Mode Connections For Clinical Incremental Learning: Lessons From The COVID-19 Pandemic
Thakur, A.; Wang, C.; Certili, T.; Eyre, D. W.; Clifton, D.
Show abstract
AO_SCPLOWBSTRACTC_SCPLOWDynamic distribution shifts caused by evolving diseases and demographic changes require domain-incremental adaptation of clinical deep learning models. However, this process of adaptation is often accompanied by catastrophic forgetting, and even the most sophisticated methods are not good enough for clinical applications. This paper studies incremental learning from the perspective of mode connections, that is, the low-loss paths connecting the minimisers of neural architectures (modes or trained weights) in the parameter space. The paper argues for learning the low-loss paths originating from an existing mode and exploring the learned paths to find an acceptable mode for the new domain. The learned paths, and hence the new domain mode, are a function of the existing mode. As a result, unlike traditional incremental learning, the proposed approach is able to exploit information from a deployed model without changing its weights. Pre-COVID and COVID-19 data collected in Oxford University hospitals are used as a case study to demonstrate the need for domain-incremental learning and the advantages of the proposed approach.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Data-driven Discovery of Mathematical and Physical Relations in Oncology Data using Human-understandable Machine Learning 96%
- PECLIDES Neuro - A Personalisable Clinical Decision Support System for Neurological Diseases 91%
- An Explainable Multi-Modal Neural Network Architecture for Predicting Epilepsy Comorbidities Based on Administrative Claims Data 90%
Similar papers in this journal
- BenchXAI: Comprehensive Benchmarking of Post-hoc Explainable AI Methods on Multi-Modal Biomedical Data 94%
- Decoding Clinical Biomarker Space of COVID-19: Exploring Matrix Factorization-based Feature Selection Methods 93%
- ISMI-VAE: A Deep Learning Model for Classifying Disease Cells Using Gene Expression and SNV Data 93%
Similar papers in this journal
- Graph Neural Network Modelling as a potentially effective Method for predicting and analyzing Procedures based on Patient Diagnoses 94%
- Stability of feature selection utilizing Graph Convolutional Neural Network and Layer-wise Relevance Propagation 93%
- Deep ensemble multitask classification of emergency medical call incidents combining multimodal data improves emergency medical dispatch 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.