Sleep-specific outcomes attributable to digitally delivered cognitive behavioral therapy for insomnia in adults with insomnia and depressive symptoms.

OBJECTIVE: Randomized controlled trials (RCTs) of digitally delivered Cognitive Behavioral Therapy for insomnia (CBT-I) have demonstrated reductions in insomnia severity, depression symptoms, anxiety symptoms, and suicidal ideation. The present study aimed to evaluate the effectiveness of self-guided, digital CBT-I to improve sleep-specific outcomes. METHOD: An RCT of Australian adults with insomnia and depressive symptoms (N = 1149) compared SHUTi, a digital CBT-I intervention, with HealthWatch, an attention-matched control internet program, at baseline, posttest (9 weeks) and at 6-, 12-, and 18-month follow-ups. Online sleep diaries were used to derive measures of sleep-onset latency (SOL), wake after sleep onset (WASO), sleep efficiency (SE), number of awakenings, sleep quality, and total sleep time (TST). RESULTS: Participants in the SHUTi condition had greater improvements at posttest compared with control for: SOL, WASO, SE, number of awakenings, and sleep quality. These improvements were sustained at every follow-up (p < .02 for all outcomes except TST, in which statistically significant increases were observed only at 12- and 18-months). CONCLUSIONS: Digitally delivered CBT-I produced lasting improvements in sleep outcomes among adults with insomnia and depressive symptoms. Findings provide further evidence of long-term improvements associated with a digital therapeutic for insomnia, compared to an attention-control condition.

Network meta-analysis comparing the effectiveness of a prescription digital therapeutic for chronic insomnia to medications and face-to-face cognitive behavioral therapy in adults.

OBJECTIVE: The purpose of this study was to compare the effectiveness of the only Food and Drug Administration-authorized prescription digital therapeutic (PDT) Somryst versus face-to-face cognitive behavioral therapy for insomnia (CBT-I), or FDA-approved prescription medications for insomnia. METHODS: A systematic literature review was undertaken to identify relevant studies. A Bayesian network meta-analysis (NMA) was conducted to examine (1) mean change in insomnia severity index (ISI); (2) proportional change in ISI remitters; (3) mean change in wake after sleep onset (WASO); and (4) mean change in sleep onset latency (SOL). RESULTS: Twenty studies provided data on the PDT, CBT-I, CBT-I in combination with self-help (SH), or two prescription medications (eszopiclone and zolpidem). The PDT was associated with significant mean change in ISI (-5.77, 95% Credible Interval [CrI] - 8.53, -3.07) and ISI remitters (OR 12.33; 95% CrI 2.28, 155.91) compared to placebo, and had the highest probability of being the most effective treatment overall for ISI mean change (56%), and ISI remitters (64%). All evaluated interventions significantly outperformed placebo for WASO but no significant differences were observed for SOL (five interventions). Sensitivity analyses excluding medications and meta-regression (assessing type, duration, delivery method for CBT-I) did not affect NMA results. CONCLUSIONS: This network meta-analysis demonstrated that a PDT delivering CBT-I had the highest probability of being most effective compared to face-to-face CBT-I, prescription sleep medications, or placebo, as measured by reductions in mean ISI score from baseline and ISI-determined remittance.

Chronic insomnia is the long-term inability to fall asleep easily or to stay asleep. This condition is much more serious than most people realize, raising the risk of many health problems including depression, heart disease, and injuries.Although sleep medications are commonly used to treat insomnia, these drugs may not be effective and can lead to harms such as accidents or clouded thinking. Clinical guidelines recommend a treatment called cognitive behavioral therapy for insomnia (CBT-I) that is safe and effective. Unfortunately, there is a shortage of clinicians trained to provide CBT-I.Prescription digital therapeutics (PDTs) are FDA-approved software programs available on mobile devices such as smartphones. A PDT for insomnia (Somryst) delivers CBT-I and can overcome barriers to access for this important type of therapy. To compare the effectiveness of this PDT with FDA-approved sleep medications and face-to-face CBT-I a special kind of study was conducted called a network meta-analysis. This is a statistical method of combining data from numerous studies in a way that allows the results to be fairly compared.This network meta-analysis of 20 studies found that the PDT was more effective at reducing insomnia symptoms than any of the sleep medications studied and was even more effective than face-to-face CBT-I as measured by scores on a clinically valid scale of insomnia symptoms. These results are encouraging because they suggest that digital delivery of CBT-I could help the millions of people who currently do not have access to this effective treatment.

