Hama Tuankasfee, Alsaleh Mohanad M, Allery Freya, Choi Jung Won, Tomlinson Christopher, Wu Honghan, Lai Alvina, Pontikos Nikolas, Thygesen Johan H
Institute of Health Informatics, University College London, London, United Kingdom.
Department of Health Informatics, College of Applied Medical Sciences, Qassim University, Buraydah, Saudi Arabia.
J Med Internet Res. 2025 Mar 18;27:e57358. doi: 10.2196/57358.
The use of structured electronic health records in health care systems has grown rapidly. These systems collect huge amounts of patient information, including diagnosis codes representing temporal medical history. Sequential diagnostic information has proven valuable for predicting patient outcomes. However, the extent to which these types of data have been incorporated into deep learning (DL) models has not been examined.
This systematic review aims to describe the use of sequential diagnostic data in DL models, specifically to understand how these data are integrated, whether sample size improves performance, and whether the identified models are generalizable.
Relevant studies published up to May 15, 2023, were identified using 4 databases: PubMed, Embase, IEEE Xplore, and Web of Science. We included all studies using DL algorithms trained on sequential diagnosis codes to predict patient outcomes. We excluded review articles and non-peer-reviewed papers. We evaluated the following aspects in the included papers: DL techniques, characteristics of the dataset, prediction tasks, performance evaluation, generalizability, and explainability. We also assessed the risk of bias and applicability of the studies using the Prediction Model Study Risk of Bias Assessment Tool (PROBAST). We used the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) checklist to report our findings.
Of the 740 identified papers, 84 (11.4%) met the eligibility criteria. Publications in this area increased yearly. Recurrent neural networks (and their derivatives; 47/84, 56%) and transformers (22/84, 26%) were the most commonly used architectures in DL-based models. Most studies (45/84, 54%) presented their input features as sequences of visit embeddings. Medications (38/84, 45%) were the most common additional feature. Of the 128 predictive outcome tasks, the most frequent was next-visit diagnosis (n=30, 23%), followed by heart failure (n=18, 14%) and mortality (n=17, 13%). Only 7 (8%) of the 84 studies evaluated their models in terms of generalizability. A positive correlation was observed between training sample size and model performance (area under the receiver operating characteristic curve; P=.02). However, 59 (70%) of the 84 studies had a high risk of bias.
The application of DL for advanced modeling of sequential medical codes has demonstrated remarkable promise in predicting patient outcomes. The main limitation of this study was the heterogeneity of methods and outcomes. However, our analysis found that using multiple types of features, integrating time intervals, and including larger sample sizes were generally related to an improved predictive performance. This review also highlights that very few studies (7/84, 8%) reported on challenges related to generalizability and less than half (38/84, 45%) of the studies reported on challenges related to explainability. Addressing these shortcomings will be instrumental in unlocking the full potential of DL for enhancing health care outcomes and patient care.
PROSPERO CRD42018112161; https://tinyurl.com/yc6h9rwu.
结构化电子健康记录在医疗系统中的应用迅速增长。这些系统收集了大量患者信息，包括代表时间病史的诊断代码。连续诊断信息已被证明对预测患者预后有价值。然而，这类数据被纳入深度学习（DL）模型的程度尚未得到研究。
本系统评价旨在描述DL模型中连续诊断数据的使用情况，具体了解这些数据是如何整合的，样本量是否能提高性能，以及所识别的模型是否具有可推广性。
使用4个数据库（PubMed、Embase、IEEE Xplore和Web of Science）识别截至2023年5月15日发表的相关研究。我们纳入了所有使用基于连续诊断代码训练的DL算法来预测患者预后的研究。我们排除了综述文章和非同行评审论文。我们在纳入的论文中评估了以下方面：DL技术、数据集特征、预测任务、性能评估、可推广性和可解释性。我们还使用预测模型研究偏倚风险评估工具（PROBAST）评估了研究的偏倚风险和适用性。我们使用PRISMA（系统评价和Meta分析的首选报告项目）清单来报告我们的发现。
在740篇识别出的论文中，84篇（11.4%）符合纳入标准。该领域的出版物逐年增加。循环神经网络（及其衍生物；47/84，56%）和变换器（22/84，26%）是基于DL的模型中最常用的架构。大多数研究（45/84，54%）将其输入特征表示为就诊嵌入序列。药物（38/84，45%）是最常见的附加特征。在128项预测结果任务中，最常见的是下次就诊诊断（n = 30，23%），其次是心力衰竭（n = 18，14%）和死亡率（n = 17，13%）。84项研究中只有7项（8%）在可推广性方面评估了其模型。观察到训练样本量与模型性能（受试者操作特征曲线下面积；P =.02）之间存在正相关。然而，84项研究中有59项（70%）存在高偏倚风险。
DL在连续医疗代码的高级建模中的应用在预测患者预后方面显示出显著的前景。本研究的主要局限性是方法和结果的异质性。然而，我们的分析发现，使用多种类型的特征、整合时间间隔以及纳入更大的样本量通常与预测性能的提高有关。本综述还强调，很少有研究（7/84，8%）报告与可推广性相关的挑战，不到一半（38/84，45%）的研究报告与可解释性相关的挑战。解决这些不足将有助于释放DL在改善医疗结果和患者护理方面的全部潜力。
PROSPERO CRD42018112161；https://tinyurl.com/yc6h9rwu 。
