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 301–400 of 749
Precision cardiovascular medicine with big data and AI
Xu, Q., Li, Y., Zhu, M., Cai, Y., Cheng, X., Wan, M., Ju, J., Xu, Y., Li, Y., & Liu, Y. (2026) · npj Digital Medicine · doi:10.1038/s41746-026-02538-0 · Cited by 8
A review of multi-omics integration techniques across five machine learning method families
Olowolayemo, A., Souag, A., Sirlantzis, K., Turner, S., & Wilson, C. M. (2026) · Bioinformatics Advances · doi:10.1093/bioadv/vbag108 · Cited by 7
“2022, Stahlschmidt et al .”
Ferrari, F., Ferreira, M. P., & Feitosa, R. Q. (2023) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-x-1-w1-2023-999-2023 · Cited by 5
“Lastly, the late fusion strategy concatenates the decoder outputs from encoder-decoder networks trained with optical and SAR images (Stahlschmidt et al., 2022).”
BackgroundBimodal Fusion of Single-Cell Impedance and Imaging Data Using Five Deep Neural Networks
Chen, S., Chen, X., Huang, X., et al. (2024) · IEEE Nanotechnology Magazine · doi:10.1109/mnano.2024.3513132 · Cited by 4
“Nowadays, bimodal fusions in deep learning (e.g., data-level direct modeling, feature-level marginal/joint fusions, and decision-level averaging/meta-learning) have been developed to merge raw data, features, or preliminary decisions of two modalities [8].”
Wang, Y., & Lam, H. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103170 · Cited by 4
Yue, X., Zhang, C., Wang, Z., Yu, Y., Cong, S., Shen, Y., & Zhao, J. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.108379 · Cited by 4
Adib, F. Z., Amirmazlaghani, M., & Rahmati, M. (2025) · Discover Artificial Intelligence · doi:10.1007/s44163-025-00279-9 · Cited by 4
“The evolution of fusion strategies has been further influenced by recent developments in deep Boltzmann machines, especially in applications involving the integration of diverse data types such as medical images and associated textual information [23].”
InfluentialGollwitzer, M., Mazanec, V., Steindl, M., Atli, B., Stroh-Holly, N., Hauser, A., Sardi, G., Rossmann, T., Aspalter, S., Rauch, P., et al. (2025) · Brain Sciences · doi:10.3390/brainsci15111187 · Cited by 4
Han, Y., Wang, Y., Cui, W., Xiu, S.-J., Yang, Y., & Zhang, J. (2025) · Journal of Magnetic Resonance Imaging · doi:10.1002/jmri.70187 · Cited by 4
Lightweight multimodal Cycle-Attention Transformer towards cancer diagnosis
Liu, S., Ma, X., Deng, S., Suo, Y., Zhang, J., & Ng, W. W. Y. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124616 · Cited by 5
Zhao, Y., Li, Y., Zhang, Y., Yan, X., Yin, G., & Liu, L. (2025) · IEEE Access · doi:10.1109/access.2025.3531705 · Cited by 4
“In multimodal learning, model fusion strategies mainly include early fusion, slow fusion, and late fusion, each differing in data integration methods [26].”
Xie, S., Peng, S., Zhao, L., Yang, B., Qu, Y., & Tang, X. (2025) · Molecular Genetics and Genomics · doi:10.1007/s00438-024-02217-3 · Cited by 6
“Machine learning algorithms can seamlessly integrate numerous variables (Stahlschmidt et al. 2022), enabling comprehensive analysis of vast datasets, including demographic and clinical factors, to better predict stroke risk.”
Fanelli, F., Guglielmi, G., Troiano, G., Rivara, F., Passeri, G., Prencipe, G., Zhurakivska, K., Guglielmi, R., & Calciolari, E. (2025) · Journal of Clinical Medicine · doi:10.3390/jcm14134462 · Cited by 8
Biran, A., & Jeremic, A. M. (2023) · Digital Medicine and Healthcare Technology · doi:10.5772/dmht.13 · Cited by 4
Applications for Deep Learning in Epilepsy Genetic Research
Zeibich, R., Kwan, P., O'Brien, T. J., Perucca, P., Ge, Z., & Anderson, A. (2023) · International Journal of Molecular Sciences · doi:10.3390/ijms241914645 · Cited by 4
“Stahlschmidt, Ulfenborg and Synnergren [101], and the book “Deep Learning” by Bengio, Goodfellow and Courville [102].”
