Intensive Care Unit Patient Data Research Articles

Predictive modelling of survival and length of stay in critically ill patients using sequential organ failure scores.

The length of stay of critically ill patients in the intensive care unit (ICU) is an indication of patient ICU resource usage and varies considerably. Planning of postoperative ICU admissions is important as ICUs often have no nonoccupied beds available. Estimation of the ICU bed availability for the next coming days is entirely based on clinical judgement by intensivists and therefore too inaccurate. For this reason, predictive models have much potential for improving planning for ICU patient admission. Our goal is to develop and optimize models for patient survival and ICU length of stay (LOS) based on monitored ICU patient data. Furthermore, these models are compared on their use of sequential organ failure (SOFA) scores as well as underlying raw data as input features. Different machine learning techniques are trained, using a 14,480 patient dataset, both on SOFA scores as well as their underlying raw data values from the first five days after admission, in order to predict (i) the patient LOS, and (ii) the patient mortality. Furthermore, to help physicians in assessing the prediction credibility, a probabilistic model is tailored to the output of our best-performing model, assigning a belief to each patient status prediction. A two-by-two grid is built, using the classification outputs of the mortality and prolonged stay predictors to improve the patient LOS regression models. For predicting patient mortality and a prolonged stay, the best performing model is a support vector machine (SVM) with GA,D=65.9% (area under the curve (AUC) of 0.77) and GS,L=73.2% (AUC of 0.82). In terms of LOS regression, the best performing model is support vector regression, achieving a mean absolute error of 1.79 days and a median absolute error of 1.22 days for those patients surviving a nonprolonged stay. Using a classification grid based on the predicted patient mortality and prolonged stay, allows more accurate modeling of the patient LOS. The detailed models allow to support the decisions made by physicians in an ICU setting.

Prediction of survival of ICU patients using computational intelligence

This paper presents a computational-intelligence-based model to predict the survival rate of critically ill patients who were admitted to an intensive care unit (ICU). The prediction input variables were based on the first 24h admission physiological data of ICU patients to forecast whether the final outcome was survival or not. The prediction model was based on a particle swarm optimization (PSO)-based Fuzzy Hyper-Rectangular Composite Neural Network (PFHRCNN) that integrates three computational intelligence tools including hyper-rectangular composite neural networks, fuzzy systems and PSO. It could help doctors to make appropriate treatment decisions without excessive laboratory tests. The performance of the proposed prediction model was evaluated on the data set collected from 300 ICU patients in the Cathy General Hospital in 2012. There were 10 input variables in total for the prediction model. Nine of these variables (e.g. systolic arterial blood pressures, systolic non-invasive blood pressures, respiratory rate, heart rate, and body temperature) were routinely available for 24h in ICU and the last variable is patient's age. The proposed model could achieve a 96% and 86% accuracy rate for the training data and testing data, respectively.

Presymptomatic Prediction of Sepsis in Intensive Care Unit Patients

Postoperative or posttraumatic sepsis remains one of the leading causes of morbidity and mortality in hospital populations, especially in populations in intensive care units (ICUs). Central to the successful control of sepsis-associated infections is the ability to rapidly diagnose and treat disease. The ability to identify sepsis patients before they show any symptoms would have major benefits for the health care of ICU patients. For this study, 92 ICU patients who had undergone procedures that increased the risk of developing sepsis were recruited upon admission. Blood samples were taken daily until either a clinical diagnosis of sepsis was made or until the patient was discharged from the ICU. In addition to standard clinical and laboratory parameter testing, the levels of expression of interleukin-1beta (IL-1beta), IL-6, IL-8, and IL-10, tumor necrosis factor-alpha, FasL, and CCL2 mRNA were also measured by real-time reverse transcriptase PCR. The results of the analysis of the data using a nonlinear technique (neural network analysis) demonstrated discernible differences prior to the onset of overt sepsis. Neural networks using cytokine and chemokine data were able to correctly predict patient outcomes in an average of 83.09% of patient cases between 4 and 1 days before clinical diagnosis with high sensitivity and selectivity (91.43% and 80.20%, respectively). The neural network also had a predictive accuracy of 94.55% when data from 22 healthy volunteers was analyzed in conjunction with the ICU patient data. Our observations from this pilot study indicate that it may be possible to predict the onset of sepsis in a mixed patient population by using a panel of just seven biomarkers.