Real-World Evaluation of Clinical Response and Long-Term Healthcare Resource Utilization Patterns Following Treatment with a Digital Therapeutic for Chronic Insomnia.

Background and Objectives: This analysis evaluated insomnia severity and long-term impact on healthcare resource utilization (HCRU) and costs after treatment with Somryst® (previously called SHUTi), a digital therapeutic delivering cognitive behavioral therapy for insomnia (CBT-I). Methods: Change from baseline in insomnia severity index (ISI) score was assessed using last observed ISI score. A pre/post analysis of claims data was conducted, comparing HCRU in patients with self-identified sleep problems who successfully initiated the therapeutic (index date) between June 1, 2016 and December 31, 2018. Results: A total of 248 patients were analyzed (median age 56.5 years, 57.3% female, mean ISI score 19.13, 52.4% treated with sleep aid medications pre-index). After 9 weeks, mean ISI score declined by 37.2% from baseline (19.1 vs 12.0), 58.8% of patients achieved ISI responder status (ISI score improved by =>7; NNT: 1.7), and 26.6% of patients achieved insomnia remission (ISI score <8; NNT for remission: 3.8). After two-year follow-up, post-index events were reduced (compared to 2 years pre-index) for emergency department visits (-53%; IRR: 0.47; 95% CI 0.27, 0.82; P=0.008), hospiatizations (-21%; IRR: 0.79; 95% CI 0.46, 1.35; P=0.389) and hospital outpatient visits (-13%; IRR: 0.87; 95% CI 0.66, 1.14; P=0.315). Slightly increased rates were observed for ambulatory surgical center visits (2%; IRR: 1.02; 95% CI 0.73, 1.44; P=0.903) and office visits (2%; IRR: 1.02; 95% CI 0.92, 1.14; P=0.672). The number of patients treated with sleep aid medications dropped 18.5% (52.4% pre-index vs 42.7% post-index). Average number of prescriptions decreased from 3.98 pre-index to 3.73 post-index (P= 0.552). Total two-year cost reduction post-index vs pre-index was $510,678, or -$2059 per patient. Conclusion: In a real-world cohort of patients with chronic insomnia, treatment with a digital therapeutic delivering CBT-I was associated with reductions in insomnia severity, emergency department visits, and net costs.

PreScription DigitaL ThErapEutic for Patients with Insomnia (SLEEP-I): a protocol for a pragmatic randomised controlled trial.

INTRODUCTION: Cognitive behavioural therapy for insomnia (CBT-I) is effective at treating chronic insomnia, yet in-person CBT-I can often be challenging to access. Prior studies have used technology to bridge barriers but have been unable to extensively assess the impact of the digital therapeutic on real-world patient experience and multidimensional outcomes. Among patients with insomnia, our aim is to determine the impact of a prescription digital therapeutic (PDT) (PEAR-003b, FDA-authorised as Somryst; herein called PDT) that provides mobile-delivered CBT-I on patient-reported outcomes (PROs) and healthcare utilisation. METHODS AND ANALYSIS: We are conducting a pragmatically designed, prospective, multicentre randomised controlled trial that leverages Hugo, a unique patient-centred health data-aggregating platform for data collection and patient follow-up from Hugo Health. A total of 100 participants with insomnia from two health centres will be enrolled onto the Hugo Health platform, provided with a linked Fitbit (Inspire 2) to track activity and then randomised 1:1 to receive (or not) the PDT for mobile-delivered CBT-I (Somryst). The primary outcome is a change in the insomnia severity index score from baseline to 9-week postrandomisation. Secondary outcomes include healthcare utilisation, health utility scores and clinical outcomes; change in sleep outcomes as measured with sleep diaries and a change in individual PROs including depressive symptoms, daytime sleepiness, health status, stress and anxiety. For those allocated to the PDT, we will also assess engagement with the PDT. ETHICS AND DISSEMINATION: The Institutional Review Boards at Yale University and the Mayo Clinic have approved the trial protocol. This trial will provide important data to patients, clinicians and policymakers about the impact of the PDT device delivering CBT-I on PROs, clinical outcomes and healthcare utilisation. Findings will be disseminated to participants, presented at professional meetings and published in peer-reviewed journals. TRIAL REGISTRATION NUMBER: NCT04909229.

Changes in sleep following internet-delivered cognitive-behavioral therapy for insomnia in women treated for breast cancer: A 3-year follow-up assessment.

