PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “multimodal integration”

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 559 records · Page 31Linked to original sources

[Is there more than one "true" theory of cognition in medicine?].

Alternative approaches such as Traditional Chinese Medicine are very popular with patients. Often, however, there is a lack of high quality studies to prove their efficacy. The question will be discussed whether different theories of cognition may coexist in medicine which are all true. Not only biological, but also psychological and social factors contribute to health and well-being. Integrative medicine should bridge the gap between mainstream evidence-based medicine and complementary methods. Shared decision making between patient and physician can help to find the optimum, often multimodal treatment strategy for each patient.

Complementary Therapies↗

[Rationale for oncological surgery in multimodal cancer treatments].

The permanent dissemination of circulating cancer cells from infiltrative cancers renders the notion of localized cancer obsolete. This raises the question of the role of treatments such as surgery which are localized in time and space. Moreover, it is now proven that surgery increases the number of circulating cancers cells and produces transient immunodepression which promotes cancer cell implantation. In addition, the healing process stimulates growth factors, which also act on tumor growth. In spite of these deleterious effects, oncological surgery remains an important tool in the anti-cancer armamentarium. Optimal cytoreductive surgery facilitates the effect of adjuvant treatments by eliminating the vascular sanctuaries present in the center of any large tumor and by its effect as a striking-force very localized in time and space. Oncological surgery must evolve as an integrative part of our improving understanding of tumor biology, taking into account recent developments in functional imaging, genomics and proteomics. Modalities and timing must be reconsidered for oncological surgery to play its proper role as one of the many components contributing to multimodal cancer treatments. New modalities will undoubtedly be necessary with the development of future technologies.

Animals↗

Evoked potentials in monitoring multiple sclerosis.

The usefulness of evoked potentials (EPs) in the diagnosis of multiple sclerosis is limited by its relatively low sensitivity to subclinical lesions. However, they are still a good tool to assess the integrity of afferent and efferent pathways and to quantify the severity of white matter involvement. Transversal and longitudinal studies have demonstrated good correlation between EP abnormalities and disability, suggesting that multimodal evoked potentials could be useful in monitoring the disease evolution in single patients and as surrogate end points in clinical trials.

Brain↗

Management of disturbed and aggressive behaviour in psychopaths.

In order to maximize the benefits of a multimodal therapeutic regime, a therapeutic group milieu setting is needed as a catalyst, followed by mandatory community care. Therefore, the treatment of choice for the psychopath seems to be the integrated comprehensive approach on a long term basis. However, should therapy be ineffective, the structure will be maintained while the elapse of time decreases the psychopathic behaviour to a virtual non-existent entity as a result of aging. In either case, society will be protected.

Adolescent↗

Optimal pain control in elderly cancer patients.

The optimal management of pain in the elderly cancer patient is founded on astute assessment of pain and other symptoms, development of a pain diagnosis derived from the clinical evaluation, treatment of underlying causes where possible, and the expert application of analgesic techniques. Analgesic techniques themselves are multimodal. Pharmacologic approaches are the mainstay, but an individual patient may benefit from the use of anesthetic, neuroaugmentative, surgical, physiatric, or psychological methods, as well. Guidelines for the assessment and integrated management of these patients are suggested, with specific emphasis on the use of pharmacologic therapy.

Aged↗

Deep learning-based cross-attention fusion of multimodal MRI for survival prediction and risk stratification in IDH-wildtype glioblastoma: a multicenter study.

