AUTHOR=Pace Giorgia , Orrù Graziella , Monaro Merylin , Gnoato Francesca , Vitaliani Roberta , Boone Kyle B. , Gemignani Angelo , Sartori Giuseppe 

TITLE=Malingering Detection of Cognitive Impairment With the b Test Is Boosted Using Machine Learning

JOURNAL=Frontiers in Psychology

VOLUME=10

YEAR=2019

URL=https://www.frontiersin.org/journals/psychology/articles/10.3389/fpsyg.2019.01650

DOI=10.3389/fpsyg.2019.01650

ISSN=1664-1078

ABSTRACT=<p><bold>Objective:</bold> Here we report an investigation on the accuracy of the b Test, a measure to identify malingering of cognitive symptoms, in detecting malingerers of mild cognitive impairment.</p><p><bold>Method:</bold> Three groups of participants, patients with Mild Neurocognitive Disorder (<italic>n</italic> = 21), healthy elders (controls, <italic>n</italic> = 21), and healthy elders instructed to simulate mild cognitive disorder (malingerers, <italic>n</italic> = 21) were administered two background neuropsychological tests (MMSE, FAB) as well as the b Test.</p><p><bold>Results:</bold> Malingerers performed significantly worse on all error scores as compared to patients and controls, and performed poorly than controls, but comparably to patients, on the time score. Patients performed significantly worse than controls on all scores, but both groups showed the same pattern of more omission than commission errors. By contrast, malingerers exhibited the opposite pattern with more commission errors than omission errors. Machine learning models achieve an overall accuracy higher than 90% in distinguishing patients from malingerers on the basis of b Test results alone.</p><p><bold>Conclusions:</bold> Our findings suggest that b Test error scores accurately distinguish patients with Mild Neurocognitive Disorder from malingerers and may complement other validated procedures such as the Medical Symptom Validity Test.</p>