Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “multimodal integration”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the 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
PubMed1995

[Role of radiotherapy in the combined treatment of invasive cancer of the vulva].

The authors review the literature on the different combinations of radiotherapy with chemotherapy and surgery with the aim of giving a state of art on the role of combined multimodality treatment of invasive vulvar carcinoma. From the data of the recent literature it appears that radiation integrated with surgery and chemotherapy can play an important role in reducing the risk of postoperative locoregional failure in patients with advanced primary or nodal disease and avoiding exenteration in patients with disease involving the anus or proximal urethra. This integrated multimodality therapy is a promising approach in the treatment of invasive vulvar carcinoma but further exploration in a larger number of patients is needed before giving consolidated data applicable in routine oncological clinical practice.

Antineoplastic Combined Chemotherapy Protocols↗
PubMed2025

Study Protocol for HeartMagic: A Prospective Observational Cohort Characterizing Subtypes of Heart Failure With Preserved Ejection Fraction.

BACKGROUND: Heart failure (HF) is a life-threatening syndrome with significant morbidity and mortality. Although evidence-based drug treatments have effectively reduced morbidity and mortality in HF with reduced ejection fraction (EF), few therapies have been demonstrated to improve outcomes in HF with preserved EF. This may be caused by the existence of several HF with preserved EF subtypes that each need different treatments. There is therefore an unmet need for a comprehensive approach to subtype patients with HF with preserved EF. This protocol details the approach employed in the HeartMagic (Heart Failure Studied With a Machine Learning, Genomics, and Imaging Combination) study to address this gap. METHODS: This prospective multicenter observational cohort study will include 500 consecutive patients with HF with preserved EF at 2 Swiss university hospitals, along with 50 age-matched patients with HF with reduced EF and 50 healthy controls. In addition to routine clinical workup, participants undergo genomic, transcriptomic, and metabolomic analyses, and the anatomy, composition, and function of the heart are quantified by comprehensive echocardiography and magnetic resonance imaging. Quantitative magnetic resonance imaging is also applied to characterize the kidney. The primary outcome is a composite of 1-year cardiovascular mortality or rehospitalization. Machine learning-based multimodal clustering will be employed to identify distinct HF with preserved EF subtypes. Statistical analysis will include group comparisons, survival analysis, and integrative multimodal clustering combining clinical, imaging, ECG, genomic, transcriptomic, and metabolomic data to identify and validate HF with preserved EF subtypes. CONCLUSIONS: The integration of comprehensive magnetic resonance imaging with extensive genomic and metabolomic profiling in this study will result in an unprecedented panoramic view of HF with preserved EF and help distinguish functional subgroups, which may provide a basis for personalized therapies.

Aged↗
PubMed2026

Cyclin-dependent kinase 4 and 6 inhibitors and the breast cancer immune ecosystem: immune remodeling, resistance, and therapeutic reprogramming.

Cyclin-dependent kinase 4 and 6 inhibitors (CDK4/6 inhibitors) combined with endocrine therapy have become a therapeutic backbone for hormone receptor-positive, human epidermal growth factor receptor 2-negative breast cancer, yet durable disease control is frequently limited by intrinsic and acquired resistance. Canonical tumor-cell mechanisms, including retinoblastoma-pathway escape, cyclin E-cyclin-dependent kinase 2 (CDK2) activation, endocrine adaptation, and phosphoinositide 3-kinase (PI3K)-AKT-mechanistic target of rapamycin (mTOR) signaling, explain only part of this failure because they do not fully capture dynamic immune and stromal remodeling. Preclinical and translational studies indicate that early CDK4/6 inhibition can enhance antigen presentation, activate interferon-related programs, restrain regulatory T cells, and promote a T-cell-inflamed state. These effects are conditional and may not persist during prolonged treatment. Sustained therapy can instead drive heterogeneous resistant niches characterized by stromal remodeling, myeloid recruitment, checkpoint adaptation, and T-cell dysfunction. This immune-state dependence provides a rationale for immune checkpoint blockade, although clinical combinations have shown mixed efficacy and clinically relevant hepatic, pulmonary, and hematologic toxicities. Sequential or lead-in strategies therefore warrant prospective evaluation. Oxidative phosphorylation (OXPHOS) and redox adaptation may sustain selected resistant states and expose context-dependent ferroptotic vulnerabilities. Ferroptosis may connect tumor-cell killing with immune regulation, whereas nanomedicine may improve tumor-selective delivery. Both strategies remain largely preclinical and require further evaluation of pharmacokinetics, biodistribution, toxicity, manufacturability, and immune-cell safety. This Review distinguishes intrinsic from acquired resistance across interpatient, intratumoral, spatial, and temporal dimensions. It integrates tumor-cell escape with cytokine, immune, stromal, vascular, and metabolic remodeling and summarizes emerging therapeutic strategies. We further propose a candidate biomarker-informed framework that integrates genomic profiling, spatial immune architecture, circulating biomarkers, T-cell receptor (TCR) dynamics, transcriptomic and single-cell analyses, artificial intelligence (AI)-assisted multimodal integration, and longitudinal sampling. This framework is intended to support biomarker development and prospective trial design rather than current clinical decision-making, providing a translational basis for testing state-informed and sequence-aware therapeutic strategies.

