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.”
MethodA Comprehensive Survey on Graph Neural Networks
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. (2020) · UTS ePRESS (University of Technology Sydney) · Cited by 3,174
Deep learning for healthcare: review, opportunities and challenges
Miotto, R., Wang, F., Wang, S., Jiang, X., & Dudley, J. T. (2018) · Briefings in Bioinformatics · doi:10.1093/bib/bbx044 · Cited by 3,076
An introduction to multisensor data fusion
Hall, D. L., & Llinas, J. (1997) · Proceedings of the IEEE · doi:10.1109/5.554205 · Cited by 2,629
Opportunities and obstacles for deep learning in biology and medicine
Ching, T., Himmelstein, D. S., Beaulieu-Jones, B. K., Kalinin, A. A., Do, B. T., Way, G. P., Ferrero, E., Agapow, P.-M., Zietz, M., Hoffman, M. M., et al. (2018) · Journal of The Royal Society Interface · doi:10.1098/rsif.2017.0387 · Cited by 2,310 · cited 1×
“Although DL architectures for biomedical applications have been reviewed [16], the different DL-based fusion strategies for heterogeneous data have not.”
BackgroundMultimodal Learning with Deep Boltzmann Machines
Srivastava, N., & Salakhutdinov, R. (2012) · Journal of Machine Learning Research · doi:10.5555/2627435.2697059 · Cited by 1,807
Miotto, R., Li, L., Kidd, B. A., & Dudley, J. T. (2016) · Scientific Reports · doi:10.1038/srep26094 · Cited by 1,710 · cited 1×
“[37] applied a stacked DAE to multimodal electronic health records (EHR) data, effectively representing patients in a lower dimensional space and thereby enabling a multitude of clinical predictive modeling such as the onset of disease.”
MethodDeep multimodal learning: a survey on recent advances and trends
Ramachandram, D., & Taylor, G. W. (2017) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2738401 · Cited by 1,139 · cited 10×
“Thus, fusing modalities gradually rather than all in one layer can be beneficial [2].”
BackgroundInfluentialDeep learning-based multi-omics integration robustly predicts survival in liver cancer
Chaudhary, K., Poirion, O. B., Lu, L., & Garmire, L. X. (2018) · Clinical Cancer Research · doi:10.1158/1078-0432.ccr-17-0853 · Cited by 1,091
Predicting cancer outcomes from histology and genomics using convolutional networks
Mobadersany, P., Yousefi, S., Amgad, M., Gutman, D. A., Barnholtz-Sloan, J. S., Velázquez Vega, J. E., Brat, D. J., & Cooper, L. A. D. (2018) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1717139115 · Cited by 1,084 · cited 1×
“[77] showed that imbalance does not necessarily lead to poor performance if the input features of the lower dimensional modality are chosen with prior knowledge.”
BackgroundA Review of Data Fusion Techniques
Castanedo, F. (2013) · The Scientific World Journal · doi:10.1155/2013/704504 · Cited by 1,027 · cited 1×
“More specifically, the advantages of data fusion can be categorized as complementary, redundant and cooperative features [4, 5], though these are not mutually exclusive.”
BackgroundHierarchical Feature Representation and Multimodal Fusion with Deep Learning for AD/MCI Diagnosis
Suk, H.-I., Lee, S.-W., & Shen, D. (2014) · NeuroImage · doi:10.1016/j.neuroimage.2014.06.077 · Cited by 968 · cited 1×
“[55] applied a multimodal deep boltzmann machine (DBM) [95] to predict AD from magnetic resonance images (MRI) and positron emission tomography (PET) scans.”
