PubMed Health⌕ Search

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 127 records · Page 7Linked to original sources
PubMed2026

Deep generative models in biological sequence and structure analysis and design.

Deep generative models have transformed biological sequence modeling from predictive analysis toward increasingly controllable design. Early biological applications of Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs) established latent representation learning and sequence synthesis, while recent advances in transformer-based language models, discrete diffusion, flow-matching, and multimodal generative frameworks have substantially expanded the scope of biological design. This review examines generative models for DNA, RNA, and protein sequence design, emphasizing how different model classes represent biological constraints, operate over discrete and continuous spaces, and integrate sequence, structure, and function. We compare VAEs, GANs, autoregressive and masked language models, diffusion models, and flow-based approaches across genomics, transcriptomics, and proteomics, with particular attention to controllability, long-range dependency modeling, structural grounding, generalization, and experimental utility. We further examine evaluation strategies, out-of-distribution generalization, and closed-loop design-build-test-learn workflows that connect in silico generation with empirical validation. We distinguish fundamental modality-dependent constraints including sequence discreteness, context length, structural coupling, and physical or thermodynamic requirements from architecture-dependent advantages that reflect the current state of the field. Current studies suggest that long-context models are particularly useful for genome-scale representation and sequence modeling, whereas structure-aware diffusion, flow-based, and inverse-folding approaches provide better frameworks for geometry-constrained RNA and protein design. This perspective provides a critical framework for understanding the present capabilities, limitations, and convergence of generative approaches toward reliable and experimentally grounded biological design.

Biological sequence analysis↗
PubMed2002

The meaning of a multimodal approach for children with ADHD: experiences of service professionals.

BACKGROUND: Attention-Deficit/Hyperactivity Disorder (ADHD) is a childhood mental disorder characterized by inattention, impulsiveness and overactivity. It is also characterized by heterogeneity and ambiguity. Effective intervention is influenced by these two factors. This pervasive disorder impacts various domains of functioning, including academics, peer relations, familial relationships and self-esteem. A confounding factor is the high rate of comorbidity with diagnoses such as learning disabilities, oppositional defiant disorder or conduct disorder. No one intervention has emerged as maximally effective across all symptoms and domains. Consequently, a multimodal approach is regarded as the favoured method of intervention. However, no clear definition of'multimodal' exists. METHOD: This study explored the meaning of multimodal from the perspective of professionals employed in a tertiary care hospital setting in which children with ADHD are assessed and treated. A qualitative design using a phenomenological approach allowed professionals to speak from their practice experiences. RESULTS AND CONCLUSION: Although no clear definition of multimodal emerged, professionals identified issues key to this approach and proposed a model for intervention.

Alberta↗
PubMed2005

A hierarchy of associations in hippocampo-cortical systems: cognitive maps and navigation strategies.

In this letter we describe a hippocampo-cortical model of spatial processing and navigation based on a cascade of increasingly complex associative processes that are also relevant for other hippocampal functions such as episodic memory. Associative learning of different types and the related pattern encoding-recognition take place at three successive levels: (1) an object location level, which computes the landmarks from merged multimodal sensory inputs in the parahippocampal cortices; (2) a subject location level, which computes place fields by combination of local views and movement-related information in the entorhinal cortex; and (3) a spatiotemporal level, which computes place transitions from contiguous place fields in the CA3-CA1 region, which form building blocks for learning temporospatial sequences. At the cell population level, superficial entorhinal place cells encode spatial, context-independent maps as landscapes of activity; populations of transition cells in the CA3-CA1 region encode context-dependent maps as sequences of transitions, which form graphs in prefrontal-parietal cortices. The model was tested on a robot moving in a real environment; these tests produced results that could help to interpret biological data. Two different goal-oriented navigation strategies were displayed depending on the type of map used by the system. Thanks to its multilevel, multimodal integration and behavioral implementation, the model suggests functional interpretations for largely unaccounted structural differences between hippocampo-cortical systems. Further, spatiotemporal information, a common denominator shared by several brain structures, could serve as a cognitive processing frame and a functional link, for example, during spatial navigation and episodic memory, as suggested by the applications of the model to other domains, temporal sequence learning and imitation in particular.

