Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jul 1;15(1):21819.
doi: 10.1038/s41598-025-06306-0.

Mamba-fusion for privacy-preserving disease prediction

Muhammad Kashif Jabbar  1   2 , Huang Jianjun  3   4 , Ayesha Jabbar  1   2 , Anas Bilal  5   6
Affiliations

Mamba-fusion for privacy-preserving disease prediction

Muhammad Kashif Jabbar et al. Sci Rep. .

Abstract

Accurate disease prediction is essential for improving patient outcomes. Privacy regulations like GDPR and HIPAA limit data sharing, hindering the development of robust predictive models across institutions. FL and multi-modal fusion frameworks counter these problems but are restricted in scalability, inter-client communication, and heterogeneity of data modalities. Techniques which provide privacy on data have an issue whereby they cause a reduction in performance or are computationally costly. This paper presents Mamba-Fusion for Disease prediction, a privacy-preserving framework for multi-modal data. It uses a hierarchical FL architecture to minimize the communication costs and improve the architecture's scalability solution and a Mixture of Experts (MoE) with LSTM based layers for dynamic temporal integration. The latest techniques like, differential privacy, secure aggregation protect both the data and its accuracy of the data as well. Experimental results on multi-modal clinical measurements, ECG, EEG, clinical notes, and demographic data support the applied framework. We have then used Mamba-Fusion to achieve 92:4% accuracy, 0:91 F-Score, and 0:96 AUC-ROC by keeping the privacy leakage at 0:02 and communication costs to 12:5 MB, which make it superior to conventional FL techniques. These results affirm Mamba-Fusion as an applications that are secure enough to support collaborative healthcare analytics on a large scale.

Keywords: Chronic disease prediction; Differential privacy in healthcare; Hierarchical aggregation mechanism; Multi-modal data fusion; Privacy-preserving federated learning; Scalable healthcare analytics.

PubMed Disclaimer

Conflict of interest statement

Declarations. Competing interests: The authors declare no competing interests. Institutional review board statement: Not applicable. All methods were carried out in accordance with relevant guidelines and regulations. Informed consent statement: Not applicable.

Figures

Fig. 1
Fig. 1
Mamba-Fusion for Privacy-Preserving Disease Prediction.
Fig. 2
Fig. 2
Federated Learning in Healthcare.
Fig. 3
Fig. 3
Federated Learning in Healthcare.
Algorithm 1
Algorithm 1
Federated Learning with Hierarchical Aggregation for Mamba-Fusion
Fig. 4
Fig. 4
Performance Metrics Comparison Across Models. Mamba-Fusion consistently outperforms Centralized LSTM and Federated GRU across all key metrics. Accuracy is shown as the highest metric achieved by Mamba-Fusion (92.4%).
Fig. 5
Fig. 5
Privacy Leakage with Communication Efficiency. The figure showcases the superior privacy-preserving properties of Mamba-Fusion compared to the baseline models. The privacy leakage rate for Mamba-Fusion is only 0.02, significantly lower than its counterparts.
Fig. 6
Fig. 6
Communication Cost and Latency Comparison. Mamba-Fusion demonstrates the lowest communication cost and latency, making it highly efficient for real-world federated setups.
Fig. 7
Fig. 7
Loss Convergence Over Epochs. The training and validation losses for Mamba-Fusion exhibit stable convergence, achieving the lowest final loss among the models.
Fig. 8
Fig. 8
Performance Comparison of Mamba-Fusion and Baseline Models: The graph compares the convergence of loss over epochs for Mamba-Fusion, Centralized LSTM, and Federated GRU models. Mamba-Fusion demonstrates superior convergence with lower loss.
Fig. 9
Fig. 9
ROC Curve Comparison Across Models. The AUC-ROC of the Mamba-Fusion is significantly high at 0.96 as indicated in the ROC curve showing the classifiers ability to classify instances between the different classes.
Fig. 10
Fig. 10
Confusion Matrix with Additional Categories. The performance of Mamba-Fusion for three categories is presented in the matrix along with class-wise precision and recall percentages.
See this image and copyright information in PMC

References

    1. Aggarwal, Meenakshi, Khullar, Vikas, & Goyal, Nitin. A comprehensive review of federated learning: Methods, applications, and challenges in privacy-preserving collaborative model training. Applied Data Science and Smart Systems, pages 570–575, (2024).
    1. Ahamed, Md. Faysal, Hossain, Md. Munawar, Nahiduzzaman, Md., Islam, Md. Rabiul, Islam, Md. Robiul, Ahsan, Mominul, Haider, Julfikar. A review on brain tumor segmentation based on deep learning methods with federated learning techniques. Computerized Medical Imaging and Graphics, 110: 102313, (2023a). ISSN 0895-6111. 10.1016/j.compmedimag.2023.102313. URL https://www.sciencedirect.com/science/article/pii/S0895611123001313. - PubMed
    1. Ahamed, Md Faysal et al. Irv2-net: A deep learning framework for enhanced polyp segmentation performance integrating inceptionresnetv2 and unet architecture with test time augmentation techniques. Sensors23(18), 7724 (2023). - PMC - PubMed
    1. Faysal Ahamed, Md. et al. Automated detection of colorectal polyp utilizing deep learning methods with explainable ai. IEEE Access12, 78074–78100. 10.1109/ACCESS.2024.3402818 (2024).
    1. Faysal Ahamed, Md., Nahiduzzaman, Md., Rabiul Islam, Md., Naznine, Mansura, Ayari, Mohamed Arselene, Khandakar, Amith, Haider, Julfikar: Detection of various gastrointestinal tract diseases through a deep learning method with ensemble elm and explainable ai. Expert Systems with Applications, 256:124908, 2024b. ISSN 0957-4174. 10.1016/j.eswa.2024.124908. URL https://www.sciencedirect.com/science/article/pii/S0957417424017755.

LinkOut - more resources