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 793 records · Page 44Linked to original sources

PubMed2004

Perceptual learning retunes the perceptual template in foveal orientation identification.

What is learned during perceptual learning? We address this question by analyzing how perceptual inefficiencies improve over the course of perceptual learning (Dosher & Lu, 1998). Systematic measurements of human performance as a function of both the amount of external noise added to the signal stimulus and the length of training received by the observers enable us to track changes of the characteristics of the perceptual system (e.g., internal noise[s] and efficiency of the perceptual template) as perceptual learning progresses, and, therefore, identifies the mechanism(s) underlying the observed performance improvements. Two different observer models, the linear amplifier model (LAM) and the perceptual template model (PTM), however, have led to two very different theories of learning mechanisms. Here we demonstrate the failure of an LAM-based prediction - that the magnitude of learning-induced threshold reduction in high external noise must be less or equal to that in low external noise. In Experiment 1, perceptual learning of Gabor orientation identification in fovea showed substantial performance improvements only in high external noise but not in zero or low noise. The LAM-based model was "forced" to account for the data with a combination of improved calculation efficiency and (paradoxical) compensatory increases of the equivalent internal noise. Based on the PTM framework, we conclude that perceptual learning in this task involved learning how to better exclude external noise, reflecting retuning of the perceptual template. The data provide the first empirical demonstration of an isolable mechanism of perceptual learning. This learning completely transferred to a different visual scale in a second experiment.

Adult↗

PubMed2001

Feature mining and predictive model construction from severe trauma patient's data.

In management of severe trauma patients, trauma surgeons need to decide which patients are eligible for damage control. Such decision may be supported by utilizing models that predict the patient's outcome. The study described in this paper investigates the possibility to construct patient outcome prediction models from retrospective patient's data at the end of initial damage control surgery by using feature mining and machine learning techniques. As the data used comprises rather excessive number of features, special attention was paid to the problem of selecting only the most relevant features. We show that a small subset of features may carry enough information to construct reasonably accurate prognostic models. Furthermore, the techniques used in our study identified two factors, namely the pH value when admitted to ICU and the worst partial active thromboplastin time, to be of highest importance for prediction. This finding is pathophysiologically reasonable and represents two of three major problems with severe trauma patients, metabolic acidosis, hypothermia, and coagulopathy.

Algorithms↗

PubMed2003

Clustering ensembles of neural network models.

We show that large ensembles of (neural network) models, obtained e.g. in bootstrapping or sampling from (Bayesian) probability distributions, can be effectively summarized by a relatively small number of representative models. In some cases this summary may even yield better function estimates. We present a method to find representative models through clustering based on the models' outputs on a data set. We apply the method on an ensemble of neural network models obtained from bootstrapping on the Boston housing data, and use the results to discuss bootstrapping in terms of bias and variance. A parallel application is the prediction of newspaper sales, where we learn a series of parallel tasks. The results indicate that it is not necessary to store all samples in the ensembles: a small number of representative models generally matches, or even surpasses, the performance of the full ensemble. The clustered representation of the ensemble obtained thus is much better suitable for qualitative analysis, and will be shown to yield new insights into the data.

Algorithms↗

PubMedDate not supplied

Implementing a predictive modeling program, part II: Use of motivational interviewing in a predictive modeling program.

This is the second article of a two-part series about issues encountered in implementing a predictive modeling program. Part I looked at how to effectively implement a program and discussed helpful hints and lessons learned for case managers who are required to change their approach to patients. In Part II, we discuss the readiness to change model, examine the spirit of motivational interviewing and related techniques, and explore how motivational interviewing is different from more traditional interviewing and assessment methods.

Anger↗

PubMed2025

ASGCL: Adaptive Sparse Mapping-based graph contrastive learning network for cancer drug response prediction.

Personalized cancer drug treatment is emerging as a frontier issue in modern medical research. Considering the genomic differences among cancer patients, determining the most effective drug treatment plan is a complex and crucial task. In response to these challenges, this study introduces the Adaptive Sparse Graph Contrastive Learning Network (ASGCL), an innovative approach to unraveling latent interactions in the complex context of cancer cell lines and drugs. The core of ASGCL is the GraphMorpher module, an innovative component that enhances the input graph structure via strategic node attribute masking and topological pruning. By contrasting the augmented graph with the original input, the model delineates distinct positive and negative sample sets at both node and graph levels. This dual-level contrastive approach significantly amplifies the model's discriminatory prowess in identifying nuanced drug responses. Leveraging a synergistic combination of supervised and contrastive loss, ASGCL accomplishes end-to-end learning of feature representations, substantially outperforming existing methodologies. Comprehensive ablation studies underscore the efficacy of each component, corroborating the model's robustness. Experimental evaluations further illuminate ASGCL's proficiency in predicting drug responses, offering a potent tool for guiding clinical decision-making in cancer therapy.