MethodMemory Fusion Network for Multi-view Sequential Learning
Zadeh, A., Liang, P. P., Mazumder, N., Poria, S., Cambria, E., & Morency, L.-P. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.12021 · Cited by 855
Manzoni, C., Kia, D. A., Vandrovcova, J., Hardy, J., Wood, N. W., Lewis, P. A., & Ferrari, R. (2018) · Briefings in Bioinformatics · doi:10.1093/bib/bbw114 · Cited by 804
Multimodal deep learning models for early detection of Alzheimer’s disease stage
Venugopalan, J., Tong, L., Hassanzadeh, H. R., & Wang, M. D. (2021) · Scientific Reports · doi:10.1038/s41598-020-74399-w · Cited by 732
Chen, R. J., Lu, M. Y., Wang, J., Williamson, D. F. K., Rodig, S. J., Lindeman, N. I., & Mahmood, F. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.3021387 · Cited by 729 · cited 3×
“[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.”
BackgroundMethodPan-cancer integrative histology-genomic analysis via multimodal deep learning
Chen, R. J., Lu, M. Y., Williamson, D. F. K., Chen, T. Y., Lipkova, J., Noor, Z., Shaban, M., Shady, M., Williams, M., Joo, B., et al. (2022) · Cancer Cell · doi:10.1016/j.ccell.2022.07.004 · Cited by 660
AI-based pathology predicts origins for cancers of unknown primary
Lu, M. Y., Chen, T. Y., Williamson, D. F. K., Zhao, M., Shady, M., Lipkova, J., & Mahmood, F. (2021) · Nature · doi:10.1038/s41586-021-03512-4 · Cited by 636 · cited 1×
“[66] showed that concatenating biological sex of the patient as a covariate with features learned from WSIs improved the performance in predicting primary sites of cancers of unknown primary.”
BackgroundWhat Makes Training Multi-modal Classification Networks Hard?
Wang, W., Tran, D., & Feiszli, M. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01271 · Cited by 588 · cited 1×
“Overfitting to the training data, and therefore poor generalizability, is a major challenge for multimodal models [103].”
BackgroundLiu, M., Li, F., Yan, H., Wang, K., Ma, Y., Shen, L., & Xu, M. (2020) · NeuroImage · doi:10.1016/j.neuroimage.2019.116459 · Cited by 568
deepDR: a network-based deep learning approach to in silico drug repositioning
Zeng, X., Zhu, S., Liu, X., Zhou, Y., Nussinov, R., & Cheng, F. (2019) · Bioinformatics · doi:10.1093/bioinformatics/btz418 · Cited by 535
Single-cell multiomics: technologies and data analysis methods
Lee, J., Hyeon, D. Y., & Hwang, D. (2020) · Experimental & Molecular Medicine · doi:10.1038/s12276-020-0420-2 · Cited by 524 · cited 1×
“Currently, spatial transcriptomics [9] and single-cell multi-omics [10] are being increasingly used.”
MethodMulti-attention Recurrent Network for Human Communication Comprehension
Zadeh, A., Liang, P. P., Poria, S., Vij, P., Cambria, E., & Morency, L.-P. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.12024 · Cited by 505 · cited 1×
“[73] used an attention mechanism for multiomics data [99] for interpreting predictions of gene expression.”
MethodA multimodal deep learning framework for predicting drug–drug interaction events
Deng, Y., Xu, X., Qiu, Y., Xia, J., Zhang, W., & Liu, S. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btaa501 · Cited by 453
A review on machine learning principles for multi-view biological data integration
Li, Y., Wu, F.-X., & Ngom, A. (2016) · Briefings in Bioinformatics · doi:10.1093/bib/bbw113 · Cited by 421 · cited 2×
“In recent years, multimodal ML methods have been increasingly studied and applied in a variety of fields [6, 11].”
BackgroundDeep learning with multimodal representation for pancancer prognosis prediction
Cheerla, A., & Gevaert, O. (2019) · Bioinformatics · doi:10.1093/bioinformatics/btz342 · Cited by 421 · cited 2×
“Different approaches have been proposed, such as multi-task learning [70], generative models [63] and multimodal dropout [78, 101].”
