Department of Anesthesiology, Perioperative and Pain Medicine, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA.
Department of Obstetrics and Gynecology, University of Washington, Seattle, WA, USA.
J Biomed Inform. 2024 Aug;156:104688. doi: 10.1016/j.jbi.2024.104688. Epub 2024 Jul 11.
Survival analysis is widely utilized in healthcare to predict the timing of disease onset. Traditional methods of survival analysis are usually based on Cox Proportional Hazards model and assume proportional risk for all subjects. However, this assumption is rarely true for most diseases, as the underlying factors have complex, non-linear, and time-varying relationships. This concern is especially relevant for pregnancy, where the risk for pregnancy-related complications, such as preeclampsia, varies across gestation. Recently, deep learning survival models have shown promise in addressing the limitations of classical models, as the novel models allow for non-proportional risk handling, capturing nonlinear relationships, and navigating complex temporal dynamics.
We present a methodology to model the temporal risk of preeclampsia during pregnancy and investigate the associated clinical risk factors. We utilized a retrospective dataset including 66,425 pregnant individuals who delivered in two tertiary care centers from 2015 to 2023. We modeled the preeclampsia risk by modifying DeepHit, a deep survival model, which leverages neural network architecture to capture time-varying relationships between covariates in pregnancy. We applied time series k-means clustering to DeepHit's normalized output and investigated interpretability using Shapley values.
We demonstrate that DeepHit can effectively handle high-dimensional data and evolving risk hazards over time with performance similar to the Cox Proportional Hazards model, achieving an area under the curve (AUC) of 0.78 for both models. The deep survival model outperformed traditional methodology by identifying time-varied risk trajectories for preeclampsia, providing insights for early and individualized intervention. K-means clustering resulted in patients delineating into low-risk, early-onset, and late-onset preeclampsia groups-notably, each of those has distinct risk factors.
This work demonstrates a novel application of deep survival analysis in time-varying prediction of preeclampsia risk. Our results highlight the advantage of deep survival models compared to Cox Proportional Hazards models in providing personalized risk trajectory and demonstrating the potential of deep survival models to generate interpretable and meaningful clinical applications in medicine.
生存分析在医疗保健中被广泛用于预测疾病发作的时间。传统的生存分析方法通常基于 Cox 比例风险模型，并假设所有受试者的风险比例相同。然而，对于大多数疾病来说，这种假设很少成立，因为潜在因素具有复杂的、非线性的和时变的关系。这种情况在妊娠中尤为重要，因为妊娠相关并发症（如子痫前期）的风险在妊娠期间会发生变化。最近，深度学习生存模型在解决经典模型的局限性方面显示出了前景，因为新模型允许处理非比例风险，捕捉非线性关系，并处理复杂的时间动态。
我们提出了一种方法来对妊娠期间子痫前期的时间风险进行建模，并研究了相关的临床风险因素。我们利用了一个包括 2015 年至 2023 年在两家三级保健中心分娩的 66425 名孕妇的回顾性数据集。我们通过修改 DeepHit 来对子痫前期风险进行建模，DeepHit 是一种深度生存模型，利用神经网络架构来捕获妊娠期间协变量随时间的变化关系。我们应用时间序列 k-means 聚类对 DeepHit 的归一化输出进行分析，并使用 Shapley 值进行解释。
我们证明 DeepHit 可以有效地处理高维数据和随时间演变的风险危害，性能与 Cox 比例风险模型相似，两种模型的曲线下面积（AUC）均为 0.78。深度生存模型通过识别子痫前期的时变风险轨迹，提供早期和个体化干预的见解，优于传统方法。k-means 聚类将患者分为低风险、早期发作和晚期发作子痫前期组——值得注意的是，每组都有不同的风险因素。
这项工作展示了深度生存分析在子痫前期风险的时变预测中的新应用。我们的结果突出了深度生存模型相对于 Cox 比例风险模型在提供个性化风险轨迹方面的优势，并展示了深度生存模型在医学中生成可解释和有意义的临床应用的潜力。