BACKGROUND: Glioblastoma (GBM) exhibits profound molecular and spatial heterogeneity, complicating prognostic evaluations. While multiparametric MRI provides crucial multidimensional biological information, conventional end-to-end deep learning integration strategies, such as early or late fusion, often fail to capture complex nonlinear cross-modal interactions. We aimed to systematically evaluate a cross-attention fusion (CAF) architecture for GBM survival prediction and quantify its incremental prognostic value relative to existing clinical tools. METHODS: In this multicenter retrospective study, 386 adults with IDH-wildtype, WHO grade 4 GBM were assembled from an institutional cohort (n = 226), the Chinese Glioma Genome Atlas (CGGA, n = 62), and The Cancer Genome Atlas (TCGA, n = 98). Using a unified 3D ResNet-18 backbone, we compared single-modality models, early fusion, late fusion, and CAF on preoperative T1-weighted, contrast-enhanced T1-weighted (T1CE), and T2-weighted MRI, and integrated the resulting deep learning risk score with routine clinical variables through multivariable Cox regression. Performance was assessed using Harrell's C-index, time-dependent AUC, and decision curve analysis. RESULTS: CAF showed numerically higher, more consistent C-index trends than early fusion, late fusion, and single-modality models (pooled C-index 0.629, 95% CI 0.594-0.664), although pairwise differences in time-dependent AUC were not statistically significant. Integrating clinical variables raised the pooled C-index to 0.691 (95% CI 0.660-0.721) in the treatment-era model, with comparable performance across the three cohorts (Local 0.688; CGGA 0.716; TCGA 0.689); a pre-treatment configuration excluding adjuvant therapy yielded a pooled C-index of 0.642. Under leave-one-cohort-out external validation, the combined model retained significant risk stratification in all held-out cohorts (C-index 0.63-0.71; all log-rank P&#xa0;<&#xa0;0.01), albeit with attenuated discrimination. The deep learning risk score remained independent after multivariable adjustment (HR 1.41 per SD, 95% CI 1.26-1.57; P&#xa0;<&#xa0;0.001). Kaplan-Meier analysis confirmed significant high- versus low-risk separation in all cohorts, and decision curve analysis showed greater net benefit than clinical-only and deep-learning-only models. CONCLUSION: The CAF-derived risk score offers prognostic information complementary to routine clinical variables, representing a promising noninvasive tool for individualized risk stratification when molecular profiling is incomplete or unavailable; these findings warrant prospective external validation before clinical use.

cross-attention fusion↗

Responses of neurons in the lamb nucleus tractus solitarius to stimulation of the caudal oral cavity and epiglottis with different stimulus modalities.

Receptors located in the posterior oral cavity and on the epiglottis play an important role in the initiation of upper airway reflexes such as swallowing, gagging, coughing and apnea. Peripheral nerves which innervate these receptor areas terminate in the nucleus tractus solitarius (NTS). We have recorded the responses of 61 neurons in the lamb NTS to stimulation of the caudal tongue, palate and epiglottis with mechanical, chemical and thermal stimuli and mapped receptive field location. Although there was some overlap in the areas of the NTS from which neurons with oral cavity and epiglottal receptive fields could be recorded, a significant difference was observed in the mean recording sites of the two groups of neurons. Neurons with oral cavity receptive fields were located more rostral, lateral and ventral in the NTS than neurons with receptive fields on the epiglottis. Little convergence of sensory input onto single cells in the NTS was observed between the oral cavity and the epiglottis. Only one NTS neuron had a receptive field in both of these receptor areas. In contrast, a large number of neurons with oral cavity receptive fields received input from two receptor areas. These neurons had a receptive field on the tongue which was located directly beneath the receptive field on the palate. Mechanical stimuli were the most effective for neurons with either oral cavity or epiglottal receptive fields and thermal stimuli were the least effective. Neurons which responded to mechanical stimuli responded better to a moving stimulus than to a punctate one, and large increases in the strength of a punctate stimulus were required to elicit significant increases in response frequency. Most NTS neurons responded to more than one of the stimulus modalities. However, a significant difference in the mean number of stimulus modalities which elicited responses was observed between neurons with oral cavity and epiglottal receptive fields. The number of multimodal neurons with epiglottal receptive fields was higher than those with oral cavity receptive fields. The multimodal nature of neurons which responded to epiglottal or oral cavity stimulation combined with their location in reflexogenic areas of the NTS suggests that these neurons could be important in the integration of afferent input from the oral cavity and upper airway. If these NTS neurons are involved in the control of oral and upper airway reflexes it would be important for them to respond to as many of the stimulus cues as possible and the majority of these neurons do just that.

Action Potentials↗

A new software tool for 3D motion analyses of the musculo-skeletal system.