BackgroundMethodMOLI: multi-omics late integration with deep neural networks for drug response prediction
Sharifi-Noghabi, H., Zolotareva, O., Collins, C. C., & Ester, M. (2019) · Bioinformatics · doi:10.1093/bioinformatics/btz318 · Cited by 421
Predicting alzheimer’s disease progression using multi-modal deep learning approach
Lee, G., Nho, K., Kang, B., Sohn, K.-A., Kim, D., Initiative, F. A. D. N., Weiner, M. W., Aisen, P., Petersen, R., Jack, C. R., et al. (2019) · Scientific Reports · doi:10.1038/s41598-018-37769-z · Cited by 406
Sensor models and multisensor integration
Durrant-Whyte, H. F. (1988) · The International Journal of Robotics Research · doi:10.1177/027836498800700608 · Cited by 352 · cited 1×
“More specifically, the advantages of data fusion can be categorized as complementary, redundant and cooperative features [4, 5], though these are not mutually exclusive.”
BackgroundSun, D., Wang, M., & Li, A. (2019) · IEEE/ACM Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2018.2806438 · Cited by 338 · cited 1×
“[87] learned the weights of the predictions by their sub-models as hyperparameters on a validation set.”
Chang, Y., Park, H., Yang, H.-J., Lee, S., Lee, K.-Y., Kim, T. S., Jung, J., & Shin, J.-M. (2018) · Scientific Reports · doi:10.1038/s41598-018-27214-6 · Cited by 320
Poirion, O. B., Jing, Z., Chaudhary, K., Huang, S., & Garmire, L. X. (2021) · Genome Medicine · doi:10.1186/s13073-021-00930-x · Cited by 297
Combining structured and unstructured data for predictive models: a deep learning approach
Zhang, D., Yin, C., Zeng, J., Yuan, X., & Zhang, P. (2020) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-020-01297-6 · Cited by 269 · cited 1×
“[64] proposed a CNN- and a RNN-based fusion model that take temporal signals, sequential clinical notes as well as static demographic and admission data as input to the different branches.”
MethodLong-term cancer survival prediction using multimodal deep learning
Vale-Silva, L. A., & Rohr, K. (2021) · Scientific Reports · doi:10.1038/s41598-021-92799-4 · Cited by 268
AI-based pathology predicts origins for cancers of unknown primary
Lu, M. Y., Chen, T., Williamson, D. F. K., Zhao, M. M., Shady, M., Lipková, J., & Mahmood, F. (2021) · RePEc: Research Papers in Economics · Cited by 263
SALMON: survival analysis learning with multi-omics neural networks on breast cancer
Huang, Z., Zhan, X., Xiang, S., Johnson, T. S., Helm, B., Yu, C. Y., Zhang, J., Salama, P., Rizkalla, M., Han, Z., et al. (2019) · Frontiers in Genetics · doi:10.3389/fgene.2019.00166 · Cited by 262 · cited 1×
“[43] fused mRNA and miRNA eigengene matrices through two locally fully connected branches.”
BackgroundHuang, S.-C., Pareek, A., Zamanian, R., Banerjee, I., & Lungren, M. P. (2020) · Scientific Reports · doi:10.1038/s41598-020-78888-w · Cited by 246 · cited 2×
“[83] applied an FCNN for fusing sub-model predictions, while Reda et al.”
BackgroundMethoddeepNF: deep network fusion for protein function prediction
Gligorijević, V., Barot, M., & Bonneau, R. (2018) · Bioinformatics · doi:10.1093/bioinformatics/bty440 · Cited by 236
Integrative data analysis of multi-platform cancer data with a multimodal deep learning approach
Liang, M., Li, Z., Chen, T., & Zeng, J. (2015) · IEEE/ACM Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2014.2377729 · Cited by 231 · cited 1×
“DBNs have been extensively used to fuse biomedical modalities for drug repurposing [52], clustering of cancer patients [53] and predicting disease-gene pairs [54].”
