Knitza Johannes, Janousek Lena, Kluge Felix, von der Decken Cay Benedikt, Kleinert Stefan, Vorbrüggen Wolfgang, Kleyer Arnd, Simon David, Hueber Axel J, Muehlensiepen Felix, Vuillerme Nicolas, Schett Georg, Eskofier Bjoern M, Welcker Martin, Bartz-Bazzanella Peter
Department of Internal Medicine 3, Friedrich-Alexander-University Erlangen-Nürnberg and Universitätsklinikum Erlangen, Erlangen, Germany.
Deutsches Zentrum für Immuntherapie (DZI), Friedrich-Alexander-University Erlangen-Nürnberg and Universitätsklinikum Erlangen, Erlangen, Germany.
Front Med (Lausanne). 2022 Jul 22;9:954056. doi: 10.3389/fmed.2022.954056. eCollection 2022.
Rheport is an online rheumatology referral system allowing automatic appointment triaging of new rheumatology patient referrals according to the respective probability of an inflammatory rheumatic disease (IRD). Previous research reported that Rheport was well accepted among IRD patients. Its accuracy was, however, limited, currently being based on an expert-based weighted sum score. This study aimed to evaluate whether machine learning (ML) models could improve this limited accuracy.
Data from a national rheumatology registry (RHADAR) was used to train and test nine different ML models to correctly classify IRD patients. Diagnostic performance was compared of ML models and the current algorithm was compared using the area under the receiver operating curve (AUROC). Feature importance was investigated using shapley additive explanation (SHAP).
A complete data set of 2265 patients was used to train and test ML models. 30.5% of patients were diagnosed with an IRD, 69.3% were female. The diagnostic accuracy of the current Rheport algorithm (AUROC of 0.534) could be improved with all ML models, (AUROC ranging between 0.630 and 0.737). Targeting a sensitivity of 90%, the logistic regression model could double current specificity (17% vs. 33%). Finger joint pain, inflammatory marker levels, psoriasis, symptom duration and female sex were the five most important features of the best performing logistic regression model for IRD classification.
In summary, ML could improve the accuracy of a currently used rheumatology online referral system. Including further laboratory parameters and enabling individual feature importance adaption could increase accuracy and lead to broader usage.
Rheport是一个在线风湿病转诊系统，可根据炎性风湿性疾病（IRD）的各自概率对新的风湿病患者转诊进行自动预约分类。先前的研究报告称，Rheport在IRD患者中广受认可。然而，其准确性有限，目前基于专家加权总分。本研究旨在评估机器学习（ML）模型是否可以提高这种有限的准确性。
使用来自国家风湿病登记处（RHADAR）的数据训练和测试九个不同的ML模型，以正确分类IRD患者。比较了ML模型的诊断性能，并使用受试者工作特征曲线下面积（AUROC）比较了当前算法。使用Shapley加性解释（SHAP）研究特征重要性。
使用2265例患者的完整数据集训练和测试ML模型。30.5%的患者被诊断为IRD，69.3%为女性。所有ML模型均可提高当前Rheport算法的诊断准确性（AUROC为0.534），（AUROC范围在0.630至0.737之间）。以90%的灵敏度为目标，逻辑回归模型可使当前特异性提高一倍（17%对33%）。指关节疼痛、炎症标志物水平、银屑病、症状持续时间和女性性别是最佳性能逻辑回归模型用于IRD分类的五个最重要特征。
总之，ML可以提高当前使用的风湿病在线转诊系统的准确性。纳入更多实验室参数并实现个体特征重要性调整可提高准确性并导致更广泛的应用。
