Leveraging machine learning to examine engagement with a digital therapeutic.

Digital Therapeutics (DTx) are evidence-based software-driven interventions for the prevention, management, and treatment of medical disorders or diseases. DTx offer the unique ability to capture rich objective data about when and how a patient engages with a treatment. Not only can one measure the quantity of patient interactions with a digital treatment with high temporal precision, but one can also assess the quality of these interactions. This is particularly useful for treatments such as cognitive interventions, where the specific manner in which a patient engages may impact likelihood of treatment success. Here, we present a technique for measuring the quality of user interactions with a digital treatment in near-real time. This approach produces evaluations at the level of a roughly four-minute gameplay session (mission). Each mission required users to engage in adaptive and personalized multitasking training. The training included simultaneous presentation of a sensory-motor navigation task and a perceptual discrimination task. We trained a machine learning model to classify user interactions with the digital treatment to determine if they were "using it as intended" or "not using it as intended" based on labeled data created by subject matter experts (SME). On a held-out test set, the classifier was able to reliably predict the SME-derived labels (Accuracy = .94; F1 Score = .94). We discuss the value of this approach and highlight exciting future directions for shared decision-making and communication between caregivers, patients and healthcare providers. Additionally, the output of this technique can be useful for clinical trials and personalized intervention.

Digital Intervention for Cognitive Deficits in Major Depression: A Randomized Controlled Trial to Assess Efficacy and Safety in Adults.

OBJECTIVE: The authors evaluated AKL-T03, an investigational digital intervention delivered through a video game-based interface, designed to target the fronto-parietal network to enhance functional domains for attentional control. AKL-T03 was tested in adult patients with major depressive disorder and a demonstrated cognitive impairment at baseline. METHODS: Adults ages 25-55 years on a stable antidepressant medication regimen with residual mild to moderate depression and an objective impairment in cognition (as measured using the symbol coding test) were enrolled in a double-blind randomized controlled study. Participants were randomized either to AKL-T03 or to an expectation-matched digital control intervention. Participants were assessed at baseline and after completion of their 6-week at-home intervention. The primary outcome measure was improvement in sustained attention, as measured by the Test of Variables of Attention (TOVA). RESULTS: AKL-T03 (N=37) showed a statistically significant medium-effect-size improvement in sustained attention compared with the control intervention on the TOVA primary outcome (N=37) (partial eta-squared=0.11). Additionally, a composite score derived from all cognitive measures demonstrated significant improvement with AKL-T03 over the control intervention. Individual secondary and exploratory endpoints did not demonstrate statistically significant between-group differences. No serious adverse events were reported, and two patients (5.5%) in the AKL-T03 group reported an intervention-related adverse event (headache). CONCLUSIONS: Treatment with AKL-T03 resulted in significant improvement in sustained attention, as well as in cognitive functioning as a whole, compared with a control intervention. AKL-T03 is a safe digital intervention that is effective in the treatment of cognitive impairment associated with major depression. Further research will be needed to understand the clinical consequences of this treatment-induced change.

Enhancing neural markers of attention in children with ADHD using a digital therapeutic.

Attention deficit hyperactivity disorder (ADHD) is a prevalent neurodevelopmental condition characterized by diminished attentional control. Critically, these difficulties are related to negative consequences in real-life functioning both during development and into adulthood. There is now growing evidence that modulating the underlying neural circuits related to attention can improve behavior and brain function in children with ADHD. We have previously shown that game-based digital therapeutics targeting a key neural marker of attention-midline frontal theta (MFT)-yield positive effects on attentional control in several populations. However, the effects of such digital therapeutics in children with ADHD and no other comorbidities has not been yet examined. To address this gap, we assessed a sample of 25 children with ADHD (8-12 years old) on neural, behavioral, and clinical metrics of attention before and after a 4-week at-home intervention on an iPad targeting MFT circuitry. We found that children showed enhancements on a neural measure of attention (MFT power), as well as on objective behavioral measures of attention and parent reports of clinical ADHD symptoms. Importantly, we observed relationships between the neural and behavioral cognitive improvements, demonstrating that those children who showed the largest intervention-related neural gains were also those that improved the most on the behavioral tasks indexing attention. These findings provide support for using targeted, digital therapeutics to enhance multiple features of attentional control in children with ADHD. Study registration: ClinicalTrials.gov registry (NCT03844269) https://clinicaltrials.gov/ct2/show/NCT03844269.

Impact of perceived interpersonal similarity on attention to the eyes of same-race and other-race faces.

