Very few data are available on predictors of minimal disease activity (MDA) in patients with recent-onset psoriatic arthritis (PsA). Such data are crucial, since the therapeutic measures used to change the adverse course of PsA are more likely to succeed if we intervene early. In the present study, we used predictive models based on machine learning to detect variables associated with achieving MDA in patients with recent-onset PsA. We performed a multicenter observational prospective study (2-year follow-up, regular annual visits). The study population comprised patients aged ≥18 years who fulfilled the CASPAR criteria and less than 2 years since the onset of symptoms. The dataset contained data for the independent variables from the baseline visit and from follow-up visit number 1. These were matched with the outcome measures from follow-up visits 1 and 2, respectively. We trained a random forest–type machine learning algorithm to analyze the association between the outcome measure and the variables selected in the bivariate analysis. In order to understand how the model uses the variables to make its predictions, we applied the SHAP technique. We used a confusion matrix to visualize the performance of the model. The sample comprised 158 patients. 55.5% and 58.3% of the patients had MDA at the first and second follow-up visit, respectively. In our model, the variables with the greatest predictive ability were global pain, impact of the disease (PsAID), patient global assessment of disease, and physical function (HAQ-Disability Index). The percentage of hits in the confusion matrix was 85.94%. A key objective in the management of PsA should be control of pain, which is not always associated with inflammatory burden, and the establishment of measures to better control the various domains of PsA.

中文翻译：

---

新发银屑病关节炎患者的最小疾病活动度 (MDA)：基于机器学习的预测模型

很少有关于新发银屑病关节炎 (PsA) 患者最小疾病活动 (MDA) 预测因子的数据。这些数据至关重要，因为如果我们及早干预，用于改变 PsA 不良过程的治疗措施更有可能成功。在本研究中，我们使用基于机器学习的预测模型来检测与新发 PsA 患者实现 MDA 相关的变量。我们进行了一项多中心观察性前瞻性研究（2 年随访，每年定期访问）。研究人群包括年龄≥18 岁且符合 CASPAR 标准且症状出现时间不足 2 年的患者。数据集包含来自基线访问和后续访问 1 的自变量数据。这些分别与随访 1 和 2 的结果测量相匹配。我们训练了一种随机森林类型的机器学习算法来分析结果测量与双变量分析中选择的变量之间的关联。为了了解模型如何使用变量进行预测，我们应用了 SHAP 技术。我们使用混淆矩阵来可视化模型的性能。样本包括 158 名患者。第一次和第二次随访时分别有 55.5% 和 58.3% 的患者出现 MDA。在我们的模型中，具有最大预测能力的变量是整体疼痛、疾病影响 (PsAID)、患者对疾病的整体评估和身体功能 (HAQ-残疾指数)。混淆矩阵中的命中率为 85.94%。