Multimodal deep learning for biomedical data fusion: a review
Open accessThe DOI matches its Crossref record; 107 of the 117 references it cites were found in a registry or an index; 60 of the 96 sources its claims cite were checked for support.
Abstract
Biomedical data are becoming increasingly multimodal and thereby capture the underlying complex relationships among biological processes. Deep learning (DL)-based data fusion strategies are a popular approach for modeling these nonlinear relationships. Therefore, we review the current state-of-the-art of such methods and propose a detailed taxonomy that facilitates more informed choices of fusion strategies for biomedical applications, as well as research on novel methods. By doing so, we find that deep fusion strategies often outperform unimodal and shallow approaches. Additionally, the proposed subcategories of fusion strategies show different advantages and drawbacks. The review of current methods has shown that, especially for intermediate fusion strategies, joint representation learning is the preferred approach as it effectively models the complex interactions of different levels of biological organization. Finally, we note that gradual fusion, based on prior biological knowledge or on search strategies, is a promising future research path. Similarly, utilizing transfer learning might overcome sample size limitations of multimodal data sets. As these data sets become increasingly available, multimodal DL approaches present the opportunity to train holistic models that can learn the complex regulatory dynamics behind health and disease.
Overview
CoChat Summary
TL;DR
This review surveys deep learning-based multimodal biomedical data fusion and proposes a taxonomy of early, intermediate, and late fusion strategies. It finds that deep fusion often outperforms unimodal and shallow approaches, with intermediate joint representation learning preferred, while gradual fusion and transfer learning remain underexplored.
Key findings
- The paper proposes a taxonomy dividing fusion into early fusion (direct modeling, autoencoder subcategories), intermediate fusion (homogeneous/heterogeneous designs; marginal/joint representations), and late fusion (averaging equal/weighted, meta-learning).
- Deep fusion strategies frequently outperform unimodal and shallow methods; joint intermediate fusion is the preferred approach because it effectively models complex interactions across levels of biological organization.
- Early fusion is simple but may miss cross-modal relationships apparent only at higher abstraction; intermediate fusion offers flexibility for heterogeneity, missing modalities, and dimensionality imbalance; late fusion combines decisions but cannot learn feature-level cross-modal interactions.
- Gradual fusion guided by prior biological knowledge or search strategies and transfer learning are promising future paths; reviewed applications included sample sizes as low as 96 patients.
Methods
- Narrative literature review of deep learning-based data fusion strategies in the biomedical domain, taking a representation learning perspective.
- Proposes a detailed taxonomy of early, intermediate, and late fusion and their subcategories, exemplified with published biomedical applications.
- No primary dataset, systematic search protocol, or quantitative meta-analysis is described; synthesis is conceptual and qualitative.
Limitations
- The paper states the literature is most likely skewed toward reporting positive results, performance of fusion strategies is problem- and data-specific, and more theoretical knowledge is needed to specify when strategies excel.
- The paper states multimodal DL faces general challenges including data volume, quality, interpretability, temporality, missing entire modalities, and overfitting/generalizability due to small sample sizes and many parameters.
- Evident from the text: as a narrative review, it does not report a systematic search strategy or quantitative comparison across studies.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures
![Figure 1 Development of technologies and multimodal deep learning (DL). ‘Omics’ and ‘multi-omics’ data become increasingly relevant in the scientific literature. To fully utilize the growing number of multimodal data sets, data fusion methods based on DL are evolving into an important approach in the biomedical field. This unprecedented generation of data has been made possible by high-throughtput technologies like microarrays and next-generation sequencing [7]. The development of bulk RNA-seq was followed by several related sequencing technologies, such as single-cell RNA-seq and ATAC-seq [8]. Currently, spatial transcriptomics [9] and single-cell multi-omics [10] are being increasingly used.](https://figures.cochat.ai/paper-figures/5c1e0ae86d784af8937add9f4a2f8906/multimodal-deep-learning-for-biomedical-data-fusion-a-review-figure-1.jpg)
![Figure 2 DL-based fusion strategies. Layers marked in blue are shared between modalities and learn joint representations. (a) Early fusion strategies take as input a concatenated vector. No marginal representations are learned. (b) Intermediate fusion strategies first learn marginal representations and fuse these later inside the network. This can occur in one layer or gradually. (c) Late fusion strategies combine decisions by sub-models for each modality. Figure adapted from [2].](https://figures.cochat.ai/paper-figures/73c64526f30e41a695c45c40cae87d27/multimodal-deep-learning-for-biomedical-data-fusion-a-review-figure-2.jpg)


Verification
Claims the paper makes
40 Valid · 5 Not valid · 23 Not checked · 87 Own results and interpretations
Some cited sources support this claim and some don’t — read each source’s verdict below.
In the paper
“Despite the aforementioned drawbacks, some reviewed papers have shown that early fusion AEs can perform on par with intermediate strategies [38, 41]”
§ Multimodal deep learning for biomedical data fusion: a review > Early fusion > Discussion of early fusion strategies
What the sources say
- Disputedcites [38] Islam, 2020, An integrative deep learning framework for classifying molecular subtypes of breast cancer, Comput Struct Biotechnol J sourceExperimental — accuracy not yet measured
The Methods section describes an early-fusion stacked autoencoder that takes concatenated CNA and gene-expression data as input, alongside a DCNN_Concat model that combines features learned separately from each source. The Results section (page unavailable) says DCNN_Concat performed better than the autoencoder-based DNN_SE, rather than reporting that they performed on par. (LLM, conf=0.86)
Checked by a reasoning model — may be wrong.
- Supportedcites [41] Simidjievski, 2019, Variational autoencoders for cancer data integration: design principles and computational practice, Front Genet source
The Methods section describes CNC-VAE as combining data at the input and the other architectures as integrating data in hidden layers. In Results > Quality of the Learned Representations (page unavailable), H-VAE and X-VAE mostly produced more accurate predictions, but the differences among the four architectures were not significant. This supports the claim that an early-fusion AE can perform on par with intermediate strategies in the tasks studied. (LLM, conf=0.89)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Disputed
Every source the paper cites for this claim was checked and supports it.
In the paper
“Questioning this assumption is relevant as many methods have shown unequal contribution of different modalities to the predictive performance (see for example [36, 42]).”