One reason for the persistence of racial discrimination may be anticipated dissimilarity with racial outgroup members that prevent meaningful interactions. In the present research, we investigated whether perceived similarity would impact the processing of same-race and other-race faces. Specifically, in two experiments, we varied the extent to which White participants were ostensibly similar to targets via bogus feedback on a personality test. With an eye tracker, we measured the effect of this manipulation on attention to the eyes, a critical region for person perception and face memory. In Experiment 1, we monitored the impact of perceived interpersonal similarity on White participants' attention to the eyes of same-race White targets. In Experiment 2, we replicated this procedure, but White participants were presented with either same-race White targets or other-race Black targets in a between-subjects design. The pattern of results in both experiments indicated a positive linear effect of similarity-greater perceived similarity between participants and targets predicted more attention to the eyes of White and Black faces. The implications of these findings related to top-down effects of perceived similarity for our understanding of basic processes in face perception, as well as intergroup relations, are discussed.

A novel digital intervention for actively reducing severity of paediatric ADHD (STARS-ADHD): a randomised controlled trial.

BACKGROUND: Attention-deficit hyperactivity disorder (ADHD) is a common paediatric neurodevelopmental disorder with substantial effect on families and society. Alternatives to traditional care, including novel digital therapeutics, have shown promise to remediate cognitive deficits associated with this disorder and may address barriers to standard therapies, such as pharmacological interventions and behavioural therapy. AKL-T01 is an investigational digital therapeutic designed to target attention and cognitive control delivered through a video game-like interface via at-home play for 25 min per day, 5 days per week for 4 weeks. This study aimed to assess whether AKL-T01 improved attentional performance in paediatric patients with ADHD. METHODS: The Software Treatment for Actively Reducing Severity of ADHD (STARS-ADHD) was a randomised, double-blind, parallel-group, controlled trial of paediatric patients (aged 8-12 years, without disorder-related medications) with confirmed ADHD and Test of Variables of Attention (TOVA) Attention Performance Index (API) scores of -1·8 and below done by 20 research institutions in the USA. Patients were randomly assigned 1:1 to AKL-T01 or a digital control intervention. The primary outcome was mean change in TOVA API from pre-intervention to post-intervention. Safety, tolerability, and compliance were also assessed. Analyses were done in the intention-to-treat population. This trial is registered with ClinicalTrials.gov, NCT02674633 and is completed. FINDINGS: Between July 15, 2016, and Nov 30, 2017, 857 patients were evaluated and 348 were randomly assigned to receive AKL-T01 or control. Among patients who received AKL-T01 (n=180 [52%]; mean [SD] age, 9·7 [1·3] years) or control (n=168 [48%]; mean [SD] age, 9·6 [1·3] years), the non-parametric estimate of the population median change from baseline TOVA API was 0·88 (95% CI 0·24-1·49; p=0·0060). The mean (SD) change from baseline on the TOVA API was 0·93 (3·15) in the AKL-T01 group and 0·03 (3·16) in the control group. There were no serious adverse events or discontinuations. Treatment-related adverse events were mild and included frustration (5 [3%] of 180) and headache (3 [2%] of 180). Patient compliance was a mean of 83 (83%) of 100 expected sessions played (SD, 29·2 sessions). INTERPRETATION: Although future research is needed for this digital intervention, this study provides evidence that AKL-T01 might be used to improve objectively measured inattention in paediatric patients with ADHD, while presenting minimal adverse events. FUNDING: Sponsored by Akili Interactive Labs.

Perceiving happiness in an intergroup context: The role of race and attention to the eyes in differentiating between true and false smiles.

The present research comprises six experiments that investigated racial biases in the perception of positive emotional expressions. In an initial study, we demonstrated that White participants distinguished more in their happiness ratings of Duchenne ("true") and non-Duchenne ("false") smiles on White compared with Black faces (Experiment 1). In a subsequent study we replicated this effect using a different set of stimuli and non-Black participants (Experiment 2). As predicted, this bias was not demonstrated by Black participants, who did not significantly differ in happiness ratings between smile types on White and Black faces (Experiment 3). Furthermore, in addition to happiness ratings, we demonstrated that non-Black participants were also more accurate when categorizing true versus false expressions on White compared with Black faces (Experiment 4). The final two studies provided evidence for the mediating role of attention to the eyes in intergroup emotion identification. In particular, eye tracking data indicated that White participants spent more time attending to the eyes of White than Black faces and that attention to the eyes predicted biases in happiness ratings between true and false smiles on White and Black faces (Experiment 5). Furthermore, an experimental manipulation focusing participants on the eyes of targets eliminated the effects of target race or perceptions of happiness (Experiment 6). Together, the findings provide novel evidence for racial biases in the identification of positive emotions and highlight the critical role of visual attention in this process. (PsycINFO Database Record (c) 2019 APA, all rights reserved).

Category-Based Learning About Deviant Outgroup Members Hinders Performance in Trust Decision Making.

