Machine learning models can support an individualized approach in the choice of bDMARDs. We developed prediction models for 5 different bDMARDs using machine learning methods based on patient data derived from the Austrian Biologics Registry (BioReg). Data from 1397 patients and 19 variables with at least 100 treat-to-target (t2t) courses per drug were derived from the BioReg biologics registry. Different machine learning algorithms were trained to predict the risk of ineffectiveness for each bDMARD within the first 26 weeks. Cross-validation and hyperparameter optimization were applied to generate the best models. Model quality was assessed by area under the receiver operating characteristic (AUROC). Using explainable AI (XAI), risk-reducing and risk-increasing factors were extracted. The best models per drug achieved an AUROC score of the following: abatacept, 0.66 (95% CI, 0.54–0.78); adalimumab, 0.70 (95% CI, 0.68–0.74); certolizumab, 0.84 (95% CI, 0.79–0.89); etanercept, 0.68 (95% CI, 0.55–0.87); tocilizumab, 0.72 (95% CI, 0.69–0.77). The most risk-increasing variables were visual analytic scores (VAS) for abatacept and etanercept and co-therapy with glucocorticoids for adalimumab. Dosage was the most important variable for certolizumab and associated with a lower risk of non-response. Some variables, such as gender and rheumatoid factor (RF), showed opposite impacts depending on the bDMARD. Ineffectiveness of biological drugs could be predicted with promising accuracy. Interestingly, individual parameters were found to be associated with drug responses in different directions, indicating highly complex interactions. Machine learning can be of help in the decision-process by disentangling these relations.

中文翻译：

---

使用机器学习和可解释的人工智能方法预测生物药物的无效性：来自奥地利生物登记处 BioReg 的数据

机器学习模型可以支持选择 bDMARD 的个性化方法。我们根据来自奥地利生物制品注册中心 (BioReg) 的患者数据，使用机器学习方法开发了 5 种不同 bDMARD 的预测模型。来自 1397 名患者和 19 个变量的数据，每种药物至少有 100 个目标治疗 (t2t) 疗程，均来自 BioReg 生物制剂注册中心。经过训练不同的机器学习算法来预测每种 bDMARD 在前 26 周内无效的风险。应用交叉验证和超参数优化来生成最佳模型。模型质量通过接受者操作特征下的面积（AUROC）进行评估。使用可解释的人工智能（XAI）提取风险降低和风险增加因素。每种药物的最佳模型达到以下 AUROC 评分：阿巴西普，0.66（95% CI，0.54-0.78）；阿达木单抗，0.70（95% CI，0.68–0.74）；赛妥珠单抗，0.84（95% CI，0.79–0.89）；依那西普，0.68（95% CI，0.55–0.87）；托珠单抗，0.72（95% CI，0.69-0.77）。风险增加最多的变量是阿巴西普和依那西普的视觉分析评分（VAS）以及阿达木单抗与糖皮质激素的联合治疗。剂量是赛妥珠单抗最重要的变量，与较低的无反应风险相关。一些变量，例如性别和类风湿因子 (RF)，根据 bDMARD 显示出相反的影响。可以非常准确地预测生物药物的无效性。有趣的是，发现各个参数与不同方向的药物反应相关，表明存在高度复杂的相互作用。机器学习可以通过理清这些关系来帮助决策过程。