Predictive Informatics Monitoring in the Neonatal Intensive Care Unit

描述（申请人提供）：新生儿ICU早产儿需住院至生理成熟，平均60天。然而，在医院里，他们面临着亚急性潜在灾难性疾病的风险，比如感染、导致紧急计划外插管的呼吸失代偿和颅内出血。这些疾病很常见，而且是致命的。在每种情况下，早期诊断都有希望通过早期干预来改善结果。我们小组的长期目标是通过对床边监视器的波形和其他信息学数据进行先进的数学和统计分析，开发诸如早期预警系统之类的新型预测监测策略。这种方法最近使该小组及其在其他7个中心的同事完成了一项由NICHD赞助的3000名早产儿的随机临床试验，这是迄今为止在这一人群中进行的最大的试验。这个结果非常重要——仅仅向临床医生展示预测监测的结果就能使死亡率降低20%以上。总体概念框架是，一些亚急性潜在灾难性疾病具有亚临床前驱症状与异常的生理特征。这是基于系统性炎症反应综合征和胆碱能抗炎途径的观点，胆碱能抗炎途径将炎症与异常信号转导和自主神经系统活动联系起来。结果是，疾病，即使在早期阶段，也会导致器官的分离和心脏和呼吸节奏的异常控制，这些都可以通过针对临床见解量身定制的数学算法来检测。实现我们预测信息学监测的目标需要一个来自弗吉尼亚大学NICU的相关临床信息和监测数据的大型数据库，包括生命体征和波形。由临床医生和数学家组成的团队——弗吉尼亚大学和哥伦比亚大学的合作团队——将发现异常生理的表型，并开发检测它们的算法。这项工作的大规模计算能力已在日常使用中，该小组将准备进行随机临床试验，以测试该技术的影响

DESCRIPTION (provided by applicant): Premature infants in the Neonatal ICU require hospitalization until they reach physiological maturity, an average of 60 days. While in the hospital, though, they are at risk of sub-acute potentially catastrophic illnesses such as infectio, respiratory decompensation leading to urgent unplanned intubation, and intracranial bleeding. These illnesses are common and deadly. In each case, early diagnosis has the promise to improve outcome through early intervention. The long-term goal of our group is to develop such novel predictive monitoring strategies as early warning systems through advanced mathematical and statistical analysis of waveforms and other informatics data from the bedside monitor. This kind of approach recently led the group and its colleagues at 7 other centers to complete a NICHD- sponsored randomized clinical trial in 3000 premature infants, the largest ever conducted in this population. The result was very important - simply showing the results of a predictive monitor to clinicians reduced the death rate by more than 20%. The overall conceptual framework is that some sub-acute potentially catastrophic illnesses have subclinical prodromes with abnormal physiologic signatures. This is based on ideas about the systemic inflammatory response syndrome and the cholinergic anti-inflammatory pathway that link inflammation to abnormal signal transduction and autonomic nervous system activity. The result is that illness, even in early stages, leads to uncoupling of organs and abnormal control of heart and respiratory rhythms that can be detected using mathematical algorithms tailored to clinical insights. Achieving our goals of predictive informatics monitoring requires a large database of relevant clinical information and monitor data from the University of Virginia NICU, including vita signs and waveforms. The team of clinicians and mathematicians - a collaboration of University of Virginia and Columbia University - will discover phenotypes of abnormal physiology and develop algorithms to detect them. The large-scale computing capability for this work is in daily use, and the group will be poised to undertake randomized clinical trials to test the impact of the new monitoring. This represents a paradigm shift in patient care - monitors that report trends of development of health and illness rather than fleeting values.