§ Multimodal deep learning for biomedical data fusion: a review > Late fusion
What the sources say
- Supportedcites [36] Chai, 2021, Integrating multi-omics data through deep learning for accurate cancer prognosis prediction, Comput Biol Med source
The Conclusion and Discussion reports an ablation study in which mRNA performed best, followed by miRNA and methylation, while copy-number variation contributed least. Table 3 also shows different C-index values when individual omics types are used or excluded, supporting unequal contributions to predictive performance. (LLM, conf=0.92)
- Supportedcites [42] Albaradei, 2021, Meta cancer: a deep learning-based pan-cancer metastasis prediction model developed using multi-omics data, Comput Struct Biotechnol J source
In “Evaluating the contribution of different omics data types” (page not supplied), MetaCancer reports different predictive contributions from mRNA, DNA methylation and microRNA. The section also describes similar differences in other studies, supporting its use as an example of the claim. (LLM, conf=0.91)
boostedstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“However, different modalities can add information to different degrees (e.g. [36, 44]).”
§ Multimodal deep learning for biomedical data fusion: a review > Early fusion > Discussion of early fusion strategies
What the sources say
- Supportedcites [36] Chai, 2021, Integrating multi-omics data through deep learning for accurate cancer prognosis prediction, Comput Biol Med source
The ‘Patients’ risks estimation by multi-omics data’ section compares the contributions of individual omics types: mRNA contributed most to prognosis prediction, while copy number variation contributed least. This supports the claim that different modalities add information to different degrees. (LLM, conf=0.93)
- Supportedcites [44] Lee, 2019, Alzheimer’s disease neuroimaging initiative. Predicting Alzheimer’s disease progression using multi-modal deep learning approach, Sci Rep source
The Results section, in its comparison of single-modality and multimodal predictions, reports that cognitive-performance data predicted conversion more accurately than the other individual modalities, while demographic data performed too poorly to include in the figure. Table 5 also shows different accuracies across modalities and higher accuracy for the combined model. The supplied passages have no page numbers. (LLM, conf=0.91)
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Vale-Silva et al. [74] compared these methods, although they did not find large differences in performance for predicting long-term cancer survival.”
§ Multimodal deep learning for biomedical data fusion: a review > Intermediate fusion > Heterogeneous network design
What the sources say
- Partly supportedcites [74] Vale-Silva, 2021, Long-term cancer survival prediction using multimodal deep learning, Sci Rep sourceExperimental — accuracy not yet measured
The Methods section (“Multimodal data fusion layer”; page unavailable) says MultiSurv used a row-wise maximum to combine modality representations and tested alternative fusion schemes without improving performance. It does not identify those alternatives in our copy or establish that performance differences among them were small. (LLM, conf=0.82)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Particularly in cancer patient survival subtyping with multi-omics modalities, this sequence of steps has become popular [25–31, 34].”
§ Multimodal deep learning for biomedical data fusion: a review > Early fusion > Latent representation with multimodal AEs
What the sources say
- Supportedcites [25] Chaudhary, 2018, Deep learning-based multi-omics integration robustly predicts survival in liver cancer, Clin Cancer Res source
In Results, the paper describes integrating three omics data types with an autoencoder, selecting bottleneck features using univariate Cox-PH regression, and inferring survival-subtype labels through K-means clustering. It therefore exemplifies the sequence for which it is cited; the citation need not establish popularity on its own. (LLM, conf=0.92)
- Partly supportedcites [26] Lv, 2020, Survival prediction in patients with colon adenocarcinoma via multiomics data integration using a deep learning algorithm, Biosci Rep sourceExperimental — accuracy not yet measured
The Results section ('Identification of two survival risk groups in TCGA multiomics data'; page unavailable) describes the stated sequence: an autoencoder transformed multiomics features, univariable Cox-PH regression selected survival-associated features, and K-means clustering inferred two groups. This establishes that the paper uses the sequence, but not that it has become popular; the Introduction instead describes deep-learning applications in prognostic modeling as being in their infancy. (LLM, conf=0.85)
- Partly supportedcites [27] Zhang, 2018, Deep learning-based multi-omics data integration reveals two prognostic subtypes in high-risk neuroblastoma, Front Genet sourceExperimental — accuracy not yet measured
The Materials and methods sections (pages unavailable) describe multi-omics features generated by an autoencoder, subsequent Cox regression to select prognostic features, and K-means clustering to infer survival-risk labels. The paper does not establish that this full sequence has become popular, and the passages do not specify that the post-autoencoder Cox modeling was univariate. (LLM, conf=0.83)
- Partly supportedcites [28] Yu, 2020, A model for predicting prognosis in patients with esophageal squamous cell carcinoma based on joint representation learning, Oncol Lett sourceExperimental — accuracy not yet measured
The Materials and methods section (page unavailable) describes joint multimodal autoencoder features, univariate Cox-PH feature selection, and K-means clustering to infer survival-risk subgroup labels. The paper therefore exemplifies the sequence, but it does not establish that the full sequence had become popular in multi-omics cancer survival subtyping. (LLM, conf=0.83)
- Supportedcites [29] Asada, 2020, Uncovering prognosis-related genes and pathways by multi-omics analysis in lung cancer, Biomol Ther source
The Methods section (2.2) describes an autoencoder followed by univariate Cox-PH feature selection and K-means clustering to infer labels. The Discussion (section 4) identifies this as the paper’s multi-omics pipeline for lung-cancer survival subtyping, so the paper supports its use as an example of the cited sequence. (LLM, conf=0.90)
- Supportedcites [30] Zhang, 2021, Robust prognostic subtyping of muscle-invasive bladder cancer revealed by deep learning-based multi-omics data integration, Front Oncol source
The Results section, “The Identification of OS-Related Subtypes Based on TCGA Multi-Omics Data,” describes the claimed sequence: autoencoder-derived multi-omics features, univariate Cox selection of survival-related features, and K-means clustering to assign subtypes. The paper therefore serves as an example of the approach cited alongside other studies; it does not independently establish how popular the approach is. (LLM, conf=0.89)
- Not checked — no full text of the sourcecites [31] Lee, 2020, Incorporating deep learning and multi-omics autoencoding for analysis of lung adenocarcinoma prognostication, Comput Biol Chem source
- Supportedcites [34] Zhao, 2020, Deep learning-based model for predicting progression in patients with head and neck squamous cell carcinoma, Cancer Biomark source
Section 3.1 describes combining three omics modalities in an autoencoder, selecting survival-associated features by univariate Cox-PH regression, and using K-means clustering to identify patient subtypes. Section 2.3 explicitly lays out the autoencoder → Cox-PH selection → clustering sequence. The paper therefore exemplifies the approach for which it is cited. (LLM, conf=0.91)
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
91 more claims · 26 with their cited sources checked
Create a free account to see all 155 claims and to verify the 4 references still open.
