Enriching Neural Models with Targeted Features for Dementia Detection
This work addresses the need for non-invasive and efficient dementia detection, which is crucial for older adults and healthcare systems, though it appears incremental as it builds on existing CNN-LSTM architectures.
The paper tackled the problem of early detection of Alzheimer's disease and related dementias by developing a neural model using conversational transcripts, achieving an F1 score of 0.929 on the DementiaBank dataset.
Alzheimer's disease (AD) is an irreversible brain disease that can dramatically reduce quality of life, most commonly manifesting in older adults and eventually leading to the need for full-time care. Early detection is fundamental to slowing its progression; however, diagnosis can be expensive, time-consuming, and invasive. In this work we develop a neural model based on a CNN-LSTM architecture that learns to detect AD and related dementias using targeted and implicitly-learned features from conversational transcripts. Our approach establishes the new state of the art on the DementiaBank dataset, achieving an F1 score of 0.929 when classifying participants into AD and control groups.