Medication information is one of the most important types of clinical data in electronic medical records. It is critical for healthcare safety and quality, as well as for clinical research that uses electronic medical record data. However, medication data are often recorded in clinical notes as free-text. As such, they are not accessible to other computerized applications that rely on coded data. We describe a new natural language processing system (MedEx), which extracts medication information from clinical notes. MedEx was initially developed using discharge summaries. An evaluation using a data set of 50 discharge summaries showed it performed well on identifying not only drug names (F-measure 93.2%), but also signature information, such as strength, route, and frequency, with F-measures of 94.5%, 93.9%, and 96.0% respectively. We then applied MedEx unchanged to outpatient clinic visit notes. It performed similarly with F-measures over 90% on a set of 25 clinic visit notes.

Studies of acute kidney injury (AKI) commonly lack data on pre-admission renal function, often substituting an inpatient or imputed serum creatinine (SCr) as an estimate for “baseline” renal function. We examined the error introduced when applying methods to estimate “baseline” on AKI classification and mortality. Within a cohort of 4863 adults with a known outpatient baseline admitted to Vanderbilt University Hospital between 10/07 and 10/08, the following surrogates were studied: (1) an eGFR of 75 ml/min/1.73m2 as suggested by the Acute Dialysis Quality Initiative (ADQI), (2) a minimum inpatient SCr, and (3) the first admission SCr. We calculated AKI incidence and mortality rates using each surrogate, and assessed their ability to correctly classify AKI incidence and mortality compared to the most recent outpatient SCr between 7-365 days before admission. Using both imputed and minimum baseline SCr values inflated AKI incidence (38.3% and 35.9% vs. 25.5%; p<0.001), reflecting low specificities of 77% and 80%, respectively. In contrast, using an admission SCr baseline underestimated AKI incidence (13.7% vs. 25.5%, p<0.001), demonstrating a low sensitivity of 39%. Using any surrogate led to frequent misclassification of patient deaths as following AKI and differences for both in-hospital and 60-day mortality rates. In summary, commonly used surrogates for baseline SCr result in bi-directional misclassification of AKI incidence and prognosis in a hospitalized setting.

We leveraged the largely untapped resource of electronic health record data to address critical clinical and epidemiological questions about Coronavirus Disease 2019 (COVID-19). To do this, we formed an international consortium (4CE) of 96 hospitals across five countries (www.covidclinical.net). Contributors utilized the Informatics for Integrating Biology and the Bedside (i2b2) or Observational Medical Outcomes Partnership (OMOP) platforms to map to a common data model. The group focused on temporal changes in key laboratory test values. Harmonized data were analyzed locally and converted to a shared aggregate form for rapid analysis and visualization of regional differences and global commonalities. Data covered 27,584 COVID-19 cases with 187,802 laboratory tests. Case counts and laboratory trajectories were concordant with existing literature. Laboratory tests at the time of diagnosis showed hospital-level differences equivalent to country-level variation across the consortium partners. Despite the limitations of decentralized data generation, we established a framework to capture the trajectory of COVID-19 disease in patients and their response to interventions.

The CPOE-based intravenous insulin protocol improved glycemia control in SICU patients compared to a previous manual protocol, and reduced time to insulin therapy initiation. Integrating a computer-based insulin protocol into a CPOE system achieved efficient, safe, and effective glycemia control in SICU patients.