Automatic Spontaneous Speech Analysis for the Detection of Cognitive Functional Decline in Older Adults: Multilanguage Cross-Sectional Study.

BACKGROUND: The rise in life expectancy is associated with an increase in long-term and gradual cognitive decline. Treatment effectiveness is enhanced at the early stage of the disease. Therefore, there is a need to find low-cost and ecological solutions for mass screening of community-dwelling older adults. OBJECTIVE: This work aims to exploit automatic analysis of free speech to identify signs of cognitive function decline. METHODS: A sample of 266 participants older than 65 years were recruited in Italy and Spain and were divided into 3 groups according to their Mini-Mental Status Examination (MMSE) scores. People were asked to tell a story and describe a picture, and voice recordings were used to extract high-level features on different time scales automatically. Based on these features, machine learning algorithms were trained to solve binary and multiclass classification problems by using both mono- and cross-lingual approaches. The algorithms were enriched using Shapley Additive Explanations for model explainability. RESULTS: In the Italian data set, healthy participants (MMSE score≥27) were automatically discriminated from participants with mildly impaired cognitive function (20≤MMSE score≤26) and from those with moderate to severe impairment of cognitive function (11≤MMSE score≤19) with accuracy of 80% and 86%, respectively. Slightly lower performance was achieved in the Spanish and multilanguage data sets. CONCLUSIONS: This work proposes a transparent and unobtrusive assessment method, which might be included in a mobile app for large-scale monitoring of cognitive functionality in older adults. Voice is confirmed to be an important biomarker of cognitive decline due to its noninvasive and easily accessible nature.

Análisis de la mejora de la calidad del sueño y la ansiedad en estudiantes universitarios, bajo estrés, mediante el consumo de cerveza sin alcohol / Analysis of improved sleep quality and anxiety in college students under stress by consuming non-alcoholic beer

Fundamentos: La cerveza sin alcohol es una bebida saludable. Esta contiene lúpulo que junto a sus polifenoles: myrcenol y xanthumol aportan a la cerveza propiedades sedantes. Nuestro objetivo es determinar la influencia de la cerveza sin alcohol sobre la ansiedad y la calidad del sueño nocturno, en una población de estudiantes sometidos a estrés. Métodos: Se reclutó una población de 31 estudiantes. Se les analizó el sueño mediante Activimetría por Actiwatch®, durante 3 semanas. Y se les realizaron el Cuestionario de sueño Pittsburgh y Cuestionario de ansiedad STAI. Las 2 últimas semanas se ingirió una cerveza sin alcohol en la cena. Resultados: En Activimetría se mostraron diferencias significativas (p<0,05) en cuanto a la disminución de la Latencia de sueño tras la ingesta de cerveza sin alcohol (16,67±17,62 min), frente al grupo control (22,19±21,34 min). También se observaron diferencias en el Cuestionario de sueño Pittsburgh, siendo estadísticamente significativas en la segunda semana de tratamiento (7,07±4,37) frente a la Semana Control (9,03±6,31). Además del Cuestionario de Ansiedad/Estado STAI, que mostró disminución. Conclusión: La Latencia de sueño analizada por Activimetría mejora tras la toma de una cerveza sin alcohol en la cena. El Índice de sueño de Pittsburgh constata dicha mejoría en el sueño nocturno. Así como la disminución de la Ansiedad/Estado por STAI (AU)

Introduction: Non-alcoholic beer it is a healthy beverage. Its contains hop, and polyphenols: myrcenol and xanthoumol giving beer sedative properties. Our aim is to determine the influence of non-alcoholic beer on anxiety and sleep quality in a student population under stress. Methods: A population of 31 students. Sleep data were collected through Actimetry (Actiwatch®) for 3 weeks. Participants filled out the Pittsburgh Sleep Questionnaire and STAI Anxiety Questionnaire. Last 2 weeks volunteers ingested a non-alcoholic beer at dinner. Results: Results showed significant differences (p<0.05) of reduction in Sleep latency after ingesting non-alcoholic beer (16.67±17.62 min) versus the control group (22.19±21.34 min). Statistically significant differences were showed in the Pittsburgh Sleep Questionnaire in the second week of treatment (7.07±4.37) compared to the Control week (9.03±6.31). Regarding the STAI Anxiety Questionnaire, it was observed a decrease. Conclusion: There is a decrease in Sleep latency after ingesting non-alcoholic beer at dinner. The Pittsburgh Sleep Index found that improvement in nighttime sleep. And the Anxiety/State by the STAI improves (AU)