BACKGROUND: Sleep disturbances are common in women treated for breast cancer. We have previously shown that internet-delivered cognitive-behavioral therapy for insomnia (e-CBT-I) is an efficacious, low-cost treatment approach. Furthermore, research has shown that e-CBT-I can result in sustained improvements at 12 months post-treatment. However, given the complexity and long duration of post-treatment symptomatology in breast cancer patients, as well as the recommended use of antihormonal therapy for up to 10 years, it is relevant to investigate long-term (>12 months) changes in sleep following e-CBT-I in this population. In the present study, we report data from a 3-year long-term follow-up assessment after e-CBT-I. METHODS: Women treated for breast cancer with sleep disturbances (Pittsburg Sleep Quality Index [PSQI] global score >5) who had previously been enrolled in a randomized-controlled trial investigating the efficacy of e-CBT-I (n = 255), were invited to participate in a 3-year follow-up study. All women in the initial control group had also been granted access to e-CBT-I. Assessment included self-reported sleep quality (PSQI), insomnia severity (Insomnia Severity Index, ISI), cancer-related fatigue and symptoms of depression. Within-group changes in these outcomes from baseline to the 3-year long-term follow-up assessment were analyzed. RESULTS: A total of 131 women (51%) participated in the 3-year follow-up study of which 77 (59%) were from the initial intervention group and 54 (41%) from the initial control group. For the pooled sample, within-group improvements from baseline to the 3-year follow-up assessment corresponding to large effect sizes were observed in sleep quality (Cohen's d = 1.0 95% CI [0.78, 1.21]) and insomnia severity (Cohen's d = 1.36 CI 95% [1.12, 1.59]). Similar changes were observed in cancer-related fatigue (Cohen's d = 0.48 CI 95% [0.30, 0.66]) and symptoms of depression (Cohen's d = 0.80 CI 95%. [0.60, 0.99]). The proportion of patients with scores above established cut-offs on the PSQI and the ISI were 56.1% and 29.8%, respectively. Within the initial intervention group, 15.6% evidenced relapse at the 3-year assessment. CONCLUSION: Overall, these results indicate that long-term sleep quality and insomnia severity following the use of e-CBT-in women treated for breast cancer is significantly lower than the pre-treatment levels. However, a substantial proportion of participants still evidence sleep disturbances.

Real-world evidence from users of a behavioral digital therapeutic for chronic insomnia.

BACKGROUND: There have been many research trials of various digital therapeutics, but few real world evaluations of their efficacy. This type of data, however, can provide a more rounded understanding of their impact, utility, reach, and adoption. Findings presented here focus on outcome and patient engagement data of SHUTi (Sleep Health Using the Internet), a digital therapeutic delivering Cognitive Behavioral Therapy for insomnia (CBT-I), in a large real-world dataset of adults with insomnia. METHODS: 7216 adults who purchased access to SHUTi between December 2015 and February 2019 are included in the analysis. The Insomnia Severity Index (ISI) was administered at the beginning of each of six treatment Cores of the intervention. Users entered sleep diaries between Cores to track changes in sleep over time and obtain tailored sleep recommendations. Number of Cores completed and sleep diaries entered indicate program usage. RESULTS: Users showed a reduction in mean ISI scores and a corresponding increase in effect size at the start of each subsequent Core (compared to Core 1) (range: d = 0.3-1.9). Effect sizes at the last Core relative to the first were moderate-to-large for diary-derived sleep onset latency and wake after sleep onset. A reduction in number of medicated nights was also found, with those with severe insomnia showing the largest reduction from last-to-first week of treatment (d = 0.3). At the last Core, 61% met criteria for meaningful treatment response (reduction of >7 points on ISI) and 40% met criteria for remission (ISI<8). Engagement was comparable to SHUTi research trials. CONCLUSION: Consistent with controlled trials, real-world data suggest that digital therapeutics can result in relatively high levels of engagement and clinically meaningful sleep improvements.

Moderators of the Effects of mySmartSkin, a Web-Based Intervention to Promote Skin Self-examination and Sun Protection Among Individuals Diagnosed With Melanoma.

