Journal of Personality and Psychosomatic Research (JPPR)

The objective of this study was to examine whether trait emotional stability functions as a protective factor against psychosomatic symptom amplification and psychosomatic symptom severity through the mediating role of perceived stress. This study employed a quantitative cross-sectional design using data collected from an adult community sample in the United Kingdom. Participants completed standardized self-report measures assessing trait emotional stability, perceived stress, somatosensory amplification, and psychosomatic symptom severity. Validated instruments with established psychometric properties were used to ensure reliability and construct validity. Data were analyzed using multilevel modeling techniques to account for potential clustering effects. A multilevel mediation framework was specified in which trait emotional stability served as the predictor, perceived stress as the mediator, and psychosomatic symptom amplification and symptom severity as outcome variables. Indirect effects were tested using bootstrapping procedures with bias-corrected confidence intervals. Multilevel regression analyses indicated that trait emotional stability was significantly and negatively associated with perceived stress, somatosensory amplification, and psychosomatic symptom severity. Perceived stress was positively associated with both somatosensory amplification and psychosomatic symptom severity. Somatosensory amplification emerged as a strong positive predictor of psychosomatic symptom severity when included alongside emotional stability and perceived stress. Mediation analyses demonstrated significant indirect effects of emotional stability on both psychosomatic symptom amplification and symptom severity via perceived stress, while direct effects remained significant, indicating partial mediation. The findings suggest that trait emotional stability protects against psychosomatic symptom amplification and somatic symptom burden through both direct pathways and indirect stress-related mechanisms, highlighting the importance of personality-informed and stress-focused approaches in psychosomatic research and practice.

The objective of this study was to develop and empirically evaluate an artificial intelligence–based framework that integrates personality traits with psychosomatic symptom profiles to generate adaptive, personalized treatment plans in psychosomatic medicine. A mixed-methods, model-development study was conducted using clinical data from adult patients with psychosomatic complaints recruited from outpatient psychosomatic and psychological services in Taiwan. Standardized personality assessments, psychosomatic symptom measures, clinician-rated evaluations, and behavioral indicators were collected and integrated into a secure digital dataset. Machine learning techniques, including unsupervised clustering and supervised predictive modeling, were applied to identify latent personality–symptom patterns and to generate individualized treatment recommendations across multiple psychosomatic intervention modalities. Model performance was evaluated using cross-validation procedures, and explainable AI methods were employed to enhance interpretability and clinical transparency. Unsupervised learning identified four distinct personality–psychosomatic clusters characterized by differential trait configurations and symptom profiles. Predictive modeling demonstrated high classification accuracy and strong discriminative capacity in matching patients to optimal treatment modalities. Inferential analyses indicated that personality traits significantly contributed to treatment recommendation variance beyond symptom severity alone, and adaptive recommendations differed systematically across clusters, supporting the model’s capacity for clinically meaningful personalization. The findings suggest that integrating personality traits into AI-driven psychosomatic treatment planning enables robust patient stratification, improves personalization of intervention strategies, and offers a scalable decision-support approach aligned with contemporary precision medicine principles. This framework represents a promising step toward adaptive, person-centered psychosomatic care that complements clinical expertise and supports iterative treatment optimization.

This study aimed to predict somatic complaints by integrating Big Five personality traits and passive smartphone-derived behavioral indicators within a machine learning framework. A cross-sectional observational design was employed with an adult community sample recruited in Armenia. Participants completed standardized self-report measures assessing somatic complaints and Big Five personality traits. In parallel, passive smartphone sensing data were collected continuously over a four-week period using a custom Android application that captured behavioral indicators such as screen time, sleep regularity proxies, physical inactivity duration, nighttime phone activity, and app usage patterns, without recording personal content. Data preprocessing included cleaning, aggregation of behavioral features at the participant level, and standardization of predictors. Supervised machine learning models were trained to predict somatic complaint scores, including regularized linear models, support vector regression, random forest, and gradient boosting. Model evaluation used train–test splits with cross-validation, and performance was assessed using error-based indices and explained variance metrics. Nonlinear ensemble models significantly outperformed linear approaches in predicting somatic complaints, with gradient boosting explaining the largest proportion of variance. Models combining personality traits and smartphone-derived behavioral data demonstrated significantly higher predictive accuracy than models using either data source alone. Neuroticism showed the strongest positive contribution to somatic complaints, while conscientiousness and extraversion contributed negatively. Among behavioral indicators, sleep regularity, daily screen time, nighttime phone activity, and physical inactivity emerged as significant predictors. Model performance remained stable across gender and age subgroups, indicating robustness of the predictive relationships. Integrating personality traits with passive smartphone-derived behavioral data using machine learning provides a powerful and ecologically valid approach for predicting somatic complaints, supporting biopsychosocial models of psychosomatic health and highlighting the potential of digital phenotyping for personalized health assessment.

