AMI-Net+: A Novel Multi-Instance Neural Network for Medical Diagnosis from Incomplete and Imbalanced Data
This work addresses a critical challenge in medical real-world studies for improving diagnostic accuracy, though it appears incremental as it builds upon the existing AMI-Net method.
The authors tackled the problem of medical diagnosis from incomplete and imbalanced data by introducing AMI-Net+, a novel multi-instance neural network, which outperformed baseline models on two real-world datasets.
In medical real-world study (RWS), how to fully utilize the fragmentary and scarce information in model training to generate the solid diagnosis results is a challenging task. In this work, we introduce a novel multi-instance neural network, AMI-Net+, to train and predict from the incomplete and extremely imbalanced data. It is more effective than the state-of-art method, AMI-Net. First, we also implement embedding, multi-head attention and gated attention-based multi-instance pooling to capture the relations of symptoms themselves and with the given disease. Besides, we propose var-ious improvements to AMI-Net, that the cross-entropy loss is replaced by focal loss and we propose a novel self-adaptive multi-instance pooling method on instance-level to obtain the bag representation. We validate the performance of AMI-Net+ on two real-world datasets, from two different medical domains. Results show that our approach outperforms other base-line models by a considerable margin.