Hsu Yu Cheng, Ye Zhiyu, Dai Lisha, Jing Yaqin, Tsui Kwok-Leung, Yip Paul S F, Li Wentian, Zhang Qingpeng
School of Data Science, City University of Hong Kong, Kowloon, Hong Kong SAR, China.
School of Education Research, China University of Geosciences, Wuhan, China.
Front Psychiatry. 2022 Jul 28;13:918999. doi: 10.3389/fpsyt.2022.918999. eCollection 2022.
Using Minnesota Multiphasic Personality Inventory-2 (MMPI-2) clinical scales to evaluate clinical symptoms in schizophrenia is a well-studied topic. Nonetheless, research focuses less on how these clinical scales interact with each other.
Investigates the network structure and interaction of the MMPI-2 clinical scales between healthy individuals and patients with schizophrenia through the Bayesian network.
Data was collected from Wuhan Psychiatric Hospital from March 2008 to May 2018. A total of 714 patients with schizophrenia and 714 healthy subjects were identified through propensity score matching according to the criteria of the International Classification of Diseases (ICD-11). Separated MMPI-2 clinical scales Bayesian networks were built for healthy subjects and patients with schizophrenia, respectively.
The Bayesian network showed that the lower 7 scale was a consequence of the correlation between the lower 2 scale and the greater 8 scale. A solely lower 7 scale does yield neither a lower 2 scale nor a higher 8 scale. The proposed method showed 72% of accuracy with 78% area under the ROC curve (AUC), similar to the previous studies.
The proposed method simplified the continuous Bayesian network to predict binary outcomes, including other categorical data is not explored. Besides, the participants might only represent an endemic as they come from a single hospital.
This study identified MMPI-2 clinical scales correlation and built separated Bayesian networks to investigate the difference between patients with schizophrenia and healthy people. These differences may contribute to a better understanding of the clinical symptoms of schizophrenia and provide medical professionals with new perspectives for diagnosis.
使用明尼苏达多相人格调查表第二版（MMPI - 2）临床量表评估精神分裂症的临床症状是一个研究充分的课题。然而，研究较少关注这些临床量表之间是如何相互作用的。
通过贝叶斯网络研究健康个体与精神分裂症患者之间MMPI - 2临床量表的网络结构及相互作用。
收集2008年3月至2018年5月武汉市精神病医院的数据。根据国际疾病分类（ICD - 11）标准，通过倾向得分匹配确定了714例精神分裂症患者和714名健康受试者。分别为健康受试者和精神分裂症患者构建了独立的MMPI - 2临床量表贝叶斯网络。
贝叶斯网络显示，7低分是2低分与8高分之间相关性的结果。单独的7低分既不会产生2低分也不会产生8高分。所提出的方法显示准确率为72%，ROC曲线下面积（AUC）为78%，与先前的研究相似。
所提出的方法简化了连续贝叶斯网络以预测二元结果，未探索包括其他分类数据在内的情况。此外，参与者可能仅代表来自单一医院的地方病例。
本研究确定了MMPI - 2临床量表的相关性，并构建了独立的贝叶斯网络来研究精神分裂症患者与健康人之间的差异。这些差异可能有助于更好地理解精神分裂症的临床症状，并为医学专业人员提供新的诊断视角。