Humans↗
PubMed1999

Integration, acceptance testing, and clinical operation of the Medical Information, Communication and Archive System, phase II.

The Medical Information, Communication and Archive System (MICAS) is a multivendor incremental approach to picture archiving and communications system (PACS). It is a multimodality integrated image management system that is seamlessly integrated with the radiology information system (RIS). Phase II enhancements of MICAS include a permanent archive, automated workflow, study caches, Microsoft (Redmond, WA) Windows NT diagnostic workstations with all components adhering to Digital Information Communications in Medicine (DICOM) standards. MICAS is designed as an enterprise-wide PACS to provide images and reports throughout the Strong Health healthcare network. Phase II includes the addition of a Cemax-Icon (Fremont, CA) archive, PACS broker (Mitra, Waterloo, Canada), an interface (IDX PACSlink, Burlington, VT) to the RIS (IDXrad) plus the conversion of the UNIX-based redundant array of inexpensive disks (RAID) 5 temporary archives in phase I to NT-based RAID 0 DICOM modality-specific study caches (ImageLabs, Bedford, MA). The phase I acquisition engines and workflow management software was uninstalled and the Cemax archive manager (AM) assumed these functions. The existing ImageLabs UNIX-based viewing software was enhanced and converted to an NT-based DICOM viewer. Installation of phase II hardware and software and integration with existing components began in July 1998. Phase II of MICAS demonstrates that a multivendor open-system incremental approach to PACS is feasible, cost-effective, and has significant advantages over a single-vendor implementation.

Compact Disks↗
PubMed2026

PASTA: versatile tyramide-oligonucleotide amplification for multimodal spatial biology.

Spatial proteomics is limited by detection sensitivity, multiplexing and multimodal integration, leaving a gap between discovery and clinical assays. Here we present protein and nucleic acid serial tyramide amplification (PASTA), using horseradish peroxidase-mediated oligonucleotide deposition and cyclical imaging for high-plex, multimodal spatial profiling. Compatible with conjugated antibodies and in situ hybridization, PASTA enables simultaneous protein and RNA codetection from formalin-fixed, paraffin-embedded samples, providing a cost-effective bridge from discovery to clinical validation.

Tyramine↗
PubMed2002

Temporal bone dissection simulation--an update.

We report on our continued development of a virtual simulation for temporal bone dissection that provides stereoscopic display, haptic feedback, and aural simulation into a straightforward, comprehensive learning environment. The multimodal interface provides a seamless simulation for non-deterministic drilling and cutting of bone in the surgical context, as well as an intuitive interface for the intelligent tutor for learning regional anatomy. We present novel methodologies for integrating multimodal and multiresolution data sets, including extension to functional and structural segmentation. We will present our initial efforts to validate this environment. Through continued iterations, it is our hope that the system will provide a valuable tool for training future otologic surgeons as well as an environment for the quantitative evaluation of surgical skill.

Aged↗
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↗
PubMed2026

AI-Based 3D Heterogeneous Network Model for Functional Prediction of Epigenetics.

Human biology and diseases are the result of constantly evolving processes within an intricately complex molecular network of interactions, such as epigenetic regulation. Epigenetics refers to heritable changes in gene expression that occur without alterations to the underlying DNA sequence. These changes, driven by mechanisms such as DNA methylation, histone modifications, and noncoding RNAs, play critical roles in regulating chromatin structure and gene activity. Epigenetic regulation offers valuable insights into biological systems, and when integrated with sophisticated analyses, it enables us to gain insights into gene regulation and cellular behavior. Here, we describe an artificial intelligence (AI)-based model that is capable of generating 3-dimensional (3D) heterogeneous network by integrating multimodal data for the functional prediction of epigenetic mechanisms, emphasizing its applications in medicine, developmental biology, and personalized therapeutics. Heterogeneous networks in biology are powerful tools for understanding the complex interactions and interdependencies within biological systems. Key advancements in AI and multiomics data integration have propelled this field, offering new insights into disease mechanisms, biomarker discovery, and therapeutic interventions.

