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 501–600 of 749
Visual Question Answering Model Based on Cross Memory Attention
文, 必. (2023) · Computer Science and Application · doi:10.12677/csa.2023.136116
Improving information fusion in deep learning
Don, D. P. M. K. (2023) · Queensland University of Technology · doi:10.5204/thesis.eprints.241291
Joint clinical and molecular subtyping of COPD with variational autoencoders
Maiorino, E., Marzio, M. D., Xu, Z., Yun, J. H., Chase, R. P., Hersh, C. P., Sin, D. D., Weiss, S. T., Silverman, E. K., Castaldi, P. J., et al. (2026) · Nature Communications · doi:10.1038/s41467-026-72989-2 · Cited by 4
Multi-Modal Lifelog Data Fusion for Improved Human Activity Recognition: A Hybrid ApproachPreprint
Oh, Y., & Kim, S. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4601110
Binary Classification of Drug Sensitivity Prediction Using Multimodal Deep LearningPreprint
Aqeeli, N., & Alzaid, E. (2023) · Research Square · doi:10.21203/rs.3.rs-3490258/v1
Neither a Picasso Nor a Da Vinci: An Examination of Novice Artwork Pricing with Multi-Modal DataPreprint
Sikdar, S., Chakraborty, I., & Doghonadze, N. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4683033
Biomedical Data Fusion for Enrichment of Medications using AIPreprint
Sarker, M., & Nandurkar, D. A. (2024) · Research Square · doi:10.21203/rs.3.rs-4084909/v1
Zhang, H., Xia, D., Qu, J., Li, Y., Shun-shi, Y., Jiang, M., Zhou, L., Tao, X., Fan, X., Zhou, H., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4760256
Deep transfer learning from limited source for abdominal CT and MR image segmentation
Krishnan, C., Schmidt, E., Onuoha, E. E., Mrug, M. M., Cárdenas, C., & Kim, H. (2024) · SPIE Medical Imaging: Image Processing · doi:10.1117/12.3006814 · Cited by 1
“However, its applicability to medical datasets raises important considerations [8].”
BackgroundDetection and metrology of micro-nano particles through the integration of image and laser modes
Tao, Y., & He, H. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad3a8c
Zhang, Z., Xie, J., Zhong, W., Liang, F., Yang, R., & Zhen, X. (2024) · PubMed Central · doi:10.12122/j.issn.1673-4254.2024.01.16 · Cited by 1
Cross-Modal Alignment and Contrastive Learning for Enhanced Cancer Survival PredictionPreprint
Li, T., Zhou, X., Xue, J., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4789219
Han, S., Wang, C., Lai, Q., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4864669
Multimodal Data-Driven Intelligent Systems for Breast Cancer Prediction
Pichai, S., Kanimozhi, G., Rani, M. M. S., & Riyaz, N. (2024) · EAI Endorsed Transactions on Pervasive Health and Technology · doi:10.4108/eetpht.10.6424
Channel and model selection for multi-channel EEG input to neural networks
Harachi, K., Yamamoto, Y., Muramatsu, A., Nagahara, H., Takemura, N., Shimojo, S., Furihata, D., & Mizuno‐Matsumoto, Y. (2024) · SICE Journal of Control Measurement and System Integration · doi:10.1080/18824889.2024.2385579 · Cited by 2
“This approach facilitates the discovery of useful shared and peripheral latent factors [12].”
CSIP: Contrastive learning with Graph Neural Network enables chemical structure to image mapping
Liu, L. (2024) · Applied and Computational Engineering · doi:10.54254/2755-2721/86/20241606
Deep Learning-Based Inference of Uterine Contractions from Maternal ECGPreprint
Tanaka, S., Ito, K., Takano, K., & Takasaki, Y. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.09.29.615726
“Although it is generally considered challenging to integrate metadata, which lacks temporal information, into time-series models such as LSTMs, recent research has explored ways to incorporate metadata into deep learning models (27)(48)(49).”
