Hänsel Katrin, Lin Inna Wanyin, Sobolev Michael, Muscat Whitney, Yum-Chan Sabrina, De Choudhury Munmun, Kane John M, Birnbaum Michael L
The Zucker Hillside Hospital, Northwell Health, Glen Oaks, NY, United States.
Feinstein Institute for Medical Research, Northwell Health, Manhasset, NY, United States.
Front Psychiatry. 2021 Aug 16;12:691327. doi: 10.3389/fpsyt.2021.691327. eCollection 2021.
Prior research has successfully identified linguistic and behavioral patterns associated with schizophrenia spectrum disorders (SSD) from user generated social media activity. Few studies, however, have explored the potential for image analysis to inform psychiatric care for individuals with SSD. Given the popularity of image-based platforms, such as Instagram, investigating user generated image data could further strengthen associations between social media activity and behavioral health. We collected 11,947 Instagram posts across 68 participants (mean age = 23.6; 59% male) with schizophrenia spectrum disorders (SSD; = 34) and healthy volunteers (HV; = 34). We extracted image features including color composition, aspect ratio, and number of faces depicted. Additionally, we considered social connections and behavioral features. We explored differences in usage patterns between SSD and HV participants. Individuals with SSD posted images with lower saturation ( = 0.033) and lower colorfulness ( = 0.005) compared to HVs, as well as images showing fewer faces on average ( = 1.5, = 2.4, < 0.001). Further, individuals with SSD demonstrated a lower ratio of followers to following compared to HV participants ( = 0.025). Differences in uploaded images and user activity on Instagram were identified in individuals with SSD. These differences highlight potential digital biomarkers of SSD from Instagram data.
先前的研究已成功地从用户生成的社交媒体活动中识别出与精神分裂症谱系障碍（SSD）相关的语言和行为模式。然而，很少有研究探讨图像分析在为患有SSD的个体提供精神科护理方面的潜力。鉴于基于图像的平台（如Instagram）很受欢迎，研究用户生成的图像数据可以进一步加强社交媒体活动与行为健康之间的关联。我们收集了68名参与者（平均年龄 = 23.6岁；59%为男性）的11947条Instagram帖子，这些参与者包括患有精神分裂症谱系障碍（SSD；n = 34）的患者和健康志愿者（HV；n = 34）。我们提取了图像特征，包括色彩构成、宽高比和所描绘的面部数量。此外，我们还考虑了社交联系和行为特征。我们探讨了SSD患者和HV参与者在使用模式上的差异。与HV相比，患有SSD的个体发布的图像饱和度较低（p = 0.033）、色彩鲜艳度较低（p = 0.005），并且平均显示的面部较少（分别为1.5和2.4，p < 0.001）。此外，与HV参与者相比，患有SSD的个体的关注者与被关注者比例较低（p = 0.025）。在患有SSD的个体中发现了Instagram上上传图像和用户活动的差异。这些差异突出了来自Instagram数据的SSD潜在数字生物标志物。