This study aimed to examine an integrated psychoneuroimmunological model linking personality traits to psychosomatic reactivity through perceived stress, neuroendocrine activity, and immune activation. A cross-sectional correlational design was employed with a community-based adult sample recruited from urban health centers in Mexico. Participants completed validated self-report measures assessing personality traits, perceived stress, and psychosomatic symptoms. Neuroendocrine activity was indexed using salivary cortisol collected at awakening and 30 minutes post-awakening, while immune activation was assessed through serum inflammatory markers, including interleukin-6 and C-reactive protein. Data were analyzed using correlation analyses, multiple regression models, mediation analyses with bootstrapping, and structural equation modeling to test direct and indirect pathways among psychological and biological variables. Inferential analyses indicated that neuroticism was a strong positive predictor of psychosomatic symptoms, whereas conscientiousness and agreeableness were significant negative predictors. Perceived stress significantly mediated the relationship between neuroticism and psychosomatic symptom severity. Elevated cortisol awakening response was associated with higher perceived stress and greater somatic symptom burden and functioned as an additional mediator. Inflammatory markers were positively associated with cortisol activity and psychosomatic symptoms. Structural equation modeling demonstrated good model fit and supported a sequential pathway from personality traits to stress appraisal, neuroendocrine dysregulation, immune activation, and psychosomatic reactivity, with protective traits exerting indirect buffering effects through reduced stress responses. The findings support a psychoneuroimmunological model in which personality traits function as central regulators of psychosomatic reactivity by shaping psychological stress appraisal and downstream neuroendocrine and immune processes, highlighting the importance of integrative, personality-informed approaches to psychosomatic health.

This study aimed to examine whether personality traits function as a core organizing system underlying mind–body health by integrating multivariate and computational modeling approaches. A cross-sectional design was employed with an adult sample recruited from Portugal. Participants completed validated self-report instruments assessing personality traits and multiple domains of mind–body health, including physical and mental health, perceived stress, affective balance, and sleep quality. Data were first examined using descriptive statistics and correlational analyses to establish basic relationships among variables. Structural equation modeling was then applied to test a theoretically informed model in which personality traits predicted latent dimensions of mind–body health. To complement explanatory analyses, machine learning techniques, including linear and non-linear predictive models, were used to estimate the extent to which personality traits could predict composite mind–body health outcomes. Model performance was evaluated using explained variance and error indices, and feature importance analyses were conducted to identify the relative contribution of each personality trait. Inferential analyses revealed significant and systematic associations between personality traits and all major mind–body health indicators. Neuroticism emerged as a strong positive predictor of stress, negative affect, and sleep disturbances and a strong negative predictor of physical and mental health, whereas Conscientiousness showed the opposite pattern, functioning as a robust protective factor. Structural equation modeling demonstrated that personality traits exerted simultaneous and differential effects on latent health, stress–affect, and sleep regulation factors, with excellent model fit indices. Machine learning models significantly outperformed traditional linear regression, indicating non-linear and interactive relationships between personality and health, with Neuroticism and Conscientiousness showing the highest predictive importance. The findings support the conceptualization of personality as a central organizing factor in mind–body health, shaping the structure, regulation, and predictability of physical and psychological well-being, and highlight the value of computational approaches for advancing integrative psychosomatic models.