BackgroundArtificial intelligence-assisted data fusion
Ding, X., Zhang, Y., Haick, H., & Zhang, M. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-15684-7.00042-7 · Cited by 2
Machine Learning in Bioinformatics
Zheng, H., Wassan, J. T., & Wang, H. (2024) · Elsevier eBooks · doi:10.1016/b978-0-323-95502-7.00166-4
Research on ICU Sepsis Prognosis Based on Multimodal Fusion Modeling
武, 瑞. (2024) · Modeling and Simulation · doi:10.12677/mos.2024.136583
Mmrag: Multimodal Medical Retrieval Augmented Generation SystemPreprint
Phani, S., Abdul, A., Kuo, C., Chen, J., & Dash, J. K. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.5021734
Schulze, E., Palm, C., Kerschbaum, M., et al. (2024) · MSK – Muskuloskelettale Physiotherapie · doi:10.1055/a-2402-9982
“Diese multimodalen KNNe können sich gegenseitig stützen - de oder ergänzende Informationen modellieren [53] (▶ abb.”
Multimodal Analysis of Bioimages
Scarpino, I., & Vallelunga, R. (2024) · Elsevier eBooks · doi:10.1016/b978-0-323-95502-7.00213-x
Shao, Q., Dai, Y., Ying, H., et al. (2024) · IEEE International Conference on Medical Artificial Intelligence (MedAI) · doi:10.1109/medai62885.2024.00060
“Fusion of multimodal data is a crucial component of multimodal artificial intelligence solutions, offering the potential to address inference challenges with greater accuracy compared to unimodal approaches [18].”
BackgroundNuevas contribuciones en aplicaciones de fusión multimodal de bioseñales
González, L. M. P. (2024) · RiuNet (Universitat Politècnica de València) · doi:10.4995/thesis/10251/213614
Transformer-Based Gene Expression Levels Prediction Using Multimodal Information
Song, T., Pan, Z., Song, H., Gao, Y., Dai, H., & Wang, X. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10822784
Jiao, Y., & He, X. (2025) · Computer Methods in Biomechanics & Biomedical Engineering · doi:10.1080/10255842.2025.2456996
“Deep learning models have recently demonstrated superior performance, and models for processing multimodal information have emerged (Stahlschmidt et al. 2022).”
Automatic Segmentation of Human Placenta from 3D Multimodal Ultrasound Data
Singh, S., Stevenson, G. N., Mian, B., Welsh, A. W., & Sowmya, A. (2024) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta63115.2024.00045
Huang, A., Xu, J., Long, H., Xiang, H., Yu, X., Meng, Y., Xu, Z., Wang, J., & Jin, S. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5152273
Wang, B., Li, W., Bradlow, A., Watt, A., Chan, A. T. Y., & Bazuaye, E. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103068 · Cited by 1
Unifying multimodal single-cell data with a mixture-of-experts β -variational autoencoder frameworkPreprint
Ashford, A. J., Enright, T., Somers, J., et al. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.02.28.640429
Vagliano, I., Rios, M., Abukmeil, M., Schut, M. C., Luik, T. T., van Asselt, K. M., van Weert, H. C. P. M., & Abu–Hanna, A. (2025) · Cancers · doi:10.3390/cancers17071151 · Cited by 1
Advances in the Application of Deep Learning in Hepatocellular Carcinoma
刘, 萧. (2025) · Advances in Clinical Medicine · doi:10.12677/acm.2025.1541004
Feature Fusion Based Motor Fault Diagnosis Method Using Vibration and Acoustic Signals
Nam, C.-K., & Kim, C. H. (2025) · Journal of Digital Contents Society · doi:10.9728/dcs.2025.26.3.707
A multimodal fusion method with interpretability for nozzle health online prediction
Xie, J., Guo, Y. H., Huang, S., Liu, D., Tao, Y., & Hu, J. (2025) · International Journal of Computer Integrated Manufacturing · doi:10.1080/0951192x.2025.2496887
“Multimodal interpretation techniques have shown potential in a number of domains such as healthcare, autonomous driving, vision and language tasks (Joshi, Walambe, and Kotecha 2021; Stahlschmidt, Ulfenborg, and Synnergren 2022; Steyaert et al. 2023).”
