Background: Gait, speech, and drawing behaviors have been shown to be sensitive to the diagnosis of Alzheimer’s disease (AD) and mild cognitive impairment (MCI). However, previous studies focused on only analyzing individual behavioral modalities, although these studies suggested that each of these modalities may capture different profiles of cognitive impairments associated with AD. Objective: We aimed to investigate if combining behavioral data of gait, speech, and drawing can improve classification performance compared with the use of individual modality and if each of these behavioral data can be associated with different cognitive and clinical measures for the diagnosis of AD and MCI. Methods: Behavioral data of gait, speech, and drawing were acquired from 118 AD, MCI, and cognitively normal (CN) participants. Results: Combining all three behavioral modalities achieved 93.0%accuracy for classifying AD, MCI, and CN, and only 81.9%when using the best individual behavioral modality. Each of these behavioral modalities was statistically significantly associated with different cognitive and clinical measures for diagnosing AD and MCI. Conclusion: Our findings indicate that these behaviors provide different and complementary information about cognitive impairments such that classification of AD and MCI is superior to using either in isolation.

Highlights What is the primary question addressed by this study? This paper explores the use of natural language processing techniques and machine learning models to predict loneliness in older community-dwelling adults. What is the main finding of this study? There are structural differences in how older men and women talk about loneliness that can be detected using natural language processing techniques. Text features can be used to predict loneliness with reasonable validity. What is the meaning of the finding? NLP and machine learning approaches provide a novel way to analyze text data to identify loneliness, while accounting for key sociodemographic factors like sex and age.

Health-monitoring technologies for automatically detecting the early signs of Alzheimer's disease (AD) have become increasingly important. Speech responses to neuropsychological tasks have been used for quantifying changes resulting from AD and differentiating AD and mild cognitive impairment (MCI) from cognitively normal (CN). However, whether and how other types of speech tasks with less burden on older adults could be used for detecting early signs of AD remains unexplored. In this study, we developed a tablet-based application and compared speech responses to daily life questions with those to neuropsychological tasks in terms of differentiating MCI from CN. We found that in daily life questions, around 80% of speech features showing significant differences between CN and MCI overlapped those showing significant differences in both our study and other studies using neuropsychological tasks, but the number of significantly different features as well as their effect sizes from life questions decreased compared with those from neuropsychological tasks. On the other hand, the results of classification models for detecting MCI by using the speech features showed that daily life questions could achieve high accuracy, i.e., 86.4%, comparable to neuropsychological tasks by using eight questions against all five neuropsychological tasks. Our results indicate that, while daily life questions may elicit weaker but statistically discernable differences in speech responses resulting from MCI than neuropsychological tasks, combining them could be useful for detecting MCI with comparable performance to using neuropsychological tasks, which could help develop health-monitoring technologies for early detection of AD in a less burdensome manner.

Background Identifying signs of Alzheimer disease (AD) through longitudinal and passive monitoring techniques has become increasingly important. Previous studies have succeeded in quantifying language dysfunctions and identifying AD from speech data collected during neuropsychological tests. However, whether and how we can quantify language dysfunction in daily conversation remains unexplored. Objective The objective of this study was to explore the linguistic features that can be used for differentiating AD patients from daily conversations. Methods We analyzed daily conversational data of seniors with and without AD obtained from longitudinal follow-up in a regular monitoring service (from n=15 individuals including 2 AD patients at an average follow-up period of 16.1 months; 1032 conversational data items obtained during phone calls and approximately 221 person-hours). In addition to the standard linguistic features used in previous studies on connected speech data during neuropsychological tests, we extracted novel features related to atypical repetition of words and topics reported by previous observational and descriptive studies as one of the prominent characteristics in everyday conversations of AD patients. Results When we compared the discriminative power for AD, we found that atypical repetition in two conversations on different days outperformed other linguistic features used in previous studies on speech data during neuropsychological tests. It was also a better indicator than atypical repetition in single conversations as well as that in two conversations separated by a specific number of conversations. Conclusions Our results show how linguistic features related to atypical repetition across days could be used for detecting AD from daily conversations in a passive manner by taking advantage of longitudinal data.

Video captioning can increase the accessibility of information for people who are deaf or hard-of-hearing and benefit second language learners and reading-deficient students. We propose a caption editing system that harvests crowdsourced work for the useful task of video captioning. To make the task an engaging activity, its interface incorporates game-like elements. Non-expert users submit their transcriptions for short video segments against a countdown timer, either in a "type" or "fix" mode, to score points. Transcriptions from multiple users are aligned and merged to form the final captions. Preliminary results with 42 participants and 578 short video segments show that the Word Error Rate of the merged captions with two users per segment improved from 20.7% in ASR to 16%. Finally, we discuss our work in progress to improve both the accuracy of the collected data and to increase the crowd engagement.