Health Care Professionals’ Views on the Use of Passive Sensing, AI, and Machine Learning in Mental Health Care: Systematic Review With Meta-Synthesis

JMIR Mental Health, Journal Year: 2024, Volume and Issue: 11, P. e49577 - e49577

Published: Jan. 23, 2024

Background Mental health difficulties are highly prevalent worldwide. Passive sensing technologies and applied artificial intelligence (AI) methods can provide an innovative means of supporting the management mental problems enhancing quality care. However, views stakeholders important in understanding potential barriers to facilitators their implementation. Objective This study aims review, critically appraise, synthesize qualitative findings relating care professionals on use passive AI Methods A systematic search studies was performed using 4 databases. meta-synthesis approach used, whereby were analyzed inductive thematic analysis within a critical realist epistemological framework. Results Overall, 10 met eligibility criteria. The 3 main themes uses clinical practice, consequences for service users. total 5 subthemes identified: barriers, facilitators, empowerment, risk well-being, data privacy protection issues. Conclusions Although clinicians open-minded about care, factors consider user clinician workloads, therapeutic relationships. Service users must be involved development digital systems ensure ease use. of, training in, clear policies guidelines including security procedures, will also key facilitating engagement. feedback how practice is being received should considered. Trial Registration PROSPERO International Prospective Register Systematic Reviews CRD42022331698; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=331698

Language: Английский

---

Exploring Digital Biomarkers of Illness Activity in Mood Episodes: Hypotheses Generating and Model Development Study

JMIR mhealth and uhealth, Journal Year: 2023, Volume and Issue: 11, P. e45405 - e45405

Published: March 20, 2023

Depressive and manic episodes within bipolar disorder (BD) major depressive (MDD) involve altered mood, sleep, activity, alongside physiological alterations wearables can capture. Firstly, we explored whether wearable data could predict (aim 1) the severity of an acute affective episode at intra-individual level 2) polarity euthymia among different individuals. Secondarily, which were related to prior predictions, generalization across patients, associations between symptoms data. We conducted a prospective exploratory observational study including patients with BD MDD on (manic, depressed, mixed) whose recorded using research-grade (Empatica E4) 3 consecutive time points (acute, response, remission episode). Euthymic healthy controls during single session (approximately 48 h). Manic assessed standardized psychometric scales. Physiological included following channels: acceleration (ACC), skin temperature, blood volume pulse, heart rate (HR), electrodermal activity (EDA). Invalid removed rule-based filter, channels aligned 1-second units segmented window lengths 32 seconds, as best-performing parameters. developed deep learning predictive models, channels' individual contribution permutation feature importance analysis, computed scales' items normalized mutual information (NMI). present novel, fully automated method for preprocessing analysis from device, viable supervised pipeline time-series analyses. Overall, 35 sessions (1512 hours) 12 mixed, euthymic) 7 (mean age 39.7, SD 12.6 years; 6/19, 32% female) analyzed. The mood was predicted moderate (62%-85%) accuracies 1), their (70%) accuracy 2). most relevant features former tasks ACC, EDA, HR. There fair agreement in classification (Kendall W=0.383). Generalization models unseen overall low accuracy, except models. ACC associated "increased motor activity" (NMI>0.55), "insomnia" (NMI=0.6), "motor inhibition" (NMI=0.75). EDA "aggressive behavior" (NMI=1.0) "psychic anxiety" (NMI=0.52). show potential identify specific mania depression quantitatively, both MDD. Motor stress-related (EDA HR) stand out digital biomarkers predicting depression, respectively. These findings represent promising pathway toward personalized psychiatry, allow early identification intervention episodes.