BackgroundInfluentialHow is Big Data reshaping preclinical aging research?
Fernández, M. E., Martínez-Romero, J., Aon, M. A., Bernier, M., Price, N. L., & de Cabo, R. (2023) · Lab Animal · doi:10.1038/s41684-023-01286-y · Cited by 5
HAC-POCD: Hardware-Aware Compressed Activity Monitoring and Fall Detector Edge POC Devices
Rashid, H.-A., & Mohsenin, T. (2023) · IEEE Biomedical Circuits and Systems Conference (BioCAS) · doi:10.1109/biocas58349.2023.10389023 · Cited by 4
“Due to its proven superiority to other fusion techniques, we used the Intermediate fusion methodology in this work to fuse several modalities [19].”
MethodWan, X., Wang, Y., Wang, Z., Tang, Y., & Liu, B. (2024) · Physiological Measurement · doi:10.1088/1361-6579/ad5bbc · Cited by 6
Schuster, E. J., Dashzeveg, N. K., Jia, Y., Golam, K., Zhang, T., Hoffman, A., Zhang, Y., Zheng, C., Ramos, E. K., Taftaf, R., et al. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.04.10.536233 · Cited by 4
Advances in Multi‐modal Intelligent Sensing
Rehman, M. U., Jamshed, M. A., & Kalsoom, T. (2024) · Wiley eBooks · doi:10.1002/9781394257744.ch1 · Cited by 13
Integrating Multimodal Data Fusion for Advanced Biomedical Analysis
Lilhore, U. K., & Simaiya, S. (2025) · Wiley eBooks · doi:10.1002/9781394269969.ch7 · Cited by 4
Dong, S., Fu, A., & Liu, J. (2024) · Quantitative Imaging in Medicine and Surgery · doi:10.21037/qims-24-100 · Cited by 5
“Despite attempts to increase the sample size and improve deep learning model classification accuracy through migration learning (39) and data augmentation (40), the results remain unsatisfactory.”
ResultCascaded cross-modal transformer for audio–textual classification
Ristea, N.-C., Anghel, A., & Ionescu, R. T. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10869-1 · Cited by 7
“…the complexity of real-world classification tasks through the combination of various modalities is not an easy challenge, requiring the development of robust and efficient methods to effectively fuse multiple data sources (Ramachandram and Taylor 2017; Gao et al. 2020; Stahlschmidt et al. 2022).”
Yao, Q., Jia, W., Zhang, T., Chen, Y., Ding, G., Dang, Z., Shi, S., Chen, C., Qu, S., Zhao, Z., et al. (2025) · Abdominal Radiology · doi:10.1007/s00261-025-04849-4 · Cited by 3
“Notably, in recent years, deep learning (DL)—a branch of machine learning inspired by the biological brain—has demonstrated superior capabilities for non-linear fitting and reasoning with high-dimensional data [18–20], making it particularly well-suited for imaging data.”
Raman spectral unmixing via multimodal time-frequency transformations and deep learning
Shang, L., Ding, C., Ji, X., Zhu, J., Wu, J., Xiong, S., Wang, H., & Yin, J. (2025) · Optics Express · doi:10.1364/oe.555722 · Cited by 3
Wang, N., Wu, M.-J., Gu, W., Dai, C., Shao, Z., & Subbalakshmi, K. P. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf217 · Cited by 6
“2(b).2, aims to achieve effective cross-modal fusion with E lT , (cid:2) Z l , and E lF , considering the complementarity and redundancy of multimodal information [42].”
MSNet: Multimodal Self-attention Network for Depression Detection via Fusion of Eye Tracking and EEG
Zhu, F., Wu, B., Huo, Y., Dang, R., Hu, B., & Wang, Q. (2025) · ACM Symposium on Eye Tracking Research and Applications (ETRA) · doi:10.1145/3715669.3723106 · Cited by 4
“…and Olatunji 2012; Skaramagkas et al. 2021], electrocardiogram (EOG) [Pan et al. 2021], and electroencephalography (EEG) [Yasin et al. 2021, 2023], the relationships between these modes can be categorized into three types: complementarity, redundancy, and collaboration [Stahlschmidt et al. 2022].”