Action Potentials↗
PubMed2025

Generative AI Models in Time-Varying Biomedical Data: Scoping Review.

BACKGROUND: Trajectory modeling is a long-standing challenge in the application of computational methods to health care. In the age of big data, traditional statistical and machine learning methods do not achieve satisfactory results as they often fail to capture the complex underlying distributions of multimodal health data and long-term dependencies throughout medical histories. Recent advances in generative artificial intelligence (AI) have provided powerful tools to represent complex distributions and patterns with minimal underlying assumptions, with major impact in fields such as finance and environmental sciences, prompting researchers to apply these methods for disease modeling in health care. OBJECTIVE: While AI methods have proven powerful, their application in clinical practice remains limited due to their highly complex nature. The proliferation of AI algorithms also poses a significant challenge for nondevelopers to track and incorporate these advances into clinical research and application. In this paper, we introduce basic concepts in generative AI and discuss current algorithms and how they can be applied to health care for practitioners with little background in computer science. METHODS: We surveyed peer-reviewed papers on generative AI models with specific applications to time-series health data. Our search included single- and multimodal generative AI models that operated over structured and unstructured data, physiological waveforms, medical imaging, and multi-omics data. We introduce current generative AI methods, review their applications, and discuss their limitations and future directions in each data modality. RESULTS: We followed the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines and reviewed 155 articles on generative AI applications to time-series health care data across modalities. Furthermore, we offer a systematic framework for clinicians to easily identify suitable AI methods for their data and task at hand. CONCLUSIONS: We reviewed and critiqued existing applications of generative AI to time-series health data with the aim of bridging the gap between computational methods and clinical application. We also identified the shortcomings of existing approaches and highlighted recent advances in generative AI that represent promising directions for health care modeling.

Artificial Intelligence↗
PubMed1999

The dopaminergic innervation of the avian telencephalon.

The present review provides an overview of the distribution of dopaminergic fibers and dopaminoceptive elements within the avian telencephalon, the possible interactions of dopamine (DA) with other biochemically identified systems as revealed by immunocytochemistry, and the involvement of DA in behavioral processes in birds. Primary sensory structures are largely devoid of dopaminergic fibers, DA receptors and the D1-related phosphoprotein DARPP-32, while all these dopaminergic markers gradually increase in density from the secondary sensory to the multimodal association and the limbic and motor output areas. Structures of the avian basal ganglia are most densely innervated but, in contrast to mammals, show a higher D2 than D1 receptor density. In most of the remaining telencephalon D1 receptors clearly outnumber D2 receptors. Dopaminergic fibers in the avian telencephalon often show a peculiar arrangement where fibers coil around the somata and proximal dendrites of neurons like baskets, probably providing them with a massive dopaminergic input. Basket-like innervation of DARPP-32-positive neurons seems to be most prominent in the multimodal association areas. Taken together, these anatomical findings indicate a specific role of DA in higher order learning and sensory-motor processes, while primary sensory processes are less affected. This conclusion is supported by behavioral findings which show that in birds, as in mammals, DA is specifically involved in sensory-motor integration, attention and arousal, learning and working memory. Thus, despite considerable differences in the anatomical organization of the avian and mammalian forebrain, the organization of the dopaminergic system and its behavioral functions are very similar in birds and mammals.

Afferent Pathways↗
PubMed2005

Hippocampus activity differentiates good from poor learners of a novel lexicon.

Language proficiency is a key to academic and workplace success for native and non-native speakers. It is largely unknown, however, why some people pick up languages more easily than others. We used event-related functional magnetic resonance imaging (e-fMRI) to elucidate which brain regions are modulated during the acquisition of a novel lexicon and which of these learning-related activity changes correlated with general semantic language knowledge. Fourteen healthy young subjects learned a novel vocabulary of 45 concrete nouns via an associative learning principle over the course of five blocks during e-fMRI. As a control condition, subjects took part in a structurally identical "No-Learning" condition lacking any learning principle. Overall, increasing vocabulary proficiency was associated with (intercorrelated) modulations of activity within the left hippocampus and the left fusiform gyrus, regions involved in the binding and integration of multimodal stimuli, and with an increasing activation of the left inferior parietal cortex, the presumed neural store of phonological associations. None of these activity changes were observed during the control condition. Furthermore, subjects who showed less suppression of hippocampal activity over learning blocks scored higher on semantic knowledge in their native language and learned the novel vocabulary more efficiently. Our findings indicate that (a) the successful acquisition of a new lexicon depends on correlated amplitude changes between the left hippocampus and neocortical regions and (b) learning-related hippocampus activity is a stable marker of individual differences in the ability to acquire and master vocabularies.

