AI in mental health

Current Opinion in Psychology, Journal Year: 2020, Volume and Issue: 36, P. 112 - 117

Published: June 3, 2020

Language: Английский

---

Circadian rhythm sleep–wake disturbances and depression in young people: implications for prevention and early intervention

The Lancet Psychiatry, Journal Year: 2021, Volume and Issue: 8(9), P. 813 - 823

Published: Aug. 19, 2021

Language: Английский

---

Comorbidity between depression and anxiety: assessing the role of bridge mental states in dynamic psychological networks

BMC Medicine, Journal Year: 2020, Volume and Issue: 18(1)

Published: Sept. 29, 2020

Comorbidity between depressive and anxiety disorders is common. A hypothesis of the network perspective on psychopathology that comorbidity arises due to interplay symptoms shared by both disorders, with overlapping acting as so-called bridges, funneling symptom activation clusters each disorder. This study investigated this testing whether (i) two mental states "worrying" "feeling irritated" functioned bridges in dynamic state networks individuals depression compared either disorder alone, (ii) or non-overlapping stronger bridges.Data come from Netherlands Study Depression Anxiety (NESDA). total 143 participants met criteria for comorbid (65%), 40 depression-only (18.2%), 37 anxiety-only (16.8%) during any NESDA wave. Participants completed momentary assessments (i.e., states) anxiety, five times a day, 2 weeks (14,185 assessments). First, dynamics were modeled multilevel vector autoregressive model, using Bayesian estimation. Summed average lagged indirect effects through hypothesized bridge groups. Second, we evaluated role all potential states.While summed effect was larger group single groups, differences groups not statistically significant. The difference became more pronounced when only examining recent diagnoses (< 6 months). However, credible intervals scores remained wide. In second analysis, item ("feeling down") acted strongest groups.This empirically examined prominent network-approach first time longitudinal data. No support found irritable" functioning vulnerable anxiety. Potentially, activity can be observed acute symptomatology. If so, these may present interesting targets treatment, but prevention. requires further investigation.

Language: Английский

---

Digital health tools for the passive monitoring of depression: a systematic review of methods

npj Digital Medicine, Journal Year: 2022, Volume and Issue: 5(1)

Published: Jan. 11, 2022

The use of digital tools to measure physiological and behavioural variables potential relevance mental health is a growing field sitting at the intersection between computer science, engineering, clinical science. We summarised literature on remote measuring technologies, mapping methodological challenges threats reproducibility, identified leading signals for depression. Medical science databases were searched January 2007 November 2019. Published studies linking depression objective data obtained from smartphone wearable device sensors in adults with unipolar healthy subjects included. A descriptive approach was taken synthesise study methodologies. included 51 found reproducibility transparency arising failure provide comprehensive descriptions recruitment strategies, sample information, feature construction determination handling missing data. characterised by small sizes, short follow-up duration great variability quality reporting, limiting interpretability pooled results. Bivariate analyses show consistency statistically significant associations features sleep, physical activity, location, phone Machine learning models predictive value aggregated features. Given pitfalls combined literature, these results should be purely as starting point hypothesis generation. Since this research ultimately aimed informing practice, we recommend improvements reporting standards including consideration generalisability such wider diversity samples, thorough methodology bias numerous

Language: Английский

---

Effect of Electroacupuncture on Insomnia in Patients With Depression

JAMA Network Open, Journal Year: 2022, Volume and Issue: 5(7), P. e2220563 - e2220563

Published: July 7, 2022

Importance

Electroacupuncture (EA) is a widely recognized therapy for depression and sleep disorders in clinical practice, but its efficacy the treatment of comorbid insomnia remains uncertain.

Objective

To assess safety EA as an alternative improving quality mental state patients with depression.

Design, Setting, Participants

A 32-week patient- assessor-blinded, randomized, sham-controlled trial (8-week intervention plus 24-week observational follow-up) was conducted from September 1, 2016, to July 30, 2019, at 3 tertiary hospitals Shanghai, China. Patients were randomized receive standard care, sham acupuncture (SA) or care only control. 18 70 years age, had insomnia, met criteria classified theDiagnostic Statistical Manual Mental Disorders (Fifth Edition). Data analyzed May 4 13, 2020.

Interventions

All groups provided guided by psychiatrists. SA received real treatment, sessions per week 8 weeks, total 24 sessions.

Main Outcomes Measures

The primary outcome change Pittsburgh Sleep Quality Index (PSQI) baseline 8. Secondary outcomes included PSQI 12, 20, 32 weeks follow-up; parameters recorded actigraphy; Insomnia Severity Index; 17-item Hamilton Depression Rating Scale score; Self-rating Anxiety score.

Results

Among 270 (194 women [71.9%] 76 men [28.1%]; mean [SD] 50.3 [14.2] years) intention-to-treat analysis, 247 (91.5%) completed all measurements 32, 23 (8.5%) dropped out trial. difference within group −6.2 (95% CI, −6.9 −5.6). At 8, score −3.6 −4.4 −2.8;P < .001) between −5.1 −6.0 −4.2;P control groups. treating sustained during postintervention follow-up. Significant improvement (−10.7 [95% −11.8 −9.7]), (−7.6 −8.5 −6.7]), (−2.9 −4.1 −1.7]) scores time actigraphy (29.1 21.5-36.7] minutes) observed 8-week period (P< .001 all). No between-group differences found frequency awakenings. serious adverse events reported.

Conclusions Relevance

In this depression, improved significantly compared 32.

