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 523 records · Page 29Linked to original sources

PubMed2006

Linking proactive personality and the Big Five to motivation to learn and development activity.

The authors investigated links between the Big Five, proactive personality, and motivation to learn. Web-based survey data were collected at 2 points in time from 183 employees of a financial services firm. Results showed that proactive personality was, only in part, a composite of Big Five facets, which accounted for 26% of its variance. Structural equation modeling results demonstrated that proactive personality, openness, extraversion, and conscientiousness predicted motivation to learn. In addition, motivation to learn was positively related to objectively assessed development activity. Proactive personality, extraversion, and openness had significant indirect links to development activity. Hierarchical regression results suggested that proactive personality had significant incremental validity in the prediction of motivation to learn over all relevant Big Five facets.

Adult↗

PubMed2025

Sparse deconvolution of cell type medleys in spatial transcriptomics.

Mapping cell distributions across spatial locations with whole-genome coverage is essential for understanding cellular responses and signaling However, current deconvolution models aim to estimate the proportions of distinct cell types in each spatial transcriptomics spot by integrating reference single-cell data. These models often assume strong overlap between the reference and spatial datasets, neglecting biology-grounded constraints such as sparsity and cell-type variations, as well as technical sparsity. As a result, these methods rely on over-permissive algorithms that ignore given constraints leading to inaccurate predictions, particularly in heterogeneous or unmatched datasets. We introduce Weight-Induced Sparse Regression (WISpR), a machine learning algorithm that integrates spot-specific hyperparameters and sparsity-driven modeling. Unlike conventional approaches that neglect biology-grounded constraints, WISpR accurately predicts cell-type distributions while preserving biological coherence, i.e., spatially and functionally consistent cell-type localization, even in unmatched datasets. Benchmarking against five alternative methods across ten datasets, WISpR consistently outperformed competitors and predicted cellular landscapes in both normal and cancerous tissues. By leveraging sparse cell-type arrangements, WISpR provides biologically informed, high-resolution cellular maps. Its ability to decode tissue organization in both healthy and diseased states highlights WISpR's practical utility for spatial transcriptomics, particularly in challenging settings involving noise, sparsity, or reference mismatches.

Humans↗

PubMed2006

Early condition, song learning, and the volume of song brain nuclei in the zebra finch (Taeniopygia guttata).

Songbirds are an important model system for the study of the neurological bases of song learning, but variation in song learning accuracy and adult song complexity remains poorly understood. Current models of sexual selection predict that signals such as song must be costly to develop or maintain to constitute honest indicators of male quality. It has been proposed that reductions of nestling condition during song development might limit the expression of song learning. Adult song could thus act as an indicator of early stress as only males that enjoy good condition during development could learn accurately and sing long songs or large repertoires. We tested this hypothesis in the zebra finch by modifying early condition through cross-fostering chicks to small, medium, and large broods. Song learning was very accurate and was found to reflect very closely tutor song characteristics and to depend on the number of males in the tutoring group. Although the brood size manipulation strongly affected several measures of nestling condition and adult biometry, we found no relationship between early condition and song learning scores or song characteristics. Similarly, brain mass and high vocal center (HVC), robust nucleus of the arcopallium (RA), and lateral magnocellular nucleus of the anterior nidopallium (LMAN) volumes did not covary with nestling condition and growth measurements. We found no significant relationship between song repertoire size and HVC and RA volumes, although there was a nonsignificant trend for HVC to increase with increasing proportion of learnt elements in a song. In conclusion, the results provide no evidence for song learning to be limited by nestling condition during the period of nutritional dependence from the parents in this species.

Analysis of Variance↗

PubMed2003

Predicting the topology of transmembrane helical proteins using mean burial propensity and a hidden-Markov-model-based method.

