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 1,513 records · Page 84Linked to original sources

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↗

PubMed1992

A good-continuation model of some occlusion phenomena.

Occlusion phenomena raise two questions: (1) When will an occluding and a partly occluded object be seen, as opposed to several nonoverlapping objects? (2) What is seen behind the occluding object? Available theories give no satisfactory description of occlusion data. In our view, this situation is at least partially due to the fact that patterns used in occlusion studies are always regular, whereas it is almost unknown which regularities are actually perceived in occlusion patterns. We have therefore collected a complete set of data for a restricted domain of patterns with minimal regularity. Starting from these data, we have developed a model of the perceptual organization of this class of patterns and tested it in a second experiment. The model is a specification of the Gestalt law of good continuation. It assumes that there is a tendency to describe a pattern by the smallest possible number of contour elements and with the smallest possible changes of direction within and between necessary contour elements. The results fit in well with the predictions of the model. It is further demonstrated that the model also describes the preferred interpretations of many regular patterns, published in other studies.

Adult↗

PubMed2026

Application of emerging technologies in the antiviral field.

Viral diseases pose a serious threat to global public health, agriculture, and biosecurity. Conventional antiviral strategies are often limited by an incomplete understanding of disease mechanisms, poor targeting precision, and slow response times. Emerging technologies are now reshaping the landscape of antiviral research. This review examines the roles of four key frontiers, including organoid models, gene editing, AI-driven molecular design, and synthetic biology. Organoids provide physiologically relevant platforms that model virus-host interactions and disease progression. Viral infections remain a major challenge to human and animal health, agriculture, and biosecurity. Progress in antiviral research is constrained by the complexity of viral pathogenesis, the diversity and rapid evolution of viruses, and the limited translational relevance of some traditional model systems. Recent advances in organoid technology, gene editing, artificial intelligence, and synthetic biology are expanding the toolkit available for antiviral research and development. In this review, we discuss how these four technological frontiers contribute to disease modeling, target discovery, molecular design, and translational innovation. Organoids, in particular, provide physiologically relevant systems for investigating viral infection, tissue tropism, host responses, and pathogenesis. Gene editing tools, such as CRISPR, enable precise manipulation of host and viral genomes, facilitating the development of resistant organisms and next-generation vaccine platforms. AI technologies, including AlphaFold for structure prediction and platforms for de novo protein design, address long-standing bottlenecks in structural biology and offer powerful means to engineer antiviral proteins, antibodies, and vaccine antigens. Synthetic biology, guided by the Design-Build-Test-Learn cycle, integrates computational design, genetic assembly, and functional validation into a cohesive pipeline. Together, these technologies form a synergistic workflow that spans disease modeling, target discovery, molecular design, construction, testing, and iterative optimization. This integrated approach is shifting antiviral development from traditional empirical methods toward more precise, intelligent strategies. The review also highlights ongoing challenges in integration and scalability, stressing that high-quality biological datasets and stronger interdisciplinary collaboration are essential for realizing translational potential. By presenting a cohesive view of these converging methodologies, this review offers a framework to guide the intelligent evolution of antiviral strategies in both human and animal health.

Antiviral↗

PubMed2006

Comparison between neural networks and multiple logistic regression to predict acute coronary syndrome in the emergency room.

OBJECTIVE: Patients with suspicion of acute coronary syndrome (ACS) are difficult to diagnose and they represent a very heterogeneous group. Some require immediate treatment while others, with only minor disorders, may be sent home. Detecting ACS patients using a machine learning approach would be advantageous in many situations. METHODS AND MATERIALS: Artificial neural network (ANN) ensembles and logistic regression models were trained on data from 634 patients presenting an emergency department with chest pain. Only data immediately available at patient presentation were used, including electrocardiogram (ECG) data. The models were analyzed using receiver operating characteristics (ROC) curve analysis, calibration assessments, inter- and intra-method variations. Effective odds ratios for the ANN ensembles were compared with the odds ratios obtained from the logistic model. RESULTS: The ANN ensemble approach together with ECG data preprocessed using principal component analysis resulted in an area under the ROC curve of 80%. At the sensitivity of 95% the specificity was 41%, corresponding to a negative predictive value of 97%, given the ACS prevalence of 21%. Adding clinical data available at presentation did not improve the ANN ensemble performance. Using the area under the ROC curve and model calibration as measures of performance we found an advantage using the ANN ensemble models compared to the logistic regression models. CONCLUSION: Clinically, a prediction model of the present type, combined with the judgment of trained emergency department personnel, could be useful for the early discharge of chest pain patients in populations with a low prevalence of ACS.