The present research examines whether individuation and categorization processes influence trust decisions about strangers at first and across repeated interactions. In a partial replication of the study reported by Cañadas et al. (2015), participants played an adaptation of the multi-round trust game paradigm and had to decide whether or not to cooperate with unknown partners. Gender (Study 1a) and ethnicity (Studies 1b, 2, and 3) served to create distinct social categories among the game partners, whose reciprocation rates were manipulated at group and individual levels. At the group level, two social groups (i.e., ingroup vs. outgroup) were associated with opposite reciprocation rates (i.e., high vs. low reciprocation rate). At the individual level, consistency was manipulated by altering the reciprocation rate of one out of four members of each social group. That is, there was one inconsistent individual in each group showing a pattern of reciprocation opposite to the group reciprocation rate. Our data, contrary to Cañadas et al.'s (2015) findings, suggested that ingroup partners were individuated given that participants made their decisions to cooperate with the trustees according to their individual reciprocation rate and independently of the group reciprocation rate. In contrast, decisions about outgroup partners (i.e., men in Study 1a and Blacks in Studies 1b, 2, and 3) were affected by category-based thinking. At the same time, in comparison with ingroup, greater cooperation was observed with ethnic outgroups but not with gender outgroups. The consistency of our results with the previous literature on social categorization and across the three experiments seems to indicate they are reliable, supporting the hypothesis that categorization and individuation processes guide trust decision-making, promoting individuation mainly for ingroup and categorization among outgroup members.

"It's Always the Judge's Fault": Attention, Emotion Recognition, and Expertise in Rhythmic Gymnastics Assessment.

In many sports, such as figure skating or gymnastics, the outcome of a performance does not rely exclusively on objective measurements, but on more subjective cues. Judges need high attentional capacities to process visual information and overcome fatigue. Also their emotion recognition abilities might have an effect in detecting errors and making a more accurate assessment. Moreover, the scoring given by judges could be also influenced by their level of expertise. This study aims to assess how rhythmic gymnastics judges' emotion recognition and attentional abilities influence accuracy of performance assessment. Data will be collected from rhythmic gymnastics judges and coaches at different international levels. This study will employ an online questionnaire consisting on an emotion recognition test and attentional test. Participants' task is to watch a set of videotaped rhythmic gymnastics performances and evaluate them on the artistic and execution components of performance. Their scoring will be compared with the official scores given at the competition the video was taken from to measure the accuracy of the participants' evaluations. The proposed research represents an interdisciplinary approach that integrates cognitive and sport psychology within experimental and applied contexts. The current study advances the theoretical understanding of how emotional and attentional aspects affect the evaluation of sport performance. The results will provide valuable evidence on the direction and strength of the relationship between the above-mentioned factors and the accuracy of sport performance evaluation. Importantly, practical implications might be drawn from this study. Intervention programs directed at improving the accuracy of judges could be created based on the understanding of how emotion recognition and attentional abilities are related to the accuracy of performance assessment.

Perceiving emotions: Cueing social categorization processes and attentional control through facial expressions.

Individuals spontaneously categorise other people on the basis of their gender, ethnicity and age. But what about the emotions they express? In two studies we tested the hypothesis that facial expressions are similar to other social categories in that they can function as contextual cues to control attention. In Experiment 1 we associated expressions of anger and happiness with specific proportions of congruent/incongruent flanker trials. We also created consistent and inconsistent category members within each of these two general contexts. The results demonstrated that participants exhibited a larger congruency effect when presented with faces in the emotional group associated with a high proportion of congruent trials. Notably, this effect transferred to inconsistent members of the group. In Experiment 2 we replicated the effects with faces depicting true and false smiles. Together these findings provide consistent evidence that individuals spontaneously utilise emotions to categorise others and that such categories determine the allocation of attentional control.

The effect of social categorization on trust decisions in a trust game paradigm.

This study investigates whether participants use categorical or individual knowledge about others in order to make cooperative decisions in an adaptation of the trust game paradigm. Concretely, participants had to choose whether to cooperate or not with black and white unknown partners as a function of expected partners' reciprocity rates. Reciprocity rates were manipulated by associating three out of four members of an ethnic group (blacks or whites consistent members) with high (or low) reciprocity rates, while the remaining member of the ethnic group is associated with the reciprocity of the other ethnic group (inconsistent member). Results show opposite performance's patterns for white and black partners. Participants seemed to categorize white partners, by making the same cooperation decision with all the partners, that is, they cooperated equally with consistent and inconsistent white partners. However, this effect was not found for black partners, suggesting a tendency to individuate them. Results are discussed in light of the implications of these categorization-individuation processes for intergroup relations and cooperative economic behavior.

Studying social interactions through immersive virtual environment technology: virtues, pitfalls, and future challenges.