The objective of this study was to identify and transparently explain personality-driven risk factors associated with psychosomatic symptom severity using explainable artificial intelligence models. This cross-sectional study was conducted on an adult clinical sample recruited from psychosomatic and general health settings in Chile. Participants completed validated self-report instruments assessing personality traits, stress-related psychological variables, and psychosomatic symptom severity. After data preprocessing and standardization, multiple supervised machine learning models were developed to predict psychosomatic symptom severity based on personality and psychological predictors. Model performance was evaluated using cross-validation procedures. The best-performing model was further analyzed using explainable artificial intelligence techniques to identify global and individual-level contributions of predictors, enabling transparent interpretation of nonlinear effects and interactions among personality traits. Nonlinear ensemble models significantly outperformed linear models in predicting psychosomatic symptom severity, explaining a substantial proportion of variance. Stress reactivity emerged as the strongest predictor, followed by emotional instability, perceived stress, and negative affectivity. Explainable analyses revealed threshold and interaction effects, indicating sharp increases in psychosomatic risk at high levels of stress reactivity and compounded effects when combined with emotional instability. Self-regulation-related traits demonstrated a protective effect, particularly at low to moderate stress levels, although this effect diminished under extreme stress conditions. Individual-level explanations highlighted marked heterogeneity in risk profiles, with distinct personality configurations driving symptom severity across participants. The findings indicate that psychosomatic symptom severity is shaped by dynamic, nonlinear interactions among personality traits and stress-related factors rather than isolated linear effects.

The objective of this study was to develop and evaluate ensemble learning models to predict somatic symptom disorder based on personality traits, perceived stress, and emotion regulation variables. This cross-sectional study was conducted on an adult sample from South Africa using a predictive modeling design. Participants completed standardized self-report measures assessing somatic symptom severity, personality traits, perceived stress, and multiple dimensions of emotion regulation. Data preprocessing included handling missing values, standardization of continuous variables, and feature preparation for machine learning analysis. Several base classifiers were trained and integrated using ensemble learning techniques, including random forest, gradient boosting, and stacking. Model training and evaluation were performed using stratified k-fold cross-validation to ensure robustness and reduce overfitting. Predictive performance was assessed using multiple inferential metrics, including accuracy, sensitivity, specificity, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Feature importance and incremental modeling analyses were conducted to examine the relative and combined contributions of predictor domains. The ensemble learning models demonstrated strong predictive performance, with the stacking ensemble yielding the highest accuracy and AUC, indicating excellent discrimination between higher and lower somatic symptom severity. Neuroticism and perceived stress emerged as the most influential predictors, followed by key emotion regulation difficulties, particularly impulse control problems and limited access to adaptive regulation strategies. Incremental analyses showed that models incorporating personality traits alone achieved moderate prediction, which significantly improved with the addition of perceived stress and further improved when emotion regulation variables were included.

This study aimed to identify and model personality disorder–related trait profiles associated with the severity of chronic somatic symptoms using artificial intelligence–based analytical approaches. A cross-sectional observational design was employed with an adult sample recruited in Hungary. Participants completed standardized self-report measures assessing chronic somatic symptom severity, dimensional personality disorder traits, and psychological distress variables. Data were collected electronically following informed consent and ethical approval. Multiple supervised machine learning models, including regularized regression and ensemble-based algorithms, were trained to predict somatic symptom severity from personality trait dimensions while controlling for demographic and psychological covariates. Model performance was evaluated using cross-validation procedures, and explainable AI techniques were applied to determine the relative importance and direction of trait contributions. Ensemble machine learning models demonstrated superior predictive performance compared with linear approaches, indicating non-linear and interactive associations between personality traits and chronic somatic symptom severity. Negative affectivity emerged as the strongest predictor, followed by detachment, with both traits showing robust positive associations with symptom severity. Disinhibition and psychoticism contributed moderately, while antagonism exhibited a smaller but significant effect. Personality disorder traits provided substantial incremental explanatory value beyond anxiety and depressive symptoms, accounting for additional variance in somatic symptom severity. Explainability analyses confirmed the dominance of internalizing and emotion-related traits in the AI-derived personality profiles associated with higher symptom burden. The findings indicate that chronic somatic symptoms are strongly linked to specific configurations of maladaptive personality traits, particularly negative affectivity and detachment, and that AI-based modeling offers a powerful framework for capturing these complex relationships.