Akademik Veri Yönetim Sistemi
ANNALS OF INDIAN PSYCHIATRY, cilt.9, sa.4, ss.360-366, 2025 (ESCI)
Aim:This study aimed to assess the severity of manic episodes in patients diagnosed with bipolar disorder using video-based emotion analysis.Materials and Methods:This cross-sectional study was performed with patients diagnosed with bipolar disorder manic episodes (n = 47). The data were obtained using the personal information form and the Young Mania Rating Scale (YMRS) and the Novface emotion recognition software. The Wilcoxon test, Friedman test, Kruskal-Wallis, Mann-Whitney U test, and Spearman correlation analysis were used to analyze the data.Results:At the research endpoint, a statistically significant positive relationship was found between the sadness and the mean score of the YMRS in the period from the clinic to discharge. Accordingly, it was determined that the sadness scores of the patients decreased as the YMRS score decreased. A statistically significant positive correlation was found between the patients' anger and the mean score of the YMRS. Accordingly, it was determined that the anger scores of the patients decreased as the YMRS score decreased. A statistically significant negative correlation was found between the patients' fear and the mean score of the YMRS. Accordingly, it was determined that the fear scores of the patients increased as the YMRS score decreased.Conclusions:Along with the results of this study, it has been revealed that the treatment response can be evaluated, and the severity of manic episodes can be determined by objectively evaluating the changes in 6 basic emotions in patients with computer vision techniques powered by machine learning.