Computerized ICU data management: pitfalls and promises

The impact of data quality defects on clinical decision-making in the intensive care unit

OBJECTIVE

Poor clinical data quality might affect clinical decision making and patient treatment. This study identifies quality defects in clinical data collected automatically by bedside monitoring devices in the Intensive Care Unit (ICU) and examines their effect on clinical decisions.

METHODS

Real-world data collected from 7688 patients admitted to the general ICU in a tertiary referral hospital over seven years was retrospectively analyzed. Data quality defect detection methods that use time-series analysis techniques identified two types of data quality defects: (a) completeness: the extent of non-missing values, and (b) validity: the extent of non-extreme values within the continuous range of values. Data quality defects were compared to five scenarios of medication and procedure prescriptions that are common in ICU settings: Blood-pressure reduction, blood-pressure elevation, anesthesia medications, intubation procedures, and muscle relaxant medications.

RESULTS

Results from a logistic regression revealed a strong connection between data quality and the clinical interventions examined: lower validity level increased the likelihood of prescription decisions for all five scenarios, and lower completeness level increased the likelihood of prescription decisions for some scenarios.

DISCUSSION

The results highlight the possible effect of data quality defects on physicians' decisions. Lower validity of certain key clinical parameters, and in some scenarios lower completeness, correlated with stronger tendency to prescribe medications or perform invasive procedures.

CONCLUSIONS

Data quality defects in clinical data affect decision making even without practitioners' awareness. Thus, it is important to emphasize these effects to ICU staff, as well as to medical device manufacturers.

Multiparameter Intelligent Monitoring in Intensive Care II: a public-access intensive care unit database

OBJECTIVE

We sought to develop an intensive care unit research database applying automated techniques to aggregate high-resolution diagnostic and therapeutic data from a large, diverse population of adult intensive care unit patients. This freely available database is intended to support epidemiologic research in critical care medicine and serve as a resource to evaluate new clinical decision support and monitoring algorithms.

DESIGN

Data collection and retrospective analysis.

SETTING

All adult intensive care units (medical intensive care unit, surgical intensive care unit, cardiac care unit, cardiac surgery recovery unit) at a tertiary care hospital.

PATIENTS

Adult patients admitted to intensive care units between 2001 and 2007.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

The Multiparameter Intelligent Monitoring in Intensive Care II (MIMIC-II) database consists of 25,328 intensive care unit stays. The investigators collected detailed information about intensive care unit patient stays, including laboratory data, therapeutic intervention profiles such as vasoactive medication drip rates and ventilator settings, nursing progress notes, discharge summaries, radiology reports, provider order entry data, International Classification of Diseases, 9th Revision codes, and, for a subset of patients, high-resolution vital sign trends and waveforms. Data were automatically deidentified to comply with Health Insurance Portability and Accountability Act standards and integrated with relational database software to create electronic intensive care unit records for each patient stay. The data were made freely available in February 2010 through the Internet along with a detailed user's guide and an assortment of data processing tools. The overall hospital mortality rate was 11.7%, which varied by critical care unit. The median intensive care unit length of stay was 2.2 days (interquartile range, 1.1-4.4 days). According to the primary International Classification of Diseases, 9th Revision codes, the following disease categories each comprised at least 5% of the case records: 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%).

CONCLUSIONS

MIMIC-II documents a diverse and very large population of intensive care unit patient stays and contains comprehensive and detailed clinical data, including physiological waveforms and minute-by-minute trends for a subset of records. It establishes a new public-access resource for critical care research, supporting a diverse range of analytic studies spanning epidemiology, clinical decision-rule development, and electronic tool development.

