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 757 records · Page 42Linked to original sources

PubMedDate not supplied

Associative learning in early vision.

Sensory discriminations often improve with practice (perceptual learning). Recent results show that practice does not necessarily lead to the best possible performance on the task. It was shown that learning a task (contrast discrimination) that has already reached saturation could be enabled by a contextual change in the stimulus (the addition of surrounding flankers) during practice. Psychophysical results with varying context show a behavior that is described by a network of local visual processors with horizontal recurrent interactions. We describe a mathematical learning rule for the modification of cortical synapses that is inspired by the experimental results and apply it to recurrent cortical networks that respond to external stimuli. The model predicts that repeated presentation of the same stimulus leads to saturation of synaptic modification, such that the strengths of recurrent connections depend on the configuration of the stimulus but not on its amplitude. When a new stimulus is introduced, the modification is rekindled until a new equilibrium is reached. This effect may explain the saturation of perceptual learning when practicing a certain task repeatedly. We present simulations of contrast discrimination in a simplified model of a cortical column in the primary visual cortex and show that performance of the model is reminiscent of context-dependent perceptual learning.

Computer Simulation↗

PubMed2004

The role of neuromuscular properties in determining the end-point of a movement.

How does the activation of several muscles combine to produce reliable multijoint movements? To study this question, we stimulated up to six sites in muscles, nerves, and the spinal cord. Flexion and extension of the hip, knee, and ankle were elicited in anesthetized and decerebrate cats. The movements occurred largely in the sagittal plane against a constant spring load and covered most of the passive range of motion of the cat's limb. The movements of the end-point (foot) were compared with predictions based on vectorial summation of end-point movements elicited by stimulating single electrodes. The lengths of the movements produced by stimulating more than one site exceeded what was expected from linear summation for small movements (<3 cm) and showed a less than linear summation for large movements (>11 cm). The data were compared with muscle and limb models. Since the deviations from linearity were predictable as a function of distance, adjustments might easily be learned by trial and error. The summation was less complete for spinal stimulation, compared to nerve and muscle stimulation, so spinal circuits do not appear to compensate for the nonlinearities. Movements were elicited from positions of the limb not only in a neutral position, but also in front and behind the neutral position. A degree of convergence was seen, even with stimulation of some individual muscles, but the convergence increased as more muscles were stimulated and more joints were actively involved. This suggests that convergence to an equilibrium-point arises at least partly from muscle properties. In conclusion, there are deviations from linear vectorial summation, and these deviations increase when more muscles are stimulated. The convergence to an equilibrium-point may simplify the computations needed to produce movements involving many muscles.

Anesthesia↗

PubMed1999

Does urge to drink predict relapse after treatment?

The urge to drink, also often referred to as craving, is an emotional state in which a person is motivated to seek and use alcohol. In abstinent alcoholics, this urge may contribute to the risk of relapse. Researchers have developed several models--including the conditioned withdrawal model, conditioned appetitive motivational model, social learning model, and information-processing model--to describe the role of urges in relapse. Several studies have evaluated the role of urges in predicting alcoholism treatment outcome and relapse. Some findings indicate that the degree of urge an alcoholic experiences when confronted with a simulated high-risk situation at the end of alcoholism treatment can predict subsequent drinking. Other studies, however, show inconsistent results regarding the role of urges in predicting treatment outcome. Overall, the study results suggest that urges do not necessarily increase the risk of relapse but may actually protect some drinkers against further drinking.

Alcoholism↗

PubMed1988

Effects of lesions of the dorsal noradrenergic bundle on successive discrimination in the rat.

Male Sprague-Dawley rats were trained to bar-press for food reward on a successive discrimination involving periods of reward on a variable-interval (VI) 18-s schedule interspersed with periods of extinction. The two components of the schedule were signaled by a steady or a flashing light, counterbalanced between VI and extinction components. Confirming previous findings, the discrimination was easier when the flashing light signaled VI and the steady light signaled extinction, than with the reverse allocation of stimuli. This pattern of results is consistent with a dynamogenic effect of flashing light relative to steady light, facilitating discrimination when the flashing light signals the occasion to respond but impairing discrimination when this stimulus signals the occasion to withhold responding. Given this interpretation of performance in the successive discrimination task, it may be used to test three different hypotheses of the functions of the dorsal noradrenergic bundle (DB): that this subserves learning, selective attention, or behavioral inhibition plus arousal. To examine these hypotheses sham-operated animals were compared to animals in which hippocampal noradrenaline levels had been reduced by 98% and hypothalamic levels by 48% after injection into the DB of the catecholamine-specific neurotoxin, 6-hydroxy-dopamine. The lesioned animals responded more slowly than controls in VI components when these were signaled by the flashing light, and more rapidly than controls in extinction components when these were signaled by the steady light. In consequence, the discrimination was impaired only in the condition (flashing light signaling VI, steady light signaling extinction) which controls found easier. These results are in conflict with predictions from the learning and attentional hypotheses of DB function. They are consistent, however, with a model that attributes behavioral inhibitory functions to the DB projection to the septohippocampal system, and arousing functions to the DB projection to the hypothalamus.

