Determinants of anxiety levels among young males in a threat of experiencing military conflict-Applying a machine-learning algorithm in a psychosociological study

A novel approach to anxiety level prediction using small sets of judgment and survey variables

Anxiety, a condition characterized by intense fear and persistent worry, affects millions each year and, when severe, is distressing and functionally impairing. Numerous machine learning frameworks have been developed and tested to predict features of anxiety and anxiety traits. This study extended these approaches by using a small set of interpretable judgment variables (n = 15) and contextual variables (demographics, perceived loneliness, COVID-19 history) to (1) understand the relationships between these variables and (2) develop a framework to predict anxiety levels [derived from the State Trait Anxiety Inventory (STAI)]. This set of 15 judgment variables, including loss aversion and risk aversion, models biases in reward/aversion judgments extracted from an unsupervised, short (2-3 min) picture rating task (using the International Affective Picture System) that can be completed on a smartphone. The study cohort consisted of 3476 de-identified adult participants from across the United States who were recruited using an email survey database. Using a balanced Random Forest approach with these judgment and contextual variables, STAI-derived anxiety levels were predicted with up to 81% accuracy and 0.71 AUC ROC. Normalized Gini scores showed that the most important predictors (age, loneliness, household income, employment status) contributed a total of 29-31% of the cumulative relative importance and up to 61% was contributed by judgment variables. Mediation/moderation statistics revealed that the interactions between judgment and contextual variables appears to be important for accurately predicting anxiety levels. Median shifts in judgment variables described a behavioral profile for individuals with higher anxiety levels that was characterized by less resilience, more avoidance, and more indifference behavior. This study supports the hypothesis that distinct constellations of 15 interpretable judgment variables, along with contextual variables, could yield an efficient and highly scalable system for mental health assessment. These results contribute to our understanding of underlying psychological processes that are necessary to characterize what causes variance in anxiety conditions and its behaviors, which can impact treatment development and efficacy.

Posttraumatic stress disorder hyperarousal event detection using smartwatch physiological and activity data

Posttraumatic Stress Disorder (PTSD) is a psychiatric condition affecting nearly a quarter of the United States war veterans who return from war zones. Treatment for PTSD typically consists of a combination of in-session therapy and medication. However; patients often experience their most severe PTSD symptoms outside of therapy sessions. Mobile health applications may address this gap, but their effectiveness is limited by the current gap in continuous monitoring and detection capabilities enabling timely intervention. The goal of this article is to develop a novel method to detect hyperarousal events using physiological and activity-based machine learning algorithms. Physiological data including heart rate and body acceleration as well as self-reported hyperarousal events were collected using a tool developed for commercial off-the-shelf wearable devices from 99 United States veterans diagnosed with PTSD over several days. The data were used to develop four machine learning algorithms: Random Forest, Support Vector Machine, Logistic Regression and XGBoost. The XGBoost model had the best performance in detecting onset of PTSD symptoms with over 83% accuracy and an AUC of 0.70. Post-hoc SHapley Additive exPlanations (SHAP) additive explanation analysis showed that algorithm predictions were correlated with average heart rate, minimum heart rate and average body acceleration. Findings show promise in detecting onset of PTSD symptoms which could be the basis for developing remote and continuous monitoring systems for PTSD. Such systems may address a vital gap in just-in-time interventions for PTSD self-management outside of scheduled clinical appointments.

Early evidence on the mental health of Ukrainian civilian and professional combatants during the Russian invasion

Background

The ongoing Russian invasion of Ukraine has led many Ukrainians to fight for their country, either in the regular army or as civilian members of voluntary territorial defense forces. There is, however, a dearth of knowledge on the mental health of combatants in this conflict. Prior research on the mental health of combatants is unlikely to translate to the situation at hand because such research is focused on combatants fighting abroad and neglects civilian combatants.

Methods

This study provides the first attempt to investigate the mental health of Ukrainian combatants in the regular army and voluntary territorial defense forces by analyzing the prevalence rates of common mental health issues, as well as their demographic and socioeconomic predictors.

Results

Between March 19 and 31, 2022, the initial period of Russia’s invasion of Ukraine, a sample of 178 Ukrainian combatants (104 in the regular army and 74 civilian combatants) participated in a survey on symptoms of anxiety (GAD-2), depression (PHQ-2), and insomnia (ISI).

Conclusions

A sizable portion of Ukrainian combatants reached cut-off levels for clinical symptoms of anxiety (44·4%), depression (43·3%), and insomnia (12·4%). Importantly, the mental health of Ukrainian combatants varied between professional soldiers and civilian combatants, as well as by gender, marital status, by whether or not they were located in Russian-occupied/active-combat areas, and dependent on whether they were personally involved in combat. This study provides early evidence on the mental health of Ukrainian combatants, pointing to their urgent need for mental health assistance in the ongoing war.

Future Anxiety Among Young People Affected by War and Armed Conflict: Indicators for Social Work Practice

Strengthening the evidence base for professional social work intervention that contributes to providing psychosocial support to international students affected by war and conflict is a major priority as this vulnerable group of youth increases. Therefore, this study aimed to determine the level of future anxiety among international students coming from areas experiencing war and conflict. This study used the descriptive correlative approach, where the future anxiety scale was applied to a sample of 287 international students affected by war and conflicts. Findings showed that there are statistically significant differences between males and females (in favor of females) in the level of the social dimension of future anxiety. The current study results showed a statistically significant relationship between future anxiety and some variables related to war and conflict (living in a war environment - direct and indirect exposure to damage). There are statistically significant differences between those who lived in Yemen at the time of wars and those who did not live (in favor of those who lived in Yemen at the time of wars) in the level of future anxiety. There are also statistically significant differences between those exposed to harm or their family because of the war and those who were not exposed (in favor of those who were exposed) in the level of future anxiety as a whole. The study recommends developing psychosocial support services for this vulnerable group, considering the cultural context to promote women and protect them from discrimination in the services they deserve on an equal basis with men.

Using Artificial Neural Networks in Predicting the Level of Stress among Military Conscripts

The present study aims to elucidate the main variables that increase the level of stress at the beginning of military conscription service using an artificial neural network (ANN)-based prediction model. Random sample data were obtained from one battalion of the Lithuanian Armed Forces, and a survey was conducted to generate data for the training and testing of the ANN models. Using nonlinearity in stress research, numerous ANN structures were constructed and verified to limit the optimal number of neurons, hidden layers, and transfer functions. The highest accuracy was obtained by the multilayer perceptron neural network (MLPNN) with a 6-2-2 partition. A standardized rescaling method was used for covariates. For the activation function, the hyperbolic tangent was used with 20 units in one hidden layer as well as the back-propagation algorithm. The best ANN model was determined as the model that showed the smallest cross-entropy error, the correct classification rate, and the area under the ROC curve. These findings show, with high precision, that cohesion in a team and adaptation to military routines are two critical elements that have the greatest impact on the stress level of conscripts.