Gandrup Julie, Selby David A, Dixon William G
Centre for Epidemiology Versus Arthritis, University of Manchester, Manchester, United Kingdom.
Department of Computer Science, Technische Universität Kaiserslautern, Kaiserslautern, Germany.
JMIR Form Res. 2024 May 14;8:e50679. doi: 10.2196/50679.
The ability to predict rheumatoid arthritis (RA) flares between clinic visits based on real-time, longitudinal patient-generated data could potentially allow for timely interventions to avoid disease worsening.
This exploratory study aims to investigate the feasibility of using machine learning methods to classify self-reported RA flares based on a small data set of daily symptom data collected on a smartphone app.
Daily symptoms and weekly flares reported on the Remote Monitoring of Rheumatoid Arthritis (REMORA) smartphone app from 20 patients with RA over 3 months were used. Predictors were several summary features of the daily symptom scores (eg, pain and fatigue) collected in the week leading up to the flare question. We fitted 3 binary classifiers: logistic regression with and without elastic net regularization, a random forest, and naive Bayes. Performance was evaluated according to the area under the curve (AUC) of the receiver operating characteristic curve. For the best-performing model, we considered sensitivity and specificity for different thresholds in order to illustrate different ways in which the predictive model could behave in a clinical setting.
The data comprised an average of 60.6 daily reports and 10.5 weekly reports per participant. Participants reported a median of 2 (IQR 0.75-4.25) flares each over a median follow-up time of 81 (IQR 79-82) days. AUCs were broadly similar between models, but logistic regression with elastic net regularization had the highest AUC of 0.82. At a cutoff requiring specificity to be 0.80, the corresponding sensitivity to detect flares was 0.60 for this model. The positive predictive value (PPV) in this population was 53%, and the negative predictive value (NPV) was 85%. Given the prevalence of flares, the best PPV achieved meant only around 2 of every 3 positive predictions were correct (PPV 0.65). By prioritizing a higher NPV, the model correctly predicted over 9 in every 10 non-flare weeks, but the accuracy of predicted flares fell to only 1 in 2 being correct (NPV and PPV of 0.92 and 0.51, respectively).
Predicting self-reported flares based on daily symptom scorings in the preceding week using machine learning methods was feasible. The observed predictive accuracy might improve as we obtain more data, and these exploratory results need to be validated in an external cohort. In the future, analysis of frequently collected patient-generated data may allow us to predict flares before they unfold, opening opportunities for just-in-time adaptative interventions. Depending on the nature and implication of an intervention, different cutoff values for an intervention decision need to be considered, as well as the level of predictive certainty required.
基于实时、纵向的患者生成数据来预测门诊就诊期间类风湿关节炎（RA）病情发作的能力，有可能实现及时干预，以避免疾病恶化。
本探索性研究旨在探讨使用机器学习方法，根据在智能手机应用程序上收集的每日症状数据的小数据集，对自我报告的RA病情发作进行分类的可行性。
使用了类风湿关节炎远程监测（REMORA）智能手机应用程序上20名RA患者在3个月内报告的每日症状和每周病情发作情况。预测指标是在病情发作问题前一周收集的每日症状评分的几个汇总特征（如疼痛和疲劳）。我们拟合了3个二元分类器：带和不带弹性网络正则化的逻辑回归、随机森林和朴素贝叶斯。根据接收器操作特征曲线的曲线下面积（AUC）评估性能。对于表现最佳的模型，我们考虑了不同阈值下的敏感性和特异性，以说明预测模型在临床环境中的不同表现方式。
数据包括每位参与者平均60.6份每日报告和10.5份每周报告。参与者在中位随访时间81天（四分位间距79 - 82天）内，每人报告的病情发作中位数为2次（四分位间距0.75 - 4.25次）。各模型的AUC大致相似，但带弹性网络正则化的逻辑回归的AUC最高，为0.82。在要求特异性为0.80的临界值下，该模型检测病情发作的相应敏感性为0.60。该人群中的阳性预测值（PPV）为53%，阴性预测值（NPV）为85%。考虑到病情发作的患病率，达到的最佳PPV意味着每3个阳性预测中只有约2个是正确的（PPV为0.65）。通过优先考虑更高的NPV，该模型在每10个非病情发作周中能正确预测超过9个，但预测病情发作的准确率降至仅2个中有1个正确（NPV和PPV分别为0.92和0.51）。
使用机器学习方法根据前一周的每日症状评分预测自我报告的病情发作是可行的。随着我们获得更多数据，观察到的预测准确性可能会提高，并且这些探索性结果需要在外部队列中进行验证。未来，对频繁收集的患者生成数据的分析可能使我们能够在病情发作前进行预测，为即时适应性干预创造机会。根据干预的性质和影响，需要考虑用于干预决策的不同临界值，以及所需的预测确定性水平。
