SEARCH · PubMed Health

Results for “multimodal learning”

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 73 records · Page 4Linked to original sources

PubMed1990

The behavioral medicine service. An administrative model for biopsychosocial medical care, teaching, and research.

The biopsychosocial model has been promoted for its advantages in many important health problems. However, the lack of administrative practice models specifically designed to develop and promote the model hinder the development of systematic clinical applications. This article describes a successful clinical teaching and research practice, The Behavioral Medicine Service, that was conceptualized and developed based on the biopsychosocial model. Systematic planning enabled the service to take advantage of clinical, research, and teaching opportunities and to reduce the constraints imposed on development from within psychiatry and the institution. Advantages of the organizational model include multidisciplinary treatment teams, a systematic method of biopsychosocial assessment and management planning, and continuity of care between several settings: the medical-surgical wards of a general hospital; a behavioral medicine inpatient unit; and outpatient subspecialty clinics for chronic pain, chronic medical illness, anxiety and stress-related disorders, and drug and alcohol abuse. The Human Behavioral Pharmacology Laboratory forms the research arm of the service. Referrals of a diversity of medical and psychiatric problems create a unique learning opportunity for residents. Billing for multimodal team treatment, training residents, establishing clinical research, and managing a plethora of referrals were developmental challenges addressed by the service.

Behavioral Medicine↗

PubMed2002

A Graduate Certificate and Master in General Practice Psychiatry by distance education--1998-2001.

BACKGROUND: The General Practice Psychiatry Program is a collaborative initiative between two universities and two professional colleges. Since 1998 it has offered general practitioners a one year part time Graduate Certificate, and a two year Master of General Practice Psychiatry. The learning is by distance education and multimode, including text packages sent out, tapes, teleconferences and two annual residential weekends with role plays and didactic teaching. OBJECTIVE: To describe the development of a Graduate Certificate and Master in General Practice Psychiatry. DISCUSSION: The program has been well supported with 141 general practitioners enrolling in the Graduate Certificate and 48 in the Masters during 1998-2001. General practitioners have been enrolling from around Australia, with rural, female and more experienced GPs predominating.

Adult↗

PubMed2026

Livestock Multi-Omics Integration: A Systematic Framework From Statistical Association to Causal Interpretation.

Livestock multi-omics integration is key to unraveling complex trait regulation, yet systematic, livestock-specific strategies remain scarce. This review traces the progression from single-omics accumulation to multi-dimensional integration, highlighting how large-scale genomic, epigenomic, and transcriptomic projects lay the foundation for functional dissection. We identify core impediments: extreme species diversity, marked data heterogeneity, limited sample sizes, and a pervasive reduction of multi-omics data to simplistic differential screens, resulting in low translational efficiency. We critically appraise four common pitfalls-overinterpreting correlation as causation, relegating proteomics to corroborating transcriptomics, incomplete microbiome-host integration lacking environmental context, and systematic neglect of metabolic fluxomics-and show how exposomics and fluxomics add necessary causal and dynamic dimensions. To address these, we propose a livestock-adapted three-tier analytical framework: (1) statistical association of cross-omics covariation patterns; (2) machine learning-driven feature mining and integrative modeling; and (3) causal interpretation encompassing Mendelian randomization, prior-knowledge-guided network inference, and physical causal evidence via fluxomics and metabolic control analysis. We further discuss how multimodal sequencing (single-cell, spatial, temporal) and generative AI can fundamentally mitigate heterogeneity and strengthen causal evidence. Finally, we outline future priorities in database standardization, livestock-specific benchmarking, and translational pipelines, charting a path from correlation-centric reporting to mechanistic causality and precision breeding.

Animals↗

PubMed2025

Integration of single cell multiomics data by deep transfer hypergraph neural network.