BACKGROUND: Identifying the characteristics of persons who benefit more from behavioral interventions can help health care providers decide which individuals should be offered particular interventions because this is the subgroup of persons who are more likely to derive greater benefit from the intervention and refine the underlying constructs of the model guiding the intervention. PURPOSE: This study evaluated possible demographic, medical, knowledge and attitudinal, and psychosocial variables that may moderate the impact of an online intervention, called mySmartSkin (MSS), on engagement in skin self-examination (SSE) and sun protection behaviors among melanoma survivors. METHODS: Participants completed a baseline survey and were then randomized to the MSS condition or usual care. Follow-up surveys were completed by participants at 8-, 24-, and 48-week postrandomization. RESULTS: A greater impact of MSS on SSE was illustrated among participants with more phenotypic skin cancer risk factors and participants reporting lower baseline self-efficacy in conducting SSE. A more favorable response of MSS on sun protection behaviors was shown when initial knowledge about abnormal lesions and sun protection barriers were high. Greater use of MSS and more favorable evaluations of it were also associated with higher intervention response. CONCLUSIONS: Future studies seeking to improve SSE and sun protection among melanoma survivors might benefit from focusing on survivors who report more skin cancer risk factors, lower self-efficacy in conducting SSE, less knowledge about what abnormal skin lesions look like, more perceived barriers to sun protection behaviors, and less worry about recurrence and cancer-related distress.

mySmartCheck, a Digital Intervention to Promote Skin Self-examination Among Individuals Diagnosed With or at Risk for Melanoma: A Randomized Clinical Trial.

BACKGROUND: Regular skin self-examination (SSE) reduces melanoma mortality but is not often conducted. PURPOSE: To promote SSE performance in individuals at increased risk for melanoma. METHODS: One hundred sixteen individuals at heightened risk for development of melanoma (i.e., personal/family history of melanoma, high-risk mole phenotype) who did not conduct a thorough SSE during in the prior 3 months were randomly assigned to receive either an automated internet-based intervention (mySmartCheck) or usual care (UC). One hundred sixteen participants completed surveys before random assignment and 99 completed the follow-up survey 13-weeks afterward. The primary outcome was participant self-reported examination (SSE) of all 15 parts of the body in the last 3 months. Secondary outcomes were SSE of any part of the body in the last 3 months and number of body parts examined during the last SSE. RESULTS: More mySmartCheck participants examined all 15 body parts (32.6% vs. 7.1%, p = .001). More individuals in mySmartCheck reported conducting SSE on any body part than those in UC (81.4% vs. 62.5%, p = .04). Effect sizes were large (d = 1.19 all 15 body parts) to moderate (d = 0.55 for any body part). mySmartCheck participants examined more body areas than UC participants (12.7 vs. 10.3, p = 0.003) during the last SSE. Participants in mySmartCheck reported higher levels of knowledge of suspicious lesions, SSE benefits, SSE self-efficacy, and planning for SSE, and lower SSE barriers, than those assigned to UC. CONCLUSIONS: mySmartCheck had a significant positive impact on SSE performance and behaviors. Additional research with a larger sample size, a longer follow-up, and more varied clinical settings is needed. TRIAL REGISTRATION: ClinicalTrials.gov registration # NCT03725449 (https://clinicaltrials.gov/ct2/show/NCT03725449).

Randomized controlled trial of the mySmartSkin web-based intervention to promote skin self-examination and sun protection among individuals diagnosed with melanoma.

Adherence to regular, thorough skin self-examination (SSE) and consistent sun protection behaviors among melanoma survivors is relatively low. This study reports on the impact of an online intervention, called mySmartSkin (MSS), on engagement in SSE and sun protection behaviors among melanoma survivors, as well as the mediators of the intervention effects. The intervention was compared with usual care (UC), and primary outcomes were assessed at 24 and 48 weeks. Short-term outcomes were also evaluated at 8 weeks postbaseline. Results demonstrate a significant effect on SSE and sun protection. At all three follow-up assessments, the proportion of participants reporting conducting a thorough SSE in the time since the previous assessment was significantly greater in MSS than in UC. In addition, both multivariate and univariate analyses indicated that engagement in sun protection behaviors was significantly higher in MSS than UC at 24 weeks, but the effect on sun protection at 48 weeks was significant only in multivariate analyses. Beneficial effects of MSS were significantly mediated by knowledge about melanoma and characteristics of suspicious lesions, as well as self-efficacy. Participant engagement in MSS was satisfactory, with approximately two-thirds of participants completing at least two of the three core components. Content was rated as highly trusted, easy to understand, easy to navigate, and helpful. In conclusion, MSS illustrated significant and durable effects on SSE and mixed results on sun protection. Future studies should consider ways to further enhance treatment effects and engagement in MSS.

Protocol for Digital Real-world Evidence trial for Adults with insomnia treated via Mobile (DREAM): an open-label trial of a prescription digital therapeutic for treating patients with chronic insomnia.

