Screening for Psychological Distress in Healthcare Workers Using Machine Learning: A Proof of Concept.

The purpose of this study was to train and test preliminary models using two machine learning algorithms to identify healthcare workers at risk of developing anxiety, depression, and post-traumatic stress disorder. The study included data from a prospective cohort study of 816 healthcare workers collected using a mobile application during the first two waves of COVID-19. Each week, the participants responded to 11 questions and completed three screening questionnaires (one for anxiety, one for depression, and one for post-traumatic stress disorder). Then, the research team selected two questions (out of the 11), which were used with biological sex to identify whether scores on each screening questionnaire would be positive or negative. The analyses involved a fivefold cross-validation to test the accuracy of models based on logistic regression and support vector machines using cross-sectional and cumulative measures. The findings indicated that the models derived from the two questions and biological sex accurately identified screening scores for anxiety, depression, and post-traumatic stress disorders in 70% to 80% of cases. However, the positive predictive value never exceeded 50%, underlining the importance of collecting more data to train better models. Our proof of concept demonstrates the feasibility of using machine learning to develop novel models to screen for psychological distress in at-risk healthcare workers. Developing models with fewer questions may reduce burdens of active monitoring in practical settings by decreasing the weekly assessment duration.

[Physical activity: What is its role in the training and practice of psychoeducators in Quebec?] / L'activité physique : quelle est sa place dans la formation et la pratique des psychoéducateurs au Québec ?

The provision of services that improve the functioning, social participation and quality of life of individuals with behavioral or mental health problems is a common denominator amongst psychosocial professionals in Quebec, including social workers, psychologists and psychoeducators. One intervention that has gained empirical support as an intervention tool is physical activity. In fact, numerous studies have demonstrated the benefits of physical activity for many populations with whom psychosocial professionals work. Objectives Thus, the primary objective of this study was to understand the role physical activity plays in psychosocial intervention, specifically in the field of psychoeducation. The specific objectives of this study are (1) to assess how physical activity spans out in the academic and continuing education of psychoeducators, (2) establish the use of physical activity, and (3) to explore whether certain variables influence the use of physical activity by psychoeducators. Method A total of 150 psychoeducators across Quebec (years of experience: M = 11.2; SD = 9.1) completed an online survey. Descriptive statistics, conditional probability, chi-square, analyses, and logistic regression were performed. Results The results suggest that physical activity is an intervention tool used by psychoeducators, with just over 75% of professionals reporting having used physical activity in their practice. However, very few psychoeducators have received academic or continuing education pertaining to this intervention tool. The use of physical activity was not found to differ across clienteles with whom psychoeducators worked, but was positively and significantly predicted by the number of years of experience of the professionals. Conclusion Considering the numerous benefits associated with physical activity, the results of the present study emphasize the need to reflect on physical activity in psychosocial intervention and on the training offered to professionals in relation to the use of this tool. Taken together, the results of the scientific literature and our study highlight that physical activity can be used as an intervention tool by psychosocial professionals. However, in order to avoid iatrogenic outcomes resulting from inappropriate use of physical activity, further research is needed to ensure that professionals have the necessary training and supervision for safe and effective implementation.

Longitudinal assessment and determinants of short-term and longer-term psychological distress in a sample of healthcare workers during the COVID-19 pandemic in Quebec, Canada.

Introduction: Previous research has demonstrated the negative impact of the COVID-19 pandemic emergency on the wellbeing of healthcare workers. However, few research contributions reported a longitudinal evaluation of psychological distress and examined determinants of its duration and course over time. The present study aims to explore the impact of the pandemic emergency on HCWs mental health by adopting a longitudinal design and assessing mental health as combination of overlapping clinical symptoms (post-traumatic stress disorder, depression and anxiety). Methods: Data were collected weekly through a mobile application during and after the first wave of COVID-19 in the province of Quebec, Canada, in 2020. Analysis was conducted on a final sample of 382 participants. Participants were grouped into "resilient" (RES) if they did not manifest clinical-level psychological distress during monitoring, "short-term distress" (STD) if distress exceeded the clinical threshold for 1-3 weeks, and longer-term distress (LTD) if it occurred for four or more weeks, even if not consecutively. Descriptive statistics for all variables were computed for each subgroup (RES, STD and LTD), and pairwise comparisons between each group for every descriptive variable were made using chi square statistics for categorical variables and t-test for continuous variables. Predictors of distress groups (STD and LTD vs RES) were assessed running multinomial hierarchical logistic regression models. Results: In our sample, almost two third (59.4%) HCWs did not manifest moderate or severe distress during the monitoring time. Short-term distress, mostly post-traumatic symptoms that lasted for less than 4 weeks, were the most common distress response, affecting almost one third of participants. Longer psychological distress occurred only in a smaller percentage (12.6%) of cases, as a combination of severe posttraumatic, depressive and anxiety symptoms. Perceived occupational stress was the most significant risk factor; moreover individual, peritraumatic work and family risk and protective factors, were likely to significantly affect the stress response. Discussion: Results tend to provide a more complex and resiliency-oriented representation of psychological distress compared to previous cross-sectional studies, but are in line with stress response studies. Findings allow us to better describe the profiles of distress response in STD and LTD groups. Participants that manifest short term distress experience acute stress reaction in which the interplay between personal, family and professional life events is associated with the stress response. Conversely, longer term distress response in HCWs presents a more complex mental health condition with an higher level of impairment and support needs compared to participants with short-term distress.

