MATERIALS AND METHODS

This study was approved by the Institutional Review Boards of Beth Israel Deaconess Medical Center (Boston, MA) and the Massachusetts Institute of Technology (Cambridge, MA). Requirement for individual patient consent was waived because the study did not impact clinical care and all protected health information was deidentified.

Table 3 provides the primary ICD-9 codes from the patients’ hospital discharges. The following disease categories each comprised at least 5% of the discharge codes: diseases of the circulatory system (39.1%); trauma (10.2%); diseases of the digestive system (9.7%); pulmonary diseases (9.0%); infectious diseases (7.0%); and neoplasms (6.8%). Table 4 reports the incidence and associated mortality of a range of diseases that can be defined by objective laboratory abnormalities. Table 5 reports the incidence and associated mortality of vital sign abnormalities, including heart rate, systolic blood pressure, respiratory rate, and arterial oxygen saturation.

DISCUSSION

We have described the development of a large ICU database that is freely accessible to clinical researchers. The highly automated methods of aggregating thousands of ICU records from disparate sources, the use of open-source data formats, and the development of Health Insurance Portability and Accountability Act-compliant distribution mechanisms (with minimal credentialing requirements and no associated fees) are all intended to provide a valuable research resource to the widest audience of users. This database provides a high-resolution record of the dynamics of a patient’s pathophysiology and the contemporaneous therapeutic interventions. The interplay between disease and therapy can thus be analyzed. Furthermore, because the data are already electronic, this database naturally supports the development of clinical decision-support systems, which are automated algorithms that provide alerts, early warnings, and other decision support for critical care. Because the data are available online, along with a comprehensive user guide, it is hoped that an online community of MIMIC-II researchers will develop in which ideas can be exchanged and collaborations can develop.

To our knowledge, MIMIC-II is the only ICU database that encompasses patient demographics, clinical laboratory data, categorical admission diagnoses as well as detailed therapeutic profiles such as intravenous medication drip rates and hourly fluid balance trends for the duration of the ICU stay. These data are supplemented with a rich set of text-based records, including nursing progress notes, discharge summaries, and radiology interpretations. Developing this database was possible only because Boston’s Beth Israel Deaconess Medical Center is one of the <5% of hospitals in the United States that have fully automated and comprehensive medical records (10). Furthermore, in the current version of MIMIC-II, physiological waveforms and minute-to-minute vital-sign are available for 2061 of the patient records (an additional 2000 records not matched to clinical data are also available).

A wide range of analyses can be performed on these data, spanning epidemiology, clinical decision-rule development, and electronic tool development. For example, Jia et al (11) assessed risk factors for acute respiratory distress syndrome in MIMIC-II patients who were mechanically ventilated for >48 hrs. Saeed (12) studied how certain ICU practices varied significantly as a function of time of day, ie, during the workday vs. the overnight shifts. From the parameter-rich MIMIC-II database, Hug (13) identified multivariate factors associated with death, successful wean of pressor infusions within 12 hrs, successful weans of intra-aortic balloon pumps, and development of septic hypotension; and he developed predictive statistical models for these outcomes. Because of the suitable size of the database, for example, Hug identified >50,000 episodes of successful pressor weans within MIMIC-II; he was able to segment the data into distinct training and testing subpopulations, which enhances the validity of such analyses.

Broadly speaking, MIMIC-II supports the development of new automated clinical decision-support systems. Although decision-support research before MIMIC-II has spanned functionality, including automated drug allergy notifications, medication interactions, and reminders about abnormal laboratory results (14, 15), little progress has been made in clinical decision support for the acute management of unstable patients, a major challenge in the ICU. The value proposition is that novel automated algorithms may operate in real time and prevent medical mistakes or promote timely responses to the patients’ conditions. Consider that Kumar et al (16) showed that the duration of hypotension before the initiation of antimicrobial therapy was the most significant factor associated with mortality in septic patients. Therefore, having a reliable automated decision support to prompt timely antibiotic administration may be expected to improve critical care outcomes.

Distinct components of the MIMIC-II database may be studied to develop a variety of software tools. For example, electronic algorithms that automatically extract information from free-text nursing notes and discharge summaries have been developed and tested (7). Alarm algorithms can be trained and validated using MIMIC-II waveform records, which may help to address the perennial problem of false alarms by bedside monitors (17). Analysis of MIMIC-II also promotes the use of effective mathematical techniques for quantifying patterns through time, because so many of its clinical parameters are complex time-series, eg, continual heart rate trends. Saeed and Mark (18) explored the use of wavelet transformation of hemodynamic time series with machine learning to predict hemodynamic deterioration in ICU patients, and Lehman et al (19) explored how to search for case records who shared similar temporal patterns in time-series variables.