Background: Cognitive behavioral therapy for insomnia (CBT-I) is underused in healthcare settings and is challenging for people with insomnia to access because of uneven geographical distribution of behavioral sleep medicine providers. Prescription digital therapeutics can overcome these barriers. This study evaluates the effectiveness of a specific digital CBT-I therapeutic. Materials & methods:Digital Real-world Evidence trial for Adults with insomnia treated via Mobile (DREAM) is a 9-week, open-label, decentralized clinical trial to collect real-world evidence for a digital therapeutic (Somryst™) delivering CBT-I to patients with chronic insomnia. The primary objective is to examine the effectiveness of Somryst to reduce self-reported insomnia symptoms and severity in a real-world population (n = 350). Conclusion: This pragmatic study seeks to assess the potential benefits of treating insomnia with an asynchronous, mobile, tailored prescription digital therapeutic. Clinical trial registration: NCT04325464 (ClinicalTrials.gov).

Lay abstract Chronic insomnia is linked to a range of health problems, including heart disease, chronic pain, high blood pressure and depression. A behavioral treatment called cognitive behavioral therapy for insomnia (CBT-I) is considered the first choice for helping patients overcome insomnia and reduce their risks of insomnia-related problems. Although the benefits of CBT-I have been established, it can be difficult for patients to access trained CBT-I therapists. One possible solution is to use digital forms of CBT-I, which patients can access on mobile devices. Somryst™ is a prescription digital therapeutic, which means it is authorized by the US FDA and has been proven effective in carefully-controlled clinical trials. Less is known, however, about how well the prescription digital therapeutic works in real-world settings. The Digital Real-world Evidence trial for Adults with insomnia treated via Mobile study (DREAM) will explore this question by evaluating a range of symptoms and outcomes in at least 350 patients with chronic insomnia who will use Somryst and be followed for 1 year.

Effects of an Internet-Based Cognitive Behavioral Therapy for Insomnia Program on Work Productivity: A Secondary Analysis.

BACKGROUND: Cognitive-behavioral therapy for insomnia (CBT-I) may improve productivity along with insomnia symptoms, but the long-term duration of productivity gains is unknown. PURPOSE: In this secondary analysis, effects of Internet-delivered CBT-I on work-related and daily activity productivity were examined through 1 year post-treatment. METHODS: Adults with chronic insomnia (N = 303) were randomized to Internet-delivered CBT-I (Sleep Healthy Using the Internet [SHUTi]) or to patient education (PE). Participants reported interference with attendance (absenteeism) and productivity (presenteeism) at paid employment and in daily activities outside work on the Work Productivity Activity Impairment scale at baseline, 9 weeks later for postintervention assessment (post-assessment), and 6- and 12-month follow-ups. RESULTS: Participants randomized to SHUTi were about 50% less likely than those in the PE condition to report any absenteeism (logistic regression odds ratio [OR] = 0.48 [95% confidence intervals {CI} = 0.24,0.96]), total impairment (OR = 0.52 [95% CI = 0.29,0.93]), or activity impairment (OR = 0.50 [95% CI = 0.30,0.85]) at post-assessment; however, differences were not detected at 6- or 12-month follow-ups. SHUTi participants also reported lower overall levels of presenteeism (constrained longitudinal data analysis MDiff = -6.84 [95% CI = -11.53, -2.15]), total impairment (MDiff = -7.62 [95% CI = -12.50, -2.73]), and activity impairment (MDiff = -7.47 [95% CI = -12.68, -2.26]) at post-assessment relative to PE participants. Differences were sustained at 6-month follow-up for presenteeism (MDiff = -5.02 [95% CI = -9.94, -0.10]) and total impairment (MDiff = -5.78 [95% CI = -10.91, -0.65]). No differences were detected by 12-month follow-up. CONCLUSIONS: Findings suggest that Internet-based CBT-I may help accelerate improvement in work-related and daily activity impairment corroborating prior research, but did not find that CBT-I has persistent, long-term benefits in productivity relative to basic insomnia education. TRIAL REGISTRATION: NCT00328250 "Effectiveness of Internet Cognitive Behavioral Therapy Intervention for Treating Insomnia" (https://clinicaltrials.gov/ct2/show/NCT00328250).

Effects of digital cognitive behavioural therapy for insomnia on insomnia severity: a large-scale randomised controlled trial.