Boppana, S. H., Komati, S. S. K., Raj, R., Maddineni, G., Chakinala, R. C., Yarra, P., Sunkesula, V. C. K., & Mintz, C. D. (2025) · Journal of Clinical Medicine · doi:10.1016/j.gie.2025.03.066
Identification and Validation of BATF3 as a Promising Biomarker Gene for Peripheral T-cell Lymphoma
Zhu, Y., Liu, J., & Zhang, T. (2025) · Current Medicinal Chemistry · doi:10.2174/0109298673367678250414061434
Multi-Modal ViT-Based Deep Learning Architecture for Binary Classification of Traffic Accident
Pérez, J. D. R., Torres, G. S., & Miranda, C. H. (2025) · REVISTA COLOMBIANA DE TECNOLOGIAS DE AVANZADA · doi:10.24054/rcta.v1i45.3751 · Cited by 1
Data Fusion and Dimensionality Reduction for Pest Management in Pitahaya Cultivation
Chango, W. G., Mazón-Fierro, M., Rodríguez, J. D. E., Fierro, G. J. M., Naranjo, S. I. L., Peñafiel-Arcos, P., & Sayago‐Heredia, J. (2025) · Computation · doi:10.3390/computation13060137
Rehan, A. M., Li, K., & Chen, P. (2025) · Electronics · doi:10.3390/electronics14122369 · Cited by 2
Bifurcations of the GKdV–mKdV-Like System with Medical Applications
Geng, Y., Shu, H., & Chen, Y. (2025) · International Journal of Bifurcation and Chaos · doi:10.1142/s0218127425501275
Generative Adversarial Networks for Longitudinal Data Imputation and Classification
Pingi, S. T. (2025) · Queensland University of Technology · doi:10.5204/thesis.eprints.258292 · Cited by 1
GLIR-GaitNet: Global-Local Interaction Rebalancing Network for gait-based disease diagnosis
Sun, Y., Yang, Q. Z., Ji, X., Zhang, Y., Yu, S. B., Si, M., Xiang, Y., & Ji, B. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103456
Enhancing Women's Fecundity Prediction in Time Series Data Using Encoder-LSTM Model Integration
Muhammad, A. S., Abdullahi, M. B., Mohammed, A. D., & Abisoye, O. A. (2025) · SN Computer Science · doi:10.1007/s42979-025-04184-x
“…approach aims to leverage the complementary strengths of LSTM (LSTMUE subfertility accommodation advantage) and transformer architectures (improved learning performance advantage) to enhance the model's (Encoder-LSTMUE) ability to handle both global and local dependencies in the data [27, 32].”
Deng, W., Hu, D., Jiang, Z., Zhang, P., & Shi, Y. (2025) · Systems · doi:10.3390/systems13080682 · Cited by 1
Zhu, J., Li, S., & Song, J. (2025) · Earth Science-Journal of China University of Geosciences · doi:10.3799/dqkx.2025.078
A Step towards Interpretable Multimodal AI Models with MultiFIX
Malafaia, M., Schlender, T., Alderliesten, T., & Bosman, P. A. N. (2025) · Genetic and Evolutionary Computation Conference Companion (GECCO Companion) · doi:10.1145/3712255.3734292 · Cited by 1
“…learning methods are commonly categorized by fusion strategies: early fusion, which concatenates input data before feature extraction; intermediate fusion, which combines modality-specific features after extraction; and late fusion, which aggregates predictions from unimodal models [9, 22].”
Han, L., & Wang, X. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5420641
Big Data Analysis From the Perspective of Fully Actuated System
Zhao, L., Guo, Y., Lin, R., & Yang, Y. Q. (2025) · Conference on Fully Actuated System Theory and Applications (FASTA) · doi:10.1109/fasta65681.2025.11138179
“Multimodal fusion architectures are stratified into early, intermediate, and late stages [39].”
Evaluating Multiomics Integration Architectures for Training With Structured MissingnessPreprint
Fisher, S., Bradley, J., Lansdown, G., Anderson, O., Hung, R., Lesh, J., Cutforth, M., Poole, I., & Voisey, J. P. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.09.10.672554
Sharma, N., & Sharma, S. (2025) · International Conference on Intelligent Computing and Knowledge Extraction (ICICKE) · doi:10.1109/icicke65317.2025.11136436
Chen, S., Chen, X., Huang, X., Fang, Z., Wang, J., Huo, X., Chen, X., & Chen, J. (2025) · IEEE International Conference on Nano/Micro Engineered and Molecular Systems · doi:10.1109/nems67320.2025.11170105
“Since the fusion methods can combine the effective information extracted from two different modalities, they tend to have better performance than simply using only one modality of data [10].”