Computerized clinical decision support: a technology to implement and validate evidence based guidelines

Faced with a documented crisis of patients not receiving appropriate care, there is a need to implement and refine evidence-based guidelines (EBGs) to ensure that patients receive the best care available. Although valuable in content, among their deficiencies, EBGs do not provide explicit methods to bring proven therapies to the bedside. Computerized information technology, now an integral part of the US healthcare system at all levels, presents clinicians with information from laboratory, imaging, physiologic monitoring systems, and many other sources. It is imperative that we clinicians use this information technology to improve medical care and efficacy of its delivery. If we do not do this, nonclinicians will use this technology to tell us how to practice medicine. Computerized clinical decision support (CCDS) offers a powerful method to use this information and implement a broad range of EBGs. CCDS is a technology that can be used to develop, implement, and refine computerized protocols for specific processes of care derived from EBGs, including complex care provided in intensive care units. We describe this technology as a desirable option for the trauma community to use information technology and maintain the trauma surgeon/intensivist's essential role in specifying and implementing best care for patients. We describe a process of logical protocol development based on standardized clinical decision making to enable EBGs. The resulting logical process is readily computerized, and, when properly implemented, provides a stable platform for systematic review and study of the process and interventions.

CONCLUSION

: CCDS to implement and refine EBG derived computerized protocols offers a method to decrease variability, test interventions, and validate improved quality of care.

Clinical decision support systems for intensive care units: using artificial neural networks

The paper provides an overview of applications of artificial neural networks (ANNs) to various medical problems, with a particular focus on the intensive care unit environment (ICU). Several technical approaches were tested to see whether they improve the ANN performance in estimating medical outcomes and resource utilization in adult ICUs. These experiments include: (1) use of the weight-elimination cost function; (2) use of 'high' and 'low' nodes for input variables; (3) verifying the effect of the total number of input variables on the results; (4) testing the impact of the value of the constant predictor on the performance of the ANNs. The developments presented intend to help medical and nursing personnel to assess patient status, assist in making a diagnosis, and facilitate the selection of a course of therapy.

Intra-arterial blood pressure reference ranges, death and morbidity in very low birthweight infants during the first seven days of life

OBJECTIVES

We aimed to: (1) assess the association of average, low, high and variable mean blood pressure (mbp) on death and the common morbidities of very low birthweight infants, and in doing so, (2) to derive representative reference ranges for mbp in very low birthweight infants.

STUDY DESIGN

This five year retrospective study assessed 1 min computer recordings of intra-arterial mbp in 232 very low birthweight infants over the first 7 days of life in a tertiary NICU. Four measures of mbp were assessed: average, variability, maximum (per time period), and percentage of time with a mean blood pressure less than the infant's gestation. Correlation was made with death and the development of intraventricular haemorrhage (IVH), periventricular leukomalacia (PVL) and retinopathy of prematurity (ROP).

RESULTS

The mbp increased with increasing birthweight and postnatal age (though with a slight decrease on days 6 and 7). Birthweight, gestation and colloid support (adjusted for birthweight and gestation) were the only factors significantly associated with mbp. IVH was predominantly associated with a low and variable mbp on the day IVH was noted or the day before. PVL and ROP were not associated with blood pressure.

CONCLUSIONS

These reference ranges include more infants and data than previously published and relate mbp in this cohort to morbidity and mortality. They could assist clinicians in judging appropriate mbp for birthweight.

Electronic medical record in the intensive care unit

The EMR in the ICU has the utility of providing the necessary information to make sound clinical decisions for critically ill patients. For it to be optimized, the EMR must be more than just what is being replicated in the written record or merely a documentation tool; it must add value that supports and enhances clinical decision support. The EMR is too expensive a tool just to be a computer designed to ease documentation and retrieve data faster. Gardner and Huff have suggested that the EMR must answer three questions: Why, What, and So What. The "Why" is relatively easy to answer, but the "What" data to use so that the information is meaningful to a provider and the "So What" are more difficult to answer. Provided one can qualitatively assess "What" information is important for a health care provider, then "So What" becomes an important objective in the empirical quantification of the benefits that the EMR provides. It is clear that to analyze some of the outcomes that health care delivery provides, one needs some mechanism to automate the information at the point of care, particularly now that the regulatory agencies are requiring it. Given the fact that there is no single integrated computerized patient record, this becomes the daunting task for the next century. Making it easier for health care providers to interact with the system and providing them with instantaneous feedback that changes their medical decision so they can deliver better care (clinical pathways, clinical practice guidelines) will be the task required of the next generation of CISs.