Acute Disease↗

PubMed1981

Contextual conditioning and the US preexposure effect in conditioned fear.

A series of five experiments was carried out in which fear of context caused by exposure to shocks was manipulated by signaling the shocks with a discrete stimulus, signaling the days during which shocks occurred with a session-long stimulus, or switching the context between exposure and the subsequent test. All these manipulations influenced fear of the context in the manner predicted by the Rescorla-Wagner associative model. Following this, all the rats were given conditioning trials with shock and a different discrete stimulus. All preexposure treatments produced consistent and reliable interference with conditioning with the exception of signaling the shocks with a discrete stimulus, which greatly reduced interference. These results are interpreted as being consistent both with a cognitive explanation of the US exposure effect, which claims that animals learn that shocks are unpredictable during conditioning and this knowledge retards future conditioning when they are predictable, and with an adaptation explanation, which claims that unpredictable shocks produce chronic fear and this fear through either a change in adaptation level or through emotional exhaustion renders the shocks less reinforcing during the conditioning test.

Adaptation, Psychological↗

PubMed1998

On Learning To Become a Successful Loser: A Comparison of Alternative Abstractions of Learning Processes in the Loss Domain.

One of the main difficulties in the development of descriptive models of learning in repeated choice tasks involves the abstraction of the effect of losses. The present paper explains this difficulty, summarizes its common solutions, and presents an experiment that was designed to compare the descriptive power of the specific quantifications of these solutions proposed in recent research. The experiment utilized a probability learning task. In each of the experiment's 500 trials participants were asked to predict the appearance of one of two colors. The probabilities of appearance of the colors were different but fixed during the entire experiment. The experimental manipulation involved an addition of a constant to the payoffs. The results demonstrate that learning in the loss domain can be faster than learning in the gain domain; adding a constant to the payoff matrix can affect the learning process. These results are consistent with Erev & Roth's (1996) adjustable reference point abstraction of the effect of losses, and violate all other models. Copyright 1998 Academic Press.

Journal Article↗

PubMed2001

Preliminary evidence for a general competency hypothesis.

Although predoctoral dental education is generally taught and evaluated by disciplines, there is no evidence bearing on whether the competencies necessary to begin independent practice are learned and practiced as a general set of skills, understanding, and values or as groups of discipline-specific skills, understanding, and values, which together constitute graduation competency. There is some support in the literature for each view In this preliminary investigation, 64,000 faculty ratings of student clinical competency were analyzed in a Year x Quarter x Discipline x Model design. The dependent variable was predictive validity of graduation quarter competency ratings using R-values from four prediction models. Results of a multiple repeated measures ANOVA show that models based on technical skills other than the one being predicted, clinical judgment and patient management, and the combination of these two models all predict graduation competency in each of four disciplines better than do ratings in the disciplines being predicted. As the time gap between predictive and predicted competence decreases, predictions become more accurate, but an asymptote is reached by the middle of the final clinical year. By using general models to evaluate students rather than discipline-specific ones, students needing intervention and remediation and those who could benefit from enrichment experiences can be identified as accurately at the beginning of their clinical careers as they can near the graduation deadline. This study provides preliminary support for a general competency hypothesis and suggests that research is necessary to better understand how students and dentists learn and practice rather than how they are taught.

Analysis of Variance↗

PubMed1978

Retrieval from long-term memory in presenile dementia:two tests of an hypothesis.

Recent experimental studies have suggested that patients with presenile dementia might have diffculty in retrieving information from memory as well as a reduced ability to acquire new information. The hypothesis that this retrieval difficulty might be due to an inability to inhibit the recall of irrelevant information was tested by two investigations. Free recall data failed to give clear support for the hypothesis but a prediction based upon recognition testing was confirmed.

Dementia↗

PubMed2006

Visuospatial function in the beagle dog: an early marker of cognitive decline in a model of human aging and dementia.

Visuospatial learning and memory impairments are an early marker for age-related cognitive decline and Alzheimer's disease. Similar to humans, aged dogs show visuospatial learning and memory deficits (). One hundred and nine beagle dogs ranging between 0.25 and 11.99 years were tested on a visuospatial delayed non-matching to position (DNMP) task to better characterize the progression of visuospatial deficits in the dog. Age predicted 48.2% of the variability in learning the DNMP, with dogs ranging from 1 to 11.99 years generally making more errors with increasing age. By contrast, puppies (<1 year) likely were showing developmental deficits, possibly due to an immature prefrontal cortex. Mild visuospatial deficits were detected by 6 years, which precedes the typical onset of amyloid-beta (Abeta) accumulation in the dog brain by two years, and can serve as an early marker for cognitive decline in the dog. These findings suggest that (1) age-related changes in visuospatial function in the dog models that seen in humans, further validating the dog as a model for human aging and dementia; and (2) other mechanisms, such as oxidative stress, soluble Abeta oligomers or cholinergic deficits, are likely contributing to the early impairment.

