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 199 records · Page 11Linked to original sources

PubMed1982

Attributional styles and life events in the classroom: vulnerability and invulnerability to depressive mood reactions.

A core prediction of the reformulated model of learned helplessness and depression (Abramson, Seligman, & Teasdale, 1978) is that when confronted with the same negative life event, people who display a generalized tendency to attribute negative outcomes to internal, stable, or global factors should be more likely to experience a depressive mood reaction than people who typically attribute negative outcomes to external, unstable, or specific factors. We tested this prediction with a prospective design in a naturalistic setting by determining whether the content of college students' attributional styles at one point in time predicted the severity of their depressive mood response to receiving a low grade on a midterm exam at a subsequent point in time. Consistent with the prediction, students with an internal or global attributional style for negative outcomes at Time 1 experienced a depressive mood response when confronted with a subsequent low midterm grade, whereas students with an external or specific attributional style for negative outcomes were invulnerable to this depressive mood response. In contrast to the results for the internality and globality dimensions, students' scores along the stability attribution dimension were not correlated with the severity of their depressive mood response to the low midterm grade. In the absence of a negative life event (i.e., receipt of a high midterm grade), students' generalized tendencies to make internal or global attributions for negative outcomes at Time 1 were not significantly correlated with their subsequent changes in depressive mood although there was a nonsignificant positive correlation between severity of depressive mood response and the tendency to make global attributions for negative outcomes at Time 1.

Achievement↗

PubMed2003

Prediction precedes control in motor learning.

Skilled motor behavior relies on the brain learning both to control the body and predict the consequences of this control. Prediction turns motor commands into expected sensory consequences, whereas control turns desired consequences into motor commands. To capture this symmetry, the neural processes underlying prediction and control are termed the forward and inverse internal models, respectively. Here, we investigate how these two fundamental processes are related during motor learning. We used an object manipulation task in which subjects learned to move a hand-held object with novel dynamic properties along a prescribed path. We independently and simultaneously measured subjects' ability to control their actions and to predict their consequences. We found different time courses for predictor and controller learning, with prediction being learned far more rapidly than control. In early stages of manipulating the object, subjects could predict the consequences of their actions, as measured by the grip force they used to grasp the object, but could not generate appropriate actions for control, as measured by their hand trajectory. As predicted by several recent theoretical models of sensorimotor control, our results indicate that people can learn to predict the consequences of their actions before they can learn to control their actions.

Biophysical Phenomena↗

PubMed1988

Predicting the secondary structure of globular proteins using neural network models.

We present a new method for predicting the secondary structure of globular proteins based on non-linear neural network models. Network models learn from existing protein structures how to predict the secondary structure of local sequences of amino acids. The average success rate of our method on a testing set of proteins non-homologous with the corresponding training set was 64.3% on three types of secondary structure (alpha-helix, beta-sheet, and coil), with correlation coefficients of C alpha = 0.41, C beta = 0.31 and Ccoil = 0.41. These quality indices are all higher than those of previous methods. The prediction accuracy for the first 25 residues of the N-terminal sequence was significantly better. We conclude from computational experiments on real and artificial structures that no method based solely on local information in the protein sequence is likely to produce significantly better results for non-homologous proteins. The performance of our method of homologous proteins is much better than for non-homologous proteins, but is not as good as simply assuming that homologous sequences have identical structures.

Amino Acid Sequence↗

PubMed2026

SCMO: a deep learning model integrating the single-cell resolution TME ecosystem and multi-omics for survival prediction in CRC patients.