Assessment of Psychological Distress in Health Care Workers During the First two Waves of COVID-19: A Follow-up of a Canadian Longitudinal Study.

Background: Health care workers (HCW) exposed to COVID-19 risk experiencing psychological distress. Little is known regarding longitudinal perspectives and evolutions of psychological distress within this population. The objective of this study is to extend the results of our previous study to the pandemic's second wave. Method: This prospective cohort study was conducted from May 8, 2020, to January 24, 2021, and includes 787 HCW. Symptoms of anxiety and depression were assessed using the Generalised Anxiety Disorder-7 (GAD-7) and the Patient Health Questionnaire-9 (PHQ-9). Descriptive statistics illustrated the evolution of psychological distress indicators, whereas latent class analysis helped identify trajectories. Results: The results showed that a lower proportion of HCW exceeded the clinical threshold during the second wave (36,5% vs. 31,1%). As in the first wave, most of our sample fell onto the resilient trajectory (67.22%). We adapted the name of the remaining trajectories to better suit their evolution: rapid recovery (15.76%), slow recovery (9.66%), and delayed (7.37%). Conclusion: Approximately two-thirds of the HCW did not manifest significant distress. For those who did, the distress was transient. We observed a trend of positive adaptability among HCW, considering that the proportion of HCW experiencing psychological distress exceeding clinical threshold remained lower than during the first wave. Our data highlight the dynamic nature of psychological distress. To be able to detect psychological distress as it arises, HCW should use self-monitoring as an essential tool. This vigilance would allow institutions to offer timely support and resources for those experiencing psychological distress.

Assessment of Psychological Distress in Health-care Workers during and after the First Wave of COVID-19: A Canadian Longitudinal Study: Évaluation de la Détresse Psychologique Chez Les Travailleurs de la Santé Durant et Après la Première Vague de la COVID-19: une étude longitudinale canadienne.

OBJECTIVES: Health-care workers (HCW) exposed to COVID-19 are at risk of experiencing psychological distress. Although several cross-sectional studies have been carried out, a longitudinal perspective is needed to better understand the evolution of psychological distress indicators within this population. The objectives of this study were to assess the evolution of psychological distress and to identify psychological distress trajectories of Canadian HCW during and after the first wave of COVID-19. METHOD: This prospective cohort study was conducted from May 8 to September 4, 2020, and includes a volunteer sample of 373 HCW. Symptoms of post-traumatic disorder, anxiety, and depression were assessed using the Post-Traumatic Stress Disorder Checklist for Diagnostic and Statistical Manual of Mental Disorders fifth edition (PCL-5), the Generalized Anxiety Disorder-7, and the Patient Health Questionnaire-9. Descriptive statistics were used to illustrate the evolution of psychological distress indicators, whereas latent class analysis was carried out to identify trajectories. RESULTS: During and after the first wave of COVID-19, the rates of clinical mental health symptoms among our sample varied between 6.2% and 22.2% for post-traumatic stress, 10.1% and 29.9% for depression, and 7.3% and 26.9% for anxiety. Finally, 4 trajectories were identified: recovered (18.77%), resilient (65.95%), subchronic (7.24%), and delayed (8.04%). CONCLUSION: The longitudinal nature of our study and the scarcity of our data are unique among existing studies on psychological distress of HCW in COVID-19 context and allow us to contextualize prior transversal data on the topic. Although our data illustrated an optimistic picture in showing that the majority of HCW follow a resilience trajectory, it is still important to focus our attention on those who present psychological distress. Implementing preventive mental health interventions in our health-care institutions that may prevent chronic distress is imperative. Further studies need to be done to identify predictors that may help to characterize these trajectories.

Effects of an Interactive Web Training to Support Parents in Reducing Challenging Behaviors in Children with Autism.