Helices in membrane spanning regions are more tightly packed than the helices in soluble proteins. Thus, we introduce a method that uses a simple scale of burial propensity and a new algorithm to predict transmembrane helical (TMH) segments and a positive-inside rule to predict amino-terminal orientation. The method (the topology predictor of transmembrane helical proteins using mean burial propensity [THUMBUP]) correctly predicted the topology of 55 of 73 proteins (or 75%) with known three-dimensional structures (the 3D helix database). This level of accuracy can be reached by MEMSAT 1.8 (a 200-parameter model-recognition method) and a new HMM-based method (a 111-parameter hidden Markov model, UMDHMM(TMHP)) if they were retrained with the 73-protein database. Thus, a method based on a physiochemical property can provide topology prediction as accurate as those methods based on more complicated statistical models and learning algorithms for the proteins with accurately known structures. Commonly used HMM-based methods and MEMSAT 1.8 were trained with a combination of the partial 3D helix database and a 1D helix database of TMH proteins in which topology information were obtained by gene fusion and other experimental techniques. These methods provide a significantly poorer prediction for the topology of TMH proteins in the 3D helix database. This suggests that the 1D helix database, because of its inaccuracy, should be avoided as either a training or testing database. A Web server of THUMBUP and UMDHMM(TMHP) is established for academic users at http://www.smbs.buffalo.edu/phys_bio/service.htm. The 3D helix database is also available from the same Web site.

Algorithms↗

PubMed2000

Does the type of judgement required modulate cue competition?

According to the comparator process hypothesis (Matute, Arcediano, & Miller, 1996), cue competition in the learning of between-events relationships arises if the judgement required involves a comparison between the probability of the outcome given the target cue and the probability of the outcome given the competing cue. Alternatively, other associative accounts (the Rescorla-Wagner model: Rescorla & Wagner, 1972) conceive cue competition as a learning deficit affecting the target cue-outcome association. Consequently, the comparator process hypothesis predicts that cue competition occurs in inference judgements but not in contiguity ones, for only the first type of judgement implicitly involves such a comparison. On the other hand, the Rescorla-Wagner model predicts cue competition in both inference and contiguity judgements, because it establishes no relevant role for the type of judgement in producing cue competition. In Experiments 1 and 2 we manipulated the relative validity of cues and the type of question (inference vs. contiguity) in a predictive learning task. In both experiments we found a cue competition effect, but no interaction between the relative validity of cues and the type of question, suggesting that the Rescorla-Wagner theory suffices to explain cue competition.

Adult↗

PubMed2000

Discovery of predictive models in an injury surveillance database: an application of data mining in clinical research.

A new, evolutionary computation-based approach to discovering prediction models in surveillance data was developed and evaluated. This approach was operationalized in EpiCS, a type of learning classifier system specially adapted to model clinical data. In applying EpiCS to a large, prospective injury surveillance database, EpiCS was found to create accurate predictive models quickly that were highly robust, being able to classify > 99% of cases early during training. After training, EpiCS classified novel data more accurately (p < 0.001) than either logistic regression or decision tree induction (C4.5), two traditional methods for discovering or building predictive models.

Artificial Intelligence↗

PubMed2003

How do people learn to allocate resources? Comparing two learning theories.

How do people learn to allocate resources? To answer this question, 2 major learning models are compared, each incorporating different learning principles. One is a global search model, which assumes that allocations are made probabilistically on the basis of expectations formed through the entire history of past decisions. The 2nd is a local adaptation model, which assumes that allocations are made by comparing the present decision with the most successful decision up to that point, ignoring all other past decisions. In 2 studies, participants repeatedly allocated a capital resource to 3 financial assets. Substantial learning effects occurred, although the optimal allocation was often not found. From the calibrated models of Study 1, a priori predictions were derived and tested in Study 2. This generalization test shows that the local adaptation model provides a better account of learning in resource allocations than the global search model.

Adult↗

PubMed1997

Hepatic protein synthesis rate of liver specimens as a predictor of viability in rat cold ischemia liver transplantation model.