Multi-omics characterization of individual cells offers remarkable potential for analyzing the dynamics and relationships of gene regulatory states across millions of cells. How to integrate multimodal data is an open problem, existing integration methods struggle with accuracy and modality-specific biological variation retention. In this paper, we present scHyper (scalable, interpretable machine learning for single cell integration), a low-code and data-efficient deep transfer model designed for integrating paired and unpaired single-cell multimodal data. We benchmark scHyper against datasets from different multimodal data. ScHyper learns a low-dimensional representation and aligns the covariance matrices of the measured modalities, achieving high accuracy even with large scale atlas-level datasets with low memory and computational time across different cell lines, shedding light on regulatory relationships between different types of omics. Altogether, we show that scHyper is a versatile and robust tool for cell-type label transfer and integration from multimodal single-cell datasets.

Single-Cell Analysis↗

PubMed1999

Filial imprinting in domestic chicks is associated with spine pruning in the associative area, dorsocaudal neostriatum.

Juvenile emotionally modulated learning events are fundamental for the normal development of socio-emotional competence and intellectual capabilities. Filial imprinting in the domestic chick provides a suitable model to investigate the neural mechanisms underlying such juvenile learning events. The forebrain area dorsocaudal neostriatum (Ndc), a multimodal integration area and presumed equivalent to mammalian parietotemporal association cortices, has been shown to be critically involved in this learning process. We investigated whether filial imprinting is associated with changes of synaptic connectivity in the Ndc. Quantitative measurements of spine densities of a large neuron type in the Ndc revealed a massive pruning of spine synapses after filial imprinting. Compared with 7-day-old naive control chicks, imprinted chicks displayed significantly lower spine frequencies on all dendritic segments. Since the average length of the dendritic segments did not change during imprinting, these results can be interpreted as a reduction of the absolute number of spine synapses on this neuron type. In a control region, the primary sensory forebrain area ectostriatum, spine density and dendritic length remained unchanged. These results indicate that synaptic pruning may represent a mechanism of selective synaptic reorganization in higher associative forebrain areas as a fundamental feature of juvenile learning events.

Animals↗

PubMed2026

Survival prediction for clear cell renal cell carcinoma based on deep multimodal synergistic survival network.

Objective.To propose a deep multimodal synergistic survival analysis framework (Deep Multimodal Synergistic Survival Network, DMSSN) to achieve accurate prognostic analysis for clear cell renal cell carcinoma (ccRCC).Methods.This study (DMSSN) utilized matched multimodal data from the Cancer Genome Atlas-KIRC database, including CT imaging data, whole slide images, copy number variation (CNV) features, and clinical data. Deep Canonical Correlation Analysis was employed to map heterogeneous modalities into a shared latent space. Contrastive learning was introduced to enhance semantic consistency across multimodal features, and a gating network was utilized for the adaptive fusion of multimodal information to achieve precise survival risk prediction for patients.Results.Experimental results demonstrated that DMSSN achieved a Concordance Index (C-index) of 0.8153 ± 0.0994, with a Log-rank testp-value of 1.6553×10-11. DMSSN exhibited significant performance advantages over traditional statistical methods like Log-rank-Cox (0.7055 ± 0.0670) and machine learning methods such as Random Survival Forest (RSF) (0.6836 ± 0.1048). Furthermore, in comparison with similar deep learning approaches, DMSSN outperformed late fusion strategies (0.7493 ± 0.1211) and discrete-time survival models such as DeepHit (0.7655 ± 0.1041) and Nnet-surv (0.7694 ± 0.0635). Notably, DMSSN still achieved the best predictive performance when compared to the classic deep survival model DeepSurv (0.7919 ± 0.0978) and advanced state-of-the-art multimodal fusion frameworks like Context-Aware Transformer (0.7735 ± 0.0818) and Multimodal Co-Attention Transformer (0.8102 ± 0.0972). Ablation studies showed that removing any single modality led to a decline in performance, with the largest numerical decrease occurring after removing CT imaging features (C-index decreased to 0.7327), validating the complementarity of multimodal data and the pivotal role of radiomic features in prognostic assessment. Module ablation experiments further confirmed the effectiveness of the core components.Conclusion:By effectively integrating imaging, pathology, genomic, and clinical features, the DMSSN framework demonstrates superior performance and robustness in the survival prediction of ccRCC.