Many children with autism spectrum disorder (ASD) engage in challenging behaviors, which may interfere with their daily functioning, development, and well-being. To address this issue, we conducted a four-week randomized waitlist control trial to examine the effects of a fully self-guided interactive web training (IWT) on (a) child engagement in challenging behaviors and (b) parental intervention. After 4 weeks, parents in the treatment group reported lower levels of challenging behaviors in their children and more frequent use of behavioral interventions than those in the waitlist groups. Furthermore, within-group analyses suggest that these changes persisted up to 12 weeks following completion of the IWT. Our results highlight the potential utility of web training, but our high attrition rate and potential side effects prevent us from recommending the training as a standalone treatment.

Artificial intelligence for the measurement of vocal stereotypy.

Both researchers and practitioners often rely on direct observation to measure and monitor behavior. When these behaviors are too complex or numerous to be measured in vivo, relying on direct observation using human observers increases the amount of resources required to conduct research and to monitor the effects of interventions in practice. To address this issue, we conducted a proof of concept examining whether artificial intelligence could measure vocal stereotypy in individuals with autism. More specifically, we used an artificial neural network with over 1,500 minutes of audio data from 8 different individuals to train and test models to measure vocal stereotypy. Our results showed that the artificial neural network performed adequately (i.e., session-by-session correlation near or above .80 with a human observer) in measuring engagement in vocal stereotypy for 6 of 8 participants. Additional research is needed to further improve the generalizability of the approach.

Increasing compliance with wearing a medical device in children with autism.

Health professionals often recommend the use of medical devices to assess the health, monitor the well-being, or improve the quality of life of their patients. Children with autism may present challenges in these situations as their sensory peculiarities may increase refusals to wear such devices. To address this issue, we systematically replicated prior research by examining the effects of differential reinforcement of other behavior (DRO) to increase compliance with wearing a heart rate monitor in 2 children with autism. The intervention increased compliance to 100% for both participants when an edible reinforcer was delivered every 90 s. The results indicate that DRO does not require the implementation of extinction to increase compliance with wearing a medical device. More research is needed to examine whether the reinforcement schedule can be further thinned.

Using the dual-criteria methods to supplement visual inspection: An analysis of nonsimulated data.

The purpose of our study was to examine the probability of observing false positives in nonsimulated data using the dual-criteria methods. We extracted data from published studies to produce a series of 16,927 datasets and then assessed the proportion of false positives for various phase lengths. Our results indicate that collecting at least three data points in the first phase (Phase A) and at least five data points in the second phase (Phase B) is generally sufficient to produce acceptable levels of false positives.

Comparing two methods to promote generalization of receptive identification in children with autism spectrum disorders.

PURPOSE: The purpose of our study was to compare the effects of serial and concurrent training on the generalization of receptive identification in children with autism spectrum disorders (ASD). METHODS: We taught one to three pairs of stimulus sets to nine children with ASD between the ages of three and six. One stimulus set within each pair was taught using concurrent training and the other using serial training. We alternated the training sessions within a multielement design and staggered the introduction of subsequent pairs for each participant as in a multiple baseline design. RESULTS: Overall, six participants generalized at least one stimulus set more rapidly with concurrent training whereas two participants showed generalization more rapidly with serial training. CONCLUSIONS: Our results differ from other comparison studies on the topic and indicate that practitioners should consider assessing the effects of both procedures prior to teaching receptive identification to children with ASD.

Newspaper Coverage of Autism Treatment in Canada: 10-Year Trends (2004-2013).

OBJECTIVE: To compare trends in coverage of empirically supported and alternative autism treatments in Canadian newspapers during a 10-year period and to examine whether the portrayal of empirically supported and alternative treatments differed. METHOD: We searched a sample of 10 daily local and national Canadian newspapers using the word autism combined with intervention or treatment in the Proquest Canadian Newsstand and Eureka.cc databases, which yielded a total of 857 articles published between 2004 and 2013. In our subsequent analyses, we only included articles whose main topic was autism and that referred to at least one treatment. We then categorized the 137 remaining articles by treatment and rated whether each treatment category was portrayed in a favourable, unfavourable, or neutral manner. RESULTS: In total, 46% of the articles discussed at least 1 empirically supported treatment, 53% at least 1 alternative treatment, and 12% at least 1 uncategorized treatment. Newspaper articles provided favourable, unfavourable, and neutral portrayals of empirically supported treatments in 75%, 10%, and 16% of cases, respectively. In contrast, alternative treatments were portrayed favourably in 52%, unfavourably in 32%, and neutrally in 16% of cases. Our analyses indicated that empirically supported treatments were portrayed more favourably than alternative treatments (χ(2) = 10.42, df = 2, P = 0.005). CONCLUSIONS: Despite some encouraging trends, our study has shown that researchers and clinicians must continue to clarify misconceptions about autism treatment. Families of people with autism spectrum disorders should be directed toward more reliable and accurate sources of information.