Adult↗
PubMed2004

Population of linear experts: knowledge partitioning and function learning.

Knowledge partitioning is a theoretical construct holding that knowledge is not always integrated and homogeneous but may be separated into independent parcels containing mutually contradictory information. Knowledge partitioning has been observed in research on expertise, categorization, and function learning. This article presents a theory of function learning (the population of linear experts model--POLE) that assumes people partition their knowledge whenever they are presented with a complex task. The authors show that POLE is a general model of function learning that accommodates both benchmark results and recent data on knowledge partitioning. POLE also makes the counterintuitive prediction that a person's distribution of responses to repeated test stimuli should be multimodal. The authors report 3 experiments that support this prediction.

Analysis of Variance↗
PubMed2005

Methods for quantifying the informational structure of sensory and motor data.

Embodied agents (organisms and robots) are situated in specific environments sampled by their sensors and within which they carry out motor activity. Their control architectures or nervous systems attend to and process streams of sensory stimulation, and ultimately generate sequences of motor actions, which in turn affect the selection of information. Thus, sensory input and motor activity are continuously and dynamically coupled with the surrounding environment. In this article, we propose that the ability of embodied agents to actively structure their sensory input and to generate statistical regularities represents a major functional rationale for the dynamic coupling between sensory and motor systems. Statistical regularities in the multimodal sensory data relayed to the brain are critical for enabling appropriate developmental processes, perceptual categorization, adaptation, and learning. To characterize the informational structure of sensory and motor data, we introduce and illustrate a set of univariate and multivariate statistical measures (available in an accompanying Matlab toolbox). We show how such measures can be used to quantify the information structure in sensory and motor channels of a robot capable of saliency-based attentional behavior, and discuss their potential importance for understanding sensorimotor coordination in organisms and for robot design.

Animals↗
PubMedDate not supplied

Attention-deficit hyperactivity disorder in adults.

It has been estimated that 30% to 70% of children who are diagnosed as having attention-deficit hyperactivity disorder (ADHD) will continue to show symptoms of the condition as adults. Since the prevalence of ADHD among school children may be 3% or more, its prevalence among adults may be 1% or 2%. The third revised edition of the Diagnostic and Statistical Manual (1987) of the American Psychiatric Association lists three essential features for the diagnosis of ADHD: "developmentally inappropriate inattention, impulsiveness, and hyperactivity." Other conditions associated with ADHD in adults include learning disabilities (or their sequelae), general anxiety disorder, drug and alcohol abuse, and dysthymic and cyclothymic disorders. Strong correlations have been found between ADHD and oppositional defiant and conduct disorders in children and an increased risk for antisocial disorders in adults. A combination of genetic, biologic, and environmental factors appears to be implicated in the etiology of ADHD. The management of adult ADHD requires a multimodal approach. The patient needs to be informed of the cause of his or her impulsive and often self-destructive behavior. Many patients will have learning difficulties that require evaluation and remediation by specialists in learning disabilities. Psychotherapy can help the patients resolve disturbances in perceptions of self and others and family therapy can address difficulties in the adult's relationships with family members. Pharmacotherapy of adult ADHD includes the use of central nervous system stimulants, such as methylphenidate, dextroamphetamine, and pemoline, of the tricyclic antidepressants imipramine and desimipramine, and of other antihypertensive, analgesic, and antimanic drugs.

Adult↗
PubMed2005

Contrasting roles for beta1, beta2 and beta3-adrenoceptors in memory formation in the chick.

