Modeling Personality–Emotion–Somatic Symptom Pathways with Explainable Machine Learning

Authors

    Mariana Torres * Department of Electrical and Computer Engineering, Monterrey Institute of Technology and Higher Education (ITESM), Monterrey, Mexico mariana.torres@tec.mx
    Fabricio Peixoto National Institute of Psychiatry Ramón de la Fuente Muñiz, Sub-directorate of Clinical Research, Mexico City, Mexico
    Jaime Martínez-Pacheco Martínez-Pacheco Department of Psychiatry and Behavioral Sciences, Johns Hopkins School of Medicine, 733 N. Broadway, Baltimore, MD 21205, USA

Keywords:

Somatic symptoms, personality traits, neuroticism, emotional distress, explainable machine learning, SHAP, psychosomatic health

Abstract

This study aimed to examine the pathways linking personality traits, emotional distress, and somatic symptoms using explainable machine learning techniques. This cross‑sectional study included 1,024 adults from Mexico (54.3% women; mean age = 34.7 years, SD = 11.2). Participants completed validated psychological instruments, including the Big Five Inventory (BFI‑44) to assess personality traits, the Depression Anxiety Stress Scales (DASS‑21) to measure emotional distress, and the Patient Health Questionnaire Somatic Symptom Scale (PHQ‑15) to assess somatic symptom severity. Descriptive statistics and Pearson correlations were first conducted to examine relationships among variables. Subsequently, machine learning models—Random Forest, Gradient Boosting, and XGBoost—were developed to predict somatic symptoms. Model performance was evaluated using the coefficient of determination (R²), and SHapley Additive exPlanations (SHAP) were used to identify the relative importance of predictors and interpret the models. Correlation analyses indicated significant positive associations between neuroticism, depression, anxiety, stress, and somatic symptoms (r range = .29–.48, p < .001). Neuroticism showed the strongest correlations with anxiety (r = .48) and somatic symptoms (r = .41). Among the machine learning models, XGBoost demonstrated the best predictive performance (R² = 0.42), followed by Gradient Boosting (R² = 0.39) and Random Forest (R² = 0.36). SHAP analyses revealed that anxiety and neuroticism were the most influential predictors of somatic symptoms, followed by stress and depression. Interaction analysis suggested that individuals with high neuroticism combined with high anxiety exhibited nearly twice the predicted level of somatic symptom severity compared to individuals with low scores on these variables. The findings highlight the central role of emotional distress and neuroticism in predicting somatic symptoms and demonstrate the value of explainable machine learning for identifying complex psychosomatic pathways.

Downloads

Download data is not yet available.

References

Allemand, M., Fend, H., & Hill, P. L. (2024). Negative Emotional Reactivity and Somatic Symptoms During Adolescence Predict Adult Health and Wellbeing in Early and Middle Adulthood. Journal of youth and adolescence, 53(7), 1513-1528. https://doi.org/10.1007/s10964-024-01940-9

Babakhanlou, A. (2023). Presenting Structural Model of Emotional Eating in People with Obesity based on Self-Regulation with the Mediating Role of Emotional Processing. Journal of Psychological Dynamics in Mood Disorders (PDMD), 2(2), 30-40. https://doi.org/10.22034/pdmd.2023.185859

Bulut, S., Bukhori, B., & Bhat, R. H. (2024). The Experience of Psychosomatic Disorders among Adolescents: Challenges and Coping Strategies. Journal of Personality and Psychosomatic Research (JPPR), 2(2), 19-25. https://doi.org/10.61838/kman.jppr.2.2.4

Efremov, A. (2023). Eliminating Psychosomatic Pain and Negative Emotions With Dehypnosis. Journal of Organizational Behavior Research, 8(1), 1-11. https://doi.org/10.51847/rnrhuqmtqy

Erbildim, E., & Nweke, G. E. (2025). The Mediator Role of Difficulties in Emotion Regulation in the Relationship Between Guilt and Shame-Proneness and Somatic Symptoms. https://doi.org/10.21203/rs.3.rs-5930990/v1