BACKGROUND: Although several large-scale randomised controlled trials have shown the efficacy of digital cognitive behavioural therapy for insomnia (dCBT-I), there is a need to validate widespread dissemination of dCBT-I using recommended key outcomes for insomnia. We investigated the effect of a fully automated dCBT-I programme on insomnia severity, sleep-wake patterns, sleep medication use, and daytime impairment. METHODS: We did a parallel-group superiority randomised controlled trial comparing dCBT-I with online patient education about sleep. The interventions were available through a free-to-access website, publicised throughout Norway, which incorporated automated screening, informed consent, and randomisation procedures, as well as outcome assessments. Adults (age ≥18 years) who had regular internet access and scored 12 or higher on the Insomnia Severity Index (ISI) were eligible for inclusion, and were allocated (1:1) to receive dCBT-I (consisting of six core interactive sessions to be completed over 9 weeks) or patient education (control group). Participants were masked to group assignment and had no contact with researchers during the intervention period. The primary outcome was the change in ISI score from baseline to 9-week follow-up, assessed in the intention-to-treat population. This trial is registered with ClinicalTrials.gov (NCT02558647) and is ongoing, with 2-year follow-up assessments planned. FINDINGS: Between Feb 26, 2016, and July 1, 2018, 5349 individuals commenced the online screening process, of which 1497 were ineligible or declined to participate, 2131 discontinued the screening process, and 1721 were randomly allocated (868 to receive dCBT-I and 853 to receive patient education). At 9-week follow-up, 584 (67%) participants in the dCBT-I group and 534 (63%) in the patient education group completed the ISI assessment. The latent growth model showed that participants in the dCBT-I group had a significantly greater reduction in ISI scores from baseline (mean score 19·2 [SD 3·9]) to 9-week follow-up (10·4 [6·2]) than those in the patient education group (from 19·6 [4·0] to 15·2 [5·3]; estimated mean difference -4·7 (95% CI -5·4 to -4·1; Cohen's d -1·21; p<0·001). Compared with patient education, the number needed to treat with dCBT-I was 2·7 (95% CI 2·4 to 3·2) for treatment response (ISI score reduction ≥8) and 3·2 (2·8 to 3·8) for insomnia remission (ISI score <8). No adverse events were reported to the trial team. INTERPRETATION: dCBT-I is effective in reducing the severity of symptoms associated with the insomnia disorder. These findings support the widespread dissemination of dCBT-I. Future research is needed to identify the moderators of response and to improve targeting. FUNDING: Norwegian Research Council; Liaison Committee for Education, Research and Innovation in Central Norway.

Developing a Process for the Analysis of User Journeys and the Prediction of Dropout in Digital Health Interventions: Machine Learning Approach.

BACKGROUND: User dropout is a widespread concern in the delivery and evaluation of digital (ie, web and mobile apps) health interventions. Researchers have yet to fully realize the potential of the large amount of data generated by these technology-based programs. Of particular interest is the ability to predict who will drop out of an intervention. This may be possible through the analysis of user journey data-self-reported as well as system-generated data-produced by the path (or journey) an individual takes to navigate through a digital health intervention. OBJECTIVE: The purpose of this study is to provide a step-by-step process for the analysis of user journey data and eventually to predict dropout in the context of digital health interventions. The process is applied to data from an internet-based intervention for insomnia as a way to illustrate its use. The completion of the program is contingent upon completing 7 sequential cores, which include an initial tutorial core. Dropout is defined as not completing the seventh core. METHODS: Steps of user journey analysis, including data transformation, feature engineering, and statistical model analysis and evaluation, are presented. Dropouts were predicted based on data from 151 participants from a fully automated web-based program (Sleep Healthy Using the Internet) that delivers cognitive behavioral therapy for insomnia. Logistic regression with L1 and L2 regularization, support vector machines, and boosted decision trees were used and evaluated based on their predictive performance. Relevant features from the data are reported that predict user dropout. RESULTS: Accuracy of predicting dropout (area under the curve [AUC] values) varied depending on the program core and the machine learning technique. After model evaluation, boosted decision trees achieved AUC values ranging between 0.6 and 0.9. Additional handcrafted features, including time to complete certain steps of the intervention, time to get out of bed, and days since the last interaction with the system, contributed to the prediction performance. CONCLUSIONS: The results support the feasibility and potential of analyzing user journey data to predict dropout. Theory-driven handcrafted features increased the prediction performance. The ability to predict dropout at an individual level could be used to enhance decision making for researchers and clinicians as well as inform dynamic intervention regimens.

Intraindividual variability in sleep schedule: effects of an internet-based cognitive-behavioral therapy for insomnia program and its relation with symptom remission.