Carcinoma, Renal Cell↗

PubMed2003

Development and evaluation of a computer-animated tutor for vocabulary and language learning in children with autism.

Using our theoretical framework of multimodal processing, we developed and evaluated a computer-animated tutor, Baldi, to teach vocabulary and grammar for children with autism. Baldi was implemented in a Language Wizard/Player, which allows easy creation and presentation of a language lesson involving the association of pictures and spoken words. The lesson plan includes both the identification of pictures and the production of spoken words. In Experiment 1, eight children were given initial assessment tests, tutorials, and reassessment tests 30 days following mastery of the vocabulary items. All of the students learned a significant number of new words and grammar. A second within-subject design with six children followed a multiple baseline design and documented that the program was responsible for the learning and generalization of new words. The research indicates that children with autism are capable of learning new language within an automated program centered around a computer-animated agent, multimedia, and active participation and can transfer and use the language in a natural, untrained environment.

Autistic Disorder↗

PubMed2025

Alzheimer's subtypes A supervised, unsupervised, multimodal, multilayered embedded recursive (SUMMER) AI study.

Since Alzheimer's disease (AD) is a heterogeneous disease, different subtypes may have distinct biological, genetic, and clinical characteristics, requiring tailored interventions. While several proposed subtypes of AD exist, there is still no clear consensus on a definitive classification. By leveraging complementary AI approaches, including supervised and unsupervised learning, within a recursive pipeline (SUMMER) that integrates multimodal datasets encompassing MRI measurements, phenotypes, and genetic data, our goal was to generate robust scientific evidence for identifying AD subtypes. Data was downloaded from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database and included neuroimaging data (MRI), genetics (SNPs), clinical diagnosis, and demographics. 1133 European American participants' images, aged 55-95, were included in this study. The analysis was multi-fold, where the first step involved applying an unsupervised application to a subset of the MRI sample (AD + cognitively normal (CN) aged matched groups, 100 men aged 68-85 years, and 76 women aged 68-85 years). The MRI brain gray matter was segmented into 44 regions of interest (ROIs) according to a standard atlas, and 618 features were extracted, including ROI voxel intensity measurements such as minimum, maximum, and histogram variables. Results identified a cluster of subtype AD men and a cluster of subtype AD women that were distinct from the rest of their respective samples. In the next step, the integrity of the identified subtype AD clusters was investigated using the XGBoost supervised machine learning application with genetic features (SNPs, N=36,724) and labels: the identified subtype AD cluster vs. the rest of the sample, stratified by sex. A significant AD subtype men model (accuracy=0.85, F1=0.72, AUC=0.83) and a significant women AD subtype model (accuracy=0.81, F1=0.81, AUC=0.81) were built, confirming the homogeneity of the isolated AD subtype clusters. Discriminative biomarkers were extracted from the significant models, including selected ROIs and SNPs. Finally, the subtype models were tested on an unseen subset of ADNI data. The genetic-based models identified clusters of AD subtype participants consisting of 34% of the men AD group and 47% of the women AD group. Phenotypic analysis indicates that lower body weight was associated with the women's AD subtype. Complex diseases like AD demand a sophisticated, multimodal approach for precise diagnosis. Effectively identifying disease subtypes enhances the potential for personalized treatment, ultimately improving patient outcomes.

Journal Article↗

PubMed2003

The efficiency of multimedia learning into old age.