- It may state two separate claims as one. 19
- Probably not a substantial claim. 43
- The quote only partly states this claim. 2
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source doesn’t support the claim as written.
In the citing paper
“This method has consistently demonstrated superior performance compared to early and late fusion strategies across diverse clinical applications14–16.”
From MoMA: a mixture-of-multimodal-agents architecture for enhancing clinical prediction modelling (2025) · cites this paper as [15]
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“However, each of these public datasets, as well as the private datasets used in included studies, contains no more than 280 subjects (with sample sizes ranging from 24 to 275), which hampers the ability to identify clinical biomarkers universally and reliably, especially with DL approaches132,133.”
From AI-assisted multi-modal information for the screening of depression: a systematic review and meta-analysis (2025) · cites this paper as [132]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“DL architectures are well-suited for intermediate fusion as they enable an easy connection of marginal representations to a shared layer, facilitating the correspondence of hierarchical representations to real-world phenomena (Stahlschmidt et al. 2022).”
From A review of multimodal deep learning methods for genomic-enabled prediction in plant breeding (2024) · cites this paper as Stahlschmidt et al. 2022
The cited source says what the claim attributes to it.
In the citing paper
“This approach assumes an equal contribution from each sub-model, as there is no weighting of their outputs (Stahlschmidt et al. 2022).”
From A review of multimodal deep learning methods for genomic-enabled prediction in plant breeding (2024) · cites this paper as Stahlschmidt et al. 2022
The cited source says what the claim attributes to it.
In the citing paper
“Stahlschmidt et al. summarized multimodal fusion methods in biomedical analysis [31]”
From Challenges in AI-driven Biomedical Multimodal Data Fusion and Analysis (2025) · cites this paper as [31]
1 more claim about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Regression Models and Life-Tables
Cox, D. R. (1972) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1972.tb00899.x · Cited by 39,793
A fast learning algorithm for deep belief nets
Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006) · Neural Computation · doi:10.1162/neco.2006.18.7.1527 · Cited by 16,336 · cited 1×
“Alternatively, the representations can serve as a useful and computationally efficient initialization of a DNN, which is fine-tuned with more expensive supervised algorithms such as back propagation to learn p(y|x) [94].”
MethodRepresentation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001 · cited 3×
“Earlier layers learn simple abstractions of the data, whereas deeper layers combine these into more abstract representations that are informative for the learning task [13].”
BackgroundInfluentialA Comprehensive Survey on Graph Neural Networks
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. S. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2978386 · Cited by 11,000
Extracting and composing robust features with denoising autoencoders
Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P.-A. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390294 · Cited by 7,436 · cited 1×
“For the same clinical task, a similar workflow has been adapted by researchers, but applying denoising AEs (DAEs) [91] instead [35, 36].”
MethodGrad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01228-7 · Cited by 6,909 · cited 2×
“[79] enabled modality-specific interpretability by applying Grad-CAM [97] for WSI and integrated gradient [98] for cell graph and genomic modalities using convolutional, graph convolutional [14] and fully connected branches.”
MethodLarge-Scale Video Classification with Convolutional Neural Networks
Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., & Fei-Fei, L. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.223 · Cited by 6,354 · cited 1×
“Despite the aforementioned drawbacks, some reviewed papers have shown that early fusion AEs can perform on par with intermediate strategies [38, 41], though other structured investigations inside [28] and outside [93] the biomedical domain have shown superiority of intermediate fusion over early fusion strategies.”
BackgroundMultimodal Machine Learning: A Survey and Taxonomy
Baltrusaitis, T., Ahuja, C., & Morency, L.-P. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2798607 · Cited by 5,018 · cited 5×
“Thereby, coordinated representations [11] of each modality could be learned in an unsupervised way, which resulted in encodings of patterns between modalities.”
BackgroundInfluentialVisualization and analysis of gene expression in tissue sections by spatial transcriptomics
Ståhl, P. L., Salmén, F., Vickovic, S., Lundmark, A., Navarro, J. F., Magnusson, J., Giacomello, S., Asp, M., Westholm, J. O., Huss, M., et al. (2016) · Science · doi:10.1126/science.aaf2403 · Cited by 3,834 · cited 1×
“Currently, spatial transcriptomics [9] and single-cell multi-omics [10] are being increasingly used.”
Method
Research works printed but not linked: 6
- Springer Nature. Milestones in Genomic Sequencing
- Goodfellow, 2016, Deep Learning
- Ballard, 1987, Modular learning in neural networks. In: Proceedings of the Sixth National Conference on Artificial Intelligence, 279
- Kingma, 2014, Proceedings of the International Conference on Learning Representations (ICLR)
- Alemi, 2017, 5th International Conference on Learning Representations
- Sundararajan, 2017, 34th International Conference on Machine Learning, 5109
Cited by
Items 101–200 of 749
An integrated chemical engineering approach to understanding microplastics
Bang, R. S., Bergman, M. T., Li, T., Mukherjee, F., Alshehri, A. S., Abbott, N. L., Crook, N., Velev, O. D., Hall, C. K., & You, F. (2023) · AIChE Journal · doi:10.1002/aic.18020 · Cited by 25
Shen, W., Tang, H.-W., Li, J., Li, X., & Chen, S. (2023) · Journal of Cheminformatics · doi:10.1186/s13321-022-00675-8 · Cited by 25
“Currently, multimodal data fusion has been widely used in other fields, but there is a lack of exploration in ligand-based drug screening [18].”