Animals↗

PubMed2006

Error criteria for cross validation in the context of chaotic time series prediction.

The prediction of a chaotic time series over a long horizon is commonly done by iterating one-step-ahead prediction. Prediction can be implemented using machine learning methods, such as radial basis function networks. Typically, cross validation is used to select prediction models based on mean squared error. The bias-variance dilemma dictates that there is an inevitable tradeoff between bias and variance. However, invariants of chaotic systems are unchanged by linear transformations; thus, the bias component may be irrelevant to model selection in the context of chaotic time series prediction. Hence, the use of error variance for model selection, instead of mean squared error, is examined. Clipping is introduced, as a simple way to stabilize iterated predictions. It is shown that using the error variance for model selection, in combination with clipping, may result in better models.

Journal Article↗

PubMed1999

A cerebellar model of timing and prediction in the control of reaching.

A simplified model of the cerebellum was developed to explore its potential for adaptive, predictive control based on delayed feedback information. An abstract representation of a single Purkinje cell with multistable properties was interfaced, using a formalized premotor network, with a simulated single degree-of-freedom limb. The limb actuator was a nonlinear spring-mass system based on the nonlinear velocity dependence of the stretch reflex. By including realistic mossy fiber signals, as well as realistic conduction delays in afferent and efferent pathways, the model allowed the investigation of timing and predictive processes relevant to cerebellar involvement in the control of movement. The model regulates movement by learning to react in an anticipatory fashion to sensory feedback. Learning depends on training information generated from corrective movements and uses a temporally asymmetric form of plasticity for the parallel fiber synapses on Purkinje cells.

Adaptation, Physiological↗

PubMed1992

Process evaluation of a home-based program to reduce diet-related cancer risk: the "WIN at Home Series".

A random mailed survey (response N = 226; 75.3%) of participants in diet-related home-based learning evaluated exposure to recruitment channels and impact on salience, utility, level of participation, sharing the course with others, knowledge, and performing recommended behaviors. A post-only design, the study was conducted in a small Minnesota city (population = 20,000), part of the Cancer and Diet Intervention (CANDI) project. About 18.5% of residents (3,711) enrolled during an 8-week media campaign; women, college graduates, and those over 44 years old were overrepresented. Participants learned about the program through mass media (97%); small media (41.9%); and interpersonal sources (50%). Women were more likely to learn about the course through interpersonal sources. In analysis of variance (ANOVA) modeling, salience and utility predicted level of participation in course activities. Level of participation in turn predicted nutrition knowledge and with salience predicted performance of recommended behaviors. Although the course appealed to individuals who needed it less, there was evidence of diffusion to the unenrolled. About 57% of responding participants reported sharing it with spouses; about 67% reported sharing it with someone outside their households.

Adult↗

PubMed1995

Psychosocial outcomes of HIV illness in male and female African American clients.

With the rapid growth of HIV infection among African Americans, the issue of how medical problems relate to psychological functioning in the black community population has acquired new meaning and urgency for health care policy. To develop effective strategies to meet the mental health needs of infected African Americans we need a better understanding of the pattern of Association between HIV and psychological distress. The objective of this study is to test several hypotheses that predict depression and anxiety in black adults infected with HIV. Our conceptual model is derived from learned helplessness theory (Seligman, 1975), the concept of perceived coherence (Antonovsky, 1980; Lewis & Gallison, 1989), and social support theory (Cohen & Willis, 1985). Instruments used in the study include: The Center for Epidemiological Studies-Depression (CES-D) Scale (Radloff, 1977), the Anxiety Scale (Lewis, Firsich, and Parsell, 1979), and the Perceived Coherence Scale (Lewis, 1989). Data were obtained from 255 HIV infected black males and females (age > or = 18) who sought support, counseling, and maintenance services from one of three HIV care and referral centers in the Mid-South. The results of the study emphasize the relative importance of perceived physical symptoms over stage of illness for psychological functioning among African American adults with HIV. Further, the findings also demonstrate the potential importance of perceived coherence for psychological functioning. Black clients who reported higher perceived coherence, regardless of the stage of illness or level of HIV symptoms, had lower anxiety and depression. Significant gender differences in depression are also observed and implications are drawn for strategies to address HIV related mental health care needs of African Americans.