Comparison of a commercially available clinical information system with other methods of measuring critical care outcomes data

Purpose: To compare the quality of data recorded by a commercially available clinical information system (CIS) to other commonly used methods for obtaining large amounts of patient data. Materials and methods: Five sets of clinical patient data were chosen as a cross-section of all the data collected by a CIS in our intensive care unit (ICU): 1) Length of stay in the ICU, 2) Vital signs, 3) Days of mechanical ventilation, 4) medications, and 5) diagnoses. Data generated by our ICU CIS was compared with other parallel data sets commonly used to obtain the same data for clinical research. Results: When compared with our CIS, the hospital database recorded a length of stay at least 1 day longer than the actual length of stay 53% of the time. A search of 139,387 sets of vital signs showed less than 0.1% rate of suspected artifact. When compared to direct observation, our CIS correctly recorded days of mechanical ventilation in 23 of 26 patients (88%). Two other data sets, medical diagnoses and medications given showed significant differences with other commonly used databases of the same information collected outside the ICU (billing codes and pharmacy records respectively Conclusions: Compared to other commonly used data sources for clinical research, a commercially available CIS is an acceptable source of ICU patient data.

Real time monitoring and analysis via the medical information bus, Part I.

Because of the complexity of monitored data in modern intensive care units (ICUs), and the risk of information being overlooked if medical staff have to pay attention to a multiplicity of monitoring apparatuses and alarm signals, the data for each patient may well be best presented on a single bedside screen after digestion by expert system techniques. Such central units should be able to deal with data from any monitoring apparatus, not just a predefined set. Furthermore, relay of the information from each bed to a central control station (one per ICU) is desirable for the purposes of permanent storage and for in-depth analysis. The paper describes a comprehensive system for ICU monitoring management and patient data analysis that integrates multiple expert systems and computers. The basic difficulties in applying expert system techniques to monitoring are overcome with the shell OPS/83, which allows calls to sequential C routines and allows time-driven reasoning through appropriate design of the inference engine and rules. Flexibility as regards connectable monitoring apparatus is afforded by basing data acquisition mainly, though not exclusively, on the IEEE Medical Information Bus.

Eight year's experience with automated anesthesia record keeping: lessons learned--new directions taken.

For the past eight years, an automated anesthesia record keeping system, COMANDAS (COMputerized ANesthesia Data Acquisition System) has been used in the cardiovascular operating rooms at Mayo Clinic. The automated anesthesia record is designed to match the traditional hand-written record and becomes part of the official medical record. COMANDAS is interfaced with the physiologic monitor and mass spectrometer in each OR, and a number of other computers within the Mayo Medical Center. Since the introduction of COMANDAS over 24,000 surgical procedures have been charted. The anesthesia record is more complete, consistent in organization, and legible when compared to a hand-written record. Recently, it was determined that the computers and peripherals that make up COMANDAS were wearing out and that the vendors would no longer support or replace the equipment. A process to find a replacement for COMANDAS was then begun. Although the cardiovascular anesthesia group was satisfied with the automated anesthesia record, there were a number of areas in which improvement was desired. A systematic evaluation of the system was begun with a survey of the users. The majority of those surveyed felt that COMANDAS was a useful system which made parts of their job easier. The user interface, method of manual data entry, time to produce the record and difficulty learning the system were the source of the greatest dissatisfaction. Artifacts, networking, interfacing with other devices and computers were also issues for the replacement system. Most commercial systems were found wanting in one or more areas of significance. The most practical solution appeared to be the modification of a currently available intensive care unit patient data management system.

Comprehensive Computerized Neonatal Intensive Care Unit Data System Including Real-Time, Computer-Generated Daily Progress Notes

A neonatal intensive care unit patient data system, NeoData, which was developed using microcomputers connected by a local area network, is described. The system allows for real-time generation of daily progress notes, as well as admission and discharge summaries. It includes two databases: one for daily patient data and one for admission/discharge summary data. Both sets of data are easily accessible for later analysis and report generation. The daily patient data are entered directly into a computer by the neonatal intensive care unit medical and nurse practitioner staff; a progress note is printed immediately thereafter for inclusion in the patient's chart. Data from the previous day are selectively carried forward into the current day's note, minimizing data entry. Several benefits are derived from this progress note system, including legibility, tracking of laboratory and other data, tracking of management plans and procedures due at a later date, and significant time savings. The system has proved to be easy to learn, and the neonatal intensive care unit staff have found it to contribute to the efficient delivery of patient care.