BACKGROUND: Colorectal cancer (CRC) remains a leading cause of global cancer mortality, highlighting the need for precise survival prediction to guide clinical decisions. Although tissue-level multi-omics is widely utilized for survival prediction, its limited resolution cannot capture tumor heterogeneity. Single-cell RNA sequencing (scRNA-seq) enables dissection of the tumor microenvironment (TME) at cellular resolution, supporting personalized prognostic assessment. METHODS: We collected 213 CRC scRNA-seq samples and established a CRC-specific TME atlas comprising 339,060 cells. Using this atlas as a reference, we deconvolved bulk RNA-seq data from TCGA-CRC cohort with the EcoTyper algorithm to reconstruct TME features. Clinical, genomic, and transcriptomic data were obtained from the Xena platform; microbial data were sourced from the BIC database. We integrated TME and multi-omics features through a self-normalizing neural network to construct a deep learning model (single-cell resolution TME ecosystem with multi-omics data [SCMO]) for survival prediction. To enhance interpretability, we utilized the Integrated Gradients algorithm and spatial transcriptomic data to analyze multi-omics and TME features. We performed anticancer drug screening with tumor necrosis factor receptor-associated protein 1 (TRAP1), a critical feature according to the Integrated Gradients algorithm, as a potential target. RESULTS: We identified 13 survival-related TME features from the CRC-specific atlas: 12 cell states and one multi-cellular ecosystem. SCMO, which combined TME and multi-omics features, improved survival prediction and outperformed existing methods, achieving a concordance index of 0.762. The SCMO demonstrated robust performance for long-term predictions, achieving areas under the curve (AUCs) of 0.752, 0.772, and 0.869 for 1-, 3-, and 5-year predictions in the training set, with corresponding test set AUCs of 0.639, 0.756, and 0.772. TME features from the SCMO model revealed that ecosystem density increased with CRC malignancy. Multi-omics features included TRAP1 as a potential drug target. Drug screening identified saikosaponin A as a novel TRAP1 inhibitor, and its anticancer activity was validated in vitro. We developed SCMO-Lite, a simplified model incorporating 12 high-attribution-weight multi-omics features, which demonstrated robust risk stratification. CONCLUSIONS: SCMO combines analytical precision with biological interpretability, offering novel insights for oncology survival prediction.

Humans↗

PubMed1993

Can we predict a high risk group in stage I epithelial ovarian cancer?

A retrospective review of 373 patients with stage I invasive epithelial ovarian cancer was undertaken over a 5 year period to develop a model to characterize the patient at high risk. Actuarial 5-year survival was 70%. To identify factors with an independent effect on 5-year survival, a logistic regression analysis was performed. Adjuvant chemotherapy, histologic grade and peritoneal washings, were identified as independent variables. A model to determine the predictivity of survival was created using a learning sample (2/3 of the cases) and the model was then used to reclassify a validation sample (1/3 of the cases). Using all the independent variables, outcome was predicted correctly in 78% of cases. However the model failed to improve identification of those at risk of recurrence (specificity of 53%).

Journal Article↗

PubMed1999

Prediction of hepatic encephalopathy in paracetamol overdose: a prospective and validated study.

BACKGROUND: Paracetamol overdose may cause hepatic encephalopathy (HE). This condition demands specialized care and, in some instances, liver transplantation evaluation. No model is available for predicting HE. We aimed to set up and validate a model for predicting the occurrence of HE in paracetamol overdose. METHODS: Prospectively, 161 patients with single-dose paracetamol overdose and no HE (defined as hepatic coma grade II or more) on admission were studied during a 26-month period. Patients admitted during the first 13-month period constituted a learning set to construct a model to predict the occurrence of HE. Patients admitted in the second 13-month period constituted the validation set. Serial biochemical variables (measured twice daily), the time line after the overdose, and demographic data were used for univariate testing, and significant factors were assessed in various multiple logistic regression analyses. RESULTS: Thirty-two patients (20%), 15 in the first period and 17 in the second, developed HE grade II. The best model (the highest chi-square) for HE included: log10 (hours from overdose to antidote treatment), log10 (plasma coagulation factors on admission), and platelet count hours from overdose (chi-square = 41.2, P < 0.00001). In the validation set 88% (confidence interval (CI), 64%-99%) of the patients who developed HE were correctly predicted by the constructed model, whereas 90% (CI, 79%-96%) of the patients in the non-HE group were correctly predicted. CONCLUSIONS: The constructed model for predicting HE in paracetamol overdose proved sensitive and accurate in the validation set and should be valuable for transferring high-risk patients to a liver intensive care unit/transplantation facility.