Noradrenaline plays distinct roles in the modulation and consolidation of memory for one-trial, discriminated, avoidance learning in the chick. We have previously shown that activation of beta2-, beta3- and alpha1-adrenoceptors (ARs) by injection into the multimodal forebrain association region (intermediate medial hyperstriatum ventrale [IMHV] or intermediate medial mesopallium [IMM]) is involved in the consolidation of memory 30 min after training and that activation of alpha2-ARs in the caudate putamen plays a role in the reinforcement of memory leading to consolidation in the IMM (IMHV). In this paper we provide evidence that noradrenaline acts at beta1-ARs in the basal ganglia (lobus parolfactorius or medial striatum) in short-term memory processing immediately post-training and demonstrate inhibition of memory by selective AR antagonists at particular times in the sequential memory processing sequence after training. These results support separate roles for beta2- and beta3-ARs in memory consolidation. Our studies suggest that, as a consequence of the learning experience, noradrenaline acts in different brain regions and at different times in memory processing, to enhance memory through distinct populations of ARs.

Adrenergic beta-Agonists↗
PubMed1994

Dissociation between conditioned taste aversion and radial maze learning following seizure-induced multifocal brain damage: quantitative tests of serial vs. parallel circuit models of memory.

Multivariate analyses between conditioned taste aversion (CTA) and radial maze acquisition (RMA) scores and percentages of neuronal dropout within thalamic and telencephalic structures were completed for rats in which overt seizures had been evoked following a single systemic injection of lithium/pilocarpine. Despite multifocal damage, only the amount of damage within the hippocampus (CA1) and the basolateral amygdala was most strongly associated with attenuated CTA, whereas damage within the mediodorsal thalamus was primarily associated with RMA. There was no significant correlation between CTA or RMA. Multiple regression analyses for specific Paxinos and Watson structures and their traditional aggregates supported more precise delineation of neuronal substrates of learning/memory and a multimodal (parallel) model for these processes.

Animals↗
PubMedDate not supplied

Lake Superior Rural Cancer Care Project, part II: provider knowledge.

PURPOSE: The purpose of this article is to report the main learning outcomes of the Lake Superior Rural Cancer Care Project. DESCRIPTION OF STUDY: The authors designed and tested a multimodal intervention directed at rural providers and their healthcare systems in a large rural area in the north central United States. An experimental design was used to randomize rural providers at the group level. The intervention consisted of providing increased education for rural providers with a number of approaches, including the use of clinical opinion leaders. The main outcome of the intervention was knowledge scoring on discipline-specific cancer management tests. RESULTS: Knowledge scores for providers in the experimental group significantly increased from pretest to post-test: 66 to 79 for physicians (and physician assistants) (P=.02); 58 to 71 for nurses (P=.01); and 54 to 64 for pharmacists (P=.01). At post-test, participating providers in the experimental group performed significantly better on the knowledge tests (P <.01) than those in the control groups. CLINICAL IMPLICATIONS: This study may be the first to test educational interventions to improve rural providers' knowledge about cancer practice using an experimental design. The intervention may possibly change provider practice behaviors and, thus, patient outcomes, data that will be reported in a future issue. Finally, this educational intervention may prove useful for providers in other rural areas.

Humans↗
PubMed1994

Group and family treatment of post-traumatic stress disorder.

A central feature of PTSD is its effect on social relationships. Trauma affects groups of people, not just individuals. Family systems, neighborhoods, and even whole generations may feel the results of psychological trauma. Because of the social nature of the effects of trauma, post-trauma treatment must address an individual's relationship to others. Group and family psychotherapy are ideally suited to this and are important components of a multimodal approach to PTSD treatment. Group and family psychotherapies provide superb opportunities for social support, social reintegration, and interpersonal learning. As with any powerful technique, these methods must be carefully applied. Although not all patients are appropriate for exposure-based treatments, improved interpersonal coping skills will likely be beneficial to many PTSD patients. Patients should be carefully evaluated for treatment types and assessed for treatment response. Although group and family therapies currently provide relief and growth for PTSD patients, many considerations remain for the future. For example, how can patients be matched with various treatments for optimal results? How should acute and chronic PTSD treatments be similar and different? What is the effectiveness of group and family therapies for PTSD? What are the social and legal implications of a prolonged course of treatment for a victim whose children meanwhile are being traumatized by the parent's relatively poor parenting skills secondary to their inadequacies and disabilities? Finally, at a global level, how do we improve systems therapy technology to enable us more radically, effectively, and quickly to bring about total systems change? Because families and groups are the "cells" that compose the "vital organs" we call nations, and these nations in turn make the total body of humankind, the answers to these questions may have a significant determining effect on the future survival of us all.

