Virtual Reality Exposure Therapy (VRET) works by presenting computer-generated, virtual equivalents of phobic stimuli in an immersive way, usually through use of a headset with stereoscopic displays covering both eyes, interactive to head movements, giving the illusion of being able to look around in the virtual world. VRET is structured in a manner similar as traditional exposure therapy (1): via graded, systematic exposure to feared stimuli under controlled conditions and without safety behaviors, the fear response gradually habituates and inhibitory learning occurs (2). Since the first clinical applications of VR technology in the early 2000's, meta-analyses have revealed that VRET is efficacious (3), and even on par with traditional exposure therapy (4). Importantly, results generalize to reduced fear of real-world stimuli (5), there are low rates of deterioration (6) and efficacy has been demonstrated also among adolescents (7). Clinicians appear to have a positive view of VR interventions (8–10), and some findings indicate that some patients may even prefer it to traditional exposure therapy when given a choice between the two, as well as lower rates of refusal (11).

Despite these promising results, as of yet, there have been few attempts to distribute VRET at a larger scale, or implement VRET in regular clinical settings (12). Arguably, the primary reason for this lies in the limitations of the past generation of VR hardware, which was both expensive and inaccessible, required a lot of auxiliary equipment and a high degree of technical skill to program and operate, and was heavy to wear for prolonged durations. With the release of consumer VR platforms, including mature digital ecosystems for development and dissemination of applications, these concerns in theory no longer apply, encouraging a new generation of VRET interventions that are scalable and can be integrated in regular care (13). A promising alternative approach enabled by this new technology is automated, self-guided VRET that provide a complete treatment package and includes no therapist guidance. Such applications, if released on ordinary digital marketplaces for VR applications, have the potential to disseminate effective, evidence-based treatment to unprecedented numbers. For example, a first-generation consumer targeted VR relaxation application, distributed on an ordinary digital marketplace, attracted more than 40,000 unique users over two years, even at a time when very few consumers had access to this technology (14).

To our knowledge, at least three automated VRET applications have been developed and evaluated in high-quality trials: two for fear of heights (15, 16), and one for fear of spiders (17, 18). In the latter study, we evaluated a novel, automated VRET application with gamified exposure tasks and level design, against gold-standard in-vivo exposure therapy using a randomized non-inferiority design, with behavioral avoidance of a real spider serving as the primary outcome measure. Results revealed that the VRET group showed large improvements on behavioral avoidance immediately after treatment (d = 1.49), albeit not as large as the in-vivo group (d = 2.39). However, the VRET group continued to improve during the follow-up period, and behavioral approach scores were non-inferior at both three- and twelve-month follow-ups (d = 2.01 and d = 2.27 for VRET and in-vivo, respectively, at twelve months) (18).

This randomized non-inferiority trial featured some design aspects that strengthened the validity of the treatment comparison, yet may at the same time have limited the generalizability of the VRET within-group effect to naturalistic conditions. First, only participants meeting DSM-5 diagnostic criteria for specific phobia were included, as assessed using a structured clinical interview during screening. While specific phobias are some of the most prevalent mental disorders, with a lifetime prevalence estimate of 7.4% (19), sub-syndromal fears are much more common (20). Thus, the vast majority of users are expected to have a sub-syndromal fear of spiders. Since baseline severity is typically positively associated with symptom decrease (larger room for improvement), treatment effects may be smaller with samples with sub-clinical fears.

Second, the primary outcome measure in the trial was a behavioral approach test (BAT) (21), which involved confrontation with a real spider regardless of treatment allocation. This was important in order to show that fear reduction from VR exposure translated to reduced fear of the in-vivo equivalent stimuli that participants would encounter in real life (5), and BAT outcomes are generally considered the gold-standard in phobia treatment evaluation. However, completing an in-vivo BAT prior to treatment may constitute a minor in-vivo exposure task in-itself, which would confound the estimate of the effect of VRET. Since the previous trial did not include a control group with the same BAT procedure but without treatment, or even additional administration of self-report measures after the BAT but before the treatment session, the degree of confounding is unknown. Clinical experience from running the trial did however suggest that some participants experienced the BAT as therapeutic, making it an important translational research question to examine treatment effectiveness without this possible confounder (which would not be present in real-life conditions), having already shown efficacy using a gold-standard BAT in the previous trial.