The goal of the present review is to explain how immersive virtual environment technology (IVET) can be used for the study of social interactions and how the use of virtual humans in immersive virtual environments can advance research and application in many different fields. Researchers studying individual differences in social interactions are typically interested in keeping the behavior and the appearance of the interaction partner constant across participants. With IVET researchers have full control over the interaction partners, can standardize them while still keeping the simulation realistic. Virtual simulations are valid: growing evidence shows that indeed studies conducted with IVET can replicate some well-known findings of social psychology. Moreover, IVET allows researchers to subtly manipulate characteristics of the environment (e.g., visual cues to prime participants) or of the social partner (e.g., his/her race) to investigate their influences on participants' behavior and cognition. Furthermore, manipulations that would be difficult or impossible in real life (e.g., changing participants' height) can be easily obtained with IVET. Beside the advantages for theoretical research, we explore the most recent training and clinical applications of IVET, its integration with other technologies (e.g., social sensing) and future challenges for researchers (e.g., making the communication between virtual humans and participants smoother).

An eye for the I: Preferential attention to the eyes of ingroup members.

Human faces, and more specifically the eyes, play a crucial role in social and nonverbal communication because they signal valuable information about others. It is therefore surprising that few studies have investigated the impact of intergroup contexts and motivations on attention to the eyes of ingroup and outgroup members. Four experiments investigated differences in eye gaze to racial and novel ingroups using eye tracker technology. Whereas Studies 1 and 3 demonstrated that White participants attended more to the eyes of White compared to Black targets, Study 2 showed a similar pattern of attention to the eyes of novel ingroup and outgroup faces. Studies 3 and 4 also provided new evidence that eye gaze is flexible and can be meaningfully influenced by current motivations. Specifically, instructions to individuate specific social categories increased attention to the eyes of target group members. Furthermore, the latter experiments demonstrated that preferential attention to the eyes of ingroup members predicted important intergroup biases such as recognition of ingroup over outgroup faces (i.e., the own-race bias; Study 3) and willingness to interact with outgroup members (Study 4). The implication of these findings for general theorizing on face perception, individuation processes, and intergroup relations are discussed.

Blocking mimicry makes true and false smiles look the same.

Recent research suggests that facial mimicry underlies accurate interpretation of subtle facial expressions. In three experiments, we manipulated mimicry and tested its role in judgments of the genuineness of true and false smiles. Experiment 1 used facial EMG to show that a new mouthguard technique for blocking mimicry modifies both the amount and the time course of facial reactions. In Experiments 2 and 3, participants rated true and false smiles either while wearing mouthguards or when allowed to freely mimic the smiles with or without additional distraction, namely holding a squeeze ball or wearing a finger-cuff heart rate monitor. Results showed that blocking mimicry compromised the decoding of true and false smiles such that they were judged as equally genuine. Together the experiments highlight the role of facial mimicry in judging subtle meanings of facial expressions.

Social categories as a context for the allocation of attentional control.

Recent studies of cognitive control have highlighted the idea that context can rapidly cue the control of attention. The present study shows that faces can be quickly categorized on the basis of gender, and these gender categories can be used as a contextual cue to allocate attentional control. Furthermore, the results reported here reveal processes implicated in the development and operation of implicit social stereotypes. Three of 4 faces from 1 gender group were associated with a high proportion of congruent trials in a flanker task, while 3 of 4 faces of the other gender group were associated with a low proportion of congruent trials. A single inconsistent face within each gender group was associated with the proportion congruency of the opposite gender group. A social context-specific proportion congruent effect (PCE) was observed (i.e., larger interference for the gender category associated with a high proportion of congruent trials), even for inconsistent members of the category. This effect is consistent with the view that a new implicit stereotype was created, linking gender with a specific proportion of congruency. In Experiment 2, the task goals modulated the use of the new created stereotype. Instructions to categorize versus individuate the target faces, respectively, led participants to allocate attention either toward the category-diagnostic or the identity-diagnostic facial features. Furthermore, and in line with stereotyping research, under instructions to categorize faces this social-context-specific PCE generalized to new faces of the same gender group with whom participants did not have previous experience. These results link attention with social categorization processes.

Spatial interference between gaze direction and gaze location: a study on the eye contact effect.

Perceived gaze in faces is an important social cue that influences spatial orienting of attention. In three experiments, we examined whether the social relevance of gaze direction modulated spatial interference in response selection, using three different stimuli: faces, isolated eyes, and symbolic eyes (Experiments 1, 2, and 3, respectively). Each experiment employed a variant of the spatial Stroop paradigm in which face location and gaze direction were put into conflict. Results showed a reverse congruency effect between face location to the right or left of fixation and gaze direction only for stimuli with a social meaning to participants (Experiments 1 and 2). The opposite was observed for the nonsocial stimuli used in Experiment 3. Results are explained as facilitation in response to eye contact.