Perceptions and Effectiveness of a Fully-Automated Brief Behavioral Insomnia Therapy, Delivered by a Virtual Companion, in Older and Young Adults

Innovation in Aging, Год журнала: 2024, Номер 9(2)

Опубликована: Сен. 24, 2024

Abstract Background and Objectives One of the most common sleep disturbances in older people is insomnia. Cognitive–behavioral therapy first-line treatment for this condition adults, but in-person costly often unavailable. In study, a group young subjects, we aimed to compare: (a) their initial perceptions fully automated mobile health intervention manage insomnia, (b) how these related completion, (c) effects on insomnia severity outcomes. Research Design Methods A case-series study was conducted with self-selected sample (≥65 years) (18–35 adults (n = 5,660) who downloaded free app, available France, that delivers brief behavioral aided by virtual companion (VC). The 17-day included hygiene stimulus control recommendations. Primary outcome completion (yes/no). At beginning intervention, acceptability trust VC were assessed 2 short questionnaires (completion rate: 1,597 users). Insomnia evaluated Severity Index. Results Logistic regression analyses showed higher credibility app’s associated odds only (trust scores × age group: ratio [OR] 1.12; 95% confidence interval [CI] 1.01–1.25; p < .05, OR 1.25 [95% CI 1.06–1.47], .01). Within subset users completed 289), remission (χ2 2.72, NS) response rates 2.34, comparable across both groups. Discussion Implications This appears be efficacious self-management symptoms adults. integration persuasive interaction elements, such as avatars coaches, interventions could particularly useful stimulate adults’ engagement. Clinical Trials Registration Number NCT05074901

Язык: Английский

---

Combining AI and Human Support in Mental Health: a Digital Intervention with Comparable Effectiveness to Human-delivered Care (Preprint)

Journal of Medical Internet Research, Год журнала: 2024, Номер unknown

Опубликована: Ноя. 28, 2024

Escalating mental health demand exceeds existing clinical capacity, requiring scalable digital solutions. However, engagement remains challenging. Conversational agents enhance by making programs more interactive and personalized but have not been widely used. This study evaluated a program for anxiety against external comparators. The used an AI-driven conversational agent to deliver clinician-written content via machine learning, with clinician oversight user support. aimed evaluate the engagement, effectiveness, safety of this structured, evidence-based human support mild, moderate severe generalized anxiety. Statistical analyses determine whether reduced than propensity-matched waiting control was statistically non-inferior real-world face-to-face typed cognitive behavioral therapy (CBT). Prospective participants (N=299) were recruited from NHS or social media in UK given use up 9 weeks (study conducted October 2023 May 2024). Endpoints collected before, during after program, at one-month follow-up. External comparator groups generated through propensity-matching sample Talking Therapies (NHS TT) data ieso Digital Health (typed-CBT) Dorset Healthcare University Foundation Trust (DHC) (face-to-face CBT). Superiority non-inferiority compare symptom reduction (change on GAD-7 scale) group groups. included time spent per participant calculated. Participants median 6 hours over 53 days, 78% (n=232) engaged (i.e. completed 2 14 days). There large clinically meaningful symptoms (per-protocol (PP; n=169): change = -7.4, d 1.6; intention-to-treat (ITT; n=299): -5.4, d=1.1). PP effect superior (d 1.3), CBT (p <.001) typed-CBT <.001). Similarly, ITT sample, showed superiority (d=0.8) (p=.002) approaching significance (p=.06). Effects sustained Clinicians overseeing mean 1.6 (31 - 200 minutes) sessions participant. By combining AI support, achieved outcomes comparable human-delivered care while significantly reducing required 8 times relative global estimates. These findings highlight potential technology scale healthcare, address unmet need, ultimately impact quality life economic burden globally. ISRCTN id: 52546704.

Язык: Английский

---

Combining Artificial Intelligence and Human Support in Mental Health: Digital Intervention With Comparable Effectiveness to Human-Delivered Care (Preprint)

