Objective

Selective serotonin reuptake inhibitors (SSRIs) are suggested as the first-line treatment for patients with major depressive disorder (MDD), but the remission rate is unsatisfactory. We aimed to establish machine learning models and explore variables available at baseline to predict the 8-week outcome among patients taking SSRIs.

Methods

Data from 400 patients were used to build machine learnings. The last observation carried forward approach was used to determine the remitter/non-remitter status of the patients at week 8. Using least absolute shrinkage and selection operator (LASSO) to select features, we built 4 different machine learning algorithms including gradient boosting decision tree, support vector machine (SVM), random forests, and logistic regression with five-fold cross-validation. Then, we adopted Shapley additive explanations (SHAP) values to interpret the model output.

Results

The remission rate is 67.8%. We obtained 78 features from the baseline characteristics, including 25 sociodemographic characteristics, 31 clinical features, 15 psychological traits and 7 neurocognitive functions, and 13 of these features were selected to establish SVM. The accuracy of the SVM prediction is 74.49%, reaching an average area under the curve of 0.734±0.043. The sensitivity is 0.899±0.038 with a positive predictive value of 0.776±0.028. The specificity is 0.422±0.091 with a negative predictive value of 0.674±0.086. According to the SHAP values, neurocognitive functions and anxiety and hypochondriasis symptoms were important predictors.

Conclusion

Our study supports the utilization of machine learning approaches with inexpensive and highly accessible variables to accurately predict the 8-week treatment outcome of SSRIs in patients with MDD.

中文翻译：

---

机器学习预测急性期选择性5-羟色胺再摄取抑制剂治疗后抑郁症患者的临床缓解

客观的

选择性5-羟色胺再摄取抑制剂（SSRIs）被建议作为重度抑郁症（MDD）患者的一线治疗，但缓解率并不令人满意。我们旨在建立机器学习模型并探索基线可用的变量，以预测服用SSRI的患者的8周结局。

方法

来自400位患者的数据被用于构建机器学习。最后的观察结转方法用于确定第8周患者的缓解/不缓解状态。使用最小绝对收缩和选择算子（LASSO）来选择特征，我们构建了4种不同的机器学习算法，包括梯度提升决策树，支持向量机（SVM），随机森林和具有五项交叉验证的逻辑回归。然后，我们采用Shapley加性解释（SHAP）值来解释模型输出。

结果

缓解率为67.8％。我们从基线特征中获得了78个特征，包括25个社会人口统计学特征，31个临床特征，15个心理特征和7个神经认知功能，并从这些特征中选择了13个来建立SVM。SVM预测的准确性为74.49％，在曲线下的平均面积达到0.734±0.043。灵敏度为0.899±0.038，阳性预测值为0.776±0.028。特异性为0.422±0.091，阴性预测值为0.674±0.086。根据SHAP值，神经认知功能以及焦虑和软骨病症状是重要的预测指标。

结论

我们的研究支持使用具有廉价且易于访问的变量的机器学习方法来准确预测MDD患者SSRI的8周治疗结果。