In this paper, we construct a novel framework that leverages several AI methods for automatically screening cognitive impairment (CI) based on the Cookie Theft picture description task with a multilingual dataset. It holds a high potential for clinical application in early AD detection as it’s fully automatic and has achieved high performance with 74% in accuracy and 75% in AUC in the external cross-lingual Chinese validation experiment, excels in distinguishing CI, and is beneficial for large-scale screening and self testing of CI, which will remind potential AD patients to undergo timely hospital-based examinations and therapies.

Abstract:

INTRODUCTION

The use of speech data for distinguishing cognitive impairment (CI) is efficient and convenient for early screening of potential AD. However, few studies have developed available automated frameworks with the external cross-lingual Chinese validation.

METHODS

This study utilized speech data from the Cookie Theft description task, employing the ADReSSo dataset and the local Chinese dataset of the STAR cohort. We constructed an automated framework for CI screening, leveraging AI methods, including ASR, LLMs, and multiple types of machine learning classifiers. We used datasets in multiple languages and addressed the issue of language inconsistency.

RESULTS

Our framework achieved 74% in accuracy and 75% in AUC in the external cross-lingual Chinese validation experiment. We conducted an ablation study to demonstrate the necessity of each module within the framework.

DISCUSSION

The proposed framework provides fully automated assessments in distinguishing CI, making it highly beneficial for large-scale early screening and self-testing.

You cen see our manuscript here