BackgroundZhou, C., Zhang, Y., Guo, S. J., Huang, Y., Qiao, X.-N., Wang, R., Zhao, L., Chang, D., Zhao, L.-M., Da, M., et al. (2024) · Frontiers in Oncology · doi:10.3389/fonc.2024.1287995 · Cited by 31
“Clinical outcomes, such as survival, response to treatment, and recurrence, may be accurately predicted using AI models that use multimodal data (12 – 14).”
BackgroundColour fusion effect on deep learning classification of uveal melanoma
Dadzie, A. K., Iddir, S. P., Abtahi, M., Ebrahimi, B., Le, D., Ganesh, S., Son, T., Heiferman, M. J., & Yao, X. (2024) · Eye · doi:10.1038/s41433-024-03148-4 · Cited by 32
Hyperdimensional computing: A fast, robust, and interpretable paradigm for biological data
Stock, M., Criekinge, W. V., Boeckaerts, D., Taelman, S., Haeverbeke, M. V., Dewulf, P., & Baets, B. D. (2024) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1012426 · Cited by 28
“We refer to [23] for a more comprehensive survey.”
BackgroundAddressing data scarcity in speech emotion recognition: A comprehensive review
Kakuba, S., & Han, D. S. (2024) · ICT Express · doi:10.1016/j.icte.2024.11.003 · Cited by 24
Advancements in Medical Radiology Through Multimodal Machine Learning: A Comprehensive Overview
Haq, I. U., Mhamed, M., Alharbi, M., Osman, H., Hamd, Z. Y., & Liu, Z. (2025) · Bioengineering · doi:10.3390/bioengineering12050477 · Cited by 40
Deep learning in bladder cancer imaging: A review
Li, M., Jiang, Z., Shen, W., & Liu, H. (2022) · Frontiers in Oncology · doi:10.3389/fonc.2022.930917 · Cited by 33
“Multimodal approaches have been shown to outperform unimodal ones (74).”
BackgroundData-Centric Foundation Models in Computational Healthcare: A Survey
Zhang, Y., Gao, J. G., Tan, Z., Zhou, L., Ding, K., Zhou, M., Zhang, S., & Wang, D. (2026) · ACM Computing Surveys · doi:10.1145/3800677 · Cited by 74
Lin, J., Yang, J., Yin, M., Tang, Y., Chen, L., Xu, C., Zhu, S., Gao, J., Liu, L., Liu, X., et al. (2024) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-024-01066-1 · Cited by 27
“In addition, multimodal fusion effectively exploits the complementary, redundant, and cooperative features of single-modal information [9].”
Chen, J., Zhou, X., Feng, L., Ling, B. W., Han, L., & Zhang, H. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3483301 · Cited by 24
Lee, H.-T., Shim, M., Liu, X., Cheon, H.-R., Kim, S., Han, C. H., & Hwang, H.-J. (2025) · Biomedical Engineering Letters · doi:10.1007/s13534-025-00469-5 · Cited by 41
“Depending on the stage of data integration, fusion strategies can be classified into three categories: early fusion, interme - diate fusion, and late fusion [85, 86].”
Unveiling the frontiers of deep learning: Innovations shaping diverse domains
Ahmed, S. F., Alam, M. S. B., Kabir, M., Afrin, S., Rafa, S. J., Mehjabin, A., & Gandomi, A. H. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06259-x · Cited by 39
AI-driven multimodal colorimetric analytics for biomedical and behavioral health diagnostics
Hagos, D. H., Aryal, S. K., Ymele‐Leki, P., & Burge, L. (2025) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2025.05.015 · Cited by 29
Deep Learning in Environmental Toxicology: Current Progress and Open Challenges
Tan, H., Jin, J., Fang, C., Zhang, Y., Chang, B., Zhang, X., Yu, H., & Shi, W. F. (2023) · ACS ES&T Water · doi:10.1021/acsestwater.3c00152 · Cited by 26
Verma, S., Magazzù, G., Eftekhari, N., Lou, T., Gilhespy, A., Occhipinti, A., & Angione, C. (2024) · Cell Reports Methods · doi:10.1016/j.crmeth.2024.100817 · Cited by 31
“108,109 Because of the heterogeneity of the data types (multi-dimensional images and high-dimensional gene expression), an early integration approach is often infeasible.”
Enhancing foundation models for scientific discovery via multimodal knowledge graph representations
López, V., Hoang, L. T., Galindo, M. M., Fernández-Díaz, R., Sbodio, M. L., Ordóñez-Hurtado, R., Zayats, M., Mulligan, N., & Bettencourt‐Silva, J. H. (2024) · Journal of Web Semantics · doi:10.1016/j.websem.2024.100845 · Cited by 28
Application of deep learning-based multimodal fusion technology in cancer diagnosis: A survey
Li, Y., Pan, L., Peng, Y., Li, X., Wang, X., Qu, L., Song, Q., Liang, Q., & Peng, S. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109972 · Cited by 28
Advancing microbial risk assessment: perspectives from the evolution of detection technologies
Xiao, L., Zhao, L., Dou, X., Long, Y., Li, Z., Liu, Y., & Dong, Q. (2025) · npj Science of Food · doi:10.1038/s41538-025-00527-3 · Cited by 26
Deep Learning‐Based Multiomics Data Integration Methods for Biomedical Application
Wen, Y., Zheng, L., Leng, D., Dai, C., Jing, L., Zhang, Z., He, S., & Bo, X. (2023) · Advanced Intelligent Systems · doi:10.1002/aisy.202200247 · Cited by 23
Chun, J., & Kim, H. (2023) · Journal of Korean Medical Science · doi:10.3346/jkms.2023.38.e253 · Cited by 29
“43 Next, a SVM (6.6%, 15/227 cases) was also used, and the accuracy, sensitivity, and specificity of the SVM were 85–98%, 73–99%, and 85–99%, respectively, in this study.”
MethodInfluentialArrhythmia Detection by Data Fusion of ECG Scalograms and Phasograms
Scarpiniti, M. (2024) · Sensors · doi:10.3390/s24248043 · Cited by 24
Multimodal data integration in early-stage breast cancer
Llinas-Bertran, A., Butjosa-Espín, M., Barberi, V., & Seoane, J. A. (2025) · The Breast · doi:10.1016/j.breast.2025.103892 · Cited by 25
“Significant attention has been paid to different levels of data fusion in both ML [39] and DL models [40].”