MethodZhang, L., Lv, C., Jin, Y., Cheng, G., Fu, Y., Yuan, D., Tao, Y., Guo, Y., Ni, X., & Shi, T. (2018) · Frontiers in Genetics · doi:10.3389/fgene.2018.00477 · Cited by 203
Integrating multi-omics data through deep learning for accurate cancer prognosis prediction
Chai, H., Zhou, X., Zhang, Z., Rao, J., Zhao, H., & Yang, Y. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.104481 · Cited by 194 · cited 2×
“For the same clinical task, a similar workflow has been adapted by researchers, but applying denoising AEs (DAEs) [91] instead [35, 36].”
BackgroundMethodPark, C., Ha, J., & Park, S. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2019.112873 · Cited by 184 · cited 1×
“The vector xconcat can be modeled with a fully connected input layer if the ordering of the features is irrelevant to the learning task, as done in [17, 18] and with constraints in [19].”
BackgroundClassifying Breast Cancer Subtypes Using Deep Neural Networks Based on Multi-Omics Data
Lin, Y., Zhang, W., Cao, H., Li, G., & Du, W. (2020) · Genes · doi:10.3390/genes11080888 · Cited by 159 · cited 1×
“[51] adopted this method for predicting breast cancer subtypes.”
MethodTong, L., Mitchel, J., Chatlin, K., & Wang, M. D. (2020) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-020-01225-8 · Cited by 158 · cited 1×
“‖zm (see Figure 4b) and used as input to further modeling, such as clustering followed by a classifier for cancer subtyping [45–47], or directly as input to a classifier for multi-class classification or survival analysis [48].”
MethodClinical Intervention Prediction and Understanding using Deep NetworksPreprint
Suresh, H., Hunt, N. J., Johnson, A. E. W., Celi, L. A., Szolovits, P., & Ghassemi, M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.08498 · Cited by 154
Variational autoencoders for cancer data integration: design principles and computational practice
Simidjievski, N., Bodnar, C., Tariq, I., Scherer, P., Andres Terre, H., Shams, Z., Jamnik, M., & Liò, P. (2019) · Frontiers in Genetics · doi:10.3389/fgene.2019.01205 · Cited by 145
Liu, T., Huang, J., Liao, T., Pu, R., Liu, S., & Peng, Y. (2022) · IRBM · doi:10.1016/j.irbm.2020.12.002 · Cited by 137
Ma’ayan, A. (2017) · Journal of The Royal Society Interface · doi:10.1098/rsif.2017.0391 · Cited by 135 · cited 1×
“Individual cells and complete organisms are prototypical complex systems, as they are composed of many different parts interacting with each other and giving rise to emergent behaviors [1].”
BackgroundIntegrated multi-omics analysis of ovarian cancer using variational autoencoders
Hira, M. T., Razzaque, M. A., Angione, C., Scrivens, J., Sawan, S., & Sarker, M. (2021) · Scientific Reports · doi:10.1038/s41598-021-85285-4 · Cited by 134 · cited 1×
“[56] also found joint multimodal VAEs useful for fusing multi-omics data and support the findings of [41] that Maximum Mean Discrepancy as a regularization term outperforms the Kullback–Leibler divergence.”
MethodXu, J., Wu, P., Chen, Y., Meng, Q., Dawood, H., & Dawood, H. (2019) · BMC Bioinformatics · doi:10.1186/s12859-019-3116-7 · Cited by 132
Zhao, L., Dong, Q., Luo, C., Wu, Y., Bu, D., Qi, X., Luo, Y., & Zhao, Y. (2021) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2021.04.067 · Cited by 127 · cited 2×
“The vector xconcat can be modeled with a fully connected input layer if the ordering of the features is irrelevant to the learning task, as done in [17, 18] and with constraints in [19].”
BackgroundMethodA gene prioritization method based on a swine multi-omics knowledgebase and a deep learning model
Fu, Y., Xu, J., Tang, Z., Wang, L., Yin, D., Fan, Y., Zhang, D., Deng, F., Zhang, Y., Zhang, H., et al. (2020) · Communications Biology · doi:10.1038/s42003-020-01233-4 · Cited by 125 · cited 1×
“If the ordering of the input features contains structural information, such as in the case of genomic data or time series of clinical data, recurrent layers [20, 24] or convolutional layers [20, 21, 23] can be applied to the concatenated vector.”