Epigenesis, Genetic↗
PubMed2005

Multimodal imaging of brain reorganization in motor areas of the contralesional hemisphere of well recovered patients after capsular stroke.

Clinical recovery after stroke can be significant and has been attributed to plastic reorganization and recruitment of novel areas previously not engaged in a given task. As equivocal results have been reported in studies using single imaging or electrophysiological methods, here we applied an integrative multimodal approach to a group of well-recovered chronic stroke patients (n = 11; aged 50-81 years) with left capsular lesions. Focal activation during recovered hand movements was assessed with EEG spectral analysis and H2(15)O-PET with EMG monitoring, cortico-cortical connectivity with EEG coherence analysis (cortico-cortical coherence) and corticospinal connectivity with transcranial magnetic stimulation (TMS). As seen from comparisons with age-matched controls, our patients showed enhanced recruitment of the lateral premotor cortex of the lesioned hemisphere [Brodmann area (BA) 6], lateral premotor and to a lesser extent primary sensorimotor and parietal cortex of the contralesional hemisphere (CON-H; BA 4 and superior parietal lobule) and left cerebellum (patients versus controls, Z > 3.09). EEG coherence analysis showed that after stroke cortico-cortical connections were reduced in the stroke hemisphere but relatively increased in the CON-H (ANOVA, contrast analysis, P < 0.05), suggesting a shift of functional connectivity towards the CON-H. Nevertheless, fast conducting corticospinal transmission originated exclusively from the lesioned hemisphere. No direct ipsilateral motor evoked potentials (MEPs) could be elicited with TMS over the contralesional primary motor cortex (iM1) in stroke patients. We conclude that (i) effective recovery is based on enhanced utilization of ipsi- and contralesional resources, (ii) basic corticospinal commands arise from the lesioned hemisphere without recruitment of ('latent') uncrossed corticospinal tract fibres and (iii) increased contralesional activity probably facilitates control of recovered motor function by operating at a higher-order processing level, similar to but not identical with the extended network concerned with complex movements in healthy subjects.

Aged↗
PubMed2026

Beyond antibiotics: artificial intelligence-enabled anti-infective ecosystems for next-generation precision therapeutics against antimicrobial resistance.

The rapid global expansion of antimicrobial resistance (AMR) threatens to undermine decades of progress in infectious disease management and highlights the limitations of conventional antibiotic-centered therapeutic strategies. Although emerging technologies-including antimicrobial peptides, bacteriophage therapy, CRISPR-based antimicrobials, microbiome therapeutics, anti-virulence approaches, nanotechnology-enabled drug delivery, and artificial intelligence (AI)-have individually demonstrated considerable promise, they are predominantly being developed as independent interventions rather than as coordinated components of an integrated therapeutic strategy. This Perspective proposes the Intelligent Anti-Infective Ecosystem (IAIE) as a conceptual systems-level framework that computationally integrates multimodal diagnostics, pathogen genomics, microbiome profiling, AI-assisted decision support, programmable precision therapeutics, ecological monitoring, and longitudinal clinical feedback within a continuously learning dynamically optimized workflow. Unlike existing paradigms that primarily optimize individual technologies or therapeutic decisions, IAIE emphasizes closed-loop coordination among complementary antimicrobial approaches to support precision-guided infection management while preserving microbiome integrity and mitigating resistance selection pressure. We further outline the core components, operational principles, translational challenges, and technology readiness of the major therapeutic platforms that could contribute to such an ecosystem, while distinguishing clinically established interventions from emerging experimental strategies. Importantly, IAIE should be interpreted as a prospective conceptual architecture rather than an existing clinical platform. Its proposed clinical value remains to be established through sequential computational, preclinical, and prospective clinical investigations using standardized microbiological, ecological, and patient-centered outcome measures. By framing antimicrobial innovation within an responsive systems perspective, IAIE provides a roadmap for future multidisciplinary research aimed at integrating artificial intelligence and systems microbiology to enable sustainable management of antimicrobial resistance.

Humans↗
PubMed1994

Integrating human brain maps.