A novel integrative multimodal classifier to enhance the diagnosis of Parkinson’s disease
Zhou, X., Parisi, L., Huang, W., Zhang, Y., Huang, X., Youseffi, M., Javid, F. A., & Ma, R. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf088 · Cited by 22
“In the literature, three types of multimodal data fusion, namely, early fusion, intermediate fusion, and late fusion, were proposed for integrating various data sources, as summarized by [33].”
Li, F., & Xu, J. (2025) · IEEE Access · doi:10.1109/access.2025.3552039 · Cited by 42
“These models apply various technologies, like computer hardware, software, networks, and databases, to allow the flow of information inside and within businesses [3], [4].”
Vaiuso, A., Immordino, G., Righi, M., & RONCH, A. D. (2025) · Aerospace Science and Technology · doi:10.1016/j.ast.2025.110301 · Cited by 27
Multi-modal lifelog data fusion for improved human activity recognition: A hybrid approach
Oh, Y., & Kim, S. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102464 · Cited by 25
Marini, N., Marchesin, S., Wodziński, M., Caputo, A., Podareanu, D., Guevara, B. C., Boytcheva, S., Vatrano, S., Fraggetta, F., Ciompi, F., et al. (2024) · Medical Image Analysis · doi:10.1016/j.media.2024.103303 · Cited by 23
Multimodal Approaches Based on Microbial Data for Accurate Postmortem Interval Estimation
Hu, S. C., Zhang, X., Yang, F., Nie, H., Lu, X., Guo, Y., & Zhao, X. (2024) · Microorganisms · doi:10.3390/microorganisms12112193 · Cited by 27
Wan, R., Wan, R., Xie, Q., Hu, A., Xie, W., Chen, J., & Liu, Y. (2024) · Behavioral Sciences · doi:10.3390/bs15010027 · Cited by 21
“Multimodal machine learning, which integrates various data types (such as text, images, audio, and video) (Stahlschmidt et al., 2022), achieves cross-perception fusion, thereby endowing machines with enhanced comprehensive perception and understanding capabilities.”
Teles, A. S., de Moura, I. R., Silva, F., Roberts, A., & Stahl, D. R. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.102981 · Cited by 27
CrossAttOmics: multiomics data integration with cross-attention
Beaude, A., Augé, F., Zehraoui, F., & Hanczar, B. (2025) · Bioinformatics · doi:10.1093/bioinformatics/btaf302 · Cited by 25
“Omics data can be noisy, and exploiting the redundancy between omics helps to increase robustness to noise (Stahlschmidt et al. 2022).”
MARIA: A multimodal transformer model for incomplete healthcare data
Caruso, C. M., Soda, P., & Guarrasi, V. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.110843 · Cited by 32
“By effectively integrating such diverse information, multimodal learning models can enhance decision-making and predictive accuracy, leading to improved diagnostic outcomes and more effective treatment plans [2].”
InfluentialMultimodal integration strategies for clinical application in oncology
Zhang, B., Wan, Z., Luo, Y., Zhao, X., Samayoa, J. A., Zhao, W., & Wu, S. (2025) · Frontiers in Pharmacology · doi:10.3389/fphar.2025.1609079 · Cited by 36
“Due to the signi fi cant divergence between certain data modalities, such as images and gene expression matrices, pre-trained unimodal models are commonly employed to extract dimensionally aligned feature vectors for each independent modality (Stahlschmidt et al., 2022).”
Muneer, A., Waqas, M. M., Saad, M. B., Showkatian, E., Bandyopadhyay, R., Xu, H. M., Li, W., Chang, J., Liao, Z., Haymaker, C., et al. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11522-9 · Cited by 28
“…deep learning domain, techniques like multimodal dropout deliberately omit random modalities during the training process, forcing the model to learn redundant and resilient representations, thereby enhancing its ability to make predictions when faced with incomplete data at inference time [191].”
Single Modality vs. Multimodality: What Works Best for Lung Cancer Screening?
Sousa, J. V., Matos, P., Silva, F., Freitas, P., Oliveira, H. P., & Pereira, T. (2023) · Sensors · doi:10.3390/s23125597 · Cited by 27
“In more recent years, multimodal approaches applied to the biomedical field have emerged, and often deep fusion methods surpass the performance of unimodal strategies [18].”
BackgroundBiomedical relation extraction method based on ensemble learning and attention mechanism
Jia, Y., Wang, H., Yuan, Z., Zhu, L., & Xiang, Z. (2024) · BMC Bioinformatics · doi:10.1186/s12859-024-05951-y · Cited by 24
Benkirane, H., Vakalopoulou, M., Planchard, D., Adam, J., Olaussen, K. A., Michiels, S., & Cournède, P.-H. (2025) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1013012 · Cited by 27
Hartmann, L. M., Langhans, D. S., Eggarter, V., Freisenich, T. J., Hillenmayer, A., König, S. F., Vounotrypidis, E., Wolf, A., & Wertheimer, C. M. (2024) · Translational Vision Science & Technology · doi:10.1167/tvst.13.5.7 · Cited by 21
“7,8 Computer vision-based convolutional neural networks have been used to detect variations in images of keratoconus patients compared with healthy control eyes.”
MethodDuST: Dual Swin Transformer for Multi-modal Video and Time-Series Modeling
Shi, L., Chen, Y., Liu, M., & Guo, F. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00456 · Cited by 29
BoneCLIP-XGBoost: A Multimodal Approach for Bone Fracture Diagnosis
Su, Z., Zhou, Y., Zhou, J., et al. (2024) · IEEE Access · doi:10.1109/access.2024.3479698 · Cited by 17
“Researchers are working on multimodal representation learning, cross-modal retrieval, visual question answering, image captioning, and multimodal fusion techniques to achieve seamless integration of visual and textual information [13], [14], [15], [16], [17], [18].”
Shi, M., Li, X., Li, M., & Si, Y. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad329 · Cited by 16
Deep learning-based geological map generation using geological routes
Li, C., Li, F., Liu, C., Tang, Z., Fu, S., Lin, M., Lv, X., Liu, S., & Liu, Y. (2024) · Remote Sensing of Environment · doi:10.1016/j.rse.2024.114214 · Cited by 20
A multi-modal deep learning solution for precise pneumonia diagnosis: the PneumoFusion-Net model
Wang, Y., Liu, C., Fan, Y., Niu, C., Huang, W., Pan, Y., Li, J., Wang, Y., & Li, J. (2025) · Frontiers in Physiology · doi:10.3389/fphys.2025.1512835 · Cited by 23
“Techniques based on self-supervised learning and transfer learning were also introduced to enhance model generalization over multi-center and heterogeneous datasets (Stahlschmidt et al., 2022).”