Acetaminophen↗

PubMed2025

DiCARN-DNase: enhancing cell-to-cell Hi-C resolution using dilated cascading ResNet with self-attention and DNase-seq chromatin accessibility data.

MOTIVATION: The spatial organization of chromatin is fundamental to gene regulation and essential for proper cellular function. The Hi-C technique remains the leading method for unraveling 3D genome structures, but the limited availability of high-resolution (HR) Hi-C data poses significant challenges for comprehensive analysis. Deep learning models have been developed to predict HR Hi-C data from low-resolution counterparts. Early Convolutional Neural Network (CNN)-based models improved resolution but struggled with issues like blurring and capturing fine details. In contrast, Generative Adversarial Network (GAN)-based methods encountered difficulties in maintaining diversity and generalization. Additionally, most existing algorithms perform poorly in cross-cell line generalization, where a model trained on one cell type is used to enhance HR data in another cell type. RESULTS: In this work, we propose Dilated Cascading Residual Network (DiCARN) to overcome these challenges and improve Hi-C data resolution. DiCARN leverages dilated convolutions and cascading residuals to capture a broader context while preserving fine-grained genomic interactions. Additionally, we incorporate DNase-seq data into our model, providing a robust framework that demonstrates superior generalizability across cell lines in HR Hi-C data reconstruction. AVAILABILITY AND IMPLEMENTATION: DiCARN is publicly available at https://github.com/OluwadareLab/DiCARN.

Chromatin↗

PubMed2026

An interpretable deep learning framework uncovers features governing CRISPR-Cas9 genome-editing efficiency.

MOTIVATION: CRISPR-Cas9 genome-editing efficiency is strongly influenced by the sequence composition and positional context of single-guide RNAs (sgRNAs). Although numerous deep learning-based models have been developed to predict Cas9 efficiency from sgRNA sequences, most operate as black boxes, offering limited insight into the sequence determinants underlying Cas9 activity. In addition, previous studies often overlook how the positional context of sequence motifs within sgRNAs influences their effects on Cas9 binding or cleavage. RESULTS: We introduce DeepCC9, an interpretable machine learning framework that combines explicit sequence feature extraction with a residual block-based deep architecture to improve interpretability and identify composition- and position-based motifs governing Cas9 genome-editing efficiency. We applied this method to multiple Cas9 variant datasets, achieving superior predictive performance compared with existing methods while enabling direct interpretation of sequence motifs and their positional effects. Our analysis uncovered 74 sequence motifs enriched or depleted at specific positions within sgRNAs and strongly associated with Cas9 efficiency, providing mechanistic insight into sequence features that influence guide performance. Together, these results establish DeepCC9 as a generalizable and interpretable framework for modeling sequence-function relationships and advancing the understanding of the sequence determinants underlying CRISPR-Cas9 genome editing. AVAILABILITY AND IMPLEMENTATION: The authors have implemented their algorithm in the Python programming language (version 3.X), which is accessible using (https://zenodo.org/records/20073890).

Deep Learning↗

PubMed2026

A multi-scale fusion model based on multi-phase contrast-enhanced CT for predicting pancreatic cancer resectability.

Purpose.Develop a multi-scale fusion model (MSFM) based on multi-phase contrast-enhanced computed tomography (CECT) to predict pancreatic cancer (PC) resectability, thereby assisting expert decision-making.Methods.This retrospective study enrolled 280 patients with PC from four institutions, which were randomly divided into a training cohort (202 patients) and an independent test cohort (78 patients). Three-phase CECT images (arterial, venous, and delayed phases) were used for modeling. The MSFM comprises two sub-networks: (1) a multi-phase fusion network for extracting cross-phase shared fusion features, (2) a phase-specific branch network for capturing phase-specific features; and a post-fusion strategy to generate the final predictive score by integrating the shared fusion features and three groups of phase-specific features. Additionally, a human-machine fusion deep learning model (HMfDL) was constructed by fusing the predictive score of the MSFM with expert assessments.Results.In the independent test, the MSFM achieved an AUC (area under the receiver operating characteristic curve) of 0.8385 (95% CI: 0.7521-0.9249), accuracy of 84.62%, sensitivity of 72.00%, and specificity of 90.57%. This performance outperformed single-phase models (AUC range: 0.7638-0.7781), two-phase models (AUC range: 0.7826-0.7864), and ten states-of-the-art classifiers (AUC range: 0.7404-0.7796). The HMfDL further improved the performance, reaching an AUC of 0.8626 (95% CI: 0.7853-0.9400), accuracy of 91.03%, sensitivity of 80.00%, and specificity of 96.23%. Notably, the HMfDL corrected 58.82% of misdiagnosis made by experts.Conclusions. The MSFM effectively fuses multi-phase CECT to enable highly accurate predictions of PC resectability, and provides valuable support for expert decision-making through HMfDL.