Aging↗

PubMed1985

A test of the differences between anticipation and study-test methods of paired-associate learning.

The identity model proposes that anticipation and study-test methods of paired-associate learning differ little in basic acquisition, retrieval, and storage processes per event: study, test, and intervening study and test events of other items plus the intercycle interval. The major difference between the two methods boils down to differential short-term loss over the differential retention interval. When the study-test interval is equated, the identity model predicts no difference between the methods. However, the feedback model predicts superiority for the anticipation method, and the differential acquisition, context effect, or task alternation models predict superiority for the study-test method. An experimental test utilized (nearly) identical study-test intervals, various materials, and both massed and spaced practice. In 15 out of 16 comparisons, there was no difference between the methods, providing support for the identity model. Within limits, the greater the study-test interval differentials, the greater the advantage for the method with the shorter study-test intervals. Quantitative analyses support the identity model.

Feedback↗

PubMed2000

Curved trajectory prediction using a self-organizing neural network.

Existing neural network models are capable of tracking linear trajectories of moving visual objects. This paper describes an additional neural mechanism, disfacilitation, that enhances the ability of a visual system to track curved trajectories. The added mechanism combines information about an object's trajectory with information about changes in the object's trajectory, to improve the estimates for the object's next probable location. Computational simulations are presented that show how the neural mechanism can learn to track the speed of objects and how the network operates to predict the trajectories of accelerating and decelerating objects.

Acceleration↗

PubMed1993

Age-related deterioration in conditional avoidance task in the SAM-P/10 mouse, an animal model of spontaneous brain atrophy.

A novel inbred strain of mouse 'SAM-P/10' (Senescence Accelerated Mouse) is a model of age-related brain atrophy characterized by age-related loss and shrinkage of neurons in the cerebral neocortex. Age-related changes in learning and memory skills of SAM-P/10 mice were investigated using a newly developed conditional avoidance task in a T-maze. Comparisons were made with findings in the SAM-R/1 strain which shows a little loss and no shrinkage of neocortical neurons. Four-month-old SAM-R/1 and SAM-P/10 performed well during a 10-day training schedule of the conditional avoidance task. SAM-R/1 mice over 17 months of age were slower learners than younger SAM-R/1 mice but reached nearly the same high percentage avoidance as seen in the 4-month-old mice during the last 4 days of the schedule. Performance of the SAM-P/10 mice gradually worsened with aging and 10- to 12-month-old SAM-P/10 mice could not reach the percentage avoidance seen with the 4-month-old mice, even after the 10-day training. When the mean percentage of successful avoidance or escape behavior on every training day was plotted, the curves were much the same for both SAM-R/1 and SAM-P/10 mice, of any age. These results show that aged SAM-P/10 mice retained the left-right turning discrimination in the T-maze and lost the ability to predict the forthcoming aversive shock by associating conditioned stimulus and unconditioned stimulus.

Aging↗

PubMed2004

Assessing the validity of the endoscopic shunt insertion trial: did surgical experience affect the results?

OBJECT: Most surgical procedures are associated with a learning curve in which the success rate is lower early in the experience before mistakes have been identified and modifications made to the procedure. Negative results obtained early in a trial's learning curve may be a matter of timing rather than a reflection of the procedure's effectiveness. The recently published results of the Endoscopic Shunt Insertion Trial (ESIT) represent the notion that endoscopically placed shunts were no more likely to survive than conventionally placed shunts. This negative result may be due to inexperience in performing endoscopic surgeries. METHODS: . Surgical experience was assessed in two ways. Shunt survival rates were compared between cases treated endoscopically in the 1st and last years of the ESIT. The effect of center volume was evaluated using a Cox proportional hazard model in which the following variables were analyzed: age at registration, the diagnosis of myelomeningocele, head size, method of shunt placement (endoscopic compared with conventional), and center volume. There was no difference in survival (endurance) of the shunt between patients enrolled in the 1st and last years (log rank = 0.08, p = 0.77). Likewise, no variable in the Cox multivariate model, including center volume, was a significant factor in predicting shunt survival. CONCLUSIONS: The primary result of the ESIT was found to be internally valid. The fact that endoscopic shunt placement did not benefit patients evaluated in the study was not due to early timing of the trial. Any learning curve among the participating surgeons did not adversely affect the results.

