Using Voice Assistant Systems to Improve Dietary Recall among Older Adults: Perspectives of Registered Dietitians.

Dietary assessments are important clinical tools used by Registered Dietitians (RDs). Current methods pose barriers to accurately assess the nutritional intake of older adults due to age-related increases in risk for cognitive decline and more complex health histories. Our qualitative study explored whether implementing Voice assistant systems (VAS) could improve current dietary recall from the perspective of 20 RDs. RDs believed the implementing VAS in dietary assessments of older adults could potentially improve patient accuracy in reporting food intake, recalling portion sizes, and increasing patient-provider efficiency during clinic visits. RDs reported that low technology literacy in older adults could be a barrier to implementation. Our study provides a better understanding of how VAS can better meet the needs of both older adults and RDs in managing and assessing dietary intake.

Evaluating Voice-Assistant Commands for Dementia Detection.

Early detection of cognitive decline involved in Alzheimer's Disease and Related Dementias (ADRD) in older adults living alone is essential for developing, planning, and initiating interventions and support systems to improve users' everyday function and quality of life. In this paper, we explore the voice commands using a Voice-Assistant System (VAS), i.e., Amazon Alexa, from 40 older adults who were either Healthy Control (HC) participants or Mild Cognitive Impairment (MCI) participants, age 65 or older. We evaluated the data collected from voice commands, cognitive assessments, and interviews and surveys using a structured protocol. We extracted 163 unique command-relevant features from each participant's use of the VAS. We then built machine-learning models including 1-layer/2-layer neural networks, support vector machines, decision tree, and random forest, for classification and comparison with standard cognitive assessment scores, e.g., Montreal Cognitive Assessment (MoCA). Our classification models using fusion features achieved an accuracy of 68%, and our regression model resulted in a Root-Mean-Square Error (RMSE) score of 3.53. Our Decision Tree (DT) and Random Forest (RF) models using selected features achieved higher classification accuracy 80-90%. Finally, we analyzed the contribution of each feature set to the model output, thus revealing the commands and features most useful in inferring the participants' cognitive status. We found that features of overall performance, features of music-related commands, features of call-related commands, and features from Automatic Speech Recognition (ASR) were the top-four feature sets most impactful on inference accuracy. The results from this controlled study demonstrate the promise of future home-based cognitive assessments using Voice-Assistant Systems.