Artificial Neural Network-Based Prediction of Death Anxiety in HIV-Positive Cases through Social Support and Distress Tolerance

Background: Distress tolerance has increasingly been used as an important construct to develop a novel insight into the onset and persistence of psychological traumas as well as prevention and treatment. Objectives: The present study investigated the relationship between social support and distress tolerance with death anxiety using artificial neural networks (ANN) in human immunodeficiency virus (HIV)-positive cases. Methods: The research method was descriptive-correlational. The statistical population included all the HIV-positive cases of Ahvaz in 2021. The convenience sampling method was employed to select 91 participants as the research sample. The research instruments included the Death Anxiety Scale (DAS), the Social Support Survey (SSS), and the Distress Tolerance Scale (DTS). The Pearson correlation coefficient, simultaneous regression, and ANN were used for data analysis. Results: The mean and standard deviation (SD) of death anxiety, social support, and distress tolerance were 9.07 ± 2.76, 63.78 ± 18.05, and 37.49 ± 12.91, respectively. The results showed a negative correlation between death anxiety, social support, and distress tolerance. Also, there was a significant negative relationship between social support and death anxiety (β = -0.31, P < 0.001). There was also a significant negative relationship between distress tolerance and death anxiety in HIV-positive cases (β = -0.53, P < 0.001). Conclusions: It is now more necessary than ever before to consider the effects of social support and distress tolerance on death anxiety in HIV-positive cases. Apparently, their death anxiety is affected by other factors and their interactive effects.