BACKGROUND: On the basis of a multimodal model of working memory, cognitive load theory predicts that a multimedia-based instructional format leads to a better acquisition of complex subject matter than a purely visual instructional format. AIMS: This study investigated the extent to which age and instructional format had an impact on training efficiency among both young and old adults. It was hypothesised that studying worked examples that are presented as a narrated animation (multimedia condition) is a more efficient means of complex skill training than studying visually presented worked examples (unimodal condition) and solving conventional problems. Furthermore, it was hypothesised that multimedia-based worked examples are especially helpful for elderly learners, who have to deal with a general decline of working-memory resources, because they address both mode-specific working-memory stores. SAMPLE: The sample consisted of 60 young (mean age = 15.98 years) and 60 old adults (mean age = 64.48 years). METHODS: Participants of both age groups were trained in either a conventional, a unimodal, or a multimedia condition. Subsequently, they had to solve a series of test problems. Dependent variables were perceived cognitive load during the training, performance on the test, and efficiency in terms of the ratio between these two variables. RESULTS: Results showed that for both age groups multimedia-based worked examples were more efficient than the other training formats in that less cognitive load led to at least an equal performance level. CONCLUSION: Although no difference in the beneficial effect of multimedia learning was found between the age groups, multimedia-based instructions seem promising for the elderly.

Adolescent↗

PubMed1980

Failure of rats to escape from a potentially lethal microwave field.

Ocularly pigmented rats, all mature females of the Long-Evans strain, were repeatedly presented an opportunity to escape from an intense 918-MHz field (whole-body dose rate = 60 mW/g) to a field of lower intensity (40, 30, 20, or 2 mW/g) by performing a simple locomotor response. Other rats could escape 800-microamperemeter faradic shock to the feet and tail by performing the same response in the same milieu, a multimode cavity. None of 20 irradiated rats learned to associate entry into a visually well-demarcated area of the cavity with immediate reduction of dose rate, in spite of field-induced elevations of body temperature to levels that exceeded 41 degrees C and would have been lethal but for a limit on durations of irradiation. In contrast, all of ten rats motivated by faradic shock rapidly learned to escape. The failure of escape learning by irradiated animals probably arose from deficiencies of motivation and, especially, sensory feedback. Whole-body hyperthermia induced by a multipath field may lack the painful or directional sensory properties that optimally promote the motive to escape. Moreover, a decline of body temperature after an escape-response-contingent reduction of field strength will be relatively slow because of the large thermal time constants of mammalian tissues. Without timely sensory feedback, which is an essential element of negative reinforcement, stimulus-response associability would be imparied, which could retard or preclude learning of an escape response.

Animals↗

PubMed1998

[Treatment of learning disorders].

INTRODUCTION: The child neurologist, developmental pediatrician or child psychiatrist involved in the care of children with learning disabilities has a crucial role that extends beyond diagnosis. DEVELOPING: Despite the lack of sound scientific studies on treatment interventions for children with learning disabilities there are specific interventions that are helpful in the remediation of children with learning disabilities. CONCLUSIONS: The role of the health professional in the treatment of learning disabilities includes: 1. Making specific recommendations regarding early intervention strategies; 2. Putting into a neurological perspective the types of educational interventions that will maximize a child's potential; 3. Discussing the role of medications in the management of learning disorders, as well as using medications in appropriate situations, and 4. Coordinating the multimodal approach which is essential to the long term treatment of all children with learning disabilities.

Antidepressive Agents↗

PubMed2000

Mirror neurons, procedural learning, and the positive new experience: a developmental systems self psychology approach.