Third, in order to match the arms for non-specific therapist factors, and for ethical reasons (no other automated VRET study had been published at time of data collection), the VRET intervention was delivered with a “technician” (clinical psychology MSc student) in the same room at all times, who was instructed to provide emotional support if deemed necessary. This occurred in an estimated 20% of the sessions (18). The automated VRET application was designed for use at-home or alone in a clinical setting, meaning that no equivalent support would be available. Thus, it is unknown whether efficacy or even tolerability of the VRET intervention will generalize to effectiveness (real-world) conditions. Finally, by necessity, the original trial was randomized and it was not deemed feasible or ethically justified to blind participants to treatment options. The moderating effect of participant treatment preference was however not examined in the original trial. Past research indicates that many participants prefer VRET over in-vivo exposure when presented with both (11), and meta-analytic research has revealed a small moderating effect of participant treatment preference in general (22) (although most of this work has been done comparing psychotherapy to medication and thus may not generalize).

In sum, while specific design aspects of the original non-inferiority trial maximized the validity of the efficacy comparison between a gamified VRET intervention and gold-standard in-vivo exposure therapy, new translational research is needed in order to study the effectiveness of the this type of intervention when delivered under real-world conditions. For this purpose, we conducted a non-randomized, single-subject trial using the publicly available version of the VRET intervention, delivered with minimal human contact, and featuring only self-reported outcome measures.

This study was approved by the Regional Ethical Review Board in Stockholm (2018/1640-32) and pre-registered at the Open Science Foundation (https://doi.org/10.17605/OSF.IO/78GUB). All included participants provided informed written consent at the start of the treatment session. Participants were not reimbursed, yet of n = 25 included participants, n = 12 participants were psychology students who received course credit for their participation.

Virtual Reality exposure therapy has well-established efficacy, and several recent studies show that this applies also to automated interventions (15, 16, 18). Effectiveness studies examining the effects of automated VRET interventions under real-world conditions are thus the next research step along the translational pipeline before dissemination and implementation into clinical and non-clinical settings can be recommended. The current study was designed as a follow-up study to an earlier randomized non-inferiority trial comparing automated VRET for spider phobia to gold-standard in-vivo exposure therapy. Despite differences in inclusion criteria (specific phobia not required), study design (no randomization), treatment administration (no technician present during treatment) and measurements (only self-reports; no confounding of behavioral approach tests with real spiders), we found remarkably similar treatment effects as in the earlier trial: d = 1.26 in the current study, d = 1.33 in the earlier. It should however be noted that participant characteristics and baseline severity were similar across studies. For example, even though meeting diagnostic criteria for specific phobia was not required for inclusion in the current study, 80% did.

Importantly, the current study shows that consumer-targeted VRET applications can have comparable effects also under simulated real-world conditions. Specific phobias show one of the largest treatment gaps, with few sufferers seeking treatment. With continued growth in consumer VR adoption, consumer-target VRET applications, disseminated through ordinary digital marketplaces, have the potential to make a substantial public health impact. Pending mass-adoption, automated VR applications could be provided at clinics or pharmacies, without the need for a qualified therapist. Automated VRET interventions could also be used as homework exercises between traditional therapy sessions, akin to so called blended internet interventions (36). While the current study simulated at-clinic conditions to the extent possible, evaluating effectiveness of VRET applications when used at-home, outside a clinical trial setting, should be considered a research priority. Since the VR modality is well-suited not just for treatment delivery but also for measurement collection [both self-rating scales and virtual behavioral approach tests (37–39)], distributing VRET applications through digital marketplaces and collecting users' consent to share outcome data anonymously with researchers, would enable perfectly naturalistic studies on real-world data on an unprecedented scale. For comparison, even during the early years of consumer VR technology (when adoption rate was relatively low), one mental health application accrued over 40,000 users over two years of availability (14). A sample size of this magnitude would allow A/B testing (randomized allocation to different versions during actual use) of even minor changes to treatment design and delivery, providing valuable insights not just into the mechanisms of VRET but exposure therapy in general (12).

Overall, session characteristics and user experience measures suggest that the VRET interventions is tolerable and practical, although a lack of comparison group or validated norm data makes it difficult to draw firm conclusions. Interestingly, although designed to be played through in around two and half hours (corresponding to the three-hour in-vivo protocol included in the original non-inferiority trial), average usage time in the current study was approximately one and a half (in addition to setup, summing-up and questionnaire time). It should be noted that even in three-hour, in-vivo exposure protocols (21), only between two and two-and-a-half hours are spent on pure exposure (including short breaks as necessary). Unlike in the original non-inferiority trial, no personnel were present in the room while the participant played through the VRET serious game. As evident by the comparable effect sizes achieved across trials, having such personnel present does not appear to have therapeutic benefits, and likely also decreased playthrough time by making outside-VR social interactions impossible. The increased time efficiency is promising for future iterations and dissemination efforts, yet more research is required to capture more specific associations between how users engage with VRET serious games, and outcomes, beyond simple elapsed time.

