external validation to investigate associations between ITH scores and pathological characteristics, genomic features, recurrence-free survival, and overall survival. The stacking ensemble classifier achieved the best predictive performance, with an area under the receiver operating characteristic curve of 0.875, outperforming models based solely on radiomics features (0.834) or clinicoradiological features (0.792). SHAP analysis identified the 3D ITH score as the most influential contributor to model output, and TCIA validation showed that higher 3D ITH scores were associated with more aggressive tumor biology and poorer survival outcomes. The topologically distinct 3D ITH score may provide a clinically meaningful imaging biomarker for preoperative risk stratification in IAC.

Journal Article↗

PubMed1993

Social networks and methadone treatment outcome: the costs and benefits of social ties.

OBJECTIVE: This study assessed the impact of social ties on substance abuse treatment outcome. Two models which predict alternative hypotheses were evaluated. 1) Based on the self-medication model, it was hypothesized that social support would aid in coping with painful affect and decrease the need for drugs. 2) Based on a social learning model, it was hypothesized that drug use in the social network would threaten abstinence due to modeling and conditioning effects. METHOD: Seventy methadone maintenance patients were given baseline measures of mood, stress, social support, and drug use in the network and followed prospectively for 3 months with weekly urine drug screens. RESULTS: Social support was correlated with positive affect (r = .59, p < .001), and stress with negative affect (r = .46, p < .001), but no measures of social support, affect, or stress correlated with the proportion of drug positive urines. However, patients with at least one drug user among the closest significant others had 63 +/- 38% positive urines versus 35 +/- 36% positive among those without a drug-using significant other (t = -3.2, p < .002). CONCLUSIONS: Substance use in the social network had a substantial negative impact on treatment outcome. Consistent with the social learning model and the traditional "persons, places, and things," this suggests interventions should get drug-using significant others into treatment and teach patients coping skills to reduce their negative influence.

Adult↗

PubMed1978

Herpetic keratitis. Proctor Lecture.

Although much needs to be learned about the serious clinical problem of herpes infection of the cornea, we have come a long way. We now have effective topical antiviral drugs. We have animal models which, with a high degree of reliability, clearly predict the effect to be expected clinically in man, as well as the toxicity. We have systemically active drugs and the potential of getting highly active, potent, completely selective drugs, with the possibility that perhaps the source of viral reinfection can be eradicated. The biology of recurrent herpes and stromal disease is gradually being understood, and this understanding may result in new and better therapy of this devastating clinical disease.

Adrenal Cortex Hormones↗

PubMed2000

Precursors of literacy delay among children at genetic risk of dyslexia.

This paper reports the literacy skills of 63 children selected as being at genetic risk of dyslexia compared with 34 children from families reporting no history of reading impairment. Fifty-seven per cent of the at-risk group were delayed in literacy development at 6 years compared with only 12% of controls. The "unimpaired" at-risk group were not statistically different from controls on most cognitive and language measures at 45 months, whereas the literacy-delayed group showed significantly slower speech and language development, although they did not differ from controls in nonverbal ability. Letter knowledge at 45 months was the strongest predictor of literacy level at 6 years. In addition, early speech and language skills predicted individual differences in literacy outcome and genetic risk accounted for unique variance over and above these other factors. The results are discussed in terms of an interactive developmental model in which semantic and phonological skills support early reading acquisition.

Child↗

PubMed2026

A machine learning approach to identify key epigenetic transcripts for ageing research in human blood (Epitage).

DNA methylation is an established biomarker of human ageing and is used by a variety of tools to identify meaningful epigenetic signals. We investigated whether analysing CpGs grouped by transcript as functional units could generate a ranked list of transcripts most correlated with age that might otherwise be overlooked in genome-wide CpG-based studies. Here we present Epitage ( https://github.com/a00s/epitage ), a continuously updated ranked list of transcripts built from the GSE87571 dataset (714 whole-blood samples, ages 14-94 years) through intensive testing with machine-learning models. To support reproducible analyses, we developed ugPlot ( https://github.com/a00s/ugplot ), an open-source R/Shiny tool with a graphical user interface that automates model training, testing, and comparison. Initially, we identified 48 transcripts across 13 genes, with some transcripts from the genes OBSCN, PRRT1, and SPTBN4 showing better predictive performance when multiple associated CpGs were analysed together rather than individually. In contrast, for the majority of transcripts, a dominant individual CpG still showed a higher Spearman correlation with age, as seen in established ageing genes such as ELOVL2, FHL2, and TRIM59. Epitage is a transcript-ranking list based on the methylation patterns observed in the analysed dataset. It provides a reproducible framework for prioritising transcripts associated with human ageing and for guiding future epigenetic studies.

Humans↗