Adaptation, Psychological↗

PubMed2005

Predicting patterns of adolescent alcohol use: a longitudinal study.

OBJECTIVE: Because most studies of adolescent alcohol use have focused primarily on the frequency and quantity of consumption, we know little about how adolescent drinking patterns change during the high school years. The purpose of this article is to provide such data, as well as to identify some of the individual, family, social life and community predictors of changes in drinking patterns over time. METHOD: A sample of 1,253 students in grades 9 through 12 (57% female) in a large metropolitan school district participated. Three ethnicities were represented: African American, European American and Mexican American. Students completed questionnaires every 6 months for a 2-year period (n = 743 at Time 4). RESULTS: Cluster analyses of the drinking variables yielded one problem-drinking group (heavy, multiple-context drinking), two high-risk groups (i.e., date and outdoor drinking) and three normative groups (light, family/parent, moderate/ party drinking). The most predictable patterns of longitudinal changes in adolescent drinking were consistent with the following progression (or the reverse): abstainer --> normative drinker --> high-risk drinker --> problem drinker. Paternal attitudes toward adolescent drinking and peer involvement in antisocial behavior predicted movement into normative drinking; social activity with peers predicted movement into high-risk drinking; and emotional distress predicted the transition into problem drinking. CONCLUSIONS: These findings are consistent with the multistage social learning model, demonstrating that the predictors of adolescent alcohol use vary across different levels of adolescent alcohol involvement.

Adolescent↗

PubMed2006

FCMAC-Yager: a novel Yager-inference-scheme-based fuzzy CMAC.

The cerebellum is a brain region important for a number of motor and cognitive functions. It is able to generate error correction signals to drive learning and for the acquisition of memory skills. The cerebellar model articulation controller (CMAC) is a neural network inspired by the neurophysiologic theory of the cerebellum and is recognized for its localized generalization and rapid algorithmic computation capabilities. The main deficiencies in the basic CMAC structure are: (1) it is difficult to interpret the internal operations of the CMAC network and (2) the resolution (quantization) problem arising from the partitioning of the input training space. These limitations lead to the synthesis of a fuzzy quantization technique and the mapping of a fuzzy inference scheme onto the CMAC structure. The discrete incremental clustering (DIC) technique is employed to alleviate the quantization problem in the CMAC structure, resulting in the fuzzy CMAC (FCMAC) network. The Yager inference scheme (Yager), which possesses firm fuzzy logic foundation and maps closely to the logical implication operations in the classical (binary) logic framework, is subsequently mapped onto the FCMAC structure. This results in a novel fuzzy neural architecture known as thefuzzy cerebellar model articulation controller-Yager (FCMAC-Yager) system. The proposed FCMAC-Yager network exhibits learning and memory capabilities of the cerebellum through the CMAC structure while emulating the human way of reasoning through the Yager. The new FCMAC-Yager network employs a two-phase training algorithm consisting of structural learning based on the DIC technique and parameter learning using hebbian learning (associative long-term potentiation). The proposed FCMAC-Yager architecture is evaluated using an extensive suite of real-life applications such as highway traffic-trend modeling and prediction and performing as an early warning system for bank failure classification and medical diagnosis of breast cancer. The experimental results are encouraging.

Algorithms↗

PubMed2004

Role of the basal ganglia in category learning: how do patients with Parkinson's disease learn?

The purpose of the present study was to gain a deeper understanding of the role of the basal ganglia in learning and memory by examining learning strategies among patients with basal ganglia dysfunction. Using a probabilistic category learning task (the "weather prediction" task) previously shown to be sensitive to basal ganglia function, the authors examined patterns of performance during learning and used mathematical models to capture different learning strategies. Results showed that patients with Parkinson's disease exhibit different patterns of strategy use. Specifically, most controls initially used a simple, but suboptimal, strategy that focused on single-cue-outcome associations; eventually, however, most controls adopted a more complex, optimal learning strategy, integrating single-cue associations to predict outcomes for multiple-cue stimuli. In contrast, the majority of individuals with Parkinson's disease continued to rely on simple single-cue learning strategies throughout the experiment.