Han, S., Wang, C., Lai, Q., et al. (2025) · Acta Materialia · doi:10.1016/j.actamat.2025.120936 · Cited by 16
Multimodal malware classification using proposed ensemble deep neural network framework
Nazim, S., Alam, M. M., Rizvi, S. S. A., Mustapha, J. C., Hussain, S. S., & Su’ud, M. M. (2025) · Scientific Reports · doi:10.1038/s41598-025-96203-3 · Cited by 27
“In contrast, Joint Representation implicates the incorporation of information from assorted modalities to form an integrated illustration that incorporates the shared characteristics of each modality 21 as illustrated in Fig.”
Căliman-Sturdza, O. A., Filip, F., Baitan, M. T., & Dimian, M. (2025) · Diagnostics · doi:10.3390/diagnostics15141830 · Cited by 18
Ge, C., Wang, Z., Wang, Y., & Wei, M. (2025) · RSC Advances · doi:10.1039/d5ra03731j · Cited by 21
Deep Multimodal Fusion of Data With Heterogeneous Dimensionality via Projective Networks
Morano, J., Aresta, G., Grechenig, C., Schmidt-Erfurth, U. M., & Bogunović, H. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3352970 · Cited by 21
“U SING complementary information provided by different imaging modalities, commonly referred to as multimodal imaging , has led to significant improvements in the diagnosis and monitoring of several diseases [1], [2], [3], [4], [5], [6], [7], [8].”
BackgroundSun, W., Wang, R., Ouyang, S., Liang, W., Duan, J., Gong, W., Hu, L., Chen, X., Li, Y.-F., Kurihara, H., et al. (2025) · Acta Pharmaceutica Sinica B · doi:10.1016/j.apsb.2025.03.009 · Cited by 18
“In contrast, DL, such as convolutional neural networks (CNN), recurrent neural networks (RNN), and transform, employs multi-layer neural networks to automatically extract features without manual intervention, excelling in handling large-scale and high-dimensional datasets 63-65 .”
Li, Y., Chang, X., Wu, J., Liu, Y., Wang, H., & Zhang, Y. (2025) · Brain Network Disorders · doi:10.1016/j.bnd.2025.04.001 · Cited by 21
Rashid, H.-A., Kallakuri, U., & Mohsenin, T. (2023) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3595633 · Cited by 27
Increasing resolution in stress neurobiology: from single cells to complex group behaviors
Miranda, L., Bordes, J., Gasperoni, S., & López, J. P. (2023) · Stress · doi:10.1080/10253890.2023.2186141 · Cited by 14
“From genetics, transcrip-tomics, epigenomics, and proteomics, to neural signaling, behavior, and environmental factors, being able to merge information acquired at different biological levels in clever ways can be key to understanding any phenotype (Stahlschmidt et al., 2022).”
BackgroundRestrepo, D. S., Wu, C., Cajas, S. A., Nakayama, L. F., Celi, L. A., & López, D. M. (2024) · medRxiv · doi:10.1101/2024.06.03.24308401 · Cited by 34
Jiao, J., Sun, H., Huang, Y., Xia, M., Qiao, M., Ren, Y., Wang, Y., & Guo, Y. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2023.3278259 · Cited by 15
“…last layer feature of each modality, joint-space-based DCCA [18], DCCAE [19], and contrastive-learning-based MICLe [21]; (III) Late fusion: the LF [8] and TMC [17] are introduced in our comparison, where the former fuses the modal decisions based on learnable weight and the latter is based on DST.”
BackgroundMethodInfluentialLv, C., Shu, X.-J., Liang, Q., Qiu, J., Xiong, Z., Ye, J. B., Li, S., Liu, C. Q., Niu, J. Z., Chen, S., et al. (2025) · Frontiers in Oncology · doi:10.3389/fonc.2025.1585891 · Cited by 17
Clinicians must participate in the development of multimodal AI
Banerji, C. R. S., Shah, A. B., Dabson, B., Chakraborti, T., Hellon, V., Harbron, C. G., & MacArthur, B. D. (2025) · EClinicalMedicine · doi:10.1016/j.eclinm.2025.103252 · Cited by 24
“8,22 By introducing a natural order (e.g., by invasiveness or risk of patient harm) these approaches — which go by many names including gradual intermediate data fusion 8 provide a more clinically relevant way to combine data from different sources.”
Ai, M., Liu, Y., Liu, D., Yan, C., Wang, X., & Chen, X. (2025) · Frontiers in Neurology · doi:10.3389/fneur.2025.1596632 · Cited by 22
“In addition, AI technologies, such as deep learning and machine learning (17– 19), are pioneering a revolutionary wave in the medical field due to their unparalleled powerful capabilities (20, 21).”
Tang, J., Yin, X. Y., Lai, J., Luo, K., & Wu, D. (2025) · JMIR Medical Informatics · doi:10.2196/70738 · Cited by 22
“Multimodal fusion can provide a more accurate description of samples, and it exploits the complementary and synergistic nature of each modality’s information more effectively than any single modality data [22].”
Scaling medical AI across clinical contexts
Li, M. M., Reis, B. Y., Rodman, A. M., Cai, T., Dagan, N., Balicer, R. D., Loscalzo, J., Kohane, I. S., & Žitnik, M. (2026) · Nature Medicine · doi:10.1038/s41591-025-04184-7 · Cited by 31
“https://doi.org/10.1038/s41591-025-04184-7 learn joint representations from raw inputs, and hybrid approaches combine both 79–82 .”
InfluentialAI-Assisted Molecular Biosensors: Design Strategies for Wearable and Real-Time Monitoring
Zhu, S., Zhang, J., He, X., Ding, L., Luo, X., & Wen, W. (2026) · International Journal of Molecular Sciences · doi:10.3390/ijms27073305 · Cited by 20
“In multimodal analysis, common deep learning algorithms fuse different data types [39].”