Trial Registration

ClinicalTrials.gov Identifier:NCT03122080

Language: Английский

---

Reshaping the healthcare world by AI-integrated wearable sensors following COVID-19

Chemical Engineering Journal, Journal Year: 2025, Volume and Issue: 505, P. 159478 - 159478

Published: Jan. 11, 2025

Language: Английский

---

Affect fluctuations examined with ecological momentary assessment in patients with current or remitted depression and anxiety disorders

Psychological Medicine, Journal Year: 2020, Volume and Issue: 51(11), P. 1906 - 1915

Published: April 1, 2020

Abstract Background There is increasing interest in day-to-day affect fluctuations of patients with depressive and anxiety disorders. Few studies have compared repeated assessments positive (PA) negative (NA) across diagnostic groups, fluctuation patterns were not uniformly defined. The aim this study to compare a current episode or disorder, remitted controls, using instability as core concept but also describing other measures variability adjusting for possible confounders. Methods Ecological momentary assessment (EMA) data obtained from 365 participants the Netherlands Study Depression Anxiety ( n = 95), 178) no 92) DSM-IV defined depression/anxiety disorder. For 2 weeks, five times per day, filled-out items on PA NA. Affect was calculated root mean square successive differences (RMSSD). Tests group RMSSD, within-person variance, autocorrelation performed, controlling levels. Results Current had highest both NA, followed by remitters then controls. Instability between groups remained significant when levels, longer significant. Conclusions Patients disorder higher NA than Especially regard could be interpreted being more sensitive internal external stressors having suboptimal regulation.

Language: Английский

---

Depressive and anxiety disorders in concert–A synthesis of findings on comorbidity in the NESDA study

Journal of Affective Disorders, Journal Year: 2021, Volume and Issue: 284, P. 85 - 97

Published: Feb. 6, 2021

Comorbidity of depressive and anxiety disorders is common remains incompletely comprehended. This paper summarizes findings from the Netherlands Study Depression Anxiety (NESDA) regarding prevalence, temporal sequence, course longitudinal patterns; sociodemographic, vulnerability neurobiological indicators; functional, somatic mental health indicators comorbidity.Narrative synthesis earlier NESDA based papers on comorbidity (n=76).Comorbidity was rule in over three-quarter subjects with and/or disorders, most often preceded by an disorder. Higher severity chronicity characterized a poorer course. Over time, transitions between were common. Consistent risk childhood trauma, neuroticism early age onset. Psychological vulnerabilities, such as trait avoidance tendencies, more pronounced comorbid than single disorders. In general, there few differences biological markers neuroimaging persons versus Most somatic, other indicators, ranging disability to cardiovascular psychiatric multimorbidity, highest disorders.The observational design limits causal inference. Attrition higher relative disorders.As compared psychosocial determinants, morbidities, functional impairments, outcome. These results justify specific attention for particularly treatment settings.

Language: Английский

---

Digital Biomarkers for Depression Screening With Wearable Devices: Cross-sectional Study With Machine Learning Modeling

JMIR mhealth and uhealth, Journal Year: 2021, Volume and Issue: 9(10), P. e24872 - e24872

Published: July 15, 2021

Background Depression is a prevalent mental disorder that undiagnosed and untreated in half of all cases. Wearable activity trackers collect fine-grained sensor data characterizing the behavior physiology users (ie, digital biomarkers), which could be used for timely, unobtrusive, scalable depression screening. Objective The aim this study was to examine predictive ability biomarkers, based on from consumer-grade wearables, detect risk working population. Methods This cross-sectional 290 healthy adults. Participants wore Fitbit Charge 2 devices 14 consecutive days completed health survey, including screening depressive symptoms using 9-item Patient Health Questionnaire (PHQ-9), at baseline weeks later. We extracted range known novel biomarkers physical activity, sleep patterns, circadian rhythms wearables steps, heart rate, energy expenditure, data. Associations between severity were examined with Spearman correlation multiple regression analyses adjusted potential confounders, sociodemographic characteristics, alcohol consumption, smoking, self-rated health, subjective loneliness. Supervised machine learning statistically selected predict symptom status). varying cutoff scores an acceptable PHQ-9 score define group different subsamples classification, while set remained same. For performance evaluation, we k-fold cross-validation obtained accuracy measures holdout folds. Results A total 267 participants included analysis. mean age 33 (SD 8.6, 21-64) years. Out participants, there mild female bias displayed (n=170, 63.7%). majority Chinese (n=211, 79.0%), single (n=163, 61.0%), had university degree (n=238, 89.1%). found greater robustly associated variation nighttime rate AM 4 6 AM; it also lower regularity weekday steps estimated nonparametric interdaily stability autocorrelation as well fewer steps-based daily peaks. Despite several reliable associations, our evidence showed limited whole sample However, balanced contrasted comprised depressed no or minimal symptoms), model achieved 80%, sensitivity 82%, specificity 78% detecting subjects high depression. Conclusions Digital have been discovered are behavioral physiological consumer increased assist screening, yet current shows ability. Machine models combining these discriminate individuals risk.

Language: Английский

---

Sleep classification from wrist-worn accelerometer data using random forests

Scientific Reports, Journal Year: 2021, Volume and Issue: 11(1)

Published: Jan. 8, 2021

Accurate and low-cost sleep measurement tools are needed in both clinical epidemiological research. To this end, wearable accelerometers widely used as they low price provide reasonably accurate estimates of movement. Techniques to classify from the high-resolution accelerometer data primarily rely on heuristic algorithms. In paper, we explore potential detecting using Random forests. Models were trained three different studies where 134 adult participants (70 with disorder 64 good healthy sleepers) wore an their wrist during a one-night polysomnography recording clinic. The forests able distinguish sleep-wake states F1 score 73.93% previously unseen test set 24 participants. Detecting when is not worn was also successful machine learning ([Formula: see text]), combined our detection models day-time estimate that correlated self-reported habitual nap behaviour text]). These forest have been made open-source aid further line literature, stage classification turned out be difficult only data.

Language: Английский

---