Interpretive algorithms can be developed and compared head-to-head using MIMIC-II. For instance, there are a number of different competing algorithms that estimate cardiac output from the arterial blood pressure waveform. MIMIC-II provides a resource for their fair comparison (20), providing a large number of radial ambulatory blood pressure waveforms and paired measurements of cardiac output by a thermodilution reference method. MIMIC-II may serve a role analogous to the public access arrhythmia databases that played an indispensable role in the development, refinement, and— ultimately—widespread acceptance of automated algorithms for electrocardiogram analysis (21). Overall, MIMIC-II offers the means to develop and assess cutting-edge algorithms, exploiting the full spectrum of data available in critical care, with the underlying goal to catalyze a new generation of automated decision-support systems that demonstrably improve the practice of critical care.

In this report, we characterized MIMIC-II using ICD-9 codes as well as quantitative data-driven measures. Although ICD-9 is the accepted coding procedure used for patient billing, prior studies have suggested that ICD-9 administrative data do not accurately reflect the true prevalence of comorbidities in hospitalized patients (22). Some analyses of MIMIC-II may require chart review by clinicians to optimize accuracy. Our group is actively investigating the application of natural language processing technology to automatically identify patients with specific comorbidities such as AIDS, metastatic cancer, chronic obstructive pulmonary disease, etc, that are needed for such scores as SAPS, Acute Physiology and Chronic Health Evaluation, etc.

MIMIC-II was developed to serve as a research resource for physicians, scientists, and engineers. If large volumes of medical data are to be widely and freely disseminated, patient privacy concerns are inevitably raised. To address this, automated deidentification tools were developed and rigorously evaluated to remove protected health information from structured and free-text fields such as nursing notes and physician discharge summaries. Ultimately, we successfully applied tools that were demonstrated to perform better than using two independent clinicians to identify protected health information in medical records. Finally, as an added layer of protection to patient privacy, MIMIC-II users must sign and abide by a data-use agreement before being granted access to the free-text elements to ensure data are used for only legitimate purposes.

Although MIMIC-II is in many respects innovative and unprecedented, it by no means represents the ultimate ICU research database. There are several notable limitations, and ideally future iterations of MIMIC-II or other complimentary public-access ICU databases can address some of these matters. First, administration of oral and intravenous bolus medication administration was paper-charted and not systematically tabulated in the electronic record. Although provider order entry records were computerized and aggregated into MIMIC-II, these data are not equivalent to documenting if and when those medications were truly administered. Second, MIMIC-II only includes ICU data (with the exception of laboratory results and discharge summaries). A database that included complete data before the development of critical illness would be invaluable. Third, MIMIC-II is limited by having ICU records from a single institution. The clinical practices and patient populations documented by this database may not be representative of other hospitals. Fourth, MIMIC-II data reflects “real-world” clinical practice as opposed to scrupulously tended research protocols. This means that certain documentation and clinical practices may be less reliable (eg, not carefully recalibrating the arterial pressure transducers every shift), which may be a source of error for some analyses, whereas it may be advantageous for other investigations. For example, when developing clinical decision rules and other automated decision-support algorithms, it is more valid to analyze “real-world” data rather than idealized research data that are unrepresentative of actual clinical practice.

Finally, only a subset (approximately 2000) of MIMIC-II records include matched physiological waveform and minute-to-minute trend data owing to technical difficulties in deploying data-archiving machines, which interfaced with bedside patient monitoring systems, and difficulties in linking waveform files to specific clinical records. Furthermore, the subset of records with waveforms is not necessarily statistically similar to the database as a whole. On the other hand, the collection of 2000 waveform records is massive by most standards. For example, the electrocardiogram database that supported development and evaluation of automated arrhythmia algorithms included much smaller data collections (48 half-hour samples in the MIT-BIH Arrhythmia Database [21] and 80 3-hr records in the American Heart Association ECG Database [23]). Machine learning strategies certainly benefit as the number of examples rise, but the 2000 waveform records matched with clinical cases are sufficient for many important investigations, and this number will grow, because we continue to collect data and to publish new versions of MIMIC-II. Also, an additional 2000 records unmatched to clinical data are available (posted on PhysioNet) and such records are adequate for many physiological and clinical studies (such as developing algorithms to predict hypotensive episodes, reducing false alarms, etc).