In summary, we are impressed with the existence of a mirror neuron system in the prefrontal cortex that serves as part of a complex neural network, including afferent and efferent connections to the limbic system, in particular the amygdala, in addition to the premotor and motor cortex. We think it is possible to arrive at an integration that postulates the mirror neuron system and its many types of associated multimodal neurons as contributing significantly to implicit procedural learning, a process that underlies a range of complex nonconscious, unconscious, preconscious and conscious cognitive activities, from playing musical instruments to character formation and traumatic configurations. This type of brain circuitry may establish an external coherence with developmental systems self psychology which implies that positive new experience is meliorative and that the intentional revival of old-old traumatic relational configurations might enhance maladaptive procedural patterns that would lead to the opposite of the intended beneficial change. When analysts revive traumatic transference patterns for the purpose of clarification and interpretation, they may fail to appreciate that such traumatic transference patterns make interpretation ineffective because, as we have stated above, the patient lacks self-reflection under such traumatic conditions. The continued plasticity and immediacy of the mirror neuron system can contribute to positive new experiences that promote the formation of new, adaptive, implicit-procedural patterns. Perhaps this broadened repertoire in the patient of ways of understanding interrelational events through the psychoanalytic process allows the less adaptive patterns ultimately to become vestigial and the newer, more adaptive patterns to emerge as dominant. Finally, as we have stated, we believe that the intentional transferential revival of trauma (i.e., the old-old relational configuration) may not contribute to therapeutic benefit. In contrast, the revival of trauma in the old-new configuration (i.e., in the presence of a helpful other who can reduce anxiety and foster eventual positive new experience) can be beneficial, as trauma research has demonstrated. This is the process that promotes new implicit-procedural learning, new-new relational configurations, and a richer understanding of the self narrative.

Brain↗

PubMedDate not supplied

The mental health needs of people with severe learning disabilities.

People with severe learning disabilities can present with complex behavioural and emotional needs that are best understood within a biopsychosocial framework. This article outlines the range of issues involved in the presentation and identification of mental health needs in people with severe learning disabilities. The use of a multidisciplinary and multimodal approach to assessment, care planning and case management is promoted in order to provide effective, comprehensive care in meeting the mental health needs of this client group. The key knowledge and skills required to meet the mental health needs of this client group are outlined and the role of the nurse as a key professional in the coordination of the assessment and care management process is explored.

Case Management↗

PubMed2026

Advancing cancer detection and treatment using longitudinal routine clinical data.

Cancer management remains fragmented across its continuum, from late-stage diagnosis and salvage therapies to non-personalized surveillance. Here, we present Oncoformer, a unified multimodal transformer model trained on the China Oncology Multimodal Prediction and Surveillance Study (COMPASS) cohort (3.67 million individuals, 17.7 million clinical visits) and validated on independent external cohorts, including the UK Biobank. Oncoformer integrates longitudinal electronic health records with chest X-ray imaging to address multiple clinical tasks: pan-cancer diagnosis (area under the receiver operating characteristic curve [AUROC] = 0.956), future cancer prediction up to 1 year before diagnosis (AUROC = 0.869), tumor stage inference (mean AUROC > 0.90), patient-specific treatment-response forecasting, and recurrence-free survival stratification across ten cancer types (all p < 0.01). Staging predictions were independently validated against postoperative pathological endpoints and shown to converge on core cancer genomic pathways. By translating routine clinical data into a dynamic view of cancer evolution, Oncoformer provides a framework for risk-informed cancer prediction and treatment stratification using routine clinical data.

Humans↗

PubMed1999

Larval and pupal development of the mushroom bodies in the honey bee, Apis mellifera.

The mushroom bodies are paired neuropils in the insect brain that act as multimodal sensory integration centers and are involved in learning and memory. Our studies, by using 5-bromo-2-deoxyuridine incorporation and the Feulgen technique, show that immediately before pupation, the brain of the developing honey bee (Apis mellifera) contains approximately 2,000 neuroblasts devoted to the production of the mushroom body intrinsic neurons (Kenyon cells). These neuroblasts are descended from four clusters of 45 or fewer neuroblasts each already present in the newly hatched larva. Subpopulations of Kenyon cells, distinct in cytoarchitecture, position, and immunohistochemical traits, are born at different, but overlapping, periods during the development of the mushroom bodies, with the final complement of these neurons in place by the mid-pupal stage. The mushroom bodies of the adult honey bee have a concentric arrangement of Kenyon cell types, with the outer layers born first and pushed to the periphery by later born neurons that remain nearer the center of proliferation. This concentricity is further reflected in morphologic and immunohistochemical traits of the adult neurons, and is demonstrated clearly by the pattern of expression of Drosophila myocyte enhancer factor 2 (DMEF2)-like immunoreactivity. This is the first comprehensive study of larval and pupal development of the honey bee mushroom bodies. Similarities to patterns of neurogenesis observed in the mushroom bodies of other insects and in the vertebrate cerebral cortex are discussed.