The evolving health-care environment: new arguments for closer collaboration between cardiac surgical intensive-care nurses and clinical engineers

"Not vain the weakest, if their force unite." Homer, Iliad (9th century, B.C.). In today's evolving health-care environment, the cardiac surgical intensive-care nurse is required to provide care to patients whose acuity levels are increasing. Simultaneously, these nurses are asked to use more technologically complex devices to deliver that care. In addition, practice protocols are being integrated into hospitals' clinical information systems. To meet these challenges, cardiac surgical intensive-care nurses must collaborate with clinical engineers on the evaluation and installation of new products and on the automation and refinement of clinical pathways and other outcomes measurement tools. Each discipline also must ensure that the other keeps pace with and maintains its levels of proficiency in the technology used to care for patients undergoing cardiac surgery.

Computers in the intensive care unit: promises yet to be fulfilled

Computers, whether disguised as microprocessor-controlled bedside devices or obvious as electronic patient charts, are proliferating in intensive care units. The history of the relationship between computers and intensive care units suggests that their joint development has been characterized by customization of a device or a program to automate each specific task. Failure to develop standard definitions of clinical data, standards for their interpretation, or a comprehensive model of the process of critical care retards development of computer systems beyond device-dedicated microprocessors. An agenda that gives priority to systematic examination of definitions, descriptions, and processes of critical care over additional hardware and software development is recommended.

A clinical decision support system prototype for cardiovascular intensive care

This paper describes the development and validation of a decision-support system prototype that can help manage hypovolemic hypotension in the Cardiovascular Intensive Care Unit (CVICU). The prototype uses physiologic pattern-matching, therapeutic protocols, computational drug-dosage response modeling and expert reasoning heuristics in its selection of intervention strategies and choices. As part of model testing, the prototype simulated real-time operation by processing historical physiologic and intervention data on a patient sequentially, generating alerts on questionable data, critiques of interventions instituted and recommendations on preferred interventions. Bench-testing with 399 interventions from 13 historical cases showed therapies for bleeding and fluid replacement proposed by the prototype were significantly more consistent (p < 0.0001) than those instituted by the staff when compared against expert critiques (80% versus 44%). This study has demonstrated the feasibility of formalizing hemodynamic management of CVICU patients in a manner that may be implemented and evaluated in a clinical setting.

Challenges and opportunities for computerizing the anesthesia record

Most observers would agree that the goal of computerizing the anesthesia record is a worthy one. Despite the fact that several academic groups and vendors have attempted to develop and provide computerized anesthesia charting, the practice is not widespread. In this review article, we attempt to outline the reasons for this reluctance to use computers for anesthesia charting. Where there are problems to be solved, there also are opportunities. We discuss the development of strategies to solve these problems and thus present opportunities for medical informatics professionals and anesthesiologists to work toward joint solutions. Solving these problems includes the development of consensus standards and working out technical, social, and educational difficulties. Details of the approaches recommended are outlined.

Data quality of bedside monitoring in an intensive care unit

Computerized record keeping promises complete, accurate and legible documentation. Reliable measurements are a prerequisite to fulfill these expectations. We analyzed the physiological variables provided by bedside monitoring devices in 657 bedside visits performed by an experienced Intensive Care nurse during 75 Intensive Care rounds. We registered which variables were displayed. If a variable was displayed, we assessed whether it could be used for documentation or should be rejected. If a value was rejected the reason was registered as: the measurement was not intended (superfluous display), the current clinical situation did not allow proper measurement, or other reasons. Basic variables (vital signs and respiration related variables) were displayed in more then 90%, specific variables (e.g. intracranial pressure) were displayed in less than 50% of the situations. Displayed variables were superfluous on an average of 11% because measurement was not intended. Variables like heart rate, temperature, airway pressure, minute volume of ventilation, arrhythmia, pulmonary arterial pressure, non-invasive blood pressure, and intracranial pressure provide high quality measured values (acceptance of more than 90%). Invasive arterial pressure, central venous pressure, respiration rate and oxygen saturation (via pulse oximetry) provided lower quality values with a rejection rate higher than 10%. Inappropriate sensor technology to match the clinical environment seems to be the root cause. In future the request for automatic documentation will increase. In order to avoid additional staff workload and to ensure reliable documentation, sensor technology especially related to respiration rate, blood pressure measurements, and pulse oximetry should be improved.