BACKGROUND/AIMS: We have previously reported that the hepatic protein synthesis rate, calculated as the uptake rate of L-[4.5 3H] leucine by the protein fraction during a 10-min incubation of a 16-G needle biopsy specimen of liver tissue, represents a high level of liver function and is therefore useful for evaluating liver function. We investigated the hepatic protein synthesis rate level in a pre-transplant liver to learn if it might predict the outcome in a rat orthotopic liver transplantation model. METHODS: Grafts were stored, liver specimens were obtained using a 21-G Chiba type II skinny needle, and the hepatic protein synthesis rate was calculated. Subsequently, liver transplantation was performed, and the hepatic protein synthesis rate level of revascularized liver, tissue blood flow rate, serum alanine aminotransferase, lactate dehydrogenase, hyaluronic acid, ketone body rate, and 2-week survival were examined. RESULTS: The hepatic protein synthesis rate of pretransplant liver was correlated with parameters of post-transplant liver function: hepatic protein synthesis rate of the revascularized liver (r=0.92, p<0.0001), tissue blood flow rate (r=0.77, p<0.004), serum alanine aminotransferase (r=-0.69, p<0.003), lactate dehydrogenase (r=-0.54, p<0.03), hyaluronic acid (r=-0.86, p<0.0002), and ketone body rate (r=0.57, p<0.02). Pretransplant hepatic protein synthesis rate in survivors was 263.6+/-54.2 nmol/mg protein/10 min, while that in nonsurvivors was significantly lower at 162.0+/-39.0 (p<0.0001). When evaluation was made using a logistic regression model, the accuracy predicted using the value of hepatic protein synthesis rate was 95% (19/20). CONCLUSIONS: These results suggest that measuring the hepatic protein synthesis rate of the grafts with a 21-G Chiba type II skinny needle may be a predictive criterion in the assessment of graft viability.

Alanine Transaminase↗

PubMed1991

Interference and the representation of events in memory.

Most current models of memory predict that the presence of increasingly well-learned, or strong, items in memory will cause increasing interference. This phenomenon, the list-strength effect, occurs as predicted when memory is tested by free recall but not when a recognition test is used. Four experiments use end-of-session testing to demonstrate that redistribution of storage time or effort from strong to weak items on mixed lists does not occur and therefore cannot be masking interference by strong items. Delay between study and test is found to cause memory loss independent of the basic list-strength findings. It is concluded that the presence of strong items in memory does not interfere with recognition performance and that interference is due to failures of retrieval rather than to composition or other forms of destructive interaction during storage.

Analysis of Variance↗

PubMed1999

Further evidence for feature correlations in semantic memory.

The role of feature correlations in semantic memory is a central issue in conceptual representation. In two versions of the feature verification task, participants were faster to verify that a feature (< is juicy >) is part of a concept (grapefruit) if it is strongly rather than weakly intercorrelated with the other features of that concept. Contrasting interactions between feature correlations and SOA were found when the concept versus the feature was presented first. An attractor network model of word meaning that naturally learns and uses feature correlations predicted those interactions. This research provides further evidence that semantic memory includes implicitly learned statistical knowledge of feature relationships, in contrast to theories such as spreading activation networks, in which feature correlations play no role.

Humans↗

PubMed2004

Dissociable roles of ventral and dorsal striatum in instrumental conditioning.

Instrumental conditioning studies how animals and humans choose actions appropriate to the affective structure of an environment. According to recent reinforcement learning models, two distinct components are involved: a "critic," which learns to predict future reward, and an "actor," which maintains information about the rewarding outcomes of actions to enable better ones to be chosen more frequently. We scanned human participants with functional magnetic resonance imaging while they engaged in instrumental conditioning. Our results suggest partly dissociable contributions of the ventral and dorsal striatum, with the former corresponding to the critic and the latter corresponding to the actor.

Adult↗

PubMed2003

Gene expression-based classification of malignant gliomas correlates better with survival than histological classification.

