Weirui Kong, Hyeju Jang, Giuseppe Carenini, Thalia Field; Proceedings of the 4th Machine Learning for Healthcare Conference, PMLR 106:270-286, 2019.
Early prediction of neurodegenerative disorders such as Alzheimer’s disease (AD) and related dementias is important in developing early medical supports and social supports, and may identify ideal stages for testing novel therapeutics aimed at preventing disease progression. Currently, a diagnosis is based on clinical expertise and cognitive screening tests, which have limited accuracy in earlier stages of disease, or invasive and resource-intensive testing, such as lumbar puncture or specialized neuroimaging.
Changes in speech and language patterns can occur in dementia in its earliest stages and may worsen as the disease progresses. This has led to recent attempts to create automatic methods that predict dementia through language analysis. In addition to features extracted from language samples, previous works have improved the prediction accuracy by introducing some task-specific features. But task-specific features prevent the model from generalizing to other tests. In this paper, we apply a neural model (Hierarchical Attention Networks) to the dementia prediction task.
Remarkably, the model requires no task-specific feature and achieves state-of-the-art classification result on a widely used dementia dataset of spoken language. We also perform a detail analysis to interpret how a prediction is made. Interestingly, the same neural model does not work well on a corpus of written text, suggesting that dementia prediction from language may require different methods depending on the genre of the source language.
We apply a picture-agnostic neural method to the DementiaBank dataset, and obtain comparable results to traditional models that use task-specific features.
We find that the attention model attends more strongly to the information unit words defined by human experts.