Humans↗

PubMed2002

Hybrid model building methodology using unsupervised fuzzy clustering and supervised neural networks.

This paper suggests a model building methodology for dealing with new processes. The methodology, called Hybrid Fuzzy Neural Networks (HFNN), combines unsupervised fuzzy clustering and supervised neural networks in order to create simple and flexible models. Fuzzy clustering was used to define relevant domains on the input space. Then, sets of multilayer perceptrons (MLP) were trained (one for each domain) to map input-output relations, creating, in the process, a set of specified sub-models. The estimated output of the model was obtained by fusing the different sub-model outputs weighted by their predicted possibilities. On-line reinforcement learning enabled improvement of the model. The determination of the optimal number of clusters is fundamental to the success of the HFNN approach. The effectiveness of several validity measures was compared to the generalization capability of the model and information criteria. The validity measures were tested with fermentation simulations and real fermentations of a yeast-like fungus, Aureobasidium pullulans. The results outline the criteria limitations. The learning capability of the HFNN was tested with the fermentation data. The results underline the advantages of HFNN over a single neural network.

Biotechnology↗

PubMed1995

Depression and attributions in children and adolescents: a meta-analytic review.

This article presents a meta-analytic review of the association between attributional styles and depressive symptoms in children and adolescents. In 28 studies involving 7500 subjects, the correlations were consistent with those predicted by the reformulated learned helplessness model of depression. For negative outcomes, attributions along the internal, stable, and global dimensions were associated positively with depression. Conversely, higher levels of depressive symptoms were related to more external, unstable, and specific attributions for positive events. Additionally, overall composite maladaptive attributional patterns for positive and negative events were correlated with higher levels of depressive symptoms in youth. Effect sizes for these associations ranged from moderate to large (Cohen, 1977). Findings from the significance tests of the combined results support the theory. A large number of unretrieved studies revealing null effects would be needed to invalidate these findings.

Adolescent↗

PubMed1993

Judgmental overshadowing: further evidence of cue interaction in contingency judgment.

We investigated a phenomenon called judgmental overshadowing. Subjects predicted whether each of several patients had a disease on the basis of whether or not the patient had each of two symptoms. For all the subjects, the presence of the disease was moderately contingent on the presence of one of the symptoms (S1). In Condition 1 of our first experiment, the presence of the disease was highly contingent on the presence of the other symptom (S2). In Condition 2, the presence of the disease was independent of S2. Judgmental overshadowing occurred in that the S1-disease contingency was judged to be stronger in Condition 2 than in Condition 1. Subsequent experiments showed that judgmental overshadowing depends little on the form of the judgment, is not due to a response bias or contrast effect, and does not depend on subjects' actively diagnosing each patient. These results are consistent with, and are generally predicted by, an associative-learning model of contingency judgment.

Adult↗

PubMedDate not supplied

Relaxation electromechanical delay of the quadriceps during selected movement velocities.

