Survival analysis deals with the expected duration of time until one or more events of interest occur. Time to the event of interest may be unobserved, a phenomenon commonly known as right censoring, which renders the analysis of these data challenging. Over the years, machine learning algorithms have been developed and adapted to right-censored data. Neural networks have been repeatedly employed to build clinical prediction models in healthcare with a focus on cancer and cardiology. We present the first ever attempt at a large-scale review of survival neural networks (SNNs) with prognostic factors for clinical prediction in medicine. This work provides a comprehensive understanding of the literature (24 studies from 1990 to August 2021, global search in PubMed). Relevant manuscripts are classified as methodological/technical (novel methodology or new theoretical model; 13 studies) or applications (11 studies). We investigate how researchers have used neural networks to fit survival data for prediction. There are two methodological trends: either time is added as part of the input features and a single output node is specified, or multiple output nodes are defined for each time interval. A critical appraisal of model aspects that should be designed and reported more carefully is performed. We identify key characteristics of prediction models (i.e., number of patients/predictors, evaluation measures, calibration), and compare ANN’s predictive performance to the Cox proportional hazards model. The median sample size is 920 patients, and the median number of predictors is 7. Major findings include poor reporting (e.g., regarding missing data, hyperparameters) as well as inaccurate model development/validation. Calibration is neglected in more than half of the studies. Cox models are not developed to their full potential and claims for the performance of SNNs are exaggerated. Light is shed on the current state of art of SNNs in medicine with prognostic factors. Recommendations are made for the reporting of clinical prediction models. Limitations are discussed, and future directions are proposed for researchers who seek to develop existing methodology.

中文翻译：

---

使用预后因素进行医学生存预测的神经网络：回顾和批判性评估

生存分析处理在发生一个或多个感兴趣的事件之前的预期持续时间。可能无法观察到感兴趣事件的时间，这种现象通常称为右删失，这使得对这些数据的分析具有挑战性。多年来，机器学习算法已被开发并适用于右删失数据。神经网络已被反复用于建立医疗保健领域的临床预测模型，重点是癌症和心脏病学。我们首次尝试对具有预后因素的生存神经网络 (SNN) 进行大规模审查，以用于医学临床预测。这项工作提供了对文献的全面理解（1990 年至 2021 年 8 月的 24 项研究，PubMed 中的全球搜索）。相关手稿分为方法论/技术（新方法或新理论模型；13 项研究）或应用（11 项研究）。我们调查研究人员如何使用神经网络来拟合生存数据以进行预测。有两种方法论趋势：将时间作为输入特征的一部分添加并指定单个输出节点，或者为每个时间间隔定义多个输出节点。对应该更仔细地设计和报告的模型方面进行严格的评估。我们确定了预测模型的关键特征（即患者/预测变量的数量、评估措施、校准），并将 ANN 的预测性能与 Cox 比例风险模型进行比较。样本量中位数为 920 名患者，预测变量的中位数为 7。主要发现包括糟糕的报告（例如，关于缺失数据、超参数）以及不准确的模型开发/验证。超过一半的研究忽略了校准。Cox 模型没有充分发挥其潜力，并且夸大了 SNN 的性能。揭示了具有预后因素的医学中 SNN 的当前状态。对临床预测模型的报告提出了建议。讨论了局限性，并为寻求开发现有方法的研究人员提出了未来的方向。揭示了具有预后因素的医学中 SNN 的当前状态。对临床预测模型的报告提出了建议。讨论了局限性，并为寻求开发现有方法的研究人员提出了未来的方向。揭示了具有预后因素的医学中 SNN 的当前状态。对临床预测模型的报告提出了建议。讨论了局限性，并为寻求开发现有方法的研究人员提出了未来的方向。