Опубликована: Ноя. 28, 2024

Escalating mental health demand exceeds existing clinical capacity, necessitating scalable digital solutions. However, engagement remains challenging. Conversational agents can enhance by making programs more interactive and personalized, but they have not been widely adopted. This study evaluated a program for anxiety in comparison to external comparators. The used an artificial intelligence (AI)–driven conversational agent deliver clinician-written content via machine learning, with clinician oversight user support. aims evaluate the engagement, effectiveness, safety of this structured, evidence-based human support mild, moderate, severe generalized anxiety. Statistical analyses sought determine whether reduced than propensity-matched waiting control was statistically noninferior real-world, face-to-face typed cognitive behavioral therapy (CBT). Prospective participants (N=299) were recruited from National Health Service (NHS) or social media United Kingdom given access up 9 weeks (study conducted October 2023 May 2024). End points collected before, during, after program, as well at 1-month follow-up. External comparator groups created through propensity matching sample NHS Talking Therapies (NHS TT) data ieso Digital (typed CBT) Dorset HealthCare (DHC) University Foundation Trust (face-to-face CBT). Superiority noninferiority compare symptom reduction (change on 7-item Generalized Anxiety Disorder Scale [GAD-7]) between group groups. included support, time spent per participant calculated. Participants median 6 hours over 53 days, 232 299 (77.6%) engaged (ie, completing 2 14 days). There large, clinically meaningful symptoms (per-protocol [PP; n=169]: mean GAD-7 change –7.4, d=1.6; intention-to-treat [ITT; n= 99]: –5.4, d=1.1). PP effect superior (d=1.3) CBT (<i>P</i>&lt;.001) (<i>P</i>&lt;.001). Similarly, ITT sample, showed superiority (d=0.8) (<i>P</i>=.002), approaching significance (<i>P</i>=.06). Effects sustained Clinicians overseeing 1.6 (range 31-200 minutes) sessions participant. By combining AI achieved outcomes comparable human-delivered care, while significantly reducing required 8 times compared global care estimates. These findings highlight potential technology scale address unmet needs, ultimately impact quality life reduce economic burden globally. ISRCTN Registry ISRCTN52546704; http://www.isrctn.com/ISRCTN52546704

Язык: Английский

---

ADL+: a digital toolkit for cognitive assessment and multidomain intervention for prevention of cognitive decline in community-dwelling older adults – a proof-of-concept study (Preprint)

Опубликована: Авг. 17, 2023

Current research highlights the importance of addressing multiple risk factors concurrently to tackle complex etiology dementia. However, limited evidence exists on efficacy technology-driven, multidomain community-based interventions for preventing cognitive decline. To evaluate ADL+, an artificial intelligence (AI)-enabled digital toolkit integrating assessments and interventions, outcomes function, activity levels, quality life in older adults at Adherence usability were also evaluated. We conducted a quasi-experimental study including community-dwelling aged 60 years above without dementia, but with subjective memory complaints (AD8 score≥2). Participants received 6-month intervention (app-based training, personalized nutritional, physical, social activities recommendations) or control group treatment (cognitive health educational package). The primary outcome was change neuropsychological test battery (NTB) Z-scores (NTB composite its individual domains–attention, processing speed, memory, executive function). Secondary levels (Frenchay Activities Index, FAI), quality-of-life (EQ-5D). Outcomes assessed end three months post-intervention using linear mixed effects models. One-hundred fifty-two individuals assigned (N=75) (N=77). 72 (96%) participants 67 (87%) completed study. At six months, showed significant NTB score improvement (mean change: 0.086 (95% CI 0.020-0.15)), resulting between-group difference 0.17 0.071-0.27). Significant differences attention, domains observed, benefits sustained speed domain nine months. group's FAI scores declined -1.04 -1.83- -0.26)), while remained stable. EQ-5D Visual Analogue Scale (VAS) improved both 4.06 0.23-7.90) 5.12 0.81-9.43) high, average obtained. ADL+ shows potential beneficial Findings will guide future randomized controlled trials implementation efforts.

Язык: Английский

---

What about Hobfoll’s Resources Conservation Model in a Digital Society? Internet use as a Moderator of the Relationship between Personal Resources and Stress in Young and Older Adults (Preprint)

Опубликована: Сен. 7, 2023

Internet use has dramatically increased worldwide, with over two-thirds of the world’s population using it, including older adult population. Technical resources such as internet have been shown to influence psychological processes stress positively. Following Conservation Resources theory by Hobfoll, experience largely depends on individuals’ personal and changes in these resources. While resource loss lead stress, we know little regarding role that technical may play relationship between stress. This study aims investigate moderating effect (internet use) younger adults. A total 275 adults (aged 18 30 years) 224 ≥65 indicated their levels stress; change (ie, cognitive, social, self-efficacy gain); use. Variance analyses, multiple regression, moderation analyses were performed correlates Results showed adults, despite experiencing higher (questionnaire scores: 1.82 vs 1.54; <i>P</i>&lt;.001) less gain 2.31; <i>P</i>&lt;.001), stressed than 1.99 2.47; <i>P</i>&lt;.001). We observed among loss, gain, was moderated level (β=.09; <i>P</i>=.05). Specifically, who used more frequently when they experienced high both compared counterparts same conditions. Furthermore, low expressed often those These findings highlight importance mitigating emphasizing potential digital interventions promote mental health this

Язык: Английский

---