In modern clinical neuro-oncology, histopathological diagnosis affects therapeutic decisions and prognostic estimation more than any other variable. Among high-grade gliomas, histologically classic glioblastomas and anaplastic oligodendrogliomas follow markedly different clinical courses. Unfortunately, many malignant gliomas are diagnostically challenging; these nonclassic lesions are difficult to classify by histological features, generating considerable interobserver variability and limited diagnostic reproducibility. The resulting tentative pathological diagnoses create significant clinical confusion. We investigated whether gene expression profiling, coupled with class prediction methodology, could be used to classify high-grade gliomas in a manner more objective, explicit, and consistent than standard pathology. Microarray analysis was used to determine the expression of approximately 12000 genes in a set of 50 gliomas, 28 glioblastomas and 22 anaplastic oligodendrogliomas. Supervised learning approaches were used to build a two-class prediction model based on a subset of 14 glioblastomas and 7 anaplastic oligodendrogliomas with classic histology. A 20-feature k-nearest neighbor model correctly classified 18 of the 21 classic cases in leave-one-out cross-validation when compared with pathological diagnoses. This model was then used to predict the classification of clinically common, histologically nonclassic samples. When tumors were classified according to pathology, the survival of patients with nonclassic glioblastoma and nonclassic anaplastic oligodendroglioma was not significantly different (P = 0.19). However, class distinctions according to the model were significantly associated with survival outcome (P = 0.05). This class prediction model was capable of classifying high-grade, nonclassic glial tumors objectively and reproducibly. Moreover, the model provided a more accurate predictor of prognosis in these nonclassic lesions than did pathological classification. These data suggest that class prediction models, based on defined molecular profiles, classify diagnostically challenging malignant gliomas in a manner that better correlates with clinical outcome than does standard pathology.

Brain Neoplasms↗

PubMed1993

Facilitated dissociation of albumin-fatty acid complexes by rat hepatocytes.

Experiments were conducted comparing palmitate clearance by hepatocyte monolayers, polyethylene and that predicted by the diffusion-reaction model. The objective was to learn whether the albumin-dependent enhancement of unbound palmitate clearance was wholly attributable to codiffusion of bound and unbound fatty acid across an unstirred fluid layer, or whether the uptake flux was also contributed by facilitated dissociation of albumin-fatty acid complexes at the cell surface. We use a model-independent formulation of the facilitation phenomenon to explore this question at low concentrations of albumin. The central finding that facilitation occurs takes into consideration albumin-dependent changes in solution viscosity, endogenous albumin secretion and the adsorption of albumin to the polyethylene surface.

Adsorption↗

PubMed2006

Predicting cancer drug response by proteomic profiling.

PURPOSE: Accurate prediction of an individual patient's drug response is an important prerequisite of personalized medicine. Recent pharmacogenomics research in chemosensitivity prediction has studied the gene-drug correlation based on transcriptional profiling. However, proteomic profiling will more directly solve the current functional and pharmacologic problems. We sought to determine whether proteomic signatures of untreated cells were sufficient for the prediction of drug response. EXPERIMENTAL DESIGN: In this study, a machine learning model system was developed to classify cell line chemosensitivity exclusively based on proteomic profiling. Using reverse-phase protein lysate microarrays, protein expression levels were measured by 52 antibodies in a panel of 60 human cancer cell (NCI-60) lines. The model system combined several well-known algorithms, including random forests, Relief, and the nearest neighbor methods, to construct the protein expression--based chemosensitivity classifiers. The classifiers were designed to be independent of the tissue origin of the cells. RESULTS: A total of 118 classifiers of the complete range of drug responses (sensitive, intermediate, and resistant) were generated for the evaluated anticancer drugs, one for each agent. The accuracy of chemosensitivity prediction of all the evaluated 118 agents was significantly higher (P < 0.02) than that of random prediction. Furthermore, our study found that the proteomic determinants for chemosensitivity of 5-fluorouracil were also potential diagnostic markers of colon cancer. CONCLUSIONS: The results showed that it was feasible to accurately predict chemosensitivity by proteomic approaches. This study provides a basis for the prediction of drug response based on protein markers in the untreated tumors.

Antineoplastic Agents↗

PubMed2026

HyLnc: a hybrid deep learning and feature-based approach for long non-coding RNA prediction.