BACKGROUND: Many clinical and biomechanical research studies, particularly in orthopaedics, nowadays involve forms of movement analysis. Gait analysis, video-fluoroscopy of joint replacement, pre-operative planning, surgical navigation, and standard radiostereometry would require tools for easy access to three-dimensional graphical representations of rigid segment motion. Relevant data from this variety of sources need to be organised in structured forms. Registration, integration, and synchronisation of segment position data are additional necessities. With this aim, the present work exploits the features of a software tool recently developed within a EU-funded project ('Multimod') in a series of different research studies. METHODS: Standard and advanced gait analysis on a normal subject, in vivo fluoroscopy-based three-dimensional motion of a replaced knee joint, patellar and ligament tracking on a knee specimen by a surgical navigation system, stem-to-femur migration pattern on a patient operated on total hip replacement, were analysed with standard techniques and all represented by this innovative software tool. Segment pose data were eventually obtained from these different techniques, and were successfully imported and organised in a hierarchical tree within the tool. FINDINGS: Skeletal bony segments, prosthesis component models and ligament links were registered successfully to corresponding marker position data for effective three-dimensional animations. These were shown in various combinations, in different views, from different perspectives, according to possible specific research interests. INTERPRETATION: Bioengineering and medical professionals would be much facilitated in the interpretation of the motion analysis measurements necessary in their research fields, and would benefit therefore from this software tool.

Aged↗

GBFN: A gated bimodal fusion network leveraging foundation model embeddings for cancer drug sensitivity prediction.

Despite recent progress in deep learning for cancer drug sensitivity prediction, many existing models still rely on task-specific representation learning or relatively simple multimodal fusion, which may limit their ability to capture complex drug-cell interactions. To address this issue, we developed GBFN, a gated bimodal fusion network for continuous IC50 prediction that integrates pretrained drug and cell-line representations. Specifically, drug embeddings were obtained from SMI-TED, whereas cell-line embeddings were derived from transcriptomic profiles using BulkFormer. These two modalities were then combined through a dimension-wise gated fusion module and used to predict IC50 values in matched drug-cell line pairs. On the CCLE-based benchmark, GBFN outperformed representative neural baselines, including GraphDRP, TGSA, and TransEDRP, and achieved the best overall performance, with an R&#xb2; of 0.8714 and an RMSE of 0.8938. Moreover, ablation analysis showed that the model using drug features and cell-line expression data with gated fusion performed better than the corresponding model using direct concatenation, indicating that the improvement was associated with the fusion strategy rather than with the input modalities alone. In addition, cell-line expression data were more informative than mutation data in the present setting, and adding mutation data to the model using drug features and expression data did not further improve performance. Across major cancer types, GBFN maintained generally high cell-line-level predictive performance, and perturbation-based attribution identified biologically relevant transcriptomic programs in selected drug-cell line settings. Together, these findings support GBFN as a compact and effective framework for continuous drug response prediction.

Humans↗

High-throughput measurements of biochemical responses using the plate::vision multimode 96 minilens array reader.

The plate::vision is a high-throughput multimode reader capable of reading absorbance, fluorescence, fluorescence polarization, time-resolved fluorescence, and luminescence. Its performance has been shown to be quite comparable with other readers. When the reader is integrated into the plate::explorer, an ultrahigh-throughput screening system with event-driven software and parallel plate-handling devices, it becomes possible to run complicated assays with kinetic readouts in high-density microtiter plate formats for high-throughput screening. For the past 5 years, we have used the plate::vision and the plate::explorer to run screens and have generated more than 30 million data points. Their throughput, performance, and robustness have speeded up our drug discovery process greatly.

Absorption↗

Development of an integrated optic oxygen sensor using a novel, generic platform.

This paper describes the development of a generic platform for enhanced, integrated optic sensors based on fluorescence detection. The platform employs a novel optical configuration in order to achieve enhanced performance and has inherent multianalyte detection capability. The sensor element comprises a multimode ridge waveguide that has been patterned with an analyte-sensitive fluorescent spot, which is excited directly using a LED. The platform was applied to the detection of gaseous oxygen as a proof of principle. The sol-gel-derived sensor spots were doped with an oxygen-sensitive fluorescent dichlororuthenium dye complex and intensity-based calibration data were generated from the oxygen-dependent waveguide output. The sensor achieved a LOD of 0.62% and a resolution of less than 0.96% gaseous oxygen, which compares favourably with a similar, recently reported system. This device highlights the combination of inexpensive rapid prototyping techniques and a dedicated sensor enhancement strategy that together facilitate the production of an effective prototype sensor platform.

Journal Article↗

Strategies to improve immunization rates and well-child care in a disadvantaged population: a cluster randomized controlled trial.