Somewhat surprisingly, the current study found no significant correlations between treatment outcomes and user experience measures. Of note, this may be a power issue, since an a priori power calculation revealed that a correlation coefficient r > .50 could be detected with 80% power and a sample size of n = 25. For example, previous meta-analytic research suggests an association between sense of presence and SUDs of r = .28 (40), which the current study was not powered to detect. The lack of association between fear reaction and in-session habituation is consistent with the extant literature on the mechanisms of exposure therapy in general, which suggest that factors such as inhibitory learning processes (not measured in the current study) are a stronger predictor of treatment outcomes than simple emotional evocation and processing (2, 41). Although the extant VR literature (not limited to VRET) is somewhat inconsistent, the balance of evidence suggests a negative association between cybersickness and sense of presence (42). Congruently, neither of these measures were associated with treatment outcomes in the current study. Participants used a modern VR headset, albeit one limited to three degrees of freedom (i.e. measuring head rotation only, not position), running a VR paradigm that did not involve any virtual first-person motion. The latter was an explicit design consideration (12) with both a therapeutic rationale (covert invasion of personal space by spiders being a common catastrophic belief) and a technical one in that sensory discrepancies between virtual and physical first-person motion is a prime driver of cybersickness (43) and should thus be avoided unless necessary. As expected, sample average cybersickness score was low, as was the standard deviation, indicating that cybersickness was not a significant issue in the current study and that a floor effect for this factor may explain the lack of association with treatment outcomes. More research is needed on what aspects of the user experience during VRET promotes symptom reduction both immediately in-virtuo and when transitioning to in-vivo exposure in daily life (44).

Interestingly, we found only a small, non-significant (p = .053) further decrease in phobia symptoms at the six-month follow-up. In the non-inferiority trial, the VRET group continued to improve as measured by both the behavioral approach test and the Spider Phobia Questionnaire (45), although not as measured by the FSQ. A marked difference between these two studies is that in non-inferiority trial, but not the current study, participants were given a standardized rationale on the importance of transitioning to in-vivo exposure and a worksheet for planning and evaluating in-vivo exposure exercises. The effect of adherence to this transition plan was however not empirically evaluated, and studying the impact of in-virtuo to in-vivo transitioning through randomized allocation and appropriate statistics (46) should be considered another research priority for the field.

The current study complements the earlier randomized non-inferiority trial (18) in terms of strengths and limitations of study design. Limitations include a small sample size (although well-powered given the hypothesized and observed large treatment effects), no control group, only self-reported outcome measures, and no long-term follow-up. Strengths of the current study include examining intervention effects under simulated real-world conditions (no randomization, minimum human contact) in sample which also included participants with sub-syndromal fear of spiders, as well as repeated measures at each study phase, and a six-month follow-up. User experience measures were self-reported only, and correlation analyses with treatment improvement low-powered. With efficacy of the intervention already having been established, the current study in some aspects prioritized the translational aim of generalizability to real-world conditions, including relying only on self-reported outcome measures as not to risk confounding the effect estimate by including a pre-treatment BAT that may constitute a brief in-vivo exposure exercise in-itself, and would not be available to at-home users. A waiting-list control group would have given unbiased estimates of treatment effects even with an included BAT, but was not included in the current study. Including more measures per phase (e.g. to model a pre-treatment trajectory), and a multiple baseline design, would have allowed for stronger inferences about causality.

Automated, gamified VRET for spider phobia, in the form of a consumer application, is tolerable and practical also when delivered under simulated real-world conditions, with effects (fear reduction) remarkably similar to those previously observed in a randomized trial under efficacy conditions. Our findings show that automated VRET is a promising treatment option for self-help use, delivered either at clinics (no qualified therapist required) or at-home as consumer-oriented applications.

The datasets generated for this study are available on request to the corresponding author.

This study was reviewed and approved by Stockholm Regional Ethical Review Board. The patients/participants provided their written informed consent to participate in this study.

Designed the study: PL, AM, PC. Technical development of the intervention: WH. Carried out data collection: CB. Made important contributions to study design and interpretation of findings: CB, WH, GA. Drafted the manuscript: PL. Made significant contributions to manuscript: AM, CB, WH, GA, and PC.

Author WH is the founder and chief technology officer of Mimerse, a company specializing in developing VR interventions for mental health. Author PL has consulted for Mimerse but holds no financial stake in the company.

The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.