Multimodal digital assessment of depression with actigraphy and app in Hong Kong Chinese.

There is an emerging potential for digital assessment of depression. In this study, Chinese patients with major depressive disorder (MDD) and controls underwent a week of multimodal measurement including actigraphy and app-based measures (D-MOMO) to record rest-activity, facial expression, voice, and mood states. Seven machine-learning models (Random Forest [RF], Logistic regression [LR], Support vector machine [SVM], K-Nearest Neighbors [KNN], Decision tree [DT], Naive Bayes [NB], and Artificial Neural Networks [ANN]) with leave-one-out cross-validation were applied to detect lifetime diagnosis of MDD and non-remission status. Eighty MDD subjects and 76 age- and sex-matched controls completed the actigraphy, while 61 MDD subjects and 47 controls completed the app-based assessment. MDD subjects had lower mobile time (P = 0.006), later sleep midpoint (P = 0.047) and Acrophase (P = 0.024) than controls. For app measurement, MDD subjects had more frequent brow lowering (P = 0.023), less lip corner pulling (P = 0.007), higher pause variability (P = 0.046), more frequent self-reference (P = 0.024) and negative emotion words (P = 0.002), lower articulation rate (P < 0.001) and happiness level (P < 0.001) than controls. With the fusion of all digital modalities, the predictive performance (F1-score) of ANN for a lifetime diagnosis of MDD was 0.81 and 0.70 for non-remission status when combined with the HADS-D item score, respectively. Multimodal digital measurement is a feasible diagnostic tool for depression in Chinese. A combination of multimodal measurement and machine-learning approach has enhanced the performance of digital markers in phenotyping and diagnosis of MDD.

Detection of Suicidal Ideation in Clinical Interviews for Depression Using Natural Language Processing and Machine Learning: Cross-Sectional Study.

Background: Assessing patients' suicide risk is challenging, especially among those who deny suicidal ideation. Primary care providers have poor agreement in screening suicide risk. Patients' speech may provide more objective, language-based clues about their underlying suicidal ideation. Text analysis to detect suicide risk in depression is lacking in the literature. Objective: This study aimed to determine whether suicidal ideation can be detected via language features in clinical interviews for depression using natural language processing (NLP) and machine learning (ML). Methods: This cross-sectional study recruited 305 participants between October 2020 and May 2022 (mean age 53.0, SD 11.77 years; female: n=176, 57%), of which 197 had lifetime depression and 108 were healthy. This study was part of ongoing research on characterizing depression with a case-control design. In this study, 236 participants were nonsuicidal, while 56 and 13 had low and high suicide risks, respectively. The structured interview guide for the Hamilton Depression Rating Scale (HAMD) was adopted to assess suicide risk and depression severity. Suicide risk was clinician rated based on a suicide-related question (H11). The interviews were transcribed and the words in participants' verbal responses were translated into psychologically meaningful categories using Linguistic Inquiry and Word Count (LIWC). Results: Ordinal logistic regression revealed significant suicide-related language features in participants' responses to the HAMD questions. Increased use of anger words when talking about work and activities posed the highest suicide risk (odds ratio [OR] 2.91, 95% CI 1.22-8.55; P=.02). Random forest models demonstrated that text analysis of the direct responses to H11 was effective in identifying individuals with high suicide risk (AUC 0.76-0.89; P<.001) and detecting suicide risk in general, including both low and high suicide risk (AUC 0.83-0.92; P<.001). More importantly, suicide risk can be detected with satisfactory performance even without patients' disclosure of suicidal ideation. Based on the response to the question on hypochondriasis, ML models were trained to identify individuals with high suicide risk (AUC 0.76; P<.001). Conclusions: This study examined the perspective of using NLP and ML to analyze the texts from clinical interviews for suicidality detection, which has the potential to provide more accurate and specific markers for suicidal ideation detection. The findings may pave the way for developing high-performance assessment of suicide risk for automated detection, including online chatbot-based interviews for universal screening.