Language: Английский

---

Identifying depression-related topics in smartphone-collected free-response speech recordings using an automatic speech recognition system and a deep learning topic model

Journal of Affective Disorders, Journal Year: 2024, Volume and Issue: 355, P. 40 - 49

Published: March 27, 2024

Prior research has associated spoken language use with depression, yet studies often involve small or non-clinical samples and face challenges in the manual transcription of speech. This paper aimed to automatically identify depression-related topics speech recordings collected from clinical samples. The data included 3919 English free-response via smartphones 265 participants a depression history. We transcribed automatic recognition (Whisper tool, OpenAI) identified principal transcriptions using deep learning topic model (BERTopic). To risk understand context, we compared participants' severity behavioral (extracted wearable devices) linguistic texts) characteristics across topics. From 29 identified, 6 for depression: 'No Expectations', 'Sleep', 'Mental Therapy', 'Haircut', 'Studying', 'Coursework'. Participants mentioning exhibited higher sleep variability, later onset, fewer daily steps used words, more negative language, leisure-related words their recordings. Our findings were derived depressed cohort specific task, potentially limiting generalizability populations other tasks. Additionally, some had sample sizes, necessitating further validation larger datasets. study demonstrates that can indicate severity. employed data-driven workflow provides practical approach analyzing large-scale real-world settings.

Language: Английский

---

Asynchronous Technologies in Mental Health Care and Education

Current Treatment Options in Psychiatry, Journal Year: 2023, Volume and Issue: 10(2), P. 59 - 71

Published: May 4, 2023

Language: Английский

---

The feasibility of collecting and linking multimodal data for digital mental health research: A pilot observational study involving digital phenotyping and genetics data (Preprint)

Published: Jan. 26, 2025

Digital phenotyping, the process of using digital data to measure and understand behaviour internal states, shows promise for predictive analytics in mental health when combined with other forms data. However, linking phenotyping datasets, particularly those that involve highly sensitive clinical genetic data, is uncommon due technical, ethical, procedural difficulties. Understanding feasibility collecting this first step create novel multimodal datasets. The Mobigene Pilot Study explores new primarily smartphone-collected from an existing cohort adults a history depression (Australian Genetics Depression Study; AGDS). This paper aims to: (1) describe rates study uptake (e.g., number consenting eligible participants, number/proportion whose could be linked) adherence who completed baseline/post-surveys, dropped out); (2) levels engagement daily diaries; (3) identify openness take part similar research; (4) determine whether these indicators differ by current symptoms. Participants aged 18-30 AGDS were invited two-week study. baseline demographic survey then downloaded Mind GRID app phenotyping. Active cognitive, voice typing tasks collected once per day on days 1 11; diaries assessing self-reported mood 2-10 (once/day 9-days). Passive Global Positioning Systems, accelerometers) throughout A post-survey was completed. To feasibility, we computed descriptive statistics explore adherence, diary engagement, future research. Correlations t-tests explored relationship between health. Out 174 153 (153/174, 87.9%) 126 provided enabled linkage genetic, self-report, (126/174, 72.4%). There 100 unique participants after duplicate removal (100/174, 57.5%) 69 complete at post (69/174, 39.7%). Dropout occurred prior completing (23/174, 13.2%) during collection (31/174, 17.8%). average 5.30 (SD=2.76) diaries. All surveys (69/69, 100%) expressed willingness participate studies. Feasibility not related symptoms |ts|<1.12, Ps>.27). It feasible collect link datasets involving clinical, next phase involves exploring links markers clinical/genetic correlates improve detection prediction problems.

Language: Английский

---

Application of a Sociotechnical Framework to Uncover Factors That Influence Effective User Engagement With Digital Mental Health Tools in Clinical Care Contexts: Scoping Review

Journal of Medical Internet Research, Journal Year: 2025, Volume and Issue: 27, P. e67820 - e67820