Aged↗

PubMedDate not supplied

Exploring environmental barriers to participation in mammography screening in an HMO.

Despite an upward trend in mammography screening rates, rates among some demographic subgroups and rates of annual mammography remain low. Behavioral-based interventions which move beyond invitational strategies to help women overcome their personal barriers may be necessary to increase participation. We developed a heuristic model based on the Health Belief Model and Social Learning Theory with the central hypothesis that the relative importance of environmental barriers in predicting screening behavior is a function of the woman's perceived risk, preventive orientation, and/or concerns about mammography. We completed telephone interviews with 313 women who did not obtain a mammogram and 350 women who had a mammogram within 365 days of an invitation from a Health Maintenance Organization-based breast cancer screening program. Results of multivariate analyses indicated that perceived risk did not mitigate the influence of logistic inconveniences associated with obtaining a mammogram. Preventive orientation as measured by smoking status interacted with belief that symptoms are a necessary prerequisite to a mammogram as a powerful predictor of participation; the greatest negative impact of concerns on participation was found among smokers. A similar relationship between concerns and participation, although only marginally significant, was observed among those who perceived it to be difficult to get to the screening center. Implications of the results for development of behavioral interventions and additional research are discussed.

Breast Neoplasms↗

PubMed2000

Inductive learning approaches to rainfall-runoff modelling.

Trying to model the rainfall-runoff process is a complex activity as it is influenced by a number of implicit and explicit factors--for example, precipitation distribution, evaporation, transpiration, abstraction, watershed topography, and soil types. However, this kind of forecasting is particularly important as it is used to predict serious flooding, estimate erosion and identify problems associated with low flow. Inductive learning approaches (e.g. decision trees and artificial neural networks) are particularly well suited to problems of this nature as they can often interpret underlying factors (such as seasonal variations) which cannot be modelled by other techniques. In addition, these approaches can easily be trained on the explicit factors (e.g. rainfall) and the inexplicit factors (e.g. abstraction) that affect river flow. Inductive learning approaches can also be extended to account for new factors that emerge over a period of time. This paper evaluates the application of decision trees and two artificial neural network models (the multilayer perceptron and the radial basis function network) to river flow forecasting in two flood prone UK catchments using real hydrometric data. Comparisons are made between the performance of these approaches and conventional flood forecasting systems.

Algorithms↗

PubMed1998

A model for the nucleotide-binding domains of ABC transporters based on the large domain of aspartate aminotransferase.

ABC transporters are a large superfamily of integral membrane proteins involved inATP-dependent transport across biological membranes. Members of this superfamily play roles in a number of phenomena of biomedical interest, including cystic fibrosis (CFTR) and multidrug resistance (P-glycoprotein, MRP). Most ABC transporters are predicted to consist of four domains, two membrane-spanning domains and two cytoplasmic domains. The latter contain conserved nucleotide-binding motifs. Attempts to determine the structure of ABC transporters and of their separate domains are in progress but have not yet been successful. To aid structure determination and possibly learn more about the domain boundaries, we set out to model nucleotide-binding domains (NBDs) of ABC transporters based on a known structure. Previous attempts to predict the 3D structure of NBDs were based solely on sequence similarity with known nucleotide-binding folds. We have analyzed the sequences of a number of nucleotide-binding domains with the algorithm THREADER, developed by D.T. Jones, and a possible fold was found in the structure of aspartate aminotransferase. We present a model for the N-terminal NBD of CFTR, based on the large domain of the A chain of aspartate aminotransferase. The model is refined using multiple sequence alignment, secondary structure prediction, and 3D-1D profiles. Our model seems to be in good agreement with known properties of nucleotide-binding domains and has some appealing characteristics compared with the previous models.

ATP-Binding Cassette Transporters↗

PubMed2025

HINN: Hierarchical Input Neural Network identifies multi-omics biomarker for cognitive decline.