The Associations of Electronic Media Use With Sleep and Circadian Problems, Social, Emotional and Behavioral Difficulties in Adolescents.

Background: Electronic media use (EMU) becomes one of the most common activities in adolescents. The present study investigated the deleterious influence of excessive EMU and EMU before bedtime on social, emotional, and behavioral difficulties (SEBD) in adolescents. The role of sleep and circadian problems in mediating the association of EMU with SEBD was examined. Methods: A cross-sectional survey study was conducted with 3,455 adolescents (55.7% female, mean age = 14.8 ± 1.57 years, 36.6% monthly family income < HK$15,000) between December 2011 and March 2012 in Hong Kong. The associations of EMU with sleep and circadian problems and SEBD were analyzed using multiple binary logistic regression and path analysis. Sleep problems were measured by the Insomnia Severity Index and the reduced Horne and Östberg Morningness and Eveningness Questionnaire. Circadian problems were calculated based on established formulas. SEBD was measured using the Strengths and Difficulties Questionnaire. Participants' mental health status was assessed by the General Health Questionnaire. Results: A longer duration of EMU, excessive EMU (daily duration ≥ 2 h), and bedtime EMU (an hour before bedtime) were associated with the risk of sleep and circadian problems, poor mental health, and SEBD (p < 0.05). Insomnia, eveningness, social jetlag, and sleep deprivation were found to mediate the associations of EMU (including bedtime EMU of computers, electronic game consoles, phones, and televisions, together with excessive EMU of computers for leisure purposes and phones) with mental health and SEBD. Conclusions: The findings suggest the need for setting up guidelines and advocacy for education for appropriate EMU and intervention for the associated sleep and circadian problems to ameliorate EMU-related mental and behavioral health problems in adolescents.

Withdrawal behaviors and mental health among college students / Comportamientos de aislamiento y salud mental en estudiantes universitarios

Youth social withdrawal has raised clinical concerns, and prevention of withdrawal behavior is important yet difficult. While human evaluation of withdrawal behavior can be subjective, technology provides objective measurement for withdrawal behavior. This study aims to examine the association between withdrawal behaviors (home-stay and non-communication) and mental health status (stress, depression and loneliness). The open-access StudentLife dataset, including the location and conversation information derived from the sensor data, stress levels, and pre- and post-questionnaires of depression (PHQ-9) and loneliness (RULS) of 47 college students over 10 weeks was used. Multilevel modeling and functional regression were employed for data analysis. Daily duration of home-stay was negatively associated with daily stress levels, and the interaction effect of daily duration of home-stay and non-communication were positively associated with daily stress levels and changes in PHQ-9 and RULS scores. Smartphone data is useful to provide adjunct information to the professional clinical judgement and early detection on withdrawal behavior

El aislamiento social de los jóvenes ha generado preocupaciones clínicas y prevenir estos comportamientos es importante pero difícil. Aunque la evaluación del aislamiento puede ser subjetiva, la tecnología proporciona medidas objetivas de este comportamiento. El objetivo de este estudio es examinar la asociación entre los comportamientos de aislamiento (permanecer en casa y no comunicarse) y el estado de la salud mental (estrés, depresión y soledad). Se utilizó la base de datos de libre acceso StudentLife, incluyendo información sobre la ubicación y la conversación registrada por un sensor de datos, los niveles de estrés y medidas de autoinforme pre y pos sobre depresión (PHQ-9) y soledad (RULS) de 47 estudiantes universitarios durante 10 semanas. Para el análisis de datos se utilizaron modelos multinivel y la regresión funcional. La duración diaria de la permanencia en casa estaba negativamente asociada con los niveles diarios de estrés y el efecto de interacción de la duración diaria de la permanencia en casa y la falta de comunicación estaban positivamente relacionados con los niveles diarios de estrés y los cambios en las puntuaciones en PHQ-9 y RULS. Los datos del teléfono inteligente son útiles para obtener información complementaria al juicio clínico profesional y para la detección temprana de los comportamientos de aislamiento