• Corpus ID: 245537343

Feature-context driven Federated Meta-Learning for Rare Disease Prediction

@article{Chen2021FeaturecontextDF,
  title={Feature-context driven Federated Meta-Learning for Rare Disease Prediction},
  author={Bingyang Chen and Tao Chen and Xingjie Zeng and Weishan Zhang and Qinghua Lu and Zhaoxiang Hou and Jiehan Zhou and Abdelsalam Helal},
  journal={ArXiv},
  year={2021},
  volume={abs/2112.14364}
}
Millions of patients suffer from rare diseases around the world. However, the samples of rare diseases are much smaller than those of common diseases. In addition, due to the sensitivity of medical data, hospitals are usually reluctant to share patient information for data fusion citing privacy concerns. These challenges make it difficult for traditional AI models to extract rare disease features for the purpose of disease prediction. In this paper, we overcome this limitation by proposing a… 
View PDF on arXiv

References

SHOWING 1-10 OF 30 REFERENCES

Difficulty-aware Meta-Learning for Rare Disease Diagnosis

A difficulty-aware meta-learning method that dynamically monitors the importance of learning tasks during the meta-optimization stage is developed to address rare disease classifications and demonstrate its capability to classify dermoscopy images.

RDAD: A Machine Learning System to Support Phenotype-Based Rare Disease Diagnosis

The phenotype-based Rare Disease Auxiliary Diagnosis system (RDAD) was developed to assist clinicians in diagnosing rare diseases with the above four diagnostic models and showed that all models had a high diagnostic precision.

MetaPred: Meta-Learning for Clinical Risk Prediction with Limited Patient Electronic Health Records

In order to predict the target risk with limited data samples, a meta-learner is trained from a set of related risk prediction tasks which learns how a good predictor is trained, which can be directly used in target risk prediction, and the limited available samples in the target domain can be used for further fine-tuning the model performance.

Federated Uncertainty-Aware Learning for Distributed Hospital EHR Data

A new FL model called Federated Uncertainty-Aware Learning Algorithm (FUALA) is proposed that improves on Federated Averaging (FedAvg) in the context of EHR and introduces model ensembling at prediction time by keeping the last layers of each hospital from the final round.

A smart healthcare monitoring system for heart disease prediction based on ensemble deep learning and feature fusion

Dynamic-Fusion-Based Federated Learning for COVID-19 Detection

The proposed novel dynamic fusion-based federated learning approach for medical diagnostic image analysis to detect COVID-19 infections is feasible and performs better than the default setting of federatedLearning in terms of model performance, communication efficiency, and fault tolerance.

Personalized Federated Learning: A Meta-Learning Approach

A personalized variant of the well-known Federated Averaging algorithm is studied and its performance is characterized by the closeness of underlying distributions of user data, measured in terms of distribution distances such as Total Variation and 1-Wasserstein metric.

Evaluation of deep learning approaches for identification of different corona-virus species and time series prediction

  • M. Younis
  • Biology
    Computerized Medical Imaging and Graphics
  • 2021

The future of digital health with federated learning

This paper considers key factors contributing to this issue, explores how federated learning (FL) may provide a solution for the future of digital health and highlights the challenges and considerations that need to be addressed.

Federated Meta-Learning for Fraudulent Credit Card Detection

A novel framework termed as Federated Meta-Learning for fraud detection that enables banks to learn fraud detection model with the training data distributed on their own local database and achieves significantly higher performance compared with the other state-of-the-art approaches.