The purpose of this study was to quantify the time between the cessation of EMG activity and cessation of torque production, or relaxation electromechanical delay, (R-EMD) of the quadriceps at three angular movement velocities. A Biodex dynamometer passively moved the right knee of 25 males through a given range at three velocities (10, 60 and 120 degrees per second). Subjects were instructed to actively extend their knees to a visual target, then to immediately relax. Biodex torque and position data, as well as surface EMG from the right Vastus Medialis (VM), Rectus Femoris (RF) and Vastus Lateralis (VL) were sampled simultaneously. EMG cessation was determined when activity fell below a threshold based on the muscle's resting EMG. Torque cessation was determined when the slope of the relaxation curve decreased to 10% of the initial value. R-EMD time for each quadriceps head at each velocity was determined by calculating the difference between these two times. To examine reliability, subjects were retested four days later. Approximately two thirds of the subjects were unable to consistently perform the motor task of abrupt relaxation at some or all of the tested velocities. This variability was ascribed to motor control issues. Average R-EMD times for all subjects, muscle segments and velocities ranged from 249 +/- 68 ms to 276 +/- 51 ms during the first test session, and 239 +/- 46 ms to 300 +/- 59 ms during the second session. These data are important in identification of physiologically meaningful cessation of muscle contraction, and may be beneficial in research studies focusing on the areas of motor control and motor learning, computerized movement analysis, and prediction models for the determination of muscular force from the EMG signal.

Adult↗

PubMed2025

Multi-criteria decision making and its application to in silico discovery of vaccine candidates for Toxoplasma gondii.

Vaccine discovery against eukaryotic parasites is not trivial and few exist. Reverse vaccinology is an in silico vaccine discovery approach, designed to identify vaccine candidates from the thousands of protein sequences encoded by a target genome. Previously, we produced the Vacceed bioinformatics pipeline for identification of parasite membrane and excreted/secreted proteins that were likely be exposed to the hosts immune system. More recently, we improved upon machine learning as the final decision-making process to identify parasite proteins that induce a protective response in an animal model. Subsequently, we combined Vacceed with metrics on B and T cell epitope types to produce a new in silico discovery workflow. In this study we extend this in silico workflow to the developability of proteins as vaccines by the incorporation of metrics on the physicochemical properties of proteins. To demonstrate this process, every Toxoplasma gondii protein was ranked in its capacity to provide exposure to the immune system (Vacceed exposure score), presence of epitopes and solubility characteristics by several multicriteria decision making (MCDM) tools (such as TOPSIS, VIKOR and MABAC). A consensus rank was subsequently generated from the results of these tools using a variety of aggregate ranking methods. Levels of uncertainty in the aggregate protein rankings was assessed by conformal interval prediction in association with a machine learning model. Several of the top ranked proteins identified by this approach were novel, uncharacterized membrane transporters or proteins associated with RNA metabolism. In conclusion, MCDM automated the decision making using well known algorithms while conformal prediction intervals varied significantly across the 8000+ proteins of T. gondii. Highly ranked proteins (e.g. the top 100) typically generated low prediction intervals, providing high levels of confidence in their ranks.

Toxoplasma↗

PubMed1995

Neural pattern formation via a competitive Hebbian mechanism.

In this contribution we investigate a simple pattern formation process [9,10] based on Hebbian learning and competitive interactions within cortex. This process generates spatial representations of afferent (sensory) information which strongly resemble patterns of response properties of neurons commonly called brain maps. For one of the most thoroughly studied phenomena in cortical development, the formation of topographic maps, orientation and ocular dominance columns in macaque striate cortex, the process, for example, generates the observed patterns of receptive field properties including the recently described correlations between orientation preference and ocular dominance. Competitive Hebbian learning has not only proven to be a useful concept in the understanding of development and plasticity in several brain areas, but the underlying principles have have been successfully applied to problems in machine learning [22]. The model's universality, simplicity, predictive power, and usefulness warrants a closer investigation.

Animals↗

PubMed1984

Influence of gender constancy and social power on sex-linked modeling.