Humans↗

PubMed1998

Perceptual categorization: connectionist modelling and decision rules.

Although it is currently popular to model human associative learning using connectionist networks, the mechanism by which their output activations are converted to probabilities of response has received relatively little attention. Several possible models of this decision process are considered here, including a simple ratio rule, a simple difference rule, their exponential versions, and a winner-take-all network. Two categorization experiments that attempt to dissociate these models are reported. Analogues of the experiments were presented to a single-layer, feed-forward, delta-rule network. Only the exponential ratio rule and the winner-take-all architecture, acting on the networks' output activations that corresponded to responses available on test, were capable of fully predicting the mean response results. In addition, unlike the exponential ratio rule, the winner-take-all model has the potential to predict latencies. Further studies will be required to determine whether latencies produced under more stringent conditions conform to the model's predictions.

Adolescent↗

PubMed2003

Learning rule-based models of biological process from gene expression time profiles using gene ontology.

MOTIVATION: Microarray technology enables large-scale inference of the participation of genes in biological process from similar expression profiles. Our aim is to induce classificatory models from expression data and biological knowledge that can automatically associate genes with novel hypotheses of biological process. RESULTS: We report a systematic supervised learning approach to predicting biological process from time series of gene expression data and biological knowledge. Biological knowledge is expressed using gene ontology and this knowledge is associated with discriminatory expression-based features to form minimal decision rules. The resulting rule model is first evaluated on genes coding for proteins with known biological process roles using cross validation. Then it is used to generate hypotheses for genes for which no knowledge of participation in biological process could be found. The theoretical foundation for the methodology based on rough sets is outlined in the paper, and its practical application demonstrated on a data set previously published by Cho et al. (Nat. Genet., 27, 48-54, 2001). AVAILABILITY: The Rosetta system is available at http://www.idi.ntnu.no/~aleks/rosetta. SUPPLEMENTARY INFORMATION: http://www.lcb.uu.se/~hvidsten/bioinf_cho/

Algorithms↗

PubMed2026

Deep learning techniques in predicting BRAF mutation status in cutaneous melanoma from histopathologic images.

AIMS: To develop and validate a deep learning framework for discriminating BRAF mutation status in cutaneous melanoma from routine H&E whole-slide images (WSIs) as a proof-of-concept complementary approach alongside molecular testing. METHODS: We built a two-stage pipeline comprising U-Net-based tumour segmentation followed by an Inception v3 classifier. In total, 272 institutional melanoma cases with confirmed BRAF status were used for model development (training and internal validation). Generalisability was assessed in an external test set of 76 cutaneous melanoma cases from the Cancer Genome Atlas (TCGA). Dermatopathologist-defined tumour-rich regions of interest were used to train and evaluate segmentation. WSIs were processed at 20×magnification using 512×512 tiles; slide-level mutation probabilities were obtained by averaging the predicted probabilities across all tumour-enriched tiles. RESULTS: Inception v3 achieved area under the receiver operating characteristic curve values of 0.973 (training), 0.954 (validation) and 0.915 (TCGA testing) and outperformed a ResNet50 baseline, showing stable external generalisation. Performance remained robust in advanced pathological T-category primary tumours (pT3-T4). Tumour probability heatmaps supported spatial interpretability by localising regions contributing most strongly to predicted mutation status. CONCLUSIONS: Deep learning applied to routine H&E WSIs can infer BRAF mutation status in cutaneous melanoma with consistent performance across institutional and external cohorts. Given the observed external sensitivity and negative predictive value, the model is not suitable for rule-out use or for deferring/omitting molecular testing. Any workflow integration is future work and would require prospective validation and calibration of probability outputs in real-world clinical series.

Artificial Intelligence↗

PubMed2000

Cancer proteomics: from identification of novel markers to creation of artifical learning models for tumor classification.

Studies of global protein expression in human tumors have led to the identification of various polypeptide markers, potentially useful as diagnostic tools. Many changes in gene expression recorded between benign and malignant human tumors are due to post-translational modifications, not detected by analyses of RNA. Proteome analyses have also yielded information about tumor heterogeneity and the degree of relatedness between primary tumors and their metastases. Results from our own studies have shown a similar pattern of changes in protein expression in different epithelial tumors, such as decreases in tropomyosin and cytokeratin expression and increases in proliferating cell nuclear antigen (PCNA) and heat shock protein expression. Such information has been used to create artificial learning models for tumor classification. The artificial learning approach has potential to improve tumor diagnosis and cancer treatment prediction.

Biomarkers, Tumor↗

PubMed2005

Plant intelligence.