BackgroundDeep Learning Role in Early Diagnosis of Prostate Cancer
Reda, I., Khalil, A., Elmogy, M., Abou El-Fetouh, A., Shalaby, A., Abou El-Ghar, M., Elmaghraby, A., Ghazal, M., & El-Baz, A. (2018) · Technology in Cancer Research & Treatment · doi:10.1177/1533034618775530 · Cited by 119 · cited 1×
“[88] used a sparse SAE connected to a classifier for the final prediction.”
MethodEvaluation of colorectal cancer subtypes and cell lines using deep learning
Ronen, J., Hayat, S., & Akalin, A. (2019) · Life Science Alliance · doi:10.26508/lsa.201900517 · Cited by 105 · cited 1×
“[40] performed survival subtyping of colorectal cancer and matched cell lines to subgroups by applying a stacked VAE based on multi-omics data.”
MethodMa, T., & Zhang, A. (2019) · BMC Genomics · doi:10.1186/s12864-019-6285-x · Cited by 105 · cited 1×
“We have seen applications where prior biological knowledge has informed architectural decisions, such as separate branches according to chromosomal position [62], regularization terms in the training loss [49] or to encode pathways into the architecture [19, 67].”
MethodGroup lasso regularized deep learning for cancer prognosis from multi-omics and clinical features
Xie, G., Dong, C., Kong, Y., Zhong, J. F., Li, M., & Wang, K. (2019) · Genes · doi:10.3390/genes10030240 · Cited by 102 · cited 1×
“The vector xconcat can be modeled with a fully connected input layer if the ordering of the features is irrelevant to the learning task, as done in [17, 18] and with constraints in [19].”
BackgroundLee, T.-Y., Huang, K.-Y., Chuang, C.-H., Lee, C.-Y., & Chang, T.-H. (2020) · Computational Biology and Chemistry · doi:10.1016/j.compbiolchem.2020.107277 · Cited by 95
Zhang, X., Zhang, J., Sun, K., Yang, X., Dai, C., & Guo, Y. (2019) · 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm47256.2019.8983228 · Cited by 93 · cited 2×
“[62] proposed an end-to-end VAE architecture that learns a task-specific joint representation of DNA methylation and gene expression data for pan-cancer classification.”
BackgroundMethodFranco, E. F., Rana, P., Cruz, A., Calderón, V. V., Azevedo, V., Ramos, R. T. J., & Ghosh, P. (2021) · Cancers · doi:10.3390/cancers13092013 · Cited by 92
An integrative deep learning framework for classifying molecular subtypes of breast cancer
Mohaiminul Islam, M., Huang, S., Ajwad, R., Chi, C., Wang, Y., & Hu, P. (2020) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2020.08.005 · Cited by 90 · cited 4×
“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.”
BackgroundInfluentialDeep learning-based ovarian cancer subtypes identification using multi-omics data
Guo, L.-Y., Wu, A.-H., Wang, Y.-X., Zhang, L.-P., Chai, H., & Liang, X.-F. (2020) · BioData Mining · doi:10.1186/s13040-020-00222-x · Cited by 89 · cited 1×
“For the same clinical task, a similar workflow has been adapted by researchers, but applying denoising AEs (DAEs) [91] instead [35, 36].”
MethodTakahashi, S., Asada, K., Takasawa, K., Shimoyama, R., Sakai, A., Bolatkan, A., Shinkai, N., Kobayashi, K., Komatsu, M., Kaneko, S., et al. (2020) · Biomolecules · doi:10.3390/biom10101460 · Cited by 85
Hao, J., Kim, Y., Mallavarapu, T., Oh, J. H., & Kang, M. (2019) · BMC Medical Genomics · doi:10.1186/s12920-019-0624-2 · Cited by 82 · cited 2×
“We have seen applications where prior biological knowledge has informed architectural decisions, such as separate branches according to chromosomal position [62], regularization terms in the training loss [49] or to encode pathways into the architecture [19, 67].”