Competing predictions derived from cognitive-developmental theory and social learning theory concerning sex-linked modeling were tested. In cognitive-developmental theory, gender constancy is considered a necessary prerequisite for the emulation of same-sex models, whereas according to social learning theory, sex-role development is promoted through a vast system of social influences with modeling serving as a major conveyor of sex role information. In accord with social learning theory, even children at a lower level of gender conception emulated same-sex models in preference to opposite-sex ones. Level of gender constancy was associated with higher emulation of both male and female models rather than operating as a selective determinant of modeling. This finding corroborates modeling as a basic mechanism in the sex-typing process. In a second experiment we explored the limits of same-sex modeling by pitting social power against the force of collective modeling of different patterns of behavior by male and female models. Social power over activities and rewarding resources produced cross-sex modeling in boys, but not in girls. This unexpected pattern of cross-sex modeling is explained by the differential sex-typing pressures that exist for boys and girls and socialization experiences that heighten the attractiveness of social power for boys.

Child Development↗

PubMed2025

Integrating Imaging-Derived Clinical Endotypes with Plasma Proteomics and External Polygenic Risk Scores Enhances Coronary Microvascular Disease Risk Prediction.

Coronary microvascular disease (CMVD) is an underdiagnosed but significant contributor to the burden of ischemic heart disease, characterized by angina and myocardial infarction. The development of risk prediction models such as polygenic risk scores (PRS) for CMVD has been limited by a lack of large-scale genome-wide association studies (GWAS). However, there is significant overlap between CMVD and enrollment criteria for coronary artery disease (CAD) GWAS. In this study, we developed CMVD PRS models by selecting variants identified in a CMVD GWAS and applying weights from an external CAD GWAS, using CMVD-associated loci as proxies for the genetic risk. We integrated plasma proteomics, clinical measures from perfusion PET imaging, and PRS to evaluate their contributions to CMVD risk prediction in comprehensive machine and deep learning models. We then developed a novel unsupervised endotyping framework for CMVD from perfusion PET-derived myocardial blood flow data, revealing distinct patient subgroups beyond traditional case-control definitions. This imaging-based stratification substantially improved classification performance alongside plasma proteomics and PRS, achieving AUROCs between 0.65 and 0.73 per class, significantly outperforming binary classifiers and existing clinical models, highlighting the potential of this stratification approach to enable more precise and personalized diagnosis by capturing the underlying heterogeneity of CMVD. This work represents the first application of imaging-based endotyping and the integration of genetic and proteomic data for CMVD risk prediction, establishing a framework for multimodal modeling in complex diseases.

Cardiovascular Disease↗

PubMed2026

Predicting food taste with bound-driven optimization.

The prediction of sensory attributes from ingredient-level formulations is an emerging challenge at the intersection of food science and artificial intelligence. We address the fundamental question of whether the taste of a food can be predicted from its ingredients by treating recipes as composite materials. We apply Hashin-Shtrikman (HS) and Reuss-Voigt (RV) bounds, techniques originally developed for elastic moduli, as a null-hypothesis additive baseline for five taste dimensions (sweetness, sourness, bitterness, umami, saltiness) on a curated dataset of 70 recipes decomposed into 115 distinct ingredients scored against a library of 209 ingredient-level taste references with trained-panel ground truth. This baseline systematically under-predicts perceived taste: 77% of actual taste values exceeded the HS upper bound, with the exceedance rate ranging from 26% (bitterness) to 97% (saltiness). We traced this gap to specific processing chemistry (Maillard reactions, caramelization, evaporative concentration, protein hydrolysis, and nucleotide synergy) and introduced a hybrid model that augments the HS baseline with eight chemistry-proxy features encoding these mechanisms. Our results show that our interpretable hybrid model eliminates the systematic bias and reduces mean absolute error by 27%-62% for sweetness, sourness, umami, and saltiness while using only 10 interpretable features, achieving performance comparable to a black-box Lasso regression on 115 per-ingredient features. We further demonstrate constrained inverse design via Differential Evolution, recovering ingredient formulations that match target taste profiles subject to compositional bounds. Our work demonstrates how key chemical processes during food preparation can inform and augment physics-based and machine learning models, providing a quantitative fingerprint of processing chemistry's contribution to taste perception and paving the way for model-driven food formulation with targeted sensory characteristics.

Composite material bounds↗