Long non-coding RNAs (lncRNAs) play important roles in gene regulation, development and disease, yet accurate identification of lncRNAs from transcriptomic data remains a major computational challenge. Existing methods often rely either on handcrafted sequence features or deep learning approaches, each with their inherent limitations in capturing the full complexity of RNA sequences. In this study, we proposed HyLnc, a computational framework that integrates transformer-based contextual embeddings with biologically meaningful sequence features for improved lncRNA prediction. A custom BERT-based model was first pre-trained on a large corpus of metazoan RNA sequences using a masked language modelling strategy to learn contextual nucleotide dependencies. The model was subsequently fine-tuned on curated datasets of lncRNAs and protein-coding transcripts and 256-dimensional deep sequence embeddings were extracted. Parallelly, 348 handcrafted features, including ORF characteristics, untranslated region (UTR) properties, nucleotide composition and Fickett scores, were computed. A multi-stage feature selection strategy was applied to identify the most informative features, resulting in optimized hybrid feature sets. Multiple machine learning classifiers were evaluated, with the RF model achieving the best performance. The proposed framework attained an accuracy of 91.30%, F1-score of 91.23% and MCC of 82.60 on an independent validation dataset, outperforming several existing lncRNA prediction tools. Thus, HyLnc demonstrates that integrating deep contextual representations with biologically interpretable features enhances lncRNA prediction. This approach provides a robust and scalable solution for large-scale transcriptome annotation and can be extended to other sequence-based prediction.

RNA, Long Noncoding↗

PubMed2005

Patient-specific models for predicting the outcomes of patients with community acquired pneumonia.

We investigated two patient-specific and four population-wide machine learning methods for predicting dire outcomes in community acquired pneumonia (CAP) patients. Predicting dire outcomes in CAP patients can significantly influence the decision about whether to admit the patient to the hospital or to treat the patient at home. Population-wide methods induce models that are trained to perform well on average on all future cases. In contrast, patient-specific methods specifically induce a model for a particular patient case. We trained the models on a set of 1601 patient cases and evaluated them on a separate set of 686 cases. One patient-specific method performed better than the population-wide methods when evaluated within a clinically relevant range of the ROC curve. Our study provides support for patient-specific methods being a promising approach for making clinical predictions.

Algorithms↗

PubMed2004

Prediction of alpha-turns in proteins using PSI-BLAST profiles and secondary structure information.

In this paper a systematic attempt has been made to develop a better method for predicting alpha-turns in proteins. Most of the commonly used approaches in the field of protein structure prediction have been tried in this study, which includes statistical approach "Sequence Coupled Model" and machine learning approaches; i) artificial neural network (ANN); ii) Weka (Waikato Environment for Knowledge Analysis) Classifiers and iii) Parallel Exemplar Based Learning (PEBLS). We have also used multiple sequence alignment obtained from PSIBLAST and secondary structure information predicted by PSIPRED. The training and testing of all methods has been performed on a data set of 193 non-homologous protein X-ray structures using five-fold cross-validation. It has been observed that ANN with multiple sequence alignment and predicted secondary structure information outperforms other methods. Based on our observations we have developed an ANN-based method for predicting alpha-turns in proteins. The main components of the method are two feed-forward back-propagation networks with a single hidden layer. The first sequence-structure network is trained with the multiple sequence alignment in the form of PSI-BLAST-generated position specific scoring matrices. The initial predictions obtained from the first network and PSIPRED predicted secondary structure are used as input to the second structure-structure network to refine the predictions obtained from the first net. The final network yields an overall prediction accuracy of 78.0% and MCC of 0.16. A web server AlphaPred (http://www.imtech.res.in/raghava/alphapred/) has been developed based on this approach.

Amino Acid Sequence↗

PubMed1992

A computational model of four regions of the cerebellum based on feedback-error learning.

We propose a computationally coherent model of cerebellar motor learning based on the feedback-error-learning scheme. We assume that climbing fiber responses represent motor-command errors generated by some of the premotor networks such as the feedback controllers at the spinal-, brain stem- and cerebral levels. Thus, in our model, climbing fiber responses are considered to convey motor errors in the motor-command coordinates rather than in the sensory coordinates. Based on the long-term depression in Purkinje cells each corticonuclear microcomplex in different regions of the cerebellum learns to execute predictive and coordinative control of different types of movements. Ultimately, it acquires an inverse model of a specific controlled object and complements crude control by the premotor networks. This general model is developed in detail as a specific neural circuit model for the lateral hemisphere. A new experiment is suggested to elucidate the coordinate frame in which climbing fiber responses are represented.

Animals↗