Adult↗
PubMedDate not supplied

A prospective study of alexithymia in obsessive-compulsive patients treated with multimodal cognitive-behavioral therapy.

BACKGROUND: Alexithymia as a predictor of treatment outcome in psychotherapy has often been discussed but rarely evaluated in prospective studies. The present study evaluated the absolute and relative stability of alexithymia in patients with obsessive-compulsive disorder (OCD), and the predictive value of alexithymia for the outcome of treatment. METHODS: We conducted a prospective study with 42 inpatients receiving intensive, multimodal cognitive-behavioral therapy (CBT). Patients were assessed for alexithymia at pre- and post-treatment with the 20-item Toronto Alexithymia Scale (TAS-20), for obsessive-compulsive symptoms and depression with the Yale-Brown Obsessive-Compulsive Scale (Y-BOCS) and the 21-item Hamilton Depression Rating Scale (HDRS). RESULTS: OCD and comorbid depression showed a highly significant symptom-reduction from pre- to post-treatment while no absolute changes in the TAS-20 total scores and its factors 1 and 3 occurred. Only factor 2 scores decreased significantly, but with a smaller effect size than the effect sizes for the changes in Y-BOCS and HDRS. Alexithymia scores at pre-treatment correlated significantly with alexithymia scores at the end of treatment, indicating its relative stability. In the linear regression analyses, no variables were identified that predicted significantly the outcome of treatment. CONCLUSIONS: Our findings support the view that alexithymia is a stable personality trait rather than a state-dependent phenomenon in obsessive-compulsive patients. Alexithymia scores do not predict response to multimodal CBT in OCD. It might be an effect of CBT that patients could at least partly regain or newly learn the capability to describe their feelings.

Adult↗
PubMed2026

Beyond Morphology: Reframing Lymph-Node Metastasis Prediction Through Clonal Ecology-Decades-Long Genomic Instability and Polyclonal-to-Monoclonal Transitions as the Missing Dimension in Cancer.

Recent whole-genome, lineage-tracing, single-cell, and spatial studies have reshaped our understanding of tumor evolution, revealing that cancers can arise from polyclonal populations, undergo decades-long genomic instability before clinical detection, and progress through dynamic changes in subclonal composition, cellular state, and ecological organization. These findings challenge the assumption underlying morphology-based prediction models that metastatic risk can be inferred from static histological features alone. Here, we revisit lymph-node metastasis prediction in colorectal cancer through clonal ecology, integrating computational pathology with evolutionary oncology. Drawing on the subclonal switchboard model proposed in 2012 and subsequent artificial intelligence (AI)-enabled approaches for tracking dominant and dormant subclones, we synthesize evidence that metastatic potential reflects clonal ancestry, evolutionary timing, spatial niche architecture, cellular plasticity, intercellular interactions, dormancy, and treatment-driven shifts in subclonal fitness. We define five complementary methodological pillars for operationalizing clonal ecology: single-cell transcriptomics for resolving rare subclones, evolutionary trajectories, and adaptive cell states; lineage tracing and phylogenetics for reconstructing clonal ancestry and divergence; spatial transcriptomics and genomics for mapping subclonal geography and tumor-stromal-immune interactions; longitudinal liquid biopsy surveillance for monitoring residual disease, clonal turnover, and emerging resistance; and AI-enabled multimodal integration for connecting histopathology, genomics, spatial biology, and longitudinal data into predictive ecological-state models. Multiple-instance learning and pathology foundation models provide scalable computational foundations for evolution-aware prediction. Translationally, dormant subclones represent actionable reservoirs of recurrence. A longitudinal clinical and experimental study of KMT2A-rearranged acute myeloid leukemia further supports central predictions of the subclonal switchboard framework by demonstrating treatment-associated shifts in subclonal dominance, persistence of cryptic adaptive programs, and ecological rewiring during resistance and relapse. We propose clonal ecology as a measurable dimension for extending morphology-driven prediction toward integrative models that anticipate evolutionary transitions, identify therapeutic windows, and proactively constrain adaptive tumor ecosystems before resistant or metastatic subclones achieve clinical dominance.