Ismail, N. M., Miller, M. A., Crossland, H., Phillips, B. E., Sharif, J.-A., Kosanovic, C., Gu, T., Brogan, R. J., Wahlestedt, C., Atherton, P. J., et al. (2025) · medRxiv · doi:10.1101/2025.10.02.25337067
“In the present study, using concatenation, a simple fusion approach [49], provided only a modest improvement in classification performance, compared to unimodal models trained on MRI features (Table 4).”
A Novel AI Approach for the Diagnosis of Alzheimer’s Disease from Multi-modal Incomplete Data
Buttaro, V., Lamanna, G., Massaro, D., Caporusso, C. B., Pio, G., Ceci, M., & Initiative, A. D. N. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05461-6_36
Lu, Z., Kumar, A., Chang, N. H., He, H., Lin, L., Xia, W., Yang, J., & Qu, G. (2025) · ACM/IEEE Workshop on Machine Learning for CAD (MLCAD) · doi:10.1109/mlcad65511.2025.11189201
“…medical image analysis, where combining visual data (e.g., X-rays or MRIs) with patient metadata and clinical notes can improve diagnostic accuracy [24] and multimodal large language models development [25], where vision and language are aligned to perform tasks such as image captioning or visual…”
Utilization of Feature Fusion in Diagnostic Applications
Abir, S. I., Shoha, S., Khan, N. I., & Mousumi, J. (2025) · Springer eBooks · doi:10.1007/978-3-031-94386-7_11
A modified deep learning approach for seminal vesicle region localization in prostate MRI
Hasbay, E., & Cengizler, Ç. (2025) · Scientific Reports · doi:10.1038/s41598-025-20284-3
Thoma, P., Piliuk, K., Bayer, I., Kneitinger, E., & Tomforde, S. (2025) · Springer eBooks · doi:10.1007/978-3-658-48573-3_18
ImmFinder: A Multiomics-Based Neural Network Approach for Predicting the Immune Genes in Livestock
Thambiraja, M., Karthikeyan, P. P., Sezen, M., Senthilkumar, S., Singh, D., Onteru, S. K., & Yennamalli, R. M. (2025) · OMICS A Journal of Integrative Biology · doi:10.1177/15578100251389910 · Cited by 1
“Compared to the traditional machine learning model, MDL enables the fusion of different data types and predicts complex underlying patterns with better accuracy than unimodal (Stahlschmidt et al., 2022).”
ProtoMM: Interpretable Prototype-Based Multimodal Model for Brain Cancer Survival Prediction
Yang, Y., Ying, R., & Tong, C. (2025) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-025-01713-1 · Cited by 3
“Existing fusion methods primarily focus on early, intermediate, and late fusion of features, with varying degrees of success across prediction tasks depending on the stage of data fusion [25].”
Multimodal Ultrasound Radiomics in Liver Disease: Current Status and Future Directions
Zhong, X., & Xie, X. (2025) · Advanced ultrasound in diagnosis and therapy · doi:10.26599/audt.2025.250101 · Cited by 5
Durães, D. A., Teixeira, R., Bezerra, R., & Nováis, P. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-97119-8_2
Thakur, L. S., Bharj, G., Nguyen, D. T., Saroya, M., & Malik, B. (2025) · medRxiv · doi:10.1101/2025.11.10.25339915
Post-earthquake Damage Assessment of Buildings Exploiting Data Fusion
Saquella, S., Scarpiniti, M., Pu, W., Pedone, L., Angelucci, G., Matteoni, M., Francioli, M., & Pampanin, S. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227606
“Motivated by these considerations, this paper aims at further advancing the state of the art by employing the EfficientNet-B0 [13] with different data fusion techniques [14] for the classification of post-earthquake structural damage in buildings.”
Liu, W. D., Lu, P., & Chen, Y. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114899 · Cited by 1
Multimodal Ensemble Deep Learning for Skin Cancer Detection
Madhuri, G., Jabbar, M. A., & Vijaylaxmi (2025) · International Conference on Intelligent Communication Networks and Computational Techniques (ICICNCT) · doi:10.1109/icicnct66124.2025.11232584
“Combining models afterwards can result in better generalization, especially when utilizing a variety of structures and modalities, as covered in recent reviews on multimodal biomedical data fusion [6] The objectives of the proposed approach are listed as follows: i.”
