Does Lexical Retrieval Deteriorate in Patients with Mild Cognitive Impairment? Analysis of Brain Functional Network Will Tell

Author(s):  
Chongyuan Lian ◽  
Tianqi Wang ◽  
Mingxiao Gu ◽  
Manwa L. Ng ◽  
Feiqi Zhu ◽  
...  
2021 ◽  
pp. 1-20
Author(s):  
Tianqi Wang ◽  
Yin Hong ◽  
Quanyi Wang ◽  
Rongfeng Su ◽  
Manwa Lawrence Ng ◽  
...  

Background: Previous studies explored the use of noninvasive biomarkers of speech and language for the detection of mild cognitive impairment (MCI). Yet, most of them employed single task which might not have adequately captured all aspects of their cognitive functions. Objective: The present study aimed to achieve the state-of-the-art accuracy in detecting individuals with MCI using multiple spoken tasks and uncover task-specific contributions with a tentative interpretation of features. Methods: Fifty patients clinically diagnosed with MCI and 60 healthy controls completed three spoken tasks (picture description, semantic fluency, and sentence repetition), from which multidimensional features were extracted to train machine learning classifiers. With a late-fusion configuration, predictions from multiple tasks were combined and correlated with the participants’ cognitive ability assessed using the Montreal Cognitive Assessment (MoCA). Statistical analyses on pre-defined features were carried out to explore their association with the diagnosis. Results: The late-fusion configuration could effectively boost the final classification result (SVM: F1 = 0.95; RF: F1 = 0.96; LR: F1 = 0.93), outperforming each individual task classifier. Besides, the probability estimates of MCI were strongly correlated with the MoCA scores (SVM: –0.74; RF: –0.71; LR: –0.72). Conclusion: Each single task tapped more dominantly to distinct cognitive processes and have specific contributions to the prediction of MCI. Specifically, picture description task characterized communications at the discourse level, while semantic fluency task was more specific to the controlled lexical retrieval processes. With greater demands on working memory load, sentence repetition task uncovered memory deficits through modified speech patterns in the reproduced sentences.


2009 ◽  
Vol 16 (1) ◽  
pp. 84-93 ◽  
Author(s):  
DAVID J. LIBON ◽  
SHARON X. XIE ◽  
JOEL EPPIG ◽  
GRAHAM WICAS ◽  
MELISSA LAMAR ◽  
...  

AbstractA group of 94 nondemented patients self-referred to an outpatient memory clinic for memory difficulties were studied to determine the incidence of single versus multi-domain mild cognitive impairment (MCI) using Petersen criteria. Fifty-five community dwelling normal controls (NC) participants without memory complaints also were recruited. Tests assessing executive control, naming/lexical retrieval, and declarative memory were administered. Thirty-four patients exhibited single-domain MCI, 43 patients presented with multi-domain MCI. When the entire MCI sample (n = 77) was subjected to a cluster analysis, 14 patients were classified with amnesic MCI, 21 patients with dysexecutive MCI, and 42 patients were classified into a mixed/multi-domain MCI group involving low scores on tests of letter fluency, “animal” fluency, and delayed recognition discriminability. Analyses comparing the three cluster-derived MCI groups versus a NC group confirmed the presence of memory and dysexecutive impairment for the amnesic and dysexecutive MCI groups. The mixed MCI group produced lower scores on tests of letter fluency compared with the amnesic MCI and NC groups and lower scores on tests of naming and memory compared with the NC group. In summary, multi-domain MCI is quite common. These data suggest that MCI is a highly nuanced and complex clinical entity. (JINS, 2010, 16, 84–93.)


2021 ◽  
Vol 429 ◽  
pp. 117849
Author(s):  
Stefano Delli Pizzi ◽  
Piero Chiacchiaretta ◽  
Miriam Punzi ◽  
Raffaella Franciotti ◽  
Manuela Bomba ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document