Cerebrospinal Fluid Shunts↗

PubMed2003

A taxonomy for spatiotemporal connectionist networks revisited: the unsupervised case.

Spatiotemporal connectionist networks (STCNs) comprise an important class of neural models that can deal with patterns distributed in both time and space. In this article, we widen the application domain of the taxonomy for supervised STCNs recently proposed by Kremer (2001) to the unsupervised case. This is possible through a reinterpretation of the state vector as a vector of latent (hidden) variables, as proposed by Meinicke (2000). The goal of this generalized taxonomy is then to provide a nonlinear generative framework for describing unsupervised spatiotemporal networks, making it easier to compare and contrast their representational and operational characteristics. Computational properties, representational issues, and learning are also discussed, and a number of references to the relevant source publications are provided. It is argued that the proposed approach is simple and more powerful than the previous attempts from a descriptive and predictive viewpoint. We also discuss the relation of this taxonomy with automata theory and state-space modeling and suggest directions for further work.

Classification↗

PubMed1997

Top-down learning of low-level vision tasks.

Perceptual tasks such as edge detection, image segmentation, lightness computation and estimation of three-dimensional structure are considered to be low-level or mid-level vision problems and are traditionally approached in a bottom-up, generic and hard-wired way. An alternative to this would be to take a top-down, object-class-specific and example-based approach. In this paper, we present a simple computational model implementing the latter approach. The results generated by our model when tested on edge-detection and view-prediction tasks for three-dimensional objects are consistent with human perceptual expectations. The model's performance is highly tolerant to the problems of sensor noise and incomplete input image information. Results obtained with conventional bottom-up strategies show much less immunity to these problems. We interpret the encouraging performance of our computational model as evidence in support of the hypothesis that the human visual system may learn to perform supposedly low-level perceptual tasks in a top-down fashion.

Algorithms↗

PubMed1998

Dissociable processes for learning the surface structure and abstract structure of sensorimotor sequences.

A sensorimotor sequence may contain information structure at several different levels. In this study, we investigated the hypothesis that two dissociable processes are required for the learning of surface structure and abstract structure, respectively, of sensorimotor sequences. Surface structure is the simple serial order of the sequence elements, whereas abstract structure is defined by relationships between repeating sequence elements. Thus, sequences ABCBAC and DEFEDF have different surface structures but share a common abstract structure, 123213, and are therefore isomorphic. Our simulations of sequence learning performance in serial reaction time (SRT) tasks demonstrated that (1) an existing model of the primate fronto-striatal system is capable of learning surface structure but fails to learn abstract structure, which requires an additional capability, (2) surface and abstract structure can be learned independently by these independent processes, and (3) only abstract structure transfers to isomorphic sequences. We tested these predictions in human subjects. For a sequence with predictable surface and abstract structure, subjects in either explicit or implicit conditions learn the surface structure, but only explicit subjects learn and transfer the abstract structure. For sequences with only abstract structure, learning and transfer of this structure occurs only in the explicit group. These results are parallel to those from the simulations and support our dissociable process hypothesis. Based on the synthesis of the current simulation and empirical results with our previous neuropsychological findings, we propose a neuro-physiological basis for these dissociable processes: Surface structure can be learned by processes that operate under implicit conditions and rely on the fronto-striatal system, whereas learning abstract structure requires a more explicit activation of dissociable processes that rely on a distributed network that includes the left anterior cortex.

Computer Simulation↗

PubMed1988

Aluminum induced encephalopathy in the rat.

Aluminum tartrate (AlT) but not sodium tartrate (NaT) produces a progressive encephalopathy when injected intracerebroventricularly in the rat. This syndrome, lethal within 30-35 days, is characterized by progressively deranged behavior. An early startle reaction (day 14), later joined by locomotor discoordination (day 19) is followed by locomotor and electrocorticographic (ECoG) seizures (day 21) in chronically instrumented AlT rats. There is early dissociation between ECoG and locomotor aspects. When tested in the shuttlebox for estimation of learning and memory function 7-8 days after AlT injection, marked impairment of both active and passive avoidance was observed. Glucose uptake capacity of synaptosomes from brain areas of AlT and NaT animals was indexed by the 2-deoxy-D-glucose method. Striatal and cortical synaptosomes showed reduced uptake activity 7 days following AlT injection. By day 14, hypothalamic areas also became affected, striatal uptake was further inhibited, and cortical uptake was reduced to 57% of control. The ECoG background rhythm remained unchanged until days 20-23, when the mean peak frequency was reduced. The model may be useful in the study of central aluminum toxicity and may have predictive validity in the testing of procedures to counter aluminum-associated encephalopathies in man.

Animals↗