OBJECTIVE: To measure the effect of a multimodal intervention on well-child care visit (WCV) and immunization rates in an inner-city population. DESIGN: Cluster randomized controlled trial. SETTING AND PARTICIPANTS: One-year cohort of 2843 infants born at a hospital in an integrated inner-city health care system. INTERVENTIONS: Eleven clinics were randomly allocated to 1 of 3 study arms: WCV intervention (n = 3), immunization intervention (n = 4), and controls (n = 4). Interventions to improve immunization and WCV rates included both patient-based and clinic-based activities. MAIN OUTCOME MEASURES: Up-to-date status with childhood immunizations and WCVs by age 12 months (primary) and health care utilization and charges (secondary). RESULTS: Compared with the control arm, the WCV and immunization arms had 5% to 6% higher immunization rates and 7% to 8% higher WCV rates. In multivariate analyses that accounted for the clustered nature of the data, the number of immunizations received was greater in the WCV arm than in controls. However, neither the WCV nor the immunization intervention increased WCV or immunization up-to-date rates. The WCV arm had slightly higher health care charges. Neither intervention affected emergency, urgent care or inpatient utilization. CONCLUSIONS: This multimodal intervention produced a small increase in the number of childhood immunizations delivered. However, patient- and clinic-based methods did not lead to significant increases in WCV or immunization up-to-date rates after controlling for other factors. Methods found in some settings to increase immunization up-to-date rates may not be as effective in a population of inner-city socioeconomically disadvantaged children.

Child Health Services↗

Interaction between different sensory cues in the control of human gait.

This experiment investigates the interaction of different sensory cues in the control of propulsive forces in human gait which in turn allow the body's forward progression to be regulated. The aim of this work was to determine how optic flow and leg-somatosensory feedback interact in this control. We therefore determined whether the responses to sinusoidal perturbations of optic flow were accentuated when leg-somatosensory feedback was modified by varying the support resistance. Subjects walked on a treadmill which was driven by their own locomotor activity (1) with a sinusoidal variation of optic flow velocity, (2) with a sinusoidal variation of support resistance which modified leg-somatosensory information and (3) with both visual and leg-somatosensory modification at different frequencies. The response of the subject was measured as changes in speed and propulsive power. The response to sinusoidal perturbations of optic flow was found to be increased and time delayed when visual perturbations are coupled with support perturbations in comparison with the response observed with visual perturbations only. This result shows the influence of leg-somatosensory feedback on the weighting of optic flow. Inversely, it was also found that the motor response to support perturbation was different when the flow was congruent (i.e., corresponding to the subject's virtual speed) and when it was not. This latter result shows the influence of optic flow on the weighting of leg-somatosensory feedback. The interaction between optic flow and leg-somatosensory feedback argues in favor of a multimodal sensory control of propulsive forces. This multimodal sensory control would be based on all the sensory feedback and all their mutual sensorial interaction. Therefore, the modification of one sensory input modifies not only this input but also the integration of the other inputs.

Adult↗

Sequential Therapy in the Treatment of Locally Advanced Noninflammatory Breast Cancer.

Optimal care of patients with locally advanced breast cancer requires the use and thoughtful integration of all effective modalities of treatment. A number of alternative combinations of surgery, chemotherapy, and radiation have been promoted, each with its own particular advantages and shortcomings. The advantages of sequenced, multimodality therapy of locally advanced, noninflammatory breast cancer include (1) the ability to convert nonresectable tumors to resectable ones, (2) early institution of systemic therapy, (3) in vivo evaluation of tumor response with the potential for optimization of therapy, and (4) relatively low morbidity rates with the ability to render most patients disease-free at their primary site. The results of this treatment strategy are discussed.

Journal Article↗

Decoding cancer with artificial intelligence: Transforming research, diagnosis, and therapy with future insights.