Farahi, S., Naziri, G., Davodi, A., & Fath, N. (2023). The Mediating Role of Cognitive Emotion Regulation Strategies in the Relationship Between Early Maladaptive Schemas, Alexithymia, and Emotional Intelligence With Somatic Symptoms in People With Somatic Symptoms Disorder. Practice in Clinical Psychology, 11(3), 187-200. https://doi.org/10.32598/jpcp.11.3.887.1

Ghanavati, M. (2024). Comparing the Effectiveness of Emotion-Based and Attachment-Based Family Therapy on Emotional Distress Tolerance, Self-Differentiation and Alexithymia in Adolescent Girls With Psychosomatic Disorders. PDMD, 3(4), 139-152. https://doi.org/10.61838/kman.pdmd.3.4.10

Kang, S., Park, C. I., Kim, S. J., & Kang, J. I. (2025). Associations Between Emotional Awareness Deficits and Somatic Symptoms in a Community and Clinical Populations: A Cross-Sectional Study. BMC psychology, 13(1). https://doi.org/10.1186/s40359-025-03087-z

Lee, D., Kim, S. J., Cheon, J., Jung, Y. C., & Kang, J. I. (2024). Changes in Interoceptive Accuracy Related to Emotional Interference in Somatic Symptom Disorder. BMC psychology, 12(1). https://doi.org/10.1186/s40359-024-01778-7

Majlessi Koupaei, H., & Farista, R. (2024). Psychological Pathways to Immunity: The Role of Emotions and Stress in Health and Disease. Journal of Personality and Psychosomatic Research (JPPR), 2(1), 1-3. https://doi.org/10.61838/kman.jppr.2.1.1

Mohammadi Begi, M. (2023). A structural model predicting somatic symptoms based on childhood trauma, emotional alexithymia, and perceived social support with the mediating role of depression/anxiety/stress in patients with epilepsy

Orzechowska, A., Maruszewska, P., Gałecka, M., Hyland, P., Boduszek, D., Gałecki, P., & Bliźniewska-Kowalska, K. (2023). Emotional Control in Selected Somatic and Psychiatric Diseases. BMC psychiatry, 23(1). https://doi.org/10.1186/s12888-023-05321-7

Petzke, T. M., & Witthöft, M. (2024). The Association of Emotion Regulation and Somatic Symptoms. Psychosomatic Medicine, 86(6), 561-568. https://doi.org/10.1097/psy.0000000000001310

Saadati, N., Kiliçaslan, F., & Salami, M. O. (2024). The Psychosomatic Effects of Childhood Trauma: Insights from Adult Survivors. Journal of Personality and Psychosomatic Research (JPPR), 2(2), 34-40. https://doi.org/10.61838/kman.jppr.2.2.6

Sefotho, M. M., Serjanaj, B., Karthik, S., & Saadati, S. A. (2024). The Psychosomatic Interface of Stress and Skin Disorders: Patient Experiences and Perceptions. Journal of Personality and Psychosomatic Research (JPPR), 2(2), 26-33. https://doi.org/10.61838/kman.jppr.2.2.5

Yang, Y. (2023). A Daily Diary Study on Stressors, Hurt Feelings, Aggression, and Somatic Symptoms: The Role of Rejection Sensitivity and Negative Emotion Differentiation. Aggressive Behavior, 49(4), 371-383. https://doi.org/10.1002/ab.22076

Downloads

Additional Files

Published

2026-04-01

Submitted

2026-01-18

Revised

2026-03-14

Accepted

2026-03-25

Issue

Section

Articles

How to Cite

Torres, M., Peixoto , F. ., & Martínez-Pacheco , J. M.-P. . (2026). Modeling Personality–Emotion–Somatic Symptom Pathways with Explainable Machine Learning. Journal of Personality and Psychosomatic Research (JPPR), 1-10. https://journals.kmanpub.com/index.php/jppr/article/view/5164