Lessons learned while building an integrated ICU workstation

The project LUCY (Linked Ulm Care sYstem) is described. The goal of this project was to build a research workstation in an Intensive Care Unit which enables evaluation of data/information processing and presentation concepts. Also evaluation of new devices and functions considering not only one device but the workplace as an entirety was an aim of the project. We describe the complete process of building from the stage of design until its testing in clinical routine. LUCY includes a patient monitor, a ventilator, 4 infusion pumps and 8 syringe pumps. All devices are connected to a preprocessing computer via serial interfaces. A high performance graphic workstation is used for central display of physiological and therapeutic variables. A versatile user interface provides touch screen, keyboard and mouse interaction. For fluid administration a bar code based control and documentation facility was included. While our scheduled development efforts were below 4 man-years, the overall man-power needed until the first routine test amounts to 8 man-years. Costs of devices and software sum up to 160,000 US$. First experiences in clinical routine show good general acceptance of the workplace concept. Analysing the recorded data we found 90% of the items to be redundant: individual filtering algorithms are necessary for each of nowaday's devices. The flexibility of the system concerning the implementation of new features is far from our expectations. Technical maintenance of the system during clinical operation requires continuous effort which we cannot afford in the current situation.

Neonatal physiological trend monitoring by computer

A premature baby born up to four months early is a fragile patient dependent on intensive care. The body systems are physiologically immature and so tolerate stress badly. The tendency of these infants to rapidly deteriorate, has led us to use a cotside computer monitoring system which displays physiological trends. Information from standard neonatal monitors is accessed by individual cotside PC's linked to a central network server and Doctors terminal. Trend graphs can be easily manipulated, displaying from 7 minutes to 3 days of physiological information on a single screen. Pathology may be observed in real time as it occurs. The system has 3 main areas of use, (a) as a real time clinical aid to patient management, e.g. apnoea of the newborn; (b) as a research tool, demonstrating the effects of procedures on physiology; (c) for educating members of staff about how physiological events develop. Data is saved for the whole of each neonates intensive care stay. Assessment of staff and parent attitudes by questionnaire have been favourable.

Acquisition of ICU data: concepts and demands

As the issue of data overload is a problem in critical care today, it is of utmost importance to improve acquisition, storage, integration, and presentation of medical data, which appears only feasible with the help of bedside computers. The data originates from four major sources: (1) the bedside medical devices, (2) the local area network (LAN) of the ICU, (3) the hospital information system (HIS) and (4) manual input. All sources differ markedly in quality and quantity of data and in the demands of the interfaces between source of data and patient database. The demands for data acquisition from bedside medical devices, ICU-LAN and HIS concentrate on technical problems, such as computational power, storage capacity, real-time processing, interfacing with different devices and networks and the unmistakable assignment of data to the individual patient. The main problem of manual data acquisition is the definition and configuration of the user interface that must allow the inexperienced user to interact with the computer intuitively. Emphasis must be put on the construction of a pleasant, logical and easy-to-handle graphical user interface (GUI). Short response times will require high graphical processing capacity. Moreover, high computational resources are necessary in the future for additional interfacing devices such as speech recognition and 3D-GUI. Therefore, in an ICU environment the demands for computational power are enormous. These problems are complicated by the urgent need for friendly and easy-to-handle user interfaces. Both facts place ICU bedside computing at the vanguard of present and future workstation development leaving no room for solutions based on traditional concepts of personal computers.(ABSTRACT TRUNCATED AT 250 WORDS)