Understanding complex diseases requires models that can integrate diverse layers of biological data while yielding insights that are biologically interpretable. Although multi-omics integration with machine learning (ML) has advanced disease prediction and biomarker discovery, most existing approaches overlook the hierarchical and regulatory relationships that connect these molecular layers. Here, we present the Hierarchical Input Neural Network (HINN), a deep learning framework that incorporates known cross-omics relationships directly into its architecture, capturing the flow of information from genomics to epigenomics, transcriptomics, and downstream biological processes. By embedding these relationships, HINN improves both predictive performance and biological interpretability. We applied HINN to blood-derived multi-omics data from individuals with Alzheimer's disease or mild cognitive impairment to predict cognitive scores from standardized assessments. HINN outperformed both baseline and state-of-the-art models and pinpointed multi-omics biomarkers-including SNPs and promoter-region CpG sites in ATP6V1C1 and RCHY1 -that were significantly correlated with plasma p-Tau181 levels. These features map to biologically relevant processes with potential implications for cognitive decline. Our findings demonstrate how combining deep learning with biological knowledge can uncover interpretable, blood-based biomarkers for cognitive decline due to complex diseases such as Alzheimer's. All code and data are openly available at https://github.com/bozdaglab/HINN.

Alzheimer’s disease↗

PubMed2002

From view cells and place cells to cognitive map learning: processing stages of the hippocampal system.

The goal of this paper is to propose a model of the hippocampal system that reconciles the presence of neurons that look like "place cells" with the implication of the hippocampus (Hs) in other cognitive tasks (e.g., complex conditioning acquisition and memory tasks). In the proposed model, "place cells" or "view cells" are learned in the perirhinal and entorhinal cortex. The role of the Hs is not fundamentally dedicated to navigation or map building, the Hs is used to learn, store, and predict transitions between multimodal states. This transition prediction mechanism could be important for novelty detection but, above all, it is crucial to merge planning and sensory-motor functions in a single and coherent system. A neural architecture embedding this model has been successfully tested on an autonomous robot, during navigation and planning in an open environment.

Animals↗

PubMed2002

Diversity and complexity of HIV-1 drug resistance: a bioinformatics approach to predicting phenotype from genotype.

Drug resistance testing has been shown to be beneficial for clinical management of HIV type 1 infected patients. Whereas phenotypic assays directly measure drug resistance, the commonly used genotypic assays provide only indirect evidence of drug resistance, the major challenge being the interpretation of the sequence information. We analyzed the significance of sequence variations in the protease and reverse transcriptase genes for drug resistance and derived models that predict phenotypic resistance from genotypes. For 14 antiretroviral drugs, both genotypic and phenotypic resistance data from 471 clinical isolates were analyzed with a machine learning approach. Information profiles were obtained that quantify the statistical significance of each sequence position for drug resistance. For the different drugs, patterns of varying complexity were observed, including between one and nine sequence positions with substantial information content. Based on these information profiles, decision tree classifiers were generated to identify genotypic patterns characteristic of resistance or susceptibility to the different drugs. We obtained concise and easily interpretable models to predict drug resistance from sequence information. The prediction quality of the models was assessed in leave-one-out experiments in terms of the prediction error. We found prediction errors of 9.6-15.5% for all drugs except for zalcitabine, didanosine, and stavudine, with prediction errors between 25.4% and 32.0%. A prediction service is freely available at http://cartan.gmd.de/geno2pheno.html.

Computational Biology↗

PubMed2004

[Prediction on the negative outcomes of anger in female adolescents].

PURPOSE: This study was designed to construct a structural model for explaining negative outcomes of anger in female adolescents. METHOD: Data was collected by questionnaires from 199 female adolescents ina female high school in Seoul. Data analysis was done with SAS for descriptive statistics and a PC-LISREL Program for Covariance structural analysis. RESULT: The fit of the hypothetical model to the data was moderate, thus it was modified by excluding 7 paths and adding free parameters to it. The modified model with the paths showed a good fit to the empirical data(chi2=5.62, p=.69, GFI=.99, AGFI=.97, NFI=.99, NNFI=1.01, RMSR=.02, RMSEA=.00). Trait anger, state anger, and psychosocial problems were found to have a significant direct effect on psychosomatic symptoms. State anger, psychosocial problems, and learning behaviors were found to have direct effects on depression of female adolescents. CONCLUSION: The derived model is considered appropriate for explaining and predicting negative outcomes of anger in female adolescents. Therefore, it can effectively be used as a reference model for further studies and is a suggested direction in nursing practice.

Adolescent↗