STUDY OBJECTIVES: Sleep schedule consistency is fundamental to cognitive-behavioral therapy for insomnia (CBT-I), although there is limited evidence suggesting whether it predicts treatment response. This analysis tested whether: (1) an Internet-based CBT-I program affects intraindividual variability (IIV) in sleep schedule and (2) sleep schedule IIV predicts insomnia symptom remission. METHODS: This secondary analysis compares participants (N = 303) randomized to an Internet-based CBT-I program (SHUTi-Sleep Healthy Using the Internet) or Internet-based patient education (PE). Participants reported daily bedtimes and rising times on 10 online sleep diaries collected over 2 weeks at baseline and 9-week post-intervention assessment. Participants completed the Insomnia Severity Index (ISI) at post-assessment and 6-month follow-up; symptom remission was defined by ISI < 8. Mixed effects location scale modeling was used to examine the effect of SHUTi on bedtime and rising time IIV; a novel two-staged analysis examined the effect of bedtime and rising time IIV on insomnia symptom remission. RESULTS: At post-assessment, SHUTi participants reported about 30% less bedtime and 32% less rising time variability compared to PE (ps < 0.03). Bedtime and rising time IIV was not independently associated with likelihood of insomnia symptom remission at the subsequent time point (ps > 0.18), nor did sleep schedule IIV moderate treatment response (ps > 0.12). CONCLUSIONS: Findings demonstrate that an Internet-delivered CBT-I program can effectively increase users' sleep schedule consistency relative to an educational control. This consistency, however, was not related to treatment outcome when defined by insomnia symptom remission, suggesting that enforcing rigid sleep schedules for patients may not be necessary for treatment success. CLINICAL TRIAL REGISTRATION: NCT00328250.

Do treatment effects of a web-based cognitive behavioral therapy for insomnia intervention differ for users with and without pain interference? A secondary data analysis.

Cognitive-behavioral therapy for insomnia (CBT-I) shows treatment benefits among individuals with pain interference; however, effects of Internet-delivered CBT-I for this population are unknown. This secondary analysis used randomized clinical trial data from adults assigned to Internet-delivered CBT-I to compare changes in sleep by pre-intervention pain interference. Participants (N = 151) completed the Insomnia Severity Index (ISI) and sleep diaries [sleep onset latency (SOL); wake after sleep onset (WASO)] at baseline, post-assessment, 6- and 12-month follow-ups. Linear mixed-effects models showed no differences between pain interference groups (no, some, moderate/severe) for changes from baseline to any follow-up timepoint for ISI (p = .72) or WASO (p = .88). There was a small difference in SOL between those reporting some versus no or moderate/severe pain interference (p = .04). Predominantly comparable and sustained treatment benefits for both those with and without pain interference suggest that Internet-delivered CBT-I is promising for delivering accessible care to individuals with comorbid pain and insomnia.

Short and long-term effects of unguided internet-based cognitive behavioral therapy for chronic insomnia in morning and evening persons: a post-hoc analysis.

A post-hoc analysis comparing morning and evening persons with insomnia on sleep and mental health characteristics was conducted in order to investigate whether an Internet-based cognitive behavioral therapy for insomnia (ICBTi) was effective both for morning and evening persons. Adult patients (N = 178, mean age = 44.8, 67% females) with insomnia were randomized to either ICBTi (N = 92; morning persons = 41; evening persons = 51) or a web-based patient education condition (N = 86; morning persons = 44; evening persons = 42). All patients were assessed with sleep diaries, the Insomnia Severity Index (ISI), the Bergen Insomnia Scale (BIS), the Dysfunctional Beliefs and Attitudes about Sleep Scale (DBAS-16), the Hospital Anxiety and Depression Scale (HADS) and the Chalder Fatigue Scale (CFQ). Patients were characterized as morning or evening persons based on a median split on the Horne-Östberg Morningness Eveningness Questionnaire. Short and long-term effects of treatment were examined with mixed-model repeated-measures analyses. Morning and evening persons did not differ in terms of age, gender or educational status. At baseline, morning persons had more wake time after sleep onset (d= 0.54, p < .001) and more early morning awakening (d= 0.38, p < .05) compared to evening persons, while evening persons reported longer sleep onset latency (d= 0.60, p < .001), more time in bed (d= 0.56, p < .001), longer total sleep time (d= 0.45, p < .01), more fatigue (d= 0.31, p < .05) and more dysfunctional beliefs and attitudes about sleep (d= 0.47, p < .01). Despite these differences at baseline, both morning and evening persons receiving ICBTi benefitted more across most measures compared to morning and evening persons who received patient education. For morning persons in the ICBTi group, ISI scores were reduced from 17.3 at baseline to 8.8 (dpre-post = 2.48, p < .001) at post-assessment, and to 10.0 at 18-month follow up (dpre-post18m = 2.13, p < .001). Comparable results were found for evening persons in the ICBTi group, with a reduction in ISI scores from 17.4 at baseline to 8.6 (dpre-post = 2.24, p < .001) at post-assessment, and to 8.7 at 18-month follow up (dpre-post18m = 2.19, p < .001). Similar results were found on the BIS, DBAS, HADS, CFQ and sleep diary data. Despite different insomnia symptomatology between the two groups, the current study suggests that ICBTi is effective across scores on the morningness-eveningness dimension. The study was pre-registered at: ClinicalTrials.gov Identifier: NCT02261272.

