A computational approach to early sepsis detection

早期脓毒症检测的计算方法

• 批准号: 9557664
• 负责人: Ritankar Das
• 金额: $ 31.08万
• 依托单位: DASCENA, INC.
• 依托单位国家: 美国
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-04-01 至 2019-09-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9557664
• 关键词: Address; Age; Algorithms; Area; Cessation of life; Classification; Clinical; Clinical Decision Support Systems; Collection; Custom; Data; Data Collection; Data Set; Detection; Discrimination; Drops; Early Diagnosis; Early Intervention; Future; Gold; Healthcare; Healthcare Systems; Hour; Image; Immune response; Institution; Knowledge; Learning; Length; Machine Learning; Medical; Methods; Multicenter Studies; Nature; Patient-Focused Outcomes; Patients; Performance; Psychological Transfer; Receiver Operating Characteristics; Research; Residual state; Risk; SCAP2 gene; Sensitivity and Specificity; Sepsis; Septic Shock; Severities; Side; Site; Small Business Innovation Research Grant; Source; Survival Rate; System; Techniques; Testing; Training; Validation; Work; base; clinical data warehouse; clinical decision support; clinical research site; cost; data acquisition; experimental study; improved; insight; learning strategy; mortality; performance site; portability; prospective; screening; septic; septic patients; success; support tools

Abstract Significance: In this SBIR project, we propose to improve the performance of InSight, a machine-learning- based sepsis screening system, in situations of limited training data from the target clinical site. The proposed work will make possible prospective clinical deployments to sites which are smaller or lack clinical data repositories, by significantly reducing the amount of training data necessary down to a few weeks of clinical observation. Classically, a machine-learning-based system like InSight requires complete retraining for each new clinical setting, in turn requiring a new and large collection of data from each target deployment site. We will circumvent this requirement via transfer learning techniques, which transfer knowledge acquired previously in a source clinical setting to a new, target setting. Research Questions: Which transfer learning methods and paired classification algorithms are most suitable for use with InSight, requiring minimal target-site training data while maintaining strong performance? Are these methods and algorithms robust across the several common sepsis-spectrum definitions? Prior Work: We have developed InSight using the MIMIC-III retrospective data set, on which it attains an area under the receiver operating characteristic curve (AUROC) of 0.88 for sepsis detection, and 0.74 for 4-hour early sepsis prediction. We have also conducted pilot transfer learning ≥ experiments in a different clinical task, mortality forecasting, in which transfer learning yields a 10-fold reduction in the amount of target-site training data required to achieve AUROC 0.80. Specific Aims: Aim 1 - to implement and assess side-by-side four diverse transfer learning methods for a retrospective clinical sepsis prediction task, where the source data set is MIMIC-III and the simulated clinical target is a data set drawn from UCSF. Aim 2 - to determine which among the best methods from Aim 1 also provide robust performance when applied to two additional sepsis-spectrum gold standards. Methods: We will prepare implementations of transfer learning methods which use instance transfer, residual learning and/or feature augmentation, kernel length scale transfer, and feature transfer. We will test these methods with applicable classifiers on subsets of the UCSF set, using cross-validation and quantifying discrimination performance in terms of AUROC. The best method/classifier pairs will require no more than 30 examples of septic patients from the target set and attain AUROC superiorities of 0.05 in 0- and 4-hour pre-onset sepsis prediction/detection, relative to the best tested alternative screening systems (Aim 1). The top three pairs will then be tested for robustness to gold standard choice, using septic shock (0- and 4-hour) and SIRS-based sepsis (0-hour) gold standards; in these tests, at least one pair must again attain 0.05 margin of superiority in AUROC versus the alternative screening systems (Aim 2). Future Directions: The results of these experiments will enable InSight to be robustly deployed to diverse clinical sites, yielding high performance without the need for extensive target-site data acquisition.

摘要 意义：在这个SBIR项目中，我们建议提高机器学习InSight的性能， 基于败血症筛查系统，在目标临床研究中心的培训数据有限的情况下。拟议 这项工作将使规模较小或缺乏临床数据的研究中心的前瞻性临床部署成为可能 存储库，通过将必要的训练数据量显著减少到几周的临床 观察.传统上，像InSight这样基于机器学习的系统需要对每个人进行完全的再培训。 新的临床环境，进而需要从每个目标部署部位收集新的大量数据。我们 我将通过迁移学习技术来规避这一要求，迁移学习技术将以前获得的知识 从一个原始的临床环境转变为一个新的目标环境。研究问题：哪些转移学习方法和 成对分类算法最适合与InSight配合使用，需要最少的目标部位训练数据 同时保持强劲的业绩？这些方法和算法在几种常见的 败血症谱的定义？之前的工作：我们使用MIMIC-III回顾性数据开发了InSight 组，在此基础上，脓毒症的受试者工作特征曲线下面积（AUROC）为0.88 检测和0.74用于4小时早期脓毒症预测。我们还进行了试点迁移学习 ≥ 在一个不同的临床任务，死亡率预测，其中迁移学习产生10倍的实验， 减少达到AUROC 0.80所需的目标部位训练数据量。具体目标：目标1 - 实施和评估并行四种不同的迁移学习方法，用于回顾性临床脓毒症 预测任务，其中源数据集是MIMIC-III，模拟临床目标是绘制的数据集 来自UCSF目标2 -确定目标1中的哪些最佳方法也能提供稳健的性能 当应用于两个额外的败血症光谱金标准时。方法：我们将准备 迁移学习方法使用实例迁移、残差学习和/或特征增强、内核 长度比例转换和特征转换。我们将测试这些方法与适用的分类器的子集 UCSF集，使用交叉验证和量化区分性能的AUROC。最好的 方法/分类器对将需要来自目标集合的不超过30个脓毒症患者的例子， 相对于最佳测试，AUROC在0小时和4小时发作前脓毒症预测/检测中的优势为0.05 替代筛选系统（目标1）。然后将测试前三对对金标准的稳健性 选择，使用脓毒性休克（0小时和4小时）和基于SIRS的脓毒症（0小时）金标准;在这些测试中， AUROC与其他筛选系统相比，至少有一对必须再次达到0.05的优效性界限 (Aim 2）。未来方向：这些实验的结果将使InSight能够稳健地部署到 不同的临床站点，无需广泛的目标站点数据采集即可获得高性能。