Zhang, J., Yang, Y., Chen, B., Zhao, Y., & Sun, H. (2025) · Interdisciplinary medicine · doi:10.1002/inmd.20250042 · Cited by 4
Vision Transformer‐Enhanced Multi‐Descriptor Approach for Robust Age‐Invariant Face Recognition
Appati, J. K., Tsifokor, E., Amissah, D. K., & Adjepon‐Yamoah, D. E. (2025) · Applied AI Letters · doi:10.1002/ail2.70000 · Cited by 4
Ortiz-Pérez, D., Benavent-Lledo, M., Rodríguez, J. G., Tomás, D., & Vizcaya-Moreno, M. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113787 · Cited by 4
“A joint or hybrid fusion strategy involves combining features obtained from each modality for later use in a final model, but only after being processed individually by each modality model [298].”
CrossFusionSleepNet: A multimodal deep learning model for automatic sleep stage classification
Cao, Y., Xiang, W., Wei, J., Cao, S., Tian, X., Zhong, J., Fang, X., Luo, B., Lyu, H., & Li, X. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.108538 · Cited by 8
Fusing Cross-Domain Knowledge from Multimodal Data to Solve Problems in the Physical World
Zheng, Y. (2025) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3768625 · Cited by 6
“As the natural processes and physical environment are very complex, it is rare that a single information acquisition method provides complete understanding of a phenomenon of interest [22].”
Li, Q., Wang, S., Safari, M., Hu, X. Y., Qiu, R. L. J., Roper, J. R., Lin, M., Lin, J. Y., Torres, M. A., & Yang, X. (2025) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ae0be6 · Cited by 5
Cognitive Internet of Things: A Review of Theory, Applications, and Recent Advances
Giuliano, A., McCafferty-Leroux, A., Yawney, J., & Gadsden, S. A. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3615461 · Cited by 14
“Common methods include concatenation, averaging or weighted combination of input data into a single matrix or tensor [188].”
Multiomics strategy-based obesity biomarkers discovery for precision medicine
Ye, Z.-W., Yang, Q.-Y., Xu, W., Li, F., Luo, P., Qin, S., & Wang, F. (2025) · International Journal of Obesity · doi:10.1038/s41366-025-01906-2 · Cited by 7
“…rapid evolution of arti fi cial intelligence (AI) has transformed this landscape, outperforming conventional methods in ef fi ciency, depth, and scalability, and the ability to resolve high-dimensional nonlinear relationships, integrate unstructured data, and support real-time decision-making [110].”
Chen, S., Wang, X., Shi, M., Tao, G., Qiao, S., & Chen, Z. (2025) · Forests · doi:10.3390/f16111709 · Cited by 3
Multimodal Fusion of Chest X-Rays and Blood Biomarkers for Automated Silicosis Staging
Priego, B., Sopo-Lambea, I., Khalili, E., Martín-Carrillo, A., Campos‐Caro, A., León‐Jiménez, A., & Morillo, D. (2025) · Journal of Clinical Medicine · doi:10.3390/jcm14228074 · Cited by 7
Fu, W., Li, H., Quan, X., Wang, X., Huang, W., & Zhang, H. (2025) · Interdisciplinary Sciences Computational Life Sciences · doi:10.1007/s12539-025-00783-7 · Cited by 3
Zhu, H.-W., Yi, H.-C., You, Z., He, S., & Shang, X. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103981 · Cited by 3
Lu, Y., Li, X., El‐Aty, A. M. A., Ju, X., & Yong, Y. (2025) · Veterinary Sciences · doi:10.3390/vetsci12121129 · Cited by 5
“Moreover, inconsistencies in data quality and standardization across research groups and experimental methodologies hinder effective data integration and comparative analysis [87].”
