Uncertainty-Aware Multi-Modal Ensembling for Severity Prediction of Alzheimer's Dementia
This work addresses reliability in healthcare applications by improving severity prediction for Alzheimer's patients, but it is incremental as it builds on existing uncertainty estimation and multi-modal methods.
The paper tackled the problem of predicting Alzheimer's Dementia severity by proposing an uncertainty-aware boosting technique for multi-modal ensembling, which outperformed state-of-the-art methods on the ADReSS dataset and reduced system entropy.
Reliability in Neural Networks (NNs) is crucial in safety-critical applications like healthcare, and uncertainty estimation is a widely researched method to highlight the confidence of NNs in deployment. In this work, we propose an uncertainty-aware boosting technique for multi-modal ensembling to predict Alzheimer's Dementia Severity. The propagation of uncertainty across acoustic, cognitive, and linguistic features produces an ensemble system robust to heteroscedasticity in the data. Weighing the different modalities based on the uncertainty estimates, we experiment on the benchmark ADReSS dataset, a subject-independent and balanced dataset, to show that our method outperforms the state-of-the-art methods while also reducing the overall entropy of the system. This work aims to encourage fair and aware models. The source code is available at https://github.com/wazeerzulfikar/alzheimers-dementia