BackgroundMethodMultimodal deep learning enhances diagnostic precision in left ventricular hypertrophy
Soto, J. T., Weston Hughes, J., Sanchez, P. A., Perez, M., Ouyang, D., & Ashley, E. A. (2022) · European Heart Journal - Digital Health · doi:10.1093/ehjdh/ztac033 · Cited by 76 · cited 1×
“[84] showed that late fusion with averaging results can outperform other late and intermediate fusion strategies.”
ResultCapsule Network Based Modeling of Multi-omics Data for Discovery of Breast Cancer-Related Genes
Chen, P., Zheng, Y., & Huang, D.-S. (2019) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2019.2909905 · Cited by 74
A Multi-modal Convolutional Neural Network Framework for the Prediction of Alzheimer’s Disease
Spasov, S. E., Passamonti, L., Duggento, A., Lio, P., & Toschi, N. (2018) · 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2018.8512468 · Cited by 73 · cited 1×
“For instance, MRI and clinical data can be fused for AD prediction [72] or MRI, clinical and genomic modalities can be fused for AD stage detection [69].”
BackgroundA multimodal deep learning-based drug repurposing approach for treatment of COVID-19
Hooshmand, S. A., Zarei Ghobadi, M., Hooshmand, S. E., Azimzadeh Jamalkandi, S., Alavi, S. M., & Masoudi-Nejad, A. (2021) · Molecular Diversity · doi:10.1007/s11030-020-10144-9 · Cited by 70 · cited 1×
“DBNs have been extensively used to fuse biomedical modalities for drug repurposing [52], clustering of cancer patients [53] and predicting disease-gene pairs [54].”
MethodLemsara, A., Ouadfel, S., & Fröhlich, H. (2020) · BMC Bioinformatics · doi:10.1186/s12859-020-3465-2 · Cited by 69
Enhancing the prediction of disease-gene associations with multimodal deep learning
Luo, P., Li, Y., Tian, L.-P., & Wu, F.-X. (2019) · Bioinformatics · doi:10.1093/bioinformatics/btz155 · Cited by 67
Uncovering Prognosis-Related Genes and Pathways by Multi-Omics Analysis in Lung Cancer
Asada, K., Kobayashi, K., Joutard, S., Tubaki, M., Takahashi, S., Takasawa, K., Komatsu, M., Kaneko, S., Sese, J., & Hamamoto, R. (2020) · Biomolecules · doi:10.3390/biom10040524 · Cited by 67
Xu, M. J., Ouyang, L., Gao, Y., Chen, Y., Yu, T., Li, Q., Sun, K., Bao, F. S., Safarnejad, L., Wen, J., et al. (2020) · Journal of Medical Internet Research · doi:10.2196/25535 · Cited by 64 · cited 1×
“[68] concatenated lab tests, clinical data and marginal representations of computed tomography (CT) scans to predict COVID-19 infections.”
MethodThung, K.-H., Yap, P.-T., & Shen, D. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-67558-9_19 · Cited by 63 · cited 2×
“Different approaches have been proposed, such as multi-task learning [70], generative models [63] and multimodal dropout [78, 101].”
BackgroundMethodHe, T., Fong, J. N., Moore, L. W., Ezeana, C. F., Victor, D., Divatia, M., Vasquez, M., Ghobrial, R. M., & Wong, S. T. C. (2021) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2021.101894 · Cited by 63 · cited 1×
“Also, latent representations of multiple imaging modalities and clinical data can be fused for risk assessment of liver transplantation for hepatocellular cancer [71].”