In the short term, collaboration with industry vendors is mandatory for the development of databases similar to MIMIC-II owing to the sophisticated interfaces and proprietary data formats of most ICU devices. For MIMIC-II, the participating patient monitoring vendor (Philips Healthcare) provided significant engineering resources to facilitate access to data from patient monitors and to the CareVue clinical information systems. In the long term, however, the adoption of common data formats that allow for seamless device communication would remove a significant barrier to developing databases similar to MIMIC-II.

9. nursing station

The nurses’ station is the fulcrum of activity on the inpatient hospital floor. At some point, virtually every hospital function intersects at this critical junction, often simultaneously, via impromptu meetings among a wide cross-section of hospital staff. This intensive and varied use presents a set of complex and challenging issues for hospitals and the people that help them effectively plan for new or renovated facilities.

Over the past three years, members of our current Nurture by Steelcase team have conducted detailed ethnographic research at leading health facilities to evaluate a wide variety of nurses’ station interactions—especially how caregivers perform their duties and how patients receive their care.

Nurture’s research and design approach is built around the user experience. We undertake five steps to provide specific solutions to our healthcare clients: Understand, Observe, Synthesize, Realize, and Pilot/Test.

After analyzing the issue—through business concerns, technology trends, and what’s new and how it affects the organization—Nurture’s research team goes on-site to build a first-hand understanding of the user’s day-to-day work life. The Nurture design research team—consisting of researchers, designers, and product specialists—then synthesizes these findings into design principles, criteria, and concepts that feed into the product development process. Finally, Nurture shares all of this information with architects, designers, and clients.

Building on existing research on nurses’ stations, our research process has allowed Nurture to more fully understand the nurses’ station and to come up with what we believe to be better design concepts.

CONTROLLED CHAOS

Many kinds of work happen in the nurses’ station, but traditional designs try to force-fit them into a single, rigid configuration—typically with a fortress-like counter and an enclosed room behind it. This assumes that work happens in neat, defined silos. In reality, there’s chaos and crowding, with many different behaviors colliding in the space.

First and foremost, nurses’ stations need to be considered in the context of providing patient care and as a functional work space. Sharp aesthetics are nice, but this space, maybe more than any other in the hospital environment, needs to be highly functional.

Through our observations, we have seen examples of different types of nursing station organizational models: centralized, decentralized, and various combinations of the two. Each has its own set of benefits and trade-offs relative to patient care and work.

Centralized. In this model (figure 1), the nurses’ station is a central hub on the unit—all workstations are located here, as are the unit assistant and most office machines.

• Pros: Nurses and clinical staff work together in a central location; quick access to peers paves the way for learning, mentoring, and efficient communication; resources can be consolidated.

• Cons: Less proximity to patients; increased congestion and noise.

Decentralized. There is no central hub in this model (figure 2). Nursing stations are located throughout the unit outside each patient room, and the unit assistant is typically located near the entrance to the unit.

• Pros: Nurses are closer to patients; possibly fewer distractions; each nurse has his or her own work space.

• Cons: Fewer opportunities for informal learning with peers; sense of isolation; less proximity to control center for the unit assistant.

KEY DESIGN PRINCIPLES

Regardless of which organizational type one chooses, our research team has identified five key principles to consider when designing a nurses’ station or series of stations.

1. Allow for Control and Flexibility. The ability for staff and patients to control their environment is crucial. The environment needs to support:

• changes in care delivery, such as bedside charting and physician order entry;

• changes in technology, such as increased access to computers (e.g. mobile carts, bedside terminals) and the integration of clinical technology with patient records; and

• the ability to adapt spaces as needs change.

2. Support the Social Ecology. Social interaction is key to learning. The environment needs to support the many ways people interact for learning. The space should:

• accommodate generational mentoring and apprenticeship;

• allow for different group sizes (e.g.,one-to-one and one-to-many);

• allow for informal versus formal instruction; and

• allow for on-the-go versus stationary instruction.

3. Understand Work Processes. The environment needs to consider and support the users and activities. The space should accommodate:

• different types of hospital units;

• different roles (e.g., physicians, nurses, radiologists); and

• different types of work (e.g., charting, group rounds, medication preparation and delivery, and shift changes.

4. Reduce Cognitive Load. Information overload leads to confusion and disorganization. The environment needs to support the display of:

• information that needs to be visible for a long time;

• information that changes frequently; and

• ways to call attention to important information (e.g., allergy alerts on a chart).

5. Maximize Spatial Relationships. Space plays an important role in security, staff and patient safety, communication, and physical demands on caregivers. Designers should strive to:

• understand the relationships between different activity zones to prioritize adjacencies;

• consider patient monitoring and staff communication when creating sight lines between zones; and

• consider travel distances when designing (e.g., supply rooms, med rooms, patient rooms, and staff respite areas).