State recognition and prediction method of smart substation based on multimodal fusion
Song, Z., Huang, Z., Zhao, Y., Guo, Z., She, S., & Liu, S. (2025) · IEEE International Conference on Sensors, Electronics and Computer Engineering (ICSECE) · doi:10.1109/icsece65727.2025.11256998
“The fused feature vector is further compressed by the fully connected layer and sent to the state recognition branch and the trend prediction branch respectively [10] .”
Gan, Y., Zhao, H., Wang, K., Yan, C., & Zou, G. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3638884
“However, inherent inter-omics heterogeneity poses fundamental challenges for effective data integration [7].”
Chen, O. T.-Y., Li, I.-H., Jong, Y., Yang, Y.-H., Hsieh, H., Chou, M.-C., & Tseng, V. S. M. (2025) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc58623.2025.11254421
“For KMU, the student model uses an MLP with layer dimensions [32, 4], trained with the Adam optimizer (learning rate = 0.01).”
InfluentialMedFMIT: A Foundation Model-Driven Multimodal Fusion Method for Image-Text Disease Diagnosis
Liang, S., Fu, J., Li, W., Chen, M., Wang, Y., & Guo, Y. (2025) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc58623.2025.11252735 · Cited by 1
Deep Mediation Analysis for Multimodal Genotype-Imaging Associations with Disease PhenotypesPreprint
Golderzahi, V., Wang, G., Hu, J., & Yeang, C. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2025.11.20.689376
“The choice of the fusion strategy (early, intermediate, or late) highly depends on datasets [13,19,20].”
Decoding omics via representation learning
Wang, D., & Zhang, Q. (2025) · Nature Computational Science · doi:10.1038/s43588-025-00909-3
Moser, T., Moser, M. J., & Mahnert, A. (2025) · mSystems · doi:10.1128/msystems.00039-24
MFCLDTA: Multi-scale feature contrastive learning for predicting drug-target binding affinity
Tian, Z., Zhu, S., Teng, Z., Yan, X., & Wang, T. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130918
A Reconfigurable Multiview CNN for Breast Tumor Classification Using Intra- and Peritumoral Regions
Gómez-Flores, W., & Pereira, W. C. A. (2025) · International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE) · doi:10.1109/cce67728.2025.11271956
“This approach is commonly known as deep multiview learning [9].”
Vacuum-Level Prediction Based on LIP Using Bimodal Fusion and Ensemble Learning
Ke, W., Yuan, H., Wang, X. H., Zhang, D. Z., & Rong, M. Z. (2025) · IEEE Transactions on Dielectrics and Electrical Insulation · doi:10.1109/tdei.2025.3644316
“Researchers often fuse data from di ff erent modalities (e.g., text, images, or audio) to leverage the complementary strengths of each modality and enhance overall model performance [11], [12], [13], [14].”
On Evaluation of Data Fusion Methods for Network Traffic Classification
Plný, R., & Hynek, K. (2025) · International Conference on Network and Service Management (CNSM) · doi:10.23919/cnsm67658.2025.11297464
“Data fusion combines multiple records of the same entity into a unified representation and can be performed at early, intermediate, or late stages [8], [14].”
Orthopedic Surgery and Artificial Intelligence: The Future Is Already Here
Ro, D. H., Choi, B. S., & Han, H. (2025) · The Journal of the Korean Orthopaedic Association · doi:10.4055/jkoa.2025.60.4.223
ZARATE-TREJO, C., & Ramos, F. (2026) · Studies in computational intelligence · doi:10.1007/978-3-032-13592-6_36
NeuMTL: A Unified Multimodal Framework for Multi-Task Prediction in CNS Drug Discovery
Zheng, Y., Wang, S., QU, S., Mi, W., & Zhang, X. (2026) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c02725
Yang, F., & Gong, F. (2026) · Scientific Reports · doi:10.1038/s41598-026-36023-1 · Cited by 2
Zheng, K., Ke, M., Wang, L., et al. (2025) · doi:10.1145/3777577.3777646
“Effectively combining this information, often approached as a multi-view learning problem [7], is crucial for a comprehensive diagnosis [8].”
