| Popis: |
Background: Early identification of bipolar disorder (BD) from major depressive disorder (MDD) is difficult since no tools available to estimate the risk of BD. This study aimed to develop and validate a model of oxidative stress injury for predicting BD. Methods: Data of 1,252 BD and 1,359 MDD patients were collected, including 64 MDD patients who were identified as converting to BD from 2009 through 2018. 30 variables from a randomly selected subsample of 1,827 (70%) patients were used to develop the model, including age, sex, oxidative stress markers (uric acid, bilirubin, albumin, prealbumin), sex hormones, cytokines, thyroid and liver function, glycolipid metabolism, etc. Univariate analyses and the Least Absolute Shrinkage and Selection Operator (LASSO) were applied for data dimension reduction and variable selection. Multivariable logistic regression was used to construct BIOS model on nomogram. Internal validation assessed in the remaining 784 patients (30%), and independent external validation done by 3,797 matched patients from five other hospitals in China. Results: 10 predictors, mainly the oxidative stress markers, were shown on nomogram. BIOS model showed good discrimination in the training sample, with AUC of 75.1% (95% CI: 72.9%~77.3%), sensitivity of 0.66, and specificity of 0.73. The discrimination was well both at internal validation (AUC 72.1%, 68.6~75.6%) and external validation (AUC 65.7%, 63.9~67.5%). Conclusion: A nomogram centered on oxidative stress injury could help individualized prediction of BD. For better real-world practice, a set of measurements especially on oxidative stress markers should be emphasized using big data in psychiatry. Funding: China Key R&D Program (2016YFC1307100), the NSFC (81930033, 81771465, 91232719), SMHC-CRC (CRC2018DSJ01-1), and the Innovative Research Team of High-level Local Universities in Shanghai. Declaration of Interest: None to declare. Ethical Approval: The study was registered at International Clinical Trials Registry Platform with the number of NCT03949218. Ethical issue was approved by the SMHC Institution Review Board (IRB, number of 2019-15R) and the informed consent requirement was omitted according to relevant research. |