Lu, T., Diao, Y.-R., Tang, X.-E., Fan, F., Zhao, P., Zhan, M., Liu, G., Lin, Y., Cheng, Z., Yi, X., et al. (2023) · European Radiology · doi:10.1007/s00330-023-09761-3 · Cited by 19
“Since different modality data could provide more useful auxiliary information, multi-modality-based DL training task has attracted extensive attention and become a major area of research within medical image analysis [38].”
BackgroundAzman, N. S., Samah, A. A., Lin, J. T., Majid, H. A., Shah, Z. A., Wen, N. H., & Howe, C. W. (2023) · Progress In Microbes & Molecular Biology · doi:10.36877/pmmb.a0000327 · Cited by 15
Oxygenation Fluctuations Associated with Severe Retinopathy of Prematurity
Lin, W.-C., Jordan, B. K., Scottoline, B. P., Ostmo, S. R., Coyner, A. S., Singh, P., Kalpathy–Cramer, J., Erdogmus, D., Chan, R. V. P., Chiang, M. F., et al. (2023) · Ophthalmology Science · doi:10.1016/j.xops.2023.100417 · Cited by 20
“30,31 The ability to process and utilize multimodal inputs enhances the model ’ s performance and the accuracy of predictions.”
BackgroundTEMINET: A Co-Informative and Trustworthy Multi-Omics Integration Network for Diagnostic Prediction
Luo, H., Liang, H., Liu, H., Fan, Z., Wei, Y., Yao, X., & Cong, S. (2024) · International Journal of Molecular Sciences · doi:10.3390/ijms25031655 · Cited by 16
Beyond images: an integrative multi-modal approach to chest x-ray report generation
Aksoy, N., Sharoff, S., Baser, S., Ravikumar, N., & Frangi, A. F. (2024) · Frontiers in Radiology · doi:10.3389/fradi.2024.1339612 · Cited by 19
“26 Deep learning fusion strategies can be broadly classified into three categories: early fusion, late/decision fusion, and hybrid/joint fusion.”
BackgroundGuo, J., Li, Y., Guo, H., Hao, D., Xu, J.-X., Huang, C., Han, H., Hou, F., Yang, S., Cui, J., et al. (2024) · Journal of Magnetic Resonance Imaging · doi:10.1002/jmri.29474 · Cited by 15
“33,34 Speci fi cally, we used the intermediate fusion strategy, which learns and fuses margin representations in the form of feature vectors, with the advantage of fi nding further disentanglement factors within the different sequences, thereby improving the performance of the fi nal classi fi er.”
Multimodal ultrasound deep learning to detect fibrosis in early chronic kidney disease
Qin, X., Liu, X., Xia, L., Luo, Q., & Zhang, C. (2024) · Renal Failure · doi:10.1080/0886022x.2024.2417740 · Cited by 23
“A multimodal method is considered to be better than a single-mode method [43,44].”
MethodZhao, H., & Song, G. (2024) · Viruses · doi:10.3390/v16111673 · Cited by 16
Ranek, J. S., Stanley, N., & Purvis, J. E. (2022) · Genome biology · doi:10.1186/s13059-022-02749-0 · Cited by 14
“This baseline approach, along with element-wise sum, is a common fusion strategy for merging multi-modal data in deep learning [46, 52, 53].”
MethodAngiogenesis goes computational – The future way forward to discover new angiogenic targets?
Subramanian, A., Zakeri, P., Mousa, M., Alnaqbi, H., Alshamsi, F. Y., Bettoni, L., Damiani, E., AlSafar, H. S., Saeys, Y., & Carmeliet, P. (2022) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2022.09.019 · Cited by 14
“Also, deep learning through various deep algorithms and different architectures successfully exploits the different structures in multiple omics data types and offers a practical and scalable framework for data fusion at all levels of data realization [112] (Fig.”
BackgroundGuo, Q., Zhan, L., Yin, Z., Feng, H., Yang, G., & Chen, Y. (2024) · Computers and Geotechnics · doi:10.1016/j.compgeo.2024.106697 · Cited by 16
Deep learning for land use classification: a systematic review of HS-LiDAR imagery
Rehman, M. Z. U., Islam, S. M. S., Blake, D., Ulhaq, A., & Janjua, N. K. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11265-z · Cited by 31
“The concept of early fusion refers to the merging of multiple modalities/sources of data into a single representation prior to its use as input for a feature extraction algorithm Stahlschmidt et al. ( 2022 ).”
InfluentialCRBSP:Prediction of CircRNA-RBP Binding Sites Based on Multimodal Intermediate Fusion
Liu, N., Zhang, Z., Wu, Y., Wang, Y., & Liang, Y. (2023) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2023.3272400 · Cited by 14
“Deep fusion is considered superior to unimodal and shallow methods [30].”
BackgroundDai, Q., Tao, Y., Liu, D., Zhao, C., Sui, D., Xu, J., Shi, T., Leng, X., & Lu, M. (2023) · Frontiers in Oncology · doi:10.3389/fonc.2023.1261080 · Cited by 16
Alzheimer's disease detection using data fusion with a deep supervised encoder
Trinh, M., Shahbaba, R., Stark, C. E. L., & Ren, Y. (2024) · Frontiers in Dementia · doi:10.3389/frdem.2024.1332928 · Cited by 17
Choudhry, I. A., Iqbal, S., Alhussein, M. A., Aurangzeb, K., Qureshi, A. N., Anwar, M. S., & Khan, F. (2024) · Internet of Things · doi:10.1016/j.iot.2024.101296 · Cited by 17
Pandey, P., McLinden, J., Rahimi, N., Kumar, C., Shao, M., Spencer, K., Ostadabbas, S., & Shahriari, Y. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109256 · Cited by 15
Mei, L., Yu, H., Ye, Z., Xu, C., Lei, C., & Yang, W. (2025) · Geo-spatial Information Science · doi:10.1080/10095020.2024.2448232 · Cited by 16
Teng, X., Liu, M., Wang, Z., & Dong, X. (2025) · Scientific Reports · doi:10.1038/s41598-025-92814-y · Cited by 18
Jiang, B., Wu, Y., Chen, X., Jian, C., & Wang, W. (2026) · Critical Reviews in Oncology/Hematology · doi:10.1016/j.critrevonc.2026.105160 · Cited by 18
Zhang, Y., Deng, Y., Zhou, Z., Zhang, X., Jiao, P., & Zhao, Z. (2022) · Frontiers in Physiology · doi:10.3389/fphys.2022.1021400 · Cited by 18
“This has the potential to solve problems with fewer errors than unimodal approaches would (Richard et al., 2022).”