Computer assisted management of information in an intensive care unit

In order to use the capability of computers for handling large amounts of information, we developed a program for the acquisition, handling, storage and retrieval of administrative and clinical information generated in the 20 bedded multidisciplinary critical care unit of a University Hospital. At an initial phase a personal computer (PC) was used to collect information from 4362 patients, that included registration data, coded admission problems, techniques and special treatments, and final diagnosis. This information combined with free text provided a discharge report. Complementary programs allowed calculation and storage of hemodynamic and gas exchange parameters. This experience led to a second phase in which a computer with microprocessor Intel 80386 at 25 MHz, 8 MB RAM, 310 MB hard disk and a streamer for 150 MB cartridge tape back up, using UNIX operating system, permitted multiple users working simultaneously through 1 central console and 7 ASCII terminals. Data input included demographic data, previous and admission problems in coded form, present history and physical examination in free text, list of present problems in coded form, comments on evolution, record of special techniques and treatments, laboratory data, treatment, final diagnosis and facility for using all the information to elaborate the final report. Side modules provide help for drugs dosing, protocols for specific conditions and clerical routines. The system is open for connection to other areas of the Hospital. Data from more than 2000 patients have been included so far.(ABSTRACT TRUNCATED AT 250 WORDS)

Problems in the development of a computerized ward monitoring system for a paediatric intensive care unit

A computerised ward monitoring system based on Archimedes PC's at each bedside is under development for the PICU at Killingbeck Hospital in Leeds. This work was initiated with a view to reducing the amount of paperwork in the unit. The present paper charts have been broken down into sections for the purpose of entry into the computer. The completed charts may be viewed in tabular form. There are several alternative displays. The default display mode illustrates the patients principal cardiovascular variables over the previous six hours. Alternative graphical displays include 12 hour trend curves for the cardiovascular variables, a screen with one hour trend graphs and panels illustrating the latest values of other patient variables, and graphical 12 hour reviews for clear fluid balance, blood volume balance and respiratory variables. The program also serves as a vehicle for testing an alarm generating system and a cardiovascular status index in the paediatric environment. A separate program has been developed which allows the retrospective construction of data bases by using some or all of the data from one or more of the charts for a series of patients. Finally the difficulties encountered in preliminary trials of the system are discussed. At the present time the program is being run at a central station while attempts are being made to surmount these difficulties.

Medical informatics in the intensive care unit: state of the art 1991

Intensive care medicine requires timely, accurate, and integrated patient records to provide the highest quality patient care. Computerized patient records offer the best method to achieve these needs. The expectations of society for medical progress through increased use of computers is growing. For optimal use of computers in the ICU there must be a harmonious collaboration between medical informaticists, physicians, nurses, therapists, and administrators. The future use of computers in ICU care will be evolutionary rather than revolutionary. We are on the frontier of some exciting times in the next decade as computers become commonplace in the clinical care process rather than an unusual event. This paper discusses the progress and challenges of computers in the ICU.

Human factors and computerisation in intensive care units: a review

Current literature on the computerisation of Intensive Care Units indicates that many human factor considerations are relevant to the design and introduction of computer systems and to the evaluation of such systems within this environment. This paper aims to review and summarise essential points from the literature.

Users' perceptions of a computerised information system in intensive care (ABICUS) on introduction and after 2 months use

The aim of the present study was to assess the perceived utility of a computerised information system in an intensive care unit (ICU). Questionnaires were devised in which ICU staff indicated the ease or difficulty of obtaining and recording information (a) under the previous manual system, (b) soon after the introduction of the computerised system and (c) two months after computerisation. Results indicated the system was well received immediately and this favourable attitude persisted unchanged after two months experience. The questionnaire method also served to pinpoint some particular interface problems which are to be remedied in future versions of the system.