[论文解读] A generative, predictive model for menstrual cycle lengths that accounts for potential self-tracking artifacts in mobile health data
本文提出了一种分层的、生成式概率模型,用于预测月经周期长度,该模型显式考虑了移动健康(mHealth)数据中用户报告的追踪伪影——尤其是周期跳过现象。通过联合建模周期长度与跳过行为,该方法在来自186,000名用户的超过200万条周期数据上实现了最先进(state-of-the-art)的预测准确率,优于神经网络和汇总统计基线模型,同时支持周期进展过程中的在线、可解释性更新。
Mobile health (mHealth) apps such as menstrual trackers provide a rich source of self-tracked health observations that can be leveraged for health-relevant research. However, such data streams have questionable reliability since they hinge on user adherence to the app. Therefore, it is crucial for researchers to separate true behavior from self-tracking artifacts. By taking a machine learning approach to modeling self-tracked cycle lengths, we can both make more informed predictions and learn the underlying structure of the observed data. In this work, we propose and evaluate a hierarchical, generative model for predicting next cycle length based on previously-tracked cycle lengths that accounts explicitly for the possibility of users skipping tracking their period. Our model offers several advantages: 1) accounting explicitly for self-tracking artifacts yields better prediction accuracy as likelihood of skipping increases; 2) because it is a generative model, predictions can be updated online as a given cycle evolves, and we can gain interpretable insight into how these predictions change over time; and 3) its hierarchical nature enables modeling of an individual's cycle length history while incorporating population-level information. Our experiments using mHealth cycle length data encompassing over 186,000 menstruators with over 2 million natural menstrual cycles show that our method yields state-of-the-art performance against neural network-based and summary statistic-based baselines, while providing insights on disentangling menstrual patterns from self-tracking artifacts. This work can benefit users, mHealth app developers, and researchers in better understanding cycle patterns and user adherence.
研究动机与目标
- 解决因用户追踪不一致,特别是周期跳过,导致的mHealth数据不可靠问题。
- 开发一种预测模型,能够从移动健康数据中区分真实的月经周期模式与自我追踪伪影。
- 实现实时、在线预测更新,随着周期的推进动态整合当日信息。
- 通过分层贝叶斯框架将个体周期历史与群体先验信息相结合。
- 提升预测准确率,并提供关于用户行为与周期规律性的可解释洞察。
提出的方法
- 该模型采用分层贝叶斯生成框架,基于个体历史追踪数据联合估计周期长度与跳过概率。
- 其计算在当前周期天数和学习到的超参数条件下,对下一周期长度的后验预测分布。
- 通过 $ p(d^{*} | \hat{u}, d_i, d^{*} > d_{\text{current}}) $ 对可能的跳过状态进行积分,实现对不确定性的感知预测。
- 通过基于当前周期天数进行条件预测,实现在线更新,动态调整预测分布。
- 该模型使用正态分布和伯努利分布的混合分布,分别表示周期长度与跳过行为。
- 超参数从群体水平数据中学习,支持迁移学习并提升个体间的泛化能力。
实验结果
研究问题
- RQ1在mHealth数据中,考虑用户周期跳过如何提升月经周期长度预测的准确性?
- RQ2与神经网络或汇总统计基线相比,生成式模型是否能在真实世界mHealth周期数据上提供更优的预测性能?
- RQ3实时、逐日预测更新在多大程度上能提升周期预测的可解释性与可靠性?
- RQ4该模型的分层结构在数据有限的情况下,如何增强个性化能力并保持鲁棒性?
- RQ5周期长度预测准确率与用户追踪伪影(如跳过)概率之间存在何种关系?
主要发现
- 所提出的模型实现了最先进水平的预测准确率,在同一数据集上显著优于基于神经网络的模型(如CNN、RNN、LSTM)和汇总统计基线(均值、中位数)。
- 考虑周期跳过显著提升了预测准确率,尤其在跳过率较高的用户中表现更优,证明了模型对自我追踪伪影的鲁棒性。
- 该模型支持实时、在线预测更新,随着当前周期的推进,预测结果动态演化,提供动态且可解释的预测结果。
- 分层结构使模型能有效利用个体历史数据实现个性化建模,同时借助群体先验信息,提升数据稀疏用户的性能。
- 模型成功将真实的周期长度模式与追踪伪影分离,表现为预测准确率提升,并在不同用户子群体中保持一致的性能表现。
- 通过RMSE、MAE和中位数周期长度差异(median CLD)指标评估,结果表明该模型保持了高准确率,并更有效地捕捉了周期规律性,优于基线模型。
更好的研究,从现在开始
从阅读论文到最终审阅,大幅缩短您的研究时间。
无需绑定信用卡
本解读由 AI 生成,并经人工编辑审核。