Perception, action, cognition, and emotion can now be mapped in the brain by a growing family of techniques. Positron emission tomography, functional magnetic resonance imaging, event-related electrical potentials, event-related magnetic fields, and other non-invasive imaging techniques are rapidly evolving and providing an increasingly rich literature on the functional organization of the human brain. Although no two techniques map identical physiological processes or physical parameters, replications of functionally specific maps by different techniques indicate sufficient common ground for multimodality integration. The process of integration is multi-tiered. Recent advances in integration range from simple image fusion, to model-based synthetic analyses, to collective databases for neural-system modeling. Spatially, temporally, physiologically, and cognitively accurate computational models of the neural systems of human behavior are the ultimate objective of functional brain mapping. This objective will be reached only through integrating the diversity of modern brain-mapping methods.

Brain Mapping↗
PubMed1983

Multimodality treatment of adenocarcinoma of the vagina Stage IV: potential for cure.

A 26-year-old nulligravida presented with a Stage IV adenocarcinoma of the vagina with a frozen pelvis and positive lymph nodes in the right external iliac and inguinal regions. Following transposition of the ovaries laterally, a successful treatment program of cyclic radiotherapy and 5-fluorouracil was undertaken. Patient is now alive 3 years posttherapy with a functional vagina, return of menses, and without evidence of tumor. She experienced a small-bowel stricture 5 months posttherapy which required small-bowel resection. This case suggests that an integrated multimodality program is feasible and that 5-fluorouracil may be synergistic with radiation.

Adenocarcinoma, Mucinous↗
PubMed2026

Combining neuromelanin-sensitive MRI and quantitative susceptibility mapping for enhanced diagnosis and differentiation of parkinson's disease: A systematic review.

BACKGROUND: Loss of dopaminergic neurones and iron deposition in the substantia nigra pars compacta (SNpc) are two major pathological hallmarks of Parkinson's disease (PD). Such changes can be visualised by advanced techniques including neuromelanin-sensitive MRI (NM-MRI) and quantitative susceptibility mapping (QSM). This systematic review investigates the diagnostic performance and methodological development of the integrated use of NM-MRI and QSM in PD. METHODS: The systematic search was performed in four databases (Scopus, PubMed, ScienceDirect, and Web of Science) according to the PRISMA 2020 guidelines until July 2026. Bias was assessed using QUADAS-2 and certainty of evidence was assessed using GRADE. RESULTS: Seventeen studies with 2228 participants were included. Combined NM-MRI and QSM consistently showed reduced neuromelanin volume/contrast and increased iron deposition in the SNpc of PD patients compared to healthy controls. Multimodal integration yielded a significant improvement in diagnostic accuracy (AUC values 0.86-0.99), and was able to successfully differentiate PD. Recent methodological advances included simultaneous acquisition sequences (e.g. MTC-GRE, STAGE, setMag) and AI-driven automated segmentation, which led to significantly reduced scan times and improved reproducibility. CONCLUSION: The combination of NM-MRI and QSM has a synergistic effect and provides powerful complementary biomarkers for the diagnosis and differential diagnosis of PD.

Humans↗
PubMed1998

A visuo-somatomotor pathway through superior parietal cortex in the macaque monkey: cortical connections of areas V6 and V6A.

This report addresses the connectivity of the cortex occupying middle to dorsal levels of the anterior bank of the parieto-occipital sulcus in the macaque monkey. We have previously referred to this territory, whose perimeter is roughly circumscribed by the distribution of interhemispheric callosal fibres, as area V6, or the 'V6 complex'. Following injections of wheatgerm agglutinin conjugated to horseradish peroxidase (WGA-HRP) into this region, we examined the laminar organization of labelled cells and axonal terminals to attain indications of relative hierarchical status among the network of connected areas. A notable transition in the laminar patterns of the local, intrinsic connections prompted a sub-designation of the V6 complex itself into two separate areas, V6 and V6A, with area V6A lying dorsal, or dorsomedial to V6 proper. V6 receives ascending input from V2 and V3, ranks equal to V3A and V5, and provides an ascending input to V6A at the level above. V6A is not connected to area V2 and in general is less heavily linked to the earliest visual areas; in other respects, the two parts of the V6 complex share similar spheres of connectivity. These include regions of peripheral representation in prestriate areas V3, V3A and V5, parietal visual areas V5A/MST and 7a, other regions of visuo-somatosensory association cortex within the intraparietal sulcus and on the medial surface of the hemisphere, and the premotor cortex. Subcortical connections include the medial and lateral pulvinar, caudate nucleus, claustrum, middle and deep layers of the superior colliculus and pontine nuclei. From this pattern of connections, it is clear that the V6 complex is heavily engaged in sensory-motor integration. The specific somatotopic locations within sensorimotor cortex that receive this input suggest a role in controlling the trunk and limbs, and outward reaching arm movements. There is a secondary contribution to the brain's complex oculomotor circuitry. That the medial region of the cortex is devoted to tightly interconnected representations of the sensory periphery, both visual and somatotopic-which are routinely stimulated in concert-would appear to be an aspect of the global organization of the cortex which must facilitate multimodal integration.