Intelligent behavior is a complex adaptive phenomenon that has evolved to enable organisms to deal with variable environmental circumstances. Maximizing fitness requires skill in foraging for necessary resources (food) in competitive circumstances and is probably the activity in which intelligent behavior is most easily seen. Biologists suggest that intelligence encompasses the characteristics of detailed sensory perception, information processing, learning, memory, choice, optimisation of resource sequestration with minimal outlay, self-recognition, and foresight by predictive modeling. All these properties are concerned with a capacity for problem solving in recurrent and novel situations. Here I review the evidence that individual plant species exhibit all of these intelligent behavioral capabilities but do so through phenotypic plasticity, not movement. Furthermore it is in the competitive foraging for resources that most of these intelligent attributes have been detected. Plants should therefore be regarded as prototypical intelligent organisms, a concept that has considerable consequences for investigations of whole plant communication, computation and signal transduction.

Animals↗

PubMed1990

Alcohol expectancies and social anxiety in male and female undergraduates.

Recent studies have demonstrated that alcohol expectancies co-vary with some measures of trait anxiety. As part of a college drinking survey with 606 respondents (75.8%) evenly distributed by sex, this study tests further whether social anxiety predicts the expectancies of tension reduction, increased social assertiveness, and social/physical pleasure. In addition, the study examines whether sex, social anxiety, and alcohol consumption interact to predict alcohol expectancies. MANOVA analysis demonstrated that social anxiety significantly predicts the expectancies of tension reduction and increased social assertiveness but not the expectancy of social/physical pleasure. No interaction effects were found among sex, social anxiety, and consumption to predict expectancy levels. However, previous evidence that consumption levels (but not sex) predict expectancies was cross-validated. Findings are discussed within the context of a broader social learning model of alcohol use.

Adult↗

PubMed2026

Uncovering hub genes and key pathways responsive to drought stress in rice via meta-analysis of transcriptomic data.

Drought stress presents a formidable threat to global rice cultivation, triggering complex molecular responses that impact plant growth and productivity. To decipher the underlying gene expression dynamics, we performed a comprehensive meta-analysis of transcriptomic datasets derived from drought-tolerant rice genotypes. Via microarray data from three independent studies, we identified a set of consistently expressed differentially expressed genes (DEGs) under drought conditions. Integration of functional annotation tools, including GO and KEGG pathway enrichment, revealed key biological processes and signaling cascades involved in stress mitigation, such as ABA signaling, protein folding, and photosynthesis suppression. Protein-protein interaction (PPI) network construction, followed by hub gene identification via maximal clique centrality (MCC), highlighted pivotal regulators including LEA proteins, dehydrins, HSP70, and several transcription factors. Machine learning approaches further prioritize potential biomarkers, with Random Forest models achieving high classification accuracy and pinpointing key predictive genes. Chromosomal localization analysis provided spatial insights into the distribution of these hub genes, whose expression patterns were further compared against qRT-PCR data from previously published studies. This integrative approach identifies candidate genomic markers and mechanistic insights that may support future breeding strategies for drought-tolerant rice, pending experimental validation.

Cytoscape↗

PubMed2006

The soft constraints hypothesis: a rational analysis approach to resource allocation for interactive behavior.

Soft constraints hypothesis (SCH) is a rational analysis approach that holds that the mixture of perceptual-motor and cognitive resources allocated for interactive behavior is adjusted based on temporal cost-benefit tradeoffs. Alternative approaches maintain that cognitive resources are in some sense protected or conserved in that greater amounts of perceptual-motor effort will be expended to conserve lesser amounts of cognitive effort. One alternative, the minimum memory hypothesis (MMH), holds that people favor strategies that minimize the use of memory. SCH is compared with MMH across 3 experiments and with predictions of an Ideal Performer Model that uses ACT-R's memory system in a reinforcement learning approach that maximizes expected utility by minimizing time. Model and data support the SCH view of resource allocation; at the under 1000-ms level of analysis, mixtures of cognitive and perceptual-motor resources are adjusted based on their cost-benefit tradeoffs for interactive behavior.

Cognition↗

PubMedDate not supplied

Modeling choice behavior for new pharmaceutical products.

This paper presents a dynamic generalization of a model often used to aid marketing decisions relating to conventional products. The model uses stated-preference data in a random-utility framework to predict adoption rates for new pharmaceutical products. In addition, this paper employs a Markov model of patient learning in drug selection. While the simple learning rule presented here is only a rough approximation to reality, this model nevertheless systematically incorporates important features including learning and the influence of shifting preferences on market share. Despite its simplifications, the integrated framework of random-utility and product attribute updating presented here is capable of accommodating a variety of pharmaceutical marketing and development problems. This research demonstrates both the strengths of stated-preference market research and some of its shortcomings for pharmaceutical applications.