BackgroundAlbaradei, S., Napolitano, F., Thafar, M. A., Gojobori, T., Essack, M., & Gao, X. (2021) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2021.08.006 · Cited by 61
Ning, Z., Pan, W., Chen, Y., Xiao, Q., Zhang, X., Luo, J., Wang, J., & Zhang, Y. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btaa056 · Cited by 53 · cited 1×
“Feature selection can also be used on the concatenated marginal representations, choosing latent features that most strongly influence the target variable, as done in [65] to predict prognosis of clear cell renal cell carcinoma patients.”
BackgroundMUFASA: Multimodal Fusion Architecture Search for Electronic Health Records
Xu, Z., So, D. R., & Dai, A. M. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i12.17260 · Cited by 52 · cited 1×
“[102] have applied search algorithms to find the optimal fusion strategy, as well as modality-specific neural architecture searches for fusing EHR data.”
MethodMUFASA: Multimodal Fusion Architecture Search for Electronic Health Records
Xu, Z., So, D. R., & Dai, A. M. (2021) · arXiv · doi:10.48550/arxiv.2102.02340 · Cited by 52
A Variational Information Bottleneck Approach to Multi-Omics Data Integration
Lee, C., & van der Schaar, M. (2021) · arXiv · doi:10.48550/arxiv.2102.03014 · Cited by 50 · cited 3×
“Robustness to missing modalities can also be achieved in homogeneous intermediate fusion, as shown by [63].”
BackgroundMethodDeep Learning data integration for better risk stratification models of bladder cancer.
Poirion, O., Chaudhary, K., & Garmire, L. X. (2018) · Europe PMC (PubMed Central) · Cited by 48
Integrative survival analysis of breast cancer with gene expression and DNA methylation data
Bichindaritz, I., Liu, G., & Bartlett, C. (2021) · Bioinformatics · doi:10.1093/bioinformatics/btab140 · Cited by 42 · cited 4×
“Recurrent layers are able to output marginal representations encoding the input sequences.”
BackgroundMethodInfluentialLv, J., Wang, J., Shang, X., Liu, F., & Guo, S. (2020) · Bioscience Reports · doi:10.1042/bsr20201482 · Cited by 33
Integration of Multimodal Data for Breast Cancer Classification Using a Hybrid Deep Learning Method
Yan, R., Ren, F., Rao, X., Shi, B., Xiang, T., Zhang, L., Liu, Y., Liang, J. S., Zheng, C.-H., & Zhang, F. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-26763-6_44 · Cited by 30 · cited 1×
“[76] fused high-dimensional WSIs and 29 clinical variables.”
BackgroundA theoretical framework for deep transfer learning
Galanti, T., Wolf, L., & Hazan, T. (2016) · Information and Inference · doi:10.1093/imaiai/iaw008 · Cited by 29 · cited 1×
“With TL the required sample size can be significantly reduced [104].”
BackgroundYu, J., Wu, X., Lv, M., Zhang, Y., Zhang, X., Li, J., Zhu, M., Huang, J., & Zhang, Q. (2020) · Oncology Letters · doi:10.3892/ol.2020.12250 · Cited by 29 · cited 4×
“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.”
BackgroundMethodInfluentialWhat Makes Training Multi-Modal Classification Networks Hard?Preprint
Wang, W., Tran, D., & Feiszli, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.12681 · Cited by 27
Modeling Uncertainty in Multi-Modal Fusion for Lung Cancer Survival Analysis
Wang, H., Subramanian, V., & Syeda-Mahmood, T. (2021) · 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi48211.2021.9433823 · Cited by 26 · cited 1×
“[85] weighted the predicted probability of each submodel by its uncertainty.”
BackgroundZhang, X., Wang, J., Lu, J., Su, L., Wang, C., Huang, Y., Zhang, X., & Zhu, X. (2021) · Frontiers in Oncology · doi:10.3389/fonc.2021.689626 · Cited by 24
Zhao, Z., Li, Y., Wu, Y., & Chen, R. (2019) · Cancer Biomarkers · doi:10.3233/cbm-190380 · Cited by 23
Kang, M., Lee, S., Lee, D., & Kim, S. (2020) · Frontiers in Genetics · doi:10.3389/fgene.2020.00869 · Cited by 21 · cited 1×
“[73] used an attention mechanism for multiomics data [99] for interpreting predictions of gene expression.”