Animals↗
PubMed2002

Evidence for widespread movement-associated functional MRI changes in patients with PPMS.

BACKGROUND: Previous work has suggested that functional reorganization of cortical motor areas might have a role in limiting the motor deficits in patients with MS. OBJECTIVE: To test whether movement-associated cortical changes in MS might extend beyond the "classic" motor areas and involve sites for multimodal integration. METHODS: fMRI was used to assess patterns of brain activations associated with 3 different motor tasks in 30 right-handed patients with primary progressive MS (PPMS) and variable degrees of motor impairment, which were compared with those from 15 right-handed, sex- and age-matched control subjects. RESULTS: Compared with control subjects, patients with MS showed increased activation of brain regions within both traditional motor planning and execution regions (including the supplementary motor area and the cingulate motor area), the insula (a region implicated in sensory processing), and several multimodal cortical regions in the temporal, parietal, and occipital lobes. In patients, the extent of the fMRI activations was strongly correlated with MR lesion burden (r ranging from 0.70 to 0.86, p < 0.001). CONCLUSIONS: This study shows that movement-associated cortical activation in patients with PPMS is widely distributed and also involves multimodal "nonmotor" cortical networks. It also suggests that adaptive cortical reorganization might be one of the mechanisms limiting the clinical impact of MS in the progressive phases of the disease.

Adult↗
PubMed1996

Improving treatment planning accuracy through multimodality imaging.

PURPOSE: In clinical practice, physicians are constantly comparing multiple images taken at various times during the patient's treatment course. One goal of such a comparison is to accurately define the gross tumor volume (GTV). The introduction of three-dimensional treatment planning has greatly enhanced the ability to define the GTV, but there are times when the GTV is not visible on the treatment-planning computed tomography (CT) scan. We have modified our treatment-planning software to allow for interactive display of multiple, registered images that enhance the physician's ability to accurately determine the GTV. METHODS AND MATERIALS: Images are registered using interactive tools developed at the University of North Carolina at Chapel Hill (UNC). Automated methods are also available. Images registered with the treatment-planning CT scan are digitized from film. After a physician has approved the registration, the registered images are made available to the treatment-planning software. Structures and volumes of interest are contoured on all images. In the beam's eye view, wire loop representations of these structures can be visualized from all image types simultaneously. Each registered image can be seamlessly viewed during the treatment-planning process, and all contours from all image types can be seen on any registered image. A beam may, therefore, be designed based on any contour. RESULTS: Nineteen patients have been planned and treated using multimodality imaging from November 1993 through August 1994. All registered images were digitized from film, and many were from outside institutions. Brain has been the most common site (12), but the techniques of registration and image display have also been used for the thorax (4), abdomen (2), and extremity (1). The registered image has been an magnetic resonance (MR) scan in 15 cases and a diagnostic CT scan in 5 cases. In one case, sequential MRs, one before treatment and another after 30 Gy, were used to plan patient's initial fields and boost, respectively. Case illustrations are shown. CONCLUSIONS: We have successfully integrated multimodality imaging into our treatment-planning system, and its routine use is increasing. Multimodality imaging holds out the promise of improving treatment planning accuracy and, thus, takes maximum advantage of three dimensional treatment planning systems.

Humans↗
PubMed1997

Germ cell tumours---local perspectives on a curable cancer.

Germ cell tumours are among the most curable solid cancers and have become a model for the multimodality approach in oncology. The experience of two institutions in Hong Kong involving 149 Chinese patients with testicular germ cell tumours and 10 patients with mediastinal germ cell tumours was reviewed and the overall results were found to be comparable with the global experience. Treatment strategies suitable for the local population are discussed. The earlier identification of patients with metastatic non-seminomatous germ cell tumours who have a poor prognosis, may be important in selecting patients for more intensive treatment such as high dose chemotherapy. With mediastinal germ cell tumours, survival is poorer and improved treatment results may only be possible with increased understanding of the biological abnormalities involved. An integrated multimodality approach to the diagnosis and treatment of this disease is vital to attain optimal management. For these reasons, it is recommended that all patients with germ cell tumours be referred to cancer centres where cross-specialty expertise and experience are available to manage these patients.

Journal Article↗
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↗