Recent Advances and Future Directions of Artificial Intelligence in Glaucoma Management
Tang, W., Hang, Y., Zhang, J., & Dang, Y. (2025) · The Open Ophthalmology Journal · doi:10.2174/0118743641430437251130165439 · Cited by 4
Rosa, L. E. C. L., Marcos, D., Slagter, B., & Reiche, J. (2025) · International Journal of Remote Sensing · doi:10.1080/01431161.2025.2598147 · Cited by 6
Islam, M. S., Jamal, A. T., & Alkhathlan, A. (2025) · Diagnostics · doi:10.3390/diagnostics16010107 · Cited by 5
Halab, K., Marzoug, N., Meslouhi, O. E., Elassad, Z. E. A., & Akhloufi, M. A. (2025) · Big Data and Cognitive Computing · doi:10.3390/bdcc10010012 · Cited by 3
Nakanishi, R., Hirata, A., & Kubota, Y. (2025) · Sensors · doi:10.3390/s26010212 · Cited by 6
“These findings are consistent with broader trends in biomedical informatics, where integrating heterogeneous modalities has been shown to enhance predictive performance and facilitate personalized medicine [36,44].”
Chen, Y., Gao, Y., Yu, S., Zhao, C., & Lu, Y. (2025) · Journal of Industrial Integration and Management · doi:10.1142/s2424862225300042 · Cited by 7
Vulfin, A., Sulavko, A. Е., Vasilyev, V. I., Minko, A., Kirillova, A., & Samotuga, A. (2026) · Machine Learning and Knowledge Extraction · doi:10.3390/make8010011 · Cited by 10
“Experience in multimodal analysis within related domains [67] indicates that late or hybrid binding facilitates the controlled updating of individual modalities and the localization of drift without requiring a comprehensive system overhaul.”
Xiao, Y., Yang, S., He, M., Chen, L., Wu, Y., & Zhong, L. (2026) · npj Digital Medicine · doi:10.1038/s41746-025-02295-6 · Cited by 7
Ibam, E. O., & Oluwagbemi, J. B. (2026) · Journal of Computing Theories and Applications · doi:10.62411/jcta.14944 · Cited by 5
“By leveraging complementary modalities, multimodal fusion enables models to capture latent interactions that are inaccessible to single-modality systems, resulting in more stable and clinically meaningful predictions [10] – [13].”
Explainable multimodal deep learning models for variable-length sequences in critically ill patients
Martin, J., Afshar, M., Afshar, A. S., Caskey, J., Dligach, D., Gao, Y., Gao, J., Chen, G., Mayampurath, A. M., & Churpek, M. M. (2026) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2026.105001 · Cited by 4
Remote Tower Air Traffic Controller Multimodal Fatigue Detection
Pan, W., Song, D., Liang, R., Yin, Z., & Han, B. (2026) · Sensors · doi:10.3390/s26061856 · Cited by 3
Raza, M., Azam, A., Qaiser, T., & Rajpoot, N. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02059 · Cited by 13
“Recently, integrating multiple data modalities have been shown to improve survival prediction in cancer research, with most studies focusing on combining genomic data such as transcriptomic data with histology whole slide images (WSIs) [7, 52, 54].”
Liang, Y., Li, S., You, X., Guo, Y., & Tang, J. (2023) · Current Bioinformatics · doi:10.2174/0115748936272040231117114252 · Cited by 3
Discriminative fusion of moments-aligned latent representation of multimodality medical data
Xie, J., Zhong, W., Yang, R., Wang, L., & Zhen, X. (2023) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ad1271 · Cited by 3
3D Object Quality Prediction for Metal Jet Printer with Multimodal Thermal Encoder Network
Chen, R. L., Zheng, W., Jalui, S., Suri, P., & Zeng, J. (2023) · IEEE Eurasia Conference on IOT, Communication and Engineering (ECICE) · doi:10.1109/ecice59523.2023.10383123 · Cited by 3
“With the nature of heterogeneity of data sources in many real-world application domains that contain multisensory data collection, such as in the healthcare field [27,34,38], sequencing prediction [39], review analysis [36], and urban infrastructure planning [37,40].”
BackgroundDranga, M., Mihai, C., Gavrilescu, O., Prelipcean, C. C., & Popa, I. V. (2024) · Biomedicines · doi:10.3390/biomedicines12030475 · Cited by 5
Bijli, M. K., Nisa, U. U., Makhdomi, A. A., & Hamadani, H. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-24001-0.00002-6 · Cited by 6
Investigating Enzyme Biochemistry by Deep Learning: A Computational Tool for a New Era
Rayka, M., Mirzaei, M., Farnoosh, G., & Latifi, A. M. (2024) · Journal of Computational Biophysics and Chemistry · doi:10.1142/s2737416524400052 · Cited by 3
Deep metric loss for multimodal learning
Moon, S., & Lee, H. (2025) · Machine Learning · doi:10.1007/s10994-024-06709-6 · Cited by 4
“Additionally, this approach may fail to identify relationships between the modalities that only become apparent at higher levels of representation (Stahlschmidt et al., 2022).”