MethodPAN-CANCER INTEGRATIVE HISTOLOGY-GENOMIC ANALYSIS VIA INTERPRETABLE MULTIMODAL DEEP LEARNING
Chen, R. J., Lu, M. Y., Williamson, D. F. K., Chen, T., Lipková, J., Shaban, M., Shady, M., Williams, M., Joo, B., Noor, Z., et al. (2022) · Journal of Pathology Informatics · doi:10.1016/j.jpi.2022.100057 · Cited by 18
Oh, M., Park, S., Lee, S., Lee, D., Lim, S., Jeong, D., Jo, K., Jung, I., & Kim, S. (2020) · Frontiers in Genetics · doi:10.3389/fgene.2020.564792 · Cited by 17
Deep Learning for Integrated Analysis of Breast Cancer Subtype Specific Multi-omics Data
Rakshit, S., Saha, I., Chakraborty, S. S., & Plewczyski, D. (2018) · TENCON 2018 - 2018 IEEE Region 10 Conference · doi:10.1109/tencon.2018.8650144 · Cited by 16 · cited 1×
“[39] used stacked AEs (SAEs) to fuse multi-omics data for classifying molecular subtypes of breast cancer.”
MethodWang, X., Liu, M., Zhang, Y., He, S., Qin, C., Li, Y., & Lu, T. (2021) · Briefings in Bioinformatics · doi:10.1093/bib/bbab289 · Cited by 16 · cited 1×
“In addition to element-wise aggregation, attention-based fusion methods can be applied in order to weight different latent features by their importance [74, 79, 81].”
MethodDropout-Enabled Ensemble Learning for Multi-scale Biomedical Data
Momeni, A., Thibault, M., & Gevaert, O. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-11723-8_41 · Cited by 12
An integrative approach for fine-mapping chromatin interactions
Jaroszewicz, A., & Ernst, J. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btz843 · Cited by 7
Chen, R. J., Lu, M. Y., Shady, M., Lipková, J., Chen, T., Williamson, D. F. K., Joo, B., & Mahmood, F. (2021) · Clinical Cancer Research · doi:10.1158/1557-3265.adi21-po-002 · Cited by 7
Dropout-Enabled Ensemble Learning for Multi-Scale Biomedical DataPreprint
Momeni, A., Thibault, M., & Gevaert, O. (2018) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/440362 · Cited by 2
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
Advance in peptide-based drug development: delivery platforms, therapeutics and vaccines
Xiao, W., Jiang, W., Chen, Z., Huang, Y., Mao, J., Zheng, W., Hu, Y., & Shi, J. (2025) · Signal Transduction and Targeted Therapy · doi:10.1038/s41392-024-02107-5 · Cited by 449
Multimodal data fusion for cancer biomarker discovery with deep learning
Steyaert, S., Pizurica, M., Nagaraj, D., Khandelwal, P., Hernandez-Boussard, T., Gentles, A. J., & Gevaert, O. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00633-5 · Cited by 402
Hybrid multimodal wearable sensors for comprehensive health monitoring
Mahato, K., Saha, T., Ding, S., Sandhu, S. S., Chang, A.-Y., & Wang, J. (2024) · Nature Electronics · doi:10.1038/s41928-024-01247-4 · Cited by 404
Deep learning based multimodal biomedical data fusion: an overview and comparative review
Duan, J., Xiong, J., Li, Y., & Ding, W. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102536 · Cited by 284
Artificial intelligence-based methods for fusion of electronic health records and imaging data
Mohsen, F., Ali, H., El Hajj, N., & Shah, Z. (2022) · Scientific Reports · doi:10.1038/s41598-022-22514-4 · Cited by 250
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.