Analgesics↗

PubMed2006

Prospective memory in HIV-1 infection.

The cognitive deficits associated with HIV-1 infection are thought to primarily reflect neuropathophysiology within the fronto-striato-thalamo-cortical circuits. Prospective memory (ProM) is a cognitive function that is largely dependent on prefronto-striatal circuits, but has not previously been examined in an HIV-1 sample. A form of episodic memory, ProM involves the complex processes of forming, monitoring, and executing future intentions vis-à-vis ongoing distractions. The current study examined ProM in 42 participants with HIV-1 infection and 29 demographically similar seronegative healthy comparison (HC) subjects. The HIV-1 sample demonstrated deficits in time- and event-based ProM, as well as more frequent 24-hour delay ProM failures and task substitution errors relative to the HC group. In contrast, there were no significant differences in recognition performance, indicating that the HIV-1 group was able to accurately retain and recognize the ProM intention when retrieval demands were minimized. Secondary analyses revealed that ProM performance correlated with validated clinical measures of executive functions, episodic memory (free recall), and verbal working memory, but not with tests of semantic memory, retention, or recognition discrimination. Taken together, these findings indicate that HIV-1 infection is associated with ProM impairment that is primarily driven by a breakdown in the strategic (i.e., executive) aspects of retrieving future intentions, which is consistent with a prefronto-striatal circuit neuropathogenesis.

Adult↗

PubMed2026

Base-pair resolution conservation data improves cell type specific sequence-to-expression prediction.

MOTIVATION: Genomic sequence-to-activity models can decipher gene regulatory mechanisms and predict the functional impact of regulatory variants. However, current models struggle to integrate information from sequences outside promoters, especially information from cell type specific regulatory elements. RESULTS: Here, we propose incorporating base-pair resolution evolutionary conservation data into genomic sequence-to-expression predictors. We explore two training strategies-training from scratch or fine-tuning an existing sequence-only model with additional conservation input. We find that in both cases, base-pair resolution conservation data improves cell type specific sequence-to-expression prediction, with training from scratch yielding the greatest benefit. The improvement in cell type specific expression prediction can be attributed in part to the fact that models trained on sequence and conservation data learn to better recognize cell type specific regulatory elements than models trained on sequence alone. AVAILABILITY: Code is available at https://github.com/ni-lab/basenji-phyloP.

Conserved Sequence↗

PubMed2006

Deterministic approach to robust adaptive learning of fuzzy models.

This study is concerned with the adaptive learning of an interpretable Sugeno-type fuzzy inference system, in a deterministic framework, in the presence of data uncertainties and modeling errors. The authors explore the use of Hinfinity estimation theory and least squares estimation for online learning of membership functions and consequent parameters without making any assumption and requiring a priori knowledge of upper bounds, statistics, and distribution of data uncertainties and modeling errors. The issues of data uncertainties, modeling errors, and time variations have been considered mathematically in a sensible way. The proposed robust approach to the adaptive learning of fuzzy models has been illustrated through the examples of adaptive system identification, time-series prediction, and estimation of an uncertain process.

Algorithms↗

PubMed2026

Donor Microbiota Features Associated With Liver Transplant Recipient Infectious Complications: A Pilot Study Using Deep Intestinal Sampling During Liver Procurement.

BACKGROUND: The gut microbiota of living organ donors has been linked to transplant outcomes. However, little is known about the characteristics of the deceased donor gut microbiota or its potential impact on recipient outcomes. METHODS: We analyzed the deep intestinal microbiota from 24 deceased donors. Samples included luminal stool from the right and left colon as well as bile. Microbial composition was characterized using 16S V4 rRNA sequencing. α- and β-diversity analyses were performed to compare microbial communities between donor enteric sites and against stool samples from 28 healthy community controls, 14 critically ill intensive care comparators, and 12 matched liver transplant recipients. Machine learning models and logistic regression analysis were applied to explore whether features of the donor microbiota could predict recipient post-transplant complications. FINDINGS: The deceased donor microbiota showed an absence of the expected compositional variability between sampling sites, with no significant differences in either α- or β-diversity observed between bile, right and left colonic samples (all p > 0.05). Donor samples exhibited distinct microbial profiles compared with stool from both healthy and ICU comparators, including increased abundance of potential pathogens within the Enterobacteriaceae family (all p < 0.001). Features of the donor microbiota, particularly enrichment of Enterobacteriaceae, were associated with an increased risk of early post-transplant infection in recipients (≤ 30 days; p = 0.011). INTERPRETATION: The deceased donor gut microbiota may represent a distinct microbial community with potential clinical relevance. Microbial profiling of donor enteric microbiota may help identify recipients at heightened risk of early post-transplant infectious complications.

Enterobacteriaceae↗