Deng, H. Y., Jiang, D.-Y., Wang, N., & Li, P. (2026) · Measurement · doi:10.1016/j.measurement.2026.120410
de Gevigney, V. D., Nicastro, N., Garibotto, V., & Schmid, J. (2026) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-025-01831-w
Hybrid Stacking–Bagging Ensembles for Robust Multi-Omics Breast Cancer PrognosisPreprint
Bozorgpour, R. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.01.21.700935
“As breast cancer is fundamentally genetic, subsequent studies incorporated multimodal data—such as clinical variables, gene expression, and CNV—to improve prognostic accuracy and capture complex biological interactions [14].”
Hu, B., & Gong, K. (2025) · International Conference on Artificial Intelligence and Future Education (AIFE) · doi:10.1145/3785987.3786018
Merta, G. B. K., & Setiawan, E. B. (2025) · doi:10.1109/icicyta68677.2025.11362759
“In reality, online communication is multimodal [8], [9], and hybrid architectures such as CNN, RNN, and GRU have shown strong potential for modality fusion [10], [11].”
Xie, X., Xue, P., Guo, Y., Chen, H., Fan, L., Tang, R., Xu, Z., Wang, X., Liu, T., & Chen, F. (2026) · Interdisciplinary Sciences Computational Life Sciences · doi:10.1007/s12539-025-00805-4 · Cited by 2
A Comprehensive Approach to Adaptive Multi-model Architecture for Heterogeneous Data Sources
Anbazhagan, E., Sudharson, S., Annamalai, R., & Krishna, V. V. (2026) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-14805-6_4 · Cited by 1
Classifying natural and non-natural earthquakes based on multimodal data and neural networks
Dai, H., 郝永梅, Miao, F., Luan, S., Zhang, Y., Ma, Q., Li, S., Zhu, J., & Song, J. D. (2026) · Journal of Applied Geophysics · doi:10.1016/j.jappgeo.2026.106164
Unveiling Reliability in Multi-omics Classification: Fusion, Calibration, and Dynamic Scaling
Nguyen, D. K., Zhang, D., Bashar, M. A., & Nayak, R. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-6786-7_5
Decoding adaptive immunity: advanced strategies in T and B cell repertoire analysis
Yu, X., Peng, N., Pan, W., Xie, S., Tang, C., Wang, X., Liu, H., Shi, Y., He, Y., Wu, W., et al. (2026) · Journal of Translational Medicine · doi:10.1186/s12967-026-07753-7
“Researchers are actively exploring various ML algorithms and tools to uncover sophisticated patterns and associations that can predict immune responses or disease outcomes [97–99].”
Selani, D., Knevel, R., Reinders, M. J. T., & van den Akker, E. B. (2026) · Journal of Medical Internet Research · doi:10.2196/86763
“To address these limitations, researchers have turned to multimodal data integration, combining clinical variables with genetic, transcriptomic, proteomic, and imaging data [2].”
Unal, S., & Unal, M. (2026) · Methods · doi:10.1016/j.ymeth.2026.02.008 · Cited by 1
MEDIATOR: Enhancing Medical Diagnosis via Gated Distillation and Decoupled Learning
Oh, K., Lee, S., Hwang, M., Yang, H., & Lee, K. (2025) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc66702.2025.11388553
“A central obstacle is the modality gap —the large discrepancy in statistical properties and dimensionality between different data types, which complicates joint representation learning [2].”
AI in multi-omics analysis in AMR
Singhal, N., & Kumar, M. (2026) · Progress in molecular biology and translational science · doi:10.1016/bs.pmbts.2026.02.001
Liu, J., Hu, Z., Zhao, Y., & Liang, L. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3667096
“Multi-modal fusion has evolved from simple concatenation [19] to sophisticated attention mechanisms.”
He, J., Tempelaere, A., Vignero, J., Verboven, P., & Nicolai, B. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00745 · Cited by 2
“…features into a joint representation, commonly through vector concatenation in the feature space, while decision-level fusion combines predictions from individual classifiers for each modality using predefined rules, such as majority voting or averaging, to yield the final decision [33].”
Yan, Y., Shang, Y., Li, P. P., et al. (2025) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio66223.2025.11378050
Lin, J. B., Mataraso, S. J., Chadha, M., Velez, G., Mruthyunjaya, P., Aghaeepour, N., & Mahajan, V. B. (2026) · medRxiv · doi:10.64898/2026.02.23.26346903 · 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.