Fuenzalida, K. M., Leal-Witt, M. J., Acevedo, A., Muñoz, M., Gudenschwager, C., Arias, C., Cabello, J. F., la Marca, G., Rizzo, C., Pietrobattista, A., et al. (2025) · International Journal of Molecular Sciences · doi:10.3390/ijms26083839 · Cited by 3
MGFNet: a multiscale gated fusion network for multimodal semantic segmentation
Wu, H., Li, Z., & Wen, Z. (2025) · The Visual Computer · doi:10.1007/s00371-025-03912-x · Cited by 11
Zheng, Z. L., Chen, X., Lin, B., et al. (2025) · Bulletin of the Seismological Society of America · doi:10.1785/0120240255 · Cited by 3
Pradhan, S., Wang, G., Xuan, J., Wang, P., Li, C., & Lü, J. (2025) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai64502.2025.00059 · Cited by 4
“This approach allows models to independently learn higher-level representations from each modality before integrating them [23, 24], making it highly effective for complex tasks.”
Martell, M. T., Haven, N. J. M., Masoumi, M. H., Cikaluk, B. D., & Zemp, R. J. (2025) · Biomedical Optics Express · doi:10.1364/boe.570451 · Cited by 4
Miao, S., Jiang, Y., Huang, W., Jiang, Y., Sun, M., Wang, M., Qi, H., Li, A., Liu, Z., Wang, Q., et al. (2025) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2025.103280 · Cited by 5
Power of Deep Learning Models in Bioinformatics
Thareja, P., & Chhillar, R. S. (2023) · Advances in intelligent systems and computing · doi:10.1007/978-981-99-0550-8_42 · Cited by 3
Cascaded Cross-Modal Transformer for Request and Complaint Detection
Ristea, N.-C., & Ionescu, R. T. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3612846 · Cited by 4
“Tackling the complexity of real-world data through the combination of multiple modalities is a challenging task, requiring the development of a robust and efficient method for aggregating all sources of information [8, 20, 23].”
MethodDeep learning for automated diagnosis of uveal melanoma
Dadzie, A. K., Iddir, S. P., Abtahi, M., Ebrahimi, B., Le, D., Son, T., Heiferman, M. J., & Yao, X. (2024) · Ophthalmic Technologies · doi:10.1117/12.3000655 · Cited by 4
“In contrast, early fusion, which combines color channels at the input level, only learns low-level features and may not capture complex inter-channel relationships, elucidating its inferior performance compared to intermediate fusion 38 .”
BackgroundMultisensor data fusion in Digital Twins for smart healthcare
Lv, Z. (2024) · Elsevier eBooks · doi:10.1016/b978-0-44-313233-9.00008-4 · Cited by 4
Hanji, S. S., & Birje, M. N. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19078-y · Cited by 4
“Using ML models, it is possible to combine multimodal data with a high degree of dimensionality, a variety of statistical properties, and various missing value patterns [13].”
Cross-Modality Calibration in Multi-Input Network for Axillary Lymph Node Metastasis Evaluation
Gravina, M., Santucci, D., Cordelli, E., Soda, P., & Sansone, C. (2024) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2024.3397246 · Cited by 3
“…strategies to implement include the concatenation ( (cid:2) ), the elementwise summation ( + ), and product ( × ), combinations of these operations [17], other functions such as Kronecker product [25], [26], or more complex methods consisting in tensor-based operations or attention mechanisms [27].”
BackgroundMethodYOLOv8 Unleashed on Orthopantomograms: Deep Learning Approach for Mandibular Cyst Diagnosis
Tropčić, M., Rašić, M., & Subašić, M. (2024) · MIPRO ICT and Electronics Convention (MIPRO) · doi:10.1109/mipro60963.2024.10569410 · Cited by 3
“As a result, they have achieved state-of-the-art performance in various domains [5].”
