A voice recognition-based digital cognitive screener for dementia detection in the community: Development and validation study

Abstract

IntroductionTo facilitate community-based dementia screening, we developed a voice recognition-based digital cognitive screener (digital cognitive screener, DCS). This proof-of-concept study aimed to investigate the reliability, validity as well as the feasibility of the DCS among community-dwelling older adults in China.MethodsEligible participants completed demographic, clinical, and the DCS. Diagnosis of mild cognitive impairment (MCI) and dementia was made based on the Montreal Cognitive Assessment (MoCA) (MCI: MoCA < 23, dementia: MoCA < 14). Time and venue for test administration were recorded and reported. Internal consistency, test-retest reliability and inter-rater reliability were examined. Receiver operating characteristic (ROC) analyses were conducted to examine the discriminate validity of the DCS in detecting MCI and dementia.ResultsA total of 103 participants completed all investigations and were included in the analysis. Administration time of the DCS was between 5.1–7.3 min. No significant difference (p > 0.05) in test scores or administration time was found between 2 assessment settings (polyclinic or community center). The DCS showed good internal consistency (Cronbach’s alpha = 0.73), test-retest reliability (Pearson r = 0.69, p < 0.001) and inter-rater reliability (ICC = 0.84). Area under the curves (AUCs) of the DCS were 0.95 (0.90, 0.99) and 0.77 (0.67, 086) for dementia and MCI detection, respectively. At the optimal cut-off (7/8), the DCS showed excellent sensitivity (100%) and good specificity (80%) for dementia detection.ConclusionThe DCS is a feasible, reliable and valid digital dementia screening tool for older adults. The applicability of the DCS in a larger-scale community-based screening stratified by age and education levels warrants further investigation.

Validity, feasibility, and effectiveness of a voice‐recognition based digital cognitive screener for dementia and mild cognitive impairment in community‐dwelling older Chinese adults: A large‐scale implementation study

“…41,42 Speech data obtained by the DCS can also be used in studies that focus on differences in vocal abilities of participants responding to cognitive testing. 14 In future investigations, it may be worthwhile to explore the development of a composite index In conclusion, our findings demonstrated that the DCS was an effective and efficient tool for case-finding of dementia and MCI in a Chinese community. The large-scale implementation of the DCS among older…”

“…A previous study also found an area under the receiver operating characteristics curve (AUC) of 0.95 (95% CI: 0.90, 0.99) for dementia with an optimal cutoff of 7/8, and an AUC of 0.77 (95% CI: 0.67, 0.86) for MCI with an optimal cutoff of 8/9. More details on the DCS development can be found elsewhere 14 …”

“…However, trained personnel are still required for such digital assessments to take place, to ensure the standardization of administration. To eliminate the involvement of professionally trained administrators and improve testing standardization, a voice recognition‐based brief digital cognitive tool (the digital cognitive screener, DCS) that runs on mobile devices has been developed 14 . Similar to a previously automated detection tool based on voice recordings of neuropsychological tests, 15 the DCS was also designed to facilitate voice recognition‐based analysis during cognitive assessments.…”

Validation of the Computerized Cognitive Assessment Test: NNCT

“…Other tests such as CogEvo [ 21 ], although suitable for the detection of early stages of cognitive impairment, focus only on the analysis of the cognitive areas of orientation and attentional processes. As the detection of MCI is complex, not all tools are suitable for it, with some tools such as DCS [ 22 ] proving only suitable for the detection of dementia.…”

“…Similarly, the CogEvo tool, which focuses on orientation games and attentional processes, is useful for assessing the early stages of cognitive impairment [ 21 ]. On the other hand, the DCS tool correctly discriminates patients with dementia but its ability to differentiate those with MCI from cognitively healthy older adults is not as good [ 22 ]. In terms of cognitive areas that are assessed as digital cognitive biomarkers, tests that analyze memory and executive functions are the most sensitive and promising for the detection of MCI and dementia [ 23 ].…”