Animals↗

PubMed2024

Digital pathology and spatial omics in steatohepatitis: Clinical applications and discovery potentials.

Steatohepatitis with diverse etiologies is the most common histological manifestation in patients with liver disease. However, there are currently no specific histopathological features pathognomonic for metabolic dysfunction-associated steatotic liver disease, alcohol-associated liver disease, or metabolic dysfunction-associated steatotic liver disease with increased alcohol intake. Digitizing traditional pathology slides has created an emerging field of digital pathology, allowing for easier access, storage, sharing, and analysis of whole-slide images. Artificial intelligence (AI) algorithms have been developed for whole-slide images to enhance the accuracy and speed of the histological interpretation of steatohepatitis and are currently employed in biomarker development. Spatial biology is a novel field that enables investigators to map gene and protein expression within a specific region of interest on liver histological sections, examine disease heterogeneity within tissues, and understand the relationship between molecular changes and distinct tissue morphology. Here, we review the utility of digital pathology (using linear and nonlinear microscopy) augmented with AI analysis to improve the accuracy of histological interpretation. We will also discuss the spatial omics landscape with special emphasis on the strengths and limitations of established spatial transcriptomics and proteomics technologies and their application in steatohepatitis. We then highlight the power of multimodal integration of digital pathology augmented by machine learning (ML)algorithms with spatial biology. The review concludes with a discussion of the current gaps in knowledge, the limitations and premises of these tools and technologies, and the areas of future research.

Humans↗

PubMed1979

A follow-up of alcoholics treated by multimodal therapy.

A general hospital sponsored for the psychotherapeutic treatment of alcoholism is described. In this context a multimodal approach, emphasizing methods derived from principles of learning, is applied to training the individual in new life-style skills for the management of alcoholism. Demographic characteristics of the population served by the program are of a predominantly blue collar clientele, mostly employed (72%), married (61%), and from urban centers (95%). Attrition as a major problem in evaluating results at the follow-up stage is identified and a method of reporting follow-up results taking this factor into account is presented. This method showed that under the most stringent conditions for reporting results, 36.64% of a sample of 131 alcoholics were showing improvement at 12 months, while under the least stringent condition 84% were showing some improvement over the same period.

Adult↗

PubMed2006

Spatio-temporal information analysis of event-related BOLD responses.

A new approach for analysis of event-related fMRI (BOLD) signals is proposed. The technique is based on measures from information theory and is used both for spatial localization of task-related activity, as well as for extracting temporal information regarding the task-dependent propagation of activation across different brain regions. This approach enables whole brain visualization of voxels (areas) most involved in coding of a specific task condition, the time at which they are most informative about the condition, as well as their average amplitude at that preferred time. The approach does not require prior assumptions about the shape of the hemodynamic response function (HRF) nor about linear relations between BOLD response and presented stimuli (or task conditions). We show that relative delays between different brain regions can also be computed without prior knowledge of the experimental design, suggesting a general method that could be applied for analysis of differential time delays that occur during natural, uncontrolled conditions. Here we analyze BOLD signals recorded during performance of a motor learning task. We show that, during motor learning, the BOLD response of unimodal motor cortical areas precedes the response in higher-order multimodal association areas, including posterior parietal cortex. Brain areas found to be associated with reduced activity during motor learning, predominantly in prefrontal brain regions, are informative about the task typically at significantly later times.

Brain↗