BackgroundBridging Multimedia Modalities: Enhanced Multimodal AI Understanding and Intelligent Agents
Gautam, S. (2023) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/3577190.3614225 · Cited by 21
“Stahlschmidt et al. [28] prioritize nonlinear biomedical data fusion, proposing a taxonomy to enhance fusion strategy selection within the biomedical domain.”
BackgroundPingi, S. T., Zhang, D., Bashar, M. A., & Nayak, R. (2023) · Data Science and Engineering · doi:10.1007/s41019-023-00232-9 · Cited by 19
“Consequently, there exists a potential risk of overlooking correlated information present at higher levels of abstraction [47].”
Data mining and machine learning in HIV infection risk research: An overview and recommendations
Ge, Q., Lu, X., Jiang, R., Zhang, Y., & Zhuang, X. (2024) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2024.102887 · Cited by 12
Fan, Y., Sun, N., Lv, S., Jiang, H., Zhang, Z., Wang, J., Xie, Y., Yue, X., Hu, B., Ju, B., et al. (2024) · The Science of The Total Environment · doi:10.1016/j.scitotenv.2024.174027 · Cited by 15
Zhu, Y., Liu, J., & Wang, B. (2024) · Diabetes Obesity and Metabolism · doi:10.1111/dom.15933 · Cited by 12
Cross-modal alignment and contrastive learning for enhanced cancer survival prediction
Li, T., Zhou, X., Xue, J., Zeng, L., Zhu, Q., Wang, R., Yu, H., & Xia, J. (2025) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2025.108633 · Cited by 22
Schuster, E. J., Dashzeveg, N. K., Tong, F., Jia, Y., El-Shennawy, L., Zhang, T., Hoffman, A. D., Kitata, R. B., Kibria, G., Zhang, Y., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-62862-z · Cited by 17
Explainable AI-enabled hybrid deep learning architecture for breast cancer detection
Zou, Y., & Miao, P. (2025) · Frontiers in Immunology · doi:10.3389/fimmu.2025.1658741 · Cited by 24
Vaida, M. L., & Huang, Z. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2025.1716706 · Cited by 31
Interpretable deep learning survival predictive tool for small cell lung cancer
Zhang, D., Lu, B., Liang, B., Li, B., Wang, Z., Gu, M., Jia, W., & Pan, Y. (2023) · Frontiers in Oncology · doi:10.3389/fonc.2023.1162181 · Cited by 11
Multimodal and multi-omics-based deep learning model for screening of optic neuropathy
Lin, Y.-T., Zhou, Q., Tan, J., & Tao, Y. (2023) · Heliyon · doi:10.1016/j.heliyon.2023.e22244 · Cited by 14
“Early fusion-based models are also incapable of learning the marginal features of different data [32].”
BackgroundIsuwa, J., Abdullahi, M., Ali, Y. S., Hassan, I. H., Buba, J. R., Aliyu, I., Kim, J., & Oyelade, O. N. (2023) · Egyptian Informatics Journal · doi:10.1016/j.eij.2023.100416 · Cited by 15
MoVAE: Multi-Omics Variational Auto-Encoder for Cancer Subtype Detection
Rahmanian, M., & Mansoori, E. G. (2024) · IEEE Access · doi:10.1109/access.2024.3462543 · Cited by 20
“The goal of fusing (integration) strategies is to effectively exploit the complementary, redundant, and cooperative features of different omics [4].”
BackgroundChen, C., Wu, M., Zuo, E., Wu, X. F., Wu, L., Liu, H., Zhou, X., Du, Y. S., Lv, X., & Chen, C. (2024) · Analytica Chimica Acta · doi:10.1016/j.aca.2024.343302 · Cited by 13
Robust multi-modal fusion architecture for medical data with knowledge distillation
Wang, M., Fan, S., Li, Y., Gao, B., Xie, Z., & Chen, H. (2024) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2024.108568 · Cited by 17
Si, F., Liu, Q., & Yu, J. (2025) · BMC Geriatrics · doi:10.1186/s12877-025-05679-1 · Cited by 15
MDFormer: Transformer-Based Multimodal Fusion for Robust Chest Disease Diagnosis
Liu, X., Pan, F., Song, H., Cao, S., Li, C., & Li, T. (2025) · Electronics · doi:10.3390/electronics14101926 · Cited by 16
A Systematic Review of Intermediate Fusion in Multimodal Deep Learning for Biomedical ApplicationsPreprint
Guarrasi, V., Aksu, F., Caruso, C. M., Feola, F. D., Rofena, A., Ruffini, F., & Soda, P. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4952813 · Cited by 21
Metadata
- Authors
- Stahlschmidt, S. R., Ulfenborg, B., & Synnergren, J.
- Affiliations
- University of Skövde (SE)
- Corresponding author
- Stahlschmidt, Sören Richard
- Venue
- Briefings in Bioinformatics
- Publisher
- Oxford University Press (OUP)
- Published
- 2022-01-28
- Volume
- 23
- Issue
- 2
- ISSN
- 1467-5463 (ISSN-L)
- 1477-4054
- PMC
- PMC8921642
- OpenAlex
- W4206042814
- Cited by
- 766
- References
- 117
- Citations by year
- 2026: 241 · 2025: 245 · 2024: 175 · 2023: 82 · 2022: 23
- FWCI
- 7.34
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Briefings in Bioinformatics (publishedVersion, cc-by-nc)
- PubMed Central (publishedVersion, cc-by-nc)
- PubMed (publishedVersion)
- KTH Publication Database DiVA (KTH Royal Institute of Technology) (submittedVersion, other-oa)
- Funders
- University of Skövde, Sweden (20170302, 20200014)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Bioinformatics and Genomic Networks
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Keywords
- multimodal fusion, biomedical data, deep learning, joint representation learning, intermediate fusion, transfer learning, biological knowledge integration
- MeSH terms
- Deep Learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.