Abstract
Background
Mild cognitive impairment (MCI) is a prevalent condition among older adults and a potential marker for dementia. The current challenge lies in diagnosing MCI among healthy older populations. This diagnosis typically requires extensive neuropsychological evaluations using tools like the Mini-Mental State Examination (MMSE) or the MoCA (Montreal Cognitive Assessment) based on specific diagnostic criteria.
Objective
This study used knowledge-guided machine learning (ML) algorithms and large language models (LLMs) to build diagnostic models. Our approach generates a clinician-guided classification by augmenting LLM with external knowledge to predict levels of MCI by using the spoken text of picture description tasks.
Methods
The models used language and speech features from two picture description tasks, along with demographic features. They aimed to distinguish between three levels of MCI (MCI, possible MCI, and healthy). We utilized the cognitive cross-domain attention model (CCDA) to integrate the attention mechanism of diverse types of information effectively into our training process, leading to better performance.
Results
We demonstrate the efficacy of machine learning, large language models (LLMs), and knowledge-integrated LLMs built on semantic, syntactic, lexical, fluency, audio, and demographic features to identify different levels of cognitive decline from the analysis of verbal utterances. Our CCDA model detected MCI from the participant input, aided by an external attention mechanism. A binomial t-test confirmed the significance (p < 0.1) of CCDA's predictions. An ablation study showed the impact of the attention mechanism and LLM approach on performance. We obtained an AUC of 0.81 and an F1 score of 0.73 on a large dataset of older adults.
Conclusion
Our knowledge-augmented approach compared favorably to contemporary LLM approaches, indicating the promise of knowledge-augmented learning in detecting MCI.