BackgroundFarhadyar, K., Bonofiglio, F., Hackenberg, M., Behrens, M., Zöller, D., & Binder, H. (2024) · BMC Medical Research Methodology · doi:10.1186/s12874-024-02327-x · Cited by 3
“There are different ways to tackle this (introduced in [25]).”
BackgroundXu, Y., Liu, S., Tian, Q., Kou, Z., Li, W., Xie, X., & Xiaotao, W. (2025) · European Spine Journal · doi:10.1007/s00586-025-08668-5 · Cited by 4
“Multi-modal model is a multi-structured composite model that can simultaneously use deep learning (DL) models and other models to extract features from image data and numerical data, improving the accuracy of model predictions [7 ].”
Speech-Based Estimation of Schizophrenia Severity Using Feature Fusion
Premananth, G., & Espy-Wilson, C. (2025) · IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) · doi:10.1109/icasspw65056.2025.11011243 · Cited by 3
“These fusion models have proven effective in data-scarce settings where training data from a single modality is insufficient to train deep learning models [14].”
Wang, F., Liu, J., Gao, F., & Li, Y. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.07.05.547886 · Cited by 3
“Then we concatenate all the omics specific feature and the shared feature as the embedding of multi-omics data in the late fusion method [32].”
MethodNunes, A. S., Patel, S., Oubre, B., Jas, M., Kulkarni, D. D., Luddy, A. C., Eklund, N. M., Yang, F. X., Manohar, R., Soja, N. N., et al. (2024) · medRxiv · doi:10.1101/2024.12.28.24319527 · Cited by 5
MoMA: a mixture-of-multimodal-agents architecture for enhancing clinical prediction modelling
Gao, J., Rahman, M., Caskey, J., Oguss, M., O’Rourke, A., Brown, R., Stey, A., Mayampurath, A., Churpek, M. M., Chen, G., et al. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-02219-4 · Cited by 2
“Published in partnership with Seoul National University Bundang Hospital https://doi.org/10.1038/s41746-025-02219-4 MoMA: a mixture-of-multimodal-agents architecture for enhancing clinical prediction modelling”
InfluentialMoTIF: a Method for Trustworthy Dynamic Multimodal Learning on Omics
Lu, Y., Peng, R., Jiang, B., & Wang, J. (2023) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm58861.2023.10386044 · Cited by 4
“This shortcoming becomes particularly poignant in domains like medicine and life sciences, where model interpretability is paramount [5].”
BackgroundZhou, C., Wang, H., Li, X., Liu, W., & Liu, Z. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10447524 · Cited by 6
“The emerging domain of multimodal learning in artificial intelligence has spurred research interest in its potential for cancer prognosis, commonly termed survival analysis [5].”
BackgroundZhi-xiu, Z. (2024) · Asia-Pacific Conference on Communications Technology and Computer Science (ACCTCS) · doi:10.1109/acctcs61748.2024.00024 · Cited by 2
“Khotsirwong et al. [7] [8] reviewed the application of deep learning for biomedical data fusion.”
BackgroundMarletta, D. A., Nanni, M., Giuca, G., Sanzarello, I., Zampogna, B., & Leonetti, D. (2024) · Applied Sciences · doi:10.3390/app142411652 · Cited by 4
Improving inner speech decoding by hybridisation of bimodal EEG and fMRI data
Wellington, S., Wilson, H., Liwicki, F., Gupta, V., Saini, R., De, K., Abid, N., Rakesh, S., Eriksson, J., Watts, O., et al. (2024) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc53108.2024.10781692 · Cited by 7
MixMAS: A Framework for Sampling-Based Mixer Architecture Search for Multimodal Fusion and Learning
Chergui, A., Bezirganyan, G., Sellami, S., Berti‐Équille, L., & Fournier, S. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825593 · Cited by 2
Cao, Y.-J., Zhang, J., Ma, Y., Zhang, S., Li, C., Liu, S., Feng, C., & Huang, P. (2025) · International Journal of Legal Medicine · doi:10.1007/s00414-025-03432-2 · Cited by 2
Shen, Y. (2025) · IEEE Access · doi:10.1109/access.2025.3587298 · Cited by 5
“Contemporary integration strategies typically begin with modality-specific feature extraction followed by various fusion mechanisms, including vector concatenation, attention-based weighted combination, and unified network architectures [25], [27], [28], [29].”