Published: April 28, 2025

Background Digital health tools such as mobile apps and patient portals continue to be embedded in clinical care pathways enhance mental delivery achieve the quintuple aim of improving experience, population health, team well-being, costs, equity. However, a key issue that has greatly hindered value these is suboptimal user engagement by patients families. With only small fraction users staying engaged over time, there great need better understand factors influence with digital settings. Objective This review aims identify relevant settings using sociotechnical approach. Methods A scoping methodology was used from literature. Five academic databases (MEDLINE, Embase, CINAHL, Web Science, PsycINFO) were searched pertinent articles terms related engagement, tools. The abstracts screened independently 2 reviewers, data extracted standardized extraction form. Articles included if tool had at least 1 patient-facing component clinician-facing component, one objectives article examine tool. An established framework developed Sittig Singh inform mapping analysis factors. Results database search identified 136 for inclusion analysis. Of articles, 84 (61.8%) published last 5 years, 47 (34.6%) United States, 23 (16.9%) Kingdom. regard examining majority (95/136, 69.9%) qualitative approach engagement. From 26 across 7 categories framework. These ranged technology-focused (eg, modality tool) environment alignment workflows) system-level issues reimbursement physician use patients). Conclusions On basis this review, we have uncovered how tool, individuals, environment, system may care. Future work should focus on validating identifying core set essential environments. Moreover, exploring strategies through would useful leaders clinicians interested

Language: Английский

---

The feasibility of collecting and linking digital phenotyping, clinical, and genetics data for mental health research: A pilot observational study (Preprint)

JMIR Formative Research, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 26, 2025

Language: Английский

---

Evaluating a smartphone-based symptom self-monitoring app for psychosis in China (YouXin): A non-randomised validity and feasibility study with a mixed-methods design

Digital Health, Journal Year: 2024, Volume and Issue: 10

Published: Jan. 1, 2024

Background Psychosis causes a significant burden globally, including in China, where limited mental health resources hinder access to care. Smartphone-based remote monitoring offers promising solution. This study aimed assess the validity, feasibility, acceptability, and safety of symptom self-monitoring smartphone app, YouXin, for people with psychosis China. Methods A pre-registered non-randomised validity feasibility mixed-methods design. Participants were recruited from major tertiary psychiatric hospital Beijing, utilised YouXin app self-monitor mood symptoms four weeks. Feasibility outcomes recruitment, retention outcome measures completeness. Active (ASM) was tested against corresponding clinical assessments (PANSS CDS) using Spearman correlation. Ten participants completed qualitative interviews at end explore acceptability trial procedures. Results parameters met. The target recruitment sample 40 met, 82.5% completing measures, 60% achieving acceptable ASM engagement (completing >33% all prompts), 33% recording sufficient passive data extract mobility indicators. Five domains (hallucinations, suspiciousness, guilt feelings, delusions, grandiosity) achieved moderate correlation assessment. Both quantitative evaluation showed high YouXin. Clinical measurements indicated no functional deterioration. No adverse events reported, suggesting is safe use this population. Conclusions met powered efficacy indicated. However, refinements are needed improve increase

Language: Английский

---

Acceptability and experience of a smartphone symptom monitoring app for people with psychosis in China (YouXin): a qualitative study

BMC Psychiatry, Journal Year: 2024, Volume and Issue: 24(1)

Published: April 9, 2024

Abstract Background Access to high-quality mental healthcare remains challenging for people with psychosis globally, including China. Smartphone-based symptom monitoring has the potential support scalable healthcare. However, no such tool, until now, been developed and evaluated in This study investigated acceptability experience of using a self-monitoring smartphone app (YouXin) specifically Methods Semi-structured interviews were conducted 10 participants explore YouXin. Participants recruited from non-randomised feasibility that tested validity, feasibility, safety YouXin app. Data analysis was guided by theoretical framework acceptability. Results Most felt acceptable easy use, unbearable burdens or opportunity costs reported. found completing rewarding experienced sense achievement. Privacy data security not major concerns participants, largely due trust their treating hospital around protection. use attributed this training provided at beginning study. A few said they had built some form relationship would miss when finished. Conclusions The is gained greater insights about symptoms As we only collected retrospective study, future studies are warranted assess hypothetical before commencement provide more comprehensive understanding implementation.

Language: Английский

---

Removal of hydrocarbon compounds from the oil effluents of Abadan refinery by a biological method

International Journal of Energy and Water Resources, Journal Year: 2023, Volume and Issue: 8(4), P. 475 - 481

Published: Sept. 25, 2023

Language: Английский

---