Integrating Data, Models, and Reasoning in Critical Care

The objective of this NIH-sponsored Bioengineering Research Partnership (BRP), established in October 2003, is to develop and evaluate advanced ICU patient monitoring and decision support systems that will improve the efficiency, accuracy, and timeliness of clinical decision-making in critical care. The partnership combines the resources of a powerful interdisciplinary team from academia (MIT), industry (Philips Medical Systems and Philips Research North America), and clinical medicine (Beth Israel Deaconess Medical Center). During the initial funding period of this BRP, substantial progress has been achieved, including the development of a massive new research database that includes detailed clinical data from more than 30,000 ICU patients (the Multiparameter Intelligent Monitoring in Intensive Care (MIMIC) II database) and a number of promising advanced monitoring concepts and algorithms. Our initial work has substantiated the hypothesis that sophisticated analysis of the rich multi-parameter data gathered from ICU patients can illuminate their changing pathophysiologic state and can even provide alerts of impending changes in state.

The major goals for the second phase of this BRP are to develop and demonstrate the effectiveness of advanced monitoring concepts and algorithms in laboratory studies utilizing the MIMIC II database, and then to carry successful concepts forward into clinical tests in the ICUs of Beth Israel Deaconess Medical Center (BIDMC) and elsewhere with the collaboration of our clinical and industrial partners. We will also enhance the value and availability of the MIMIC II database by adding new adult and neonatal data, designing and improving sophisticated data mining and signal processing tools, and freely distributing to the research community the database and its associated exploration tools via PhysioNet. More information concerning MIMIC II can be found at http://www.physionet.org/mimic2, together with extensive documentation on the data.

Clinical databases such as MIMIC provide a unique opportunity to evaluate both practice variation and the impact of diagnostic and treatment decisions on patient outcomes. Critically ill patients are an ideal population for database investigations because the clinical value of many treatments and interventions they receive is unproven, and high-quality data supporting or discouraging specific practices is relatively sparse. In addition, significant practice variation exists in the ICU; decisions are often based on clinician training and knowledge and local ICU culture. MIMIC presents an opportunity to examine which diagnostic and therapeutic interventions impact clinical outcomes in the real world setting.

We have formed teams consisting of clinicians (nurses, doctors, pharmacists) and scientists (database engineers, modelers, epidemiologists) who translate the questions into study designs, perform the modeling and the analysis and publish their findings. The scientists have been joining the clinicians during ICU rounds to gain a better understanding of clinical medicine and the clinicians have been attending conferences at MIT on data mining and machine learning. The studies fall into the following broad categories: identification and interrogation of practice variation, predictive modeling of clinical outcomes within patient subsets, and comparative effectiveness research on diagnostic tests and therapeutic interventions.

This grant was funded through 2013 by the National Institute of Biomedical Imaging and BioEngineering (NIBIB) under grant 2RO1-EB001659.