We are involved in many short-term and long-term projects in medical informatics. Our group leads investigations in the following areas:
- Data extraction, validation, and reporting
- Predictive analytics and risk stratification
- Research in data-driven quality improvement including clinical decision support (CDS).
We are always interested in partnering with others in the use of “big data” to pursue scientific knowledge.
Data extraction, validation, and reporting: The Perioperative Data Warehouse
The foundation of much of the work in the division is the creation and maintenance of the Perioperative Data Warehouse (PDW), a custom-designed data warehouse that enables extraction of data from EPIC’s “Clarity” database into a format that facilitates its use in research and quality improvement. The PDW is a joint collaboration with the UCLA Office of Health Informatics and Analytics (OHIA) and is currently in its fourth version. We are actively engaged in a multi-center project to demonstrate and better understand the application of this architecture at other institutions that use the EPIC EMR.
In addition to publishing work on the creation of the PDW, the division continues to use the PDW as the source of data for retrospective and prospective trials based on large data sets. These have included multi-center collaborations using perioperative data, as well as single-center, hypothesis-driven examinations of perioperative questions.
Historically, administrative data (ICD codes or DRGs) have been used to classify patients for large retrospective reviews. Multiple previous studies have demonstrated that these data are highly specific but can lack sensitivity. We want to understand the validity of data extracted from various sources, especially the EMR, and use data from multiple sources to yield more accurate information.
Using a technique that we call “triangulation”, we have developed a series of algorithms to automate patient phenotyping and outcome calculation using structured data from the EMR. These techniques have been successfully used to populate over 4000 discrete measures in the PDW. Our group has been able to automate the extraction of the entire anesthesia component of the Society of Thoracic Surgeons (STS) cardiac surgery registry, and has further validated one component of the registry (postoperative ventilator requirement) to demonstrate increased accuracy of automated review compared to manual review.
Currently, our team is applying these techniques prospectively to improve the accuracy of administrative data in the medical record, and to track the results of clinical improvement initiatives. After successfully developing algorithms to detect diseases, we are working with colleagues in our Preoperative Evaluation and Planning Clinic (PEPC) to create a risk-based screening system for patients before surgery. Detecting preexisting diseases early in the admission process, we hope, will improve documentation by clinical teams, and facilitate both accurate coding and optimized care.
Predictive Analytics and Risk Stratification
We are actively engaged in a collaboration with our UCLA Computer Science colleagues in order to use machine-learning techniques to predict which patients are at greatest risk of postoperative complications including mortality, readmission, and acute kidney injury (AKI). Our work in this area has been featured prominently in Anesthesiology, and has been recognized with internal and external grant funding. Maxime Cannesson, MD, PhD, the department's Vice-Chair for Perioperative Medicine, has been awarded funding from Edwards Lifesciences to support his work using deep learning on features extracted from waveforms to predict hypotension and other adverse physiologic states.
We are currently working to incorporate genetic and epigenetic information into our models, as well as to integrate waveform and EMR data to enhance predictive ability. In collaboration with OHIA, we are creating the infrastructure to allow the implementation of our models in near-real time, so that they can be integrated into clinical decision support pathways.
Clinical Decision Support (CDS)
We are actively engaged in implementing and testing clinical decision support (CDS) tools in order to help clinicians deliver better care. This includes both real-time decision-making and the reinforcing effect of physician feedback reports. Our division works directly with the EPIC build team in Los Angeles and at the headquarters in Wisconsin. This work has been integral to developing perioperative care pathways, including protocols to reduce PONV and intraoperative hypotension. We are developing tools to allow us to deliver data from the PDW directly to clinical personnel, providing detailed information on patients' postoperative outcomes.
In addition to these research projects, the division serves as a resource for all faculty requiring data for their research questions. We are participating in several ongoing prospective projects and data collection efforts with the UCLA Anderson School of Management and UCLA School of Engineering. We are always open to working with other teams and departments on projects that can help improve the care of patients throughout the perioperative period.