Author(s)

WenBei Zheng^*, Xi Yang, WenYun Xia

Affiliation(s)

Guangxi Normal University, Guilin 541000, Guangxi, China.

Corresponding Author

WenBei Zheng

ABSTRACT

Post-traumatic stress disorder (PTSD) is a mental disorder caused by traumatic events, characterized by recurrence of memories and nightmares, avoidance of stimulation, difficulty in regulating emotions, and persistent hypervigilance. Due to the particularity of their work, rescuers are often more likely to suffer from PTSD. Identifying and clarifying the influencing factors of PTSD, establishing an effective prediction model for rescuers, and providing effective evaluation tools to provide targeted treatment and support measures for rescuers are of great significance in helping rescuers cope with and prevent PTSD. Based on the data set provided by the PLA Medical College, this study used a decision tree classification model to construct an effective prediction model for rescuers, identify important variables that affect rescuers' PTSD, and evaluate the prediction efficiency of the model by the receiver operating characteristic curve (ROC). Results: The accuracy was 95.56%, the sensitivity was 93.75%, the specificity was 95.69%, the false positive rate was 4.31%, the F1 score was 75%, and the AUC value was 94.72%. The features classified by the model were ranked according to their importance. The top eight features of the decision tree model were: ASD alertness, ASD avoidance, ASD re-experience, ASD separation, ASD nature, smoking status, psychological resilience, and age. Conclusions: The decision tree model has high accuracy and stability and can be used to guide clinical prevention and treatment.

KEYWORDS

PTSD; Decision tree model; Influencing factors; Feature selection

CITE THIS PAPER

WenBei Zheng, Xi Yang, WenYun Xia. PTSD characteristics of rescuers based on decision tree. Innovation and Technology Studies. 2025, 2(1): 41-45. DOI: https://doi.org/10.61784/its3010.

REFERENCES

[1] First MB. Diagnostic and statistical manual of mental disorders, 5th edition, and clinical utility. J Nerv Ment Dis, 2013, 201(9): 727-729. DOI: 10.1097/NMD.0b013e3182a2168a.

[2] Asmundson GG, Stapleton JA. Associations between dimensions of anxiety sensitivity and PTSD symptom clusters in active-duty police officers. Cognitive Behavior Therapy, 2008, 37(2): 66–75.

[3] Oniszczenko W. Temperamental correlates of trauma symptoms in firemen, policemen and soldiers. Int J Occup Med Environ Health, 2014, 27(4): 599-607.

[4] Witt M, Stelcer B, Czarnecka-Iwanczuk M. Stress coping styles in firemen exposed to severe stress. Psychiatria Polska, 2018, 52(3): 543-555.

[5] Hui Wuli, Shi Wanghong, Xu Dezhong, et al. Analysis of influencing factors of PTSD in rescue soldiers from shipwreck in Yantai. Chinese Journal of Mental Health, 2001, 15(3): 148-149.

[6] Liu Xiaohan, Chen Minglong, Guo Jing. Application of machine learning in the identification and prognosis prediction of post-traumatic stress disorder in children. Advances in Psychological Science, 2022, 30(4): 851-862.

[7] Tehrany MS, Pradhan B, Jebur MN. Spatial prediction of flood susceptible areas using rule-based decision tree (DT) and a novel ensemble bivariate and multivariate statistical models in GIS. Journal of Hydrology (Amsterdam), 2013, 504: 69-79.

[8] Liu Siyu, Nadalin. Application of decision tree analysis in English teaching. Medical Education Management, 2023, 9(S1): 54-60.