Randomized controlled trial of the mySmartSkin web-based intervention to promote skin self-examination and sun protection behaviors among individuals diagnosed with melanoma: study design and baseline characteristics.

>1.2 million people in the United States have a personal history of melanoma skin cancer and are at increased risk for disease recurrence and second primary melanomas. Many of these individuals do not follow recommendations to conduct regular, thorough skin self-examinations that facilitate early disease detection and do not sufficiently engage in sun protection behaviors. In this project, we are conducting a randomized controlled trial of an innovative, tailored, theory-driven Internet intervention-called mySmartSkin-to promote these behaviors among melanoma patients. This paper outlines the study design and characteristics of the study sample. A total of 441 patients were recruited (40.9% response rate) and randomized to the mySmartSkin or a Usual Care condition. Participants complete surveys at baseline and 8 weeks, 24 weeks, and 48 weeks later. The primary aim of the project is to examine the impact of mySmartSkin versus Usual Care on skin self-examination and sun protection behaviors. The secondary aim focuses on identifying mediators of the intervention's effects. In an exploratory aim, we will examine potential moderators of the impact of the intervention. At baseline, the recruited participants had a mean age of 61 years, 49% were female, 7.5% met criteria for having conducted a recent, thorough skin self-examination, and the mean score on the index of sun protection behaviors was 3.3 (on a scale from 1 to 5). The results of the project will determine whether the mySmartSkin intervention is efficacious in promoting skin self-examination and sun protection behaviors among individuals diagnosed with melanoma. Trial registration: ClinicalTrials.govNCT03028948.

Long-Term Effects of an Unguided Online Cognitive Behavioral Therapy for Chronic Insomnia.

STUDY OBJECTIVES: The aim of this study was to test the efficacy of fully automated Internet-delivered cognitive behavioral therapy for insomnia (CBT-I) 18 months after the intervention period on sleep, daytime functioning, and beliefs about sleep for adults with chronic insomnia. METHODS: Participants in this study had participated in a randomized controlled trial comparing the efficacy of unguided Internet CBT-I with web-based patient education. Participants who had received Internet CBT-I (n = 95) completed online questionnaires and online sleep diaries 18 months after the intervention period. We used linear mixed models to study changes from baseline to postassessment and to 18-month follow-up, and a separate mixed-models analysis to study changes from postassessment to 18-month follow-up. RESULTS: Mean age of the participants was 45.5 years (standard deviation = 12.6) and 64% were females. Sixty-six participants (70%) completed the 18-month follow-up assessment. There were significant improvements from baseline to 18-month follow-up on the Insomnia Severity Index (ISI) (Cohen d = 2.04 [95% confidence interval (CI) 1.66-2.42]) and the Bergen Insomnia Scale (BIS) (d = 1.64 [95% CI 1.30-1.98]), levels of daytime fatigue (d = 0.85 [95% CI 0.59-1.11]), psychological distress (d = 0.51 [95% CI 0.29-0.73]), and beliefs about sleep (d = 1.44 [95% CI 1.15-1.73]). Moderate to large effect size improvements were also shown on the diary-derived sleep variables. All improvements from baseline to postassessment were essentially maintained to 18-month follow-up. CONCLUSIONS: Unguided Internet CBT-I appears to have sustained effects on sleep, daytime functioning, and beliefs about sleep up to 18 months after the intervention period. CLINICAL TRIAL REGISTRATION: This study presents long-term follow-up data of a previous clinical trial. Registry: ClinicalTrials.gov, Title: Internet-based Treatment for Insomnia in Norway, Identifier: NCT02261272, URL: https://clinicaltrials.gov/ct2/show/NCT02261272.