Humans↗
PubMed2026

Artificial Intelligence for Colorectal Surgeons-Part II: Research Applications, Challenges in Adoption, and Practical Resources.

BACKGROUND: This is part II of a 2-part series examining artificial intelligence in colorectal surgery. Part I established foundational concepts and clinical applications. Implementation, however, requires understanding research methodologies, available resources, and the specific challenges currently limiting widespread adoption. These topics are the focus of part II. OBJECTIVE: To examine artificial intelligence's transformation of surgical research, provide practical implementation resources, address adoption challenges, and explore future directions in colorectal surgery. METHODS: Comprehensive literature review focusing on artificial intelligence research methodology, implementation barriers, educational resources, and emerging technologies relevant to colorectal surgeons. RESULTS: Artificial intelligence streamlines clinical trial design through predictive modeling and natural language processing, reducing enrollment challenges that contribute to failed or inadequate trial accrual. Machine learning enables heterogeneity analysis within clinical trials, identifying treatment-responsive subgroups. Foundation models unlock analysis of unstructured electronic health record data at scale. Professional societies and universities offer specialized artificial intelligence education programs, with open-access data sets facilitating research participation. However, implementation faces multifaceted challenges: technical infrastructure demands, with real-time processing requiring dedicated graphics processing unit clusters; regulatory frameworks struggling with continuously evolving algorithms; undefined liability distribution for artificial intelligence-assisted decisions; algorithmic bias risking health care disparities; and the "black box" problem limiting clinical trust. Economic barriers include substantial initial costs without clear reimbursement pathways. Future directions include multimodal artificial intelligence integrating imaging, genomics, and histopathology; cognitive robotic systems with real-time decision support; digital twin technology for patient-specific surgical simulation; and global surgical artificial intelligence networks enabling distributed learning across institutions. CONCLUSIONS: Although artificial intelligence offers transformative potential for colorectal surgery research and practice, successful implementation requires addressing technical, regulatory, ethical, and economic challenges. The surgeon's evolving role demands both traditional expertise and computational fluency. Future advances in multimodal integration, autonomous systems, and global collaboration will fundamentally reshape surgical practice but will require thoughtful implementation prioritizing patient benefit and clinical value.

Humans↗
PubMed2000

Incorporating the management of ADHD into your practice. Can it be done?

BACKGROUND: Management of children with learning and behavioural disorders has traditionally been the precinct of specialist paediatricians, psychiatrists, psychologists and teaching professionals. Networks and teams have not generally included general practitioners. In Geraldton a professional network of health and educational professionals were of the view that learning disorders including attention deficit hyperactivity disorder (ADHD) frequently went unrecognised or misdiagnosed. In 1996 the National Health and Medical Research Council recommended use of the DSM-IV American Psychiatric Association diagnostic criteria for ADHD. A multimodal model of shared care was considered optimal. In 1999 the US National Institute of Mental Health's Multimodal Treatment Study of Children with ADHD was released. OBJECTIVE: To outline the development of a program to educate and support local professionals (doctors, teachers, psychologists, nurses, counsellors) in the management of behavioural disorders in which specific goals were to: build capacity for accurate diagnosis and management of children with learning and behavioural disorders facilitate via the Midwest Division of General Practice, a network of professionals to assess and manage learning disorders, including ADHD create a model of shared care with potential for application elsewhere formalise shared care/coprescriber arrangements for stimulant medications between GPs and specialists, including fast-tracking of medication develop school networks for early identification, referral and support of ADHD cases. DISCUSSION: Our creation of a strong professional network enabling a GP case manager role has been very successful. Multiple treatment successes have created much community goodwill toward the Midwest Division of General Practice and my private practice has changed forever with the inclusion of 200 ADHD families. Colleagues considering entering this area need to recognise the potential for disruption to both their practice and their personal lives. A well organised practice with firm boundaries for difficult cases is essential.

Attention Deficit Disorder with Hyperactivity↗