ISSN : 1229-067X
본 연구는 한국 성인의 PTSD 증상을 예측하는 사건(DSM-5 진단기준사건(직접경험), DSM-5 비진단기준 사건(직접경험), 간접경험 사건)을 확인하고자 수행되었다. 이를 위해 국내 성인 1,136명의 자료를 기계학습 기법인 Elastic Net 회귀분석을 통해 분석하였다. 본 연구에서는 DSM-5 진단기준사건(직접경험) 19개, DSM-5 비진단기준사건(직접경험) 17개, 간접경험사건 19개, 총 55개의 사건 경험 여부를 PTSD 증상에 대한 독립변수로 투입하였다. 연구 결과, DSM-5 진단기준사건(직접경험) 6개, DSM-5 비진단기준사건(직접경험) 9개, 간접경험사건 4개, 총 19개의 사건이 PTSD 증상을 예측하는 것으로 나타났다. 본 연구의 결과는 DSM-5 진단기준사건(직접경험)뿐만 아니라 DSM-5 비진단기준사건(직접경험)과 간접경험 사건이 PTSD 증상을 예측할 수 있음을 확인하였다는 것에 의의가 있다.
This study aimed to identify events that predict PTSD symptoms in Korean adults, including DSM-5 diagnostic criteria events(direct experience events), DSM-5 non-diagnostic criteria events(direct experience), and indirect experience events. Data from 1,136 Korean adults were analyzed using the machine learning technique of Elastic Net regression analysis. In this study, a total of 55 events were included as independent variables for PTSD symptoms: 19 DSM-5 diagnostic criteria events(direct experience), 17 DSM-5 non-diagnostic criteria events(direct experience), and 19 indirect experience events. The results showed that 19 events predicted PTSD symptoms, including 6 DSM-5 diagnostic criteria events(direct experience), 9 DSM-5 non-diagnostic criteria events(direct experience), and 4 indirect experience events. The significance of this study lies in confirming that not only DSM-5 diagnostic criteria events(direct experience) but also DSM-5 non-diagnostic criteria events(direct experience) and indirect experience events can predict PTSD symptoms.