Cancer remains one of the leading global health burdens, with increasing complexity in genomic, imaging, and clinical datasets presenting significant challenges for effective management. Artificial intelligence (AI) has emerged as a powerful tool to address these challenges by enabling pattern recognition, knowledge integration, and data-driven decision-making. This review highlights recent advances in the application of AI across cancer research, diagnosis, and therapy. In research, AI accelerates drug discovery and repurposing, enhances genomic data interpretation, and facilitates biomarker identification through multi-omics integration. In diagnosis, AI has demonstrated high technical performance in radiology for lesion detection and image segmentation, in pathology for tumour grading and molecular prediction, and in liquid biopsy for non-invasive biomarker analysis. In therapy, AI supports precision medicine by predicting treatment responses, monitoring disease progression, and optimizing clinical trial design. Despite these advances, barriers such as data heterogeneity, algorithmic bias, interpretability, and regulatory challenges remain. Future directions, including explainable AI, federated learning, multimodal modelling, and digital twins, hold promise for translating AI-driven innovations into routine oncology practice. Significance Statement This review provides a timely synthesis of recent (2020-2025) advances in artificial intelligence across cancer research, diagnosis, and therapy, highlighting applications in drug discovery, genomics, multi-omics biomarker identification, and clinical decision-making. By integrating technological progress with translational and clinical relevance, this work serves as a valuable resource for bridging AI innovation with precision oncology practice. As a narrative review, the literature was identified through targeted PubMed, Scopus, and Google Scholar searches, combining terms for artificial intelligence, machine learning, and deep learning with cancer-related keywords, with priority given to peer-reviewed studies published between 2020 and 2025, seminal earlier works, and official regulatory or guideline documents. Within each domain, representative studies were selected to illustrate methodological diversity, clinical context, and current translational readiness rather than to provide exhaustive coverage of an extremely rapidly evolving field.

Artificial intelligence↗

Transfer of sensory-integration training.

96 university students participated in one of six treatments to assess whether training to make cross-modal or intramodal matches of one linear-movement distance would transfer to other distances. Three groups received unimodal training (vision, audition, or kinesthesis) and three groups received multimodal training (all combinations of vision, audition, and kinesthesis) to make kinesthetic matches of one common linear-movement distance. All subjects were subsequently tested on kinesthetic matches of novel distances both shorter and longer than the training distance. A multivariate analysis of variance and Bonferroni contrasts indicated that cross-modal matching was enhanced by multimodal experience but only for distances shorter than the training distance. It was speculated that transferring to distances shorter than a training distance might involve processes different from those used to transfer to distances longer than the training distance.

Adolescent↗

[A psychological therapy methods in chronic non-radicular backache].

The presence of psychological co-morbidity and difficulties in coping with chronic low-back pain are indications for the application of psychological therapy procedures. In the treatment of patients with chronic pain, the aim of therapy as well as the technique of the traditionally employed psychotherapeutic procedures need to be modified. What is of immediate importance is to promote an active pattern of coping with pain and discourage pain-related inactivity and reduce feelings of helplessness and hopelessness. To achieve this, it is necessary to combine various psychological treatment modalities (relaxation techniques and behavioural or psychodynamic therapy) with exercise programs as in physiotherapy or sports medicine. In the choice of the appropriate psychotherapeutic modalities, it is important to take into consideration the extent of chronicity of pain, the patient's subjective understanding of the illness, a possible wish of the patient for early retirement, previous experience with chronic pain and the extent to which the patient has been psychologically traumatised (especially in his childhood and youth). Relatives should be integrated in the planning and possibly also in carrying out of the treatment. Symptom-specific group therapy might motivate patients to undergo treatment and to change their habitual ways of life. A multimodal treatment approach incorporating orthopaedic, sports medicine, physiotherapeutic, psychological and socio-therapeutic procedures have proved to be more effective in the treatment of chronic pain than one employing monocausal treatment modalities.

Adaptation, Psychological↗

Multisensory convergence in calcarine visual areas in macaque monkey.

The neural substrates of multisensory perception and integration are still obscure, especially at the cortical level. Alternative viewpoints emphasize (1) 'bottom-up' processes, where different modalities converge in higher order multisensory areas, or (2) 'top-down' projections from multimodal to unimodal areas. In this anatomic study, we use anterograde tracer injections in parietal (8 monkeys) and auditory (3 monkeys) association areas, and demonstrate direct projections to areas V1 and V2 in the calcarine fissure (i.e. the peripheral visual field representation). The laminar signature, with terminations in layers 1 and/or 6, could be consistent with feedback-type connections. A subset of connections from parietal areas, however, branch to both V1 and a ventral extrastriate area (TEO or TEp). Thus, the direct connections to early visual areas V1 and V2 may well operate in conjunction with polysynaptic pathways in a densely parallel network.

Animals↗