Autonomous system supporting patient-specific transfer and discharge decisions

支持患者特定转移和出院决策的自主系统

• 批准号: 9256278
• 负责人: Ritankar Das
• 金额: $ 34.78万
• 依托单位: DASCENA, INC.
• 依托单位国家: 美国
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-01-01 至 2018-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9256278
• 关键词: Address; Antibiotics; Area; Cessation of life; Chronic; Clinical; Clinical Decision Support Systems; Computer software; Cues; Data; Data Quality; Data Set; Databases; Deterioration; Event; Future; Geography; Goals; Gold; Health; Healthcare Systems; Homeostasis; Hospital Mortality; Hour; Inpatients; Intensive Care Units; Intervention; Knowledge; Life; Liquid substance; Machine Learning; Measurement; Medical; Methods; Patient Care; Patient Discharge; Patient Transfer; Patients; Performance; Phase; Physiology; Process; ROC Curve; Receiver Operating Characteristics; Recommendation; Research; Risk; SCAP2 gene; Sensitivity and Specificity; Series; Site; Small Business Innovation Research Grant; Support System; System; Techniques; Testing; Time; Training; Triage; Update; Validation; Work; base; cost; experimental study; high standard; improved; mortality; novel; patient population; success; support tools; tool; trend

Significance: In this SBIR project, we propose to improve the utility of AutoTriage, a machine-learning based clinical decision support (CDS) system, by integrating clinician intervention medical information into its predictions. Despite identified needs for CDS systems in patient transfer and discharge decisions, existing tools do not meet high standards for sensitivity and specificity. This is because current CDS methods are unable to distinguish changes in patient health due to clinician intervention from those arising due to an internal homeostatic mechanism. Thus, for example, existing tools may erroneously suggest discharge for a patient currently undergoing a life-sustaining treatment. Research Question: Can machine learning principles be used to create a classifier which incorporates signs of clinical intervention to inform transfer and discharge decision support, ultimately leading to higher quality predictions? In addition, will such a tool be able to maintain its performance when tested on a different patient population or one for which the data quality is much poorer? Prior Work: We have developed AutoTriage, a machine learning-based CDSS for 12-hour mortality prediction. On the publicly available MIMIC-III retrospective data set, this system attains an area under the receiver operating characteristic curve (AUROC) of 0.88, which is superior to commonly used triage scores MEWS (AUROC = 0.75), SOFA (0.71), and SAPS-II (0.72) on the same data set. Specific Aims: To integrate clinician intervention information into existing AutoTriage software (Aim 1), and to test the robustness of this modified tool to changes in patient population and data quality (Aim 2). Methods: We will create gold standards for periods of clinician intervention, using chart events and keywords from clinician notes. Then, we will train a binary classifier for identifying these periods and, ultimately, use the classifier to modify AutoTriage scores. Robustness studies will be performed on the retrospective UC ReX and sparse MIMIC III databases. Successful completion of Aim 1will be demonstrated if 75% of all hours of clinician intervention are correctly classified, if the test-set area under the ROC curve improves by 5% over its current value, and if 30-day readmission predictions are 10% more accurate for patients treated within the last hour. Aim 2 will be completed if AutoTriage ROC area performance is within ± 0.10 of its original value for both UC ReX and sparse MIMIC III sets. Future Directions: Following the proposed work, the AutoTriage system will be deployed at the sites of our ongoing clinical implementations. During this study, we project that AutoTriage will assess mortality risk for 25,000 ICU patients per year, helping clinicians more effectively allocate interventions totaling $15 million.

意义：在这个SBIR项目中，我们建议改善Autotrage的实用性，这是一种基于机器的学习 临床决策支持（CD）系统，通过将临床干预医学信息整合到其 预测。尽管确定了患者转移和出院决策中CDS系统的需求，但现有 工具不符合敏感性和特异性的高标准。这是因为当前的CD方法是 由于临床干预措施而无法区分患者健康的变化与由于内部引起的患者的变化 稳态机制。例如，现有工具可能会错误地建议患者出院 目前正在接受维持生命的治疗。研究问题：机器学习原理可以 用于创建分类器，该分类器包含临床干预迹象以告知转移和出院 决策支持，最终导致更高质量的预测？此外，这样的工具将能够 在对不同的患者人群进行测试或数据质量大多的患者人群测试时保持其表现 贫穷？先前的工作：我们已经开发了自动化，这是一种基于机器学习的CDS，用于12小时死亡率 预言。在公开可用的模仿-III回顾性数据集中，该系统达到了 接收器工作特性曲线（AUROC）为0.88，优于常用的分类分数 在相同的数据集上，MeWS（AUROC = 0.75），沙发（0.71）和SAPS-II（0.72）。具体目标：集成 临床医生干预信息到现有的自动支架软件（AIM 1），并测试此功能的鲁棒性 修改了改变患者人群和数据质量的工具（AIM 2）。方法：我们将创建黄金 使用临床注释中的图表事件和关键字的临床干预期间标准。然后，我们 将训练二进制分类器以识别这些时期，并最终使用分类器修改自动分支 分数。鲁棒性研究将在回顾性UC REX和稀疏模拟III数据库上进行。 如果正确的所有临床干预措施中有75％的75％是正确完成AIM 1 分类，如果ROC曲线下的测试集面积比当前值提高5％，并且如果30天 对于过去一小时内治疗的患者，再入院预测的准确性要高10％。 AIM 2将是 如果自动架ROC面积性能在其原始值的±0.10以内，则完成。 稀疏模拟III集。未来的方向：遵循拟议的工作，自动架系统将是 部署在我们正在进行的临床实施的地点。在这项研究中，我们预测自动马车将 评估每年25,000名ICU患者的死亡率风险，帮助临床医生更有效地分配干预措施 总计1500万美元。

项目成果

Effect of a machine learning-based severe sepsis prediction algorithm on patient survival and hospital length of stay: a randomised clinical trial.

• DOI: 10.1136/bmjresp-2017-000234
• 发表时间: 2017
• 期刊: BMJ open respiratory research
• 影响因子: 4.1
• 作者: Shimabukuro DW;Barton CW;Feldman MD;Mataraso SJ;Das R
• 通讯作者: Das R

Machine learning landscapes and predictions for patient outcomes.

• DOI: 10.1098/rsos.170175
• 发表时间: 2017-07
• 期刊: Royal Society open science
• 影响因子: 3.5
• 作者: Das R;Wales DJ
• 通讯作者: Wales DJ

Prediction of early unplanned intensive care unit readmission in a UK tertiary care hospital: a cross-sectional machine learning approach.

• DOI: 10.1136/bmjopen-2017-017199
• 发表时间: 2017-09-15
• 期刊: BMJ open
• 影响因子: 2.9
• 作者: Desautels T;Das R;Calvert J;Trivedi M;Summers C;Wales DJ;Ercole A
• 通讯作者: Ercole A

Using Transfer Learning for Improved Mortality Prediction in a Data-Scarce Hospital Setting.

• DOI: 10.1177/1178222617712994
• 发表时间: 2017
• 期刊: Biomedical informatics insights
• 作者: Desautels T;Calvert J;Hoffman J;Mao Q;Jay M;Fletcher G;Barton C;Chettipally U;Kerem Y;Das R
• 通讯作者: Das R