Liu, P., Zhou, X., Lv, X., Chen, C., Chen, X., Luo, C., Wu, X. F., Chen, C., & Wu, L. (2025) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2025.105513 · Cited by 2
A Laplace diffusion-based transformer model for heart rate forecasting within daily activity context
Mateescu, A., Hadarau, I., Anghel, I. M., Cioara, T., Anchidin, O., & Nemes, A. (2025) · Machine Learning with Applications · doi:10.1016/j.mlwa.2025.100746 · Cited by 3
Multimodal Deep Learning for Diabetic Retinopathy: A Survey
Qin, G.-Y., Peng, Q., Zhou, Y.-S., Peng, J., Liu, Q., & Xu, J. (2025) · Journal of Ophthalmology · doi:10.1109/mipr67560.2025.00032 · Cited by 4
“…and late (ensemble-based)—each offer distinct trade-offs, with late fusion often outperforming others for independent modalities, but all approaches risk overfitting and “black-box” complexity as more modalities are added despite regularization and attention mechanisms to mitigate this [40][41].”
Wu, S., Huang, Y., Luo, L., Deng, J., Wang, Y.-F., Ye, F., & Li, D. (2025) · Frontiers in Cellular and Infection Microbiology · doi:10.3389/fcimb.2025.1665468 · Cited by 3
“For ML model construction, six easily obtainable and objective laboratory variables (age, serum TRUST titer, CSF protein, CSF nucleated cells, IgG index, CSF TTs) were selected to .capture nonlinear biological relationships (Stahlschmidt et al., 2022).”
Xie, Y., Li, J., Zhang, Z., Meng, B., Dai, S., Zhou, Y., Kennedy, E., Jiao, N., Chen, H. I., & Dong, Z. (2025) · Bioinformatics · doi:10.1093/bioinformatics/btaf657 · Cited by 5
“…fields such as computer vision (Voulodimos et al. 2018, Esteva et al. 2019), natural language processing (Young et al. 2018, Li et al. 2021, Otter et al. 2021), and speech recognition (Yoo et al. 2022), and has shown great potential in other fields such as biomedicine (Stahlschmidt et al. 2022).”
Yilmaz, U., & Solak, F. Z. (2026) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.70546 · Cited by 4
MM-GHiNet: A multimodal graph hierarchical network for brain disease diagnosis
Li, C., Xu, J., Huang, Z., & Deng, L. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.131202 · Cited by 3
Huang, J., Yang, X., Liang, X., Chen, S., Sun, Y., Mok, G. S. P., Li, S., Wang, Y., & Tan, T. (2026) · Medical Image Analysis · doi:10.1016/j.media.2026.103956 · Cited by 4
Xie, L., Xiao, S., Ming, B., Xiang, Z., Rui, Z., Liu, X., & Zhan, Y. (2026) · Sensors · doi:10.3390/s26020737 · Cited by 2
“Simultaneously, multimodal deep learning frameworks have been increasingly explored to fuse imaging and clinical data in order to enhance overall predictive performance [31].”
Zhu, P.-F., Zhang, X., Mao, Y., Zhou, P., Lin, J.-J., Shi, L., Cui, X., & He, Y. (2026) · BMC Cancer · doi:10.1186/s12885-025-15153-1 · Cited by 2
“In this study, all of our fusion strategies use early fusion, combining features from different modalities into a single feature vector [34].”
A survey On large language models for medical time series
Liu, X., Zhou, F., Xiao, H., Li, Z., Liu, S., & Qian, L. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.131364 · Cited by 7
Peng, L., Li, Q., Cui, K., Qin, X., Qing, Y., Guo, Z., & Qin, W. (2026) · International Communications in Heat and Mass Transfer · doi:10.1016/j.icheatmasstransfer.2026.110696 · Cited by 2
Alsanie, S. A. (2026) · Frontiers in Nutrition · doi:10.3389/fnut.2026.1778056 · Cited by 5
Zhang, W., Hou, C., Wang, X., Kang, H., Li, S., Sun, Y., Zheng, Y., Zhang, W., & Lam, S.-K. (2026) · Diagnostics · doi:10.3390/diagnostics16050807 · Cited by 1
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.