Integrating data, models, and reasoning in critical care

Medical staff in the Intensive Care Unit (ICU) need to interpret the high volumes of noisy data generated from the monitors attached to their patients. In this paper we propose a software architecture which processes the ICU monitor data to remove clinically insignificant events and to provide enhanced clinical decision support to ICU staff in order to improve the quality of patient care by giving accurate summaries. Our architecture has been tested on three datasets from an adult ICU and six datasets from a neonatal ICU and the results are very encouraging.

Critical care medicine, 2011

Measurement, 1991

This paper focuses upon the need to provide information to the clinician in the critical care unit in order to enhance the decision-making capability. The role of intelligent instrumentation is highlighted, indicating its function in converting data into information which is then interpreted in the clinical context. Examples drawn from the interpretation of blood gas results and the provision of ventilation management are presented. The role of intelligent instrumentation in the wider role of patient management is discussed.

The intensive care unit (ICU) is a highly complex environment that houses critically ill patients requiring constant monitoring and care, as well as vast amounts of time-oriented data disseminated through a range of health information technologies (HIT), e.g., bedside and clinical decision support systems. Studies show the occurrence of medical mishaps due to diagnostic errors, impacting patient safety in spite of advances in HIT. Available visual representations of data, although time-oriented and multivariate, lack contextual information for communication among the ICU intensivists. We present a medical data visualization system (MIVA) that delivers multivariate data via a visualization display. The system organizes data into controllable time resolutions, providing contextual knowledge and communication tools at point-of-care. When comparing MIVA to paper charts, findings from two studies suggest that MIVA enabled significantly greater speed and accuracy during an in-lab experime...

Web of science[Bulletin of Environment, Pharmacology and Life Sciences], 2022

In the modern-day world, patients with critical conditions get monitored in the intensive care units in which every condition of the patient is monitored and necessary treatment is taken in a timely. These patients are susceptible to many diseases and that’s why many of their important and damaged organs are taken special care of. To provide such an amount of care to a single patient, much of the staff is required on a single patient for 24 hours. Due to such an amount of care, a lot of useful data is generated which can play an important role to understand many important factors which get ignored usually. To make sense of such large data on paper for a doctor is a very difficult task that can consume a lot of time and still we don’t know the analyzed finding are correct or not. To detect high risks and failure of the organs, machine learning can play an important role to detect such events and actions can be taken place promptly. In this paper, findings from a lot of research papers have been discussed and summarized to give the best possible solution. The goal of this research article is to give useful insights that can improve the already available models. Keywords: Patient Monitoring System, Artificial Intelligence, Intensive Care Unit (ICU)

2010

Intensive Care Medicine, 2020

TheScientificWorldJournal, 2015

There is a broad consensus that 21st century health care will require intensive use of information technology to acquire and analyze data and then manage and disseminate information extracted from the data. No area is more data intensive than the intensive care unit. While there have been major improvements in intensive care monitoring, the medical industry, for the most part, has not incorporated many of the advances in computer science, biomedical engineering, signal processing, and mathematics that many other industries have embraced. Acquiring, synchronizing, integrating, and analyzing patient data remain frustratingly difficult because of incompatibilities among monitoring equipment, proprietary limitations from industry, and the absence of standard data formatting. In this paper, we will review the history of computers in the intensive care unit along with commonly used monitoring and data acquisition systems, both those commercially available and those being developed for res...

Mayo Clinic Proceedings, 2010

OBJECTIVE: To develop and validate an informatics infrastructure for syndrome surveillance, decision support, reporting, and modeling of critical illness.

Information Technology in Bio- and Medical Informatics, 2014

In the Intensive Care Units (ICU) it is notorious the high number of data sources available. This situation brings more complexity to the way of how a professional makes a decision based on information provided by those data sources. Normally, the decisions are based on empirical knowledge and common sense. Often, they don't make use of the information provided by the ICU data sources, due to the difficulty in understanding them. To overcome these constraints an integrated and pervasive system called INTCare has been deployed. This paper is focused in presenting the system architecture and the knowledge obtained by each one of the decision modules: Patient Vital Signs, Critical Events, ICU Medical Scores and Ensemble Data Mining. This system is able to make hourly predictions in terms of organ failure and outcome. High values of sensitivity where reached, e.g. 97.95% for the cardiovascular system, 99.77% for the outcome. In addition, the system is prepared for tracking patients' critical events and for evaluating medical scores automatically and in real time.

IEEE Transactions on Information Technology in Biomedicine, 1997

Validation of intelligent systems is an important task to perform. Typically the results of the validation analysis are used to verify whether or not the system satisfies the initial design requirements, and to acquire new knowledge and/or refine the knowledge already acquired. In practice, the validation of intelligent systems usually requires the application of several different techniques (e.g., retrospective, prospective, quantitative). In this work the authors present the methodology devised to validate PATRICIA: an intelligent monitoring system designed to advise clinicians on the management of patients dependent on mechanical ventilation. The application of this methodology requires that appropriate validation paradigms are selected, depending on both the application domain and the characteristics of the intelligent system. The article also presents and discusses validation results.

1983

An interactive patient data base system for recording of patient data and trend analysis was developed for use in a respiratory intensive care unit. The system incorporates patient demographic information, as well as forty-five numerical cardiopulmonary variables. Numerical data may be displayed in either tabular or graphical form. Graphical trend analysis is allowed in time or between any selected variables. In addition, the system allows for removal of patient data (at the end of the patient's stay) for compact, permanent storage on a floppy disk.

British Journal of Anaesthesia, 2006

Recently there has been an upsurge of interest in strategies for detecting at-risk patients in order to trigger the timely intervention of a Medical Emergency Team (MET), also known as a Rapid Response Team (RRT). We review a real-time automated system, BioSign, which tracks patient status by combining information from vital signs monitored non-invasively on the general ward. BioSign fuses the vital signs in order to produce a single-parameter representation of patient status, the Patient Status Index. The data fusion method adopted in BioSign is a probabilistic model of normality in five dimensions, previously learnt from the vital sign data acquired from a representative sample of patients. BioSign alerts occur either when a single vital sign deviates by close to ±3 standard deviations from its normal value or when two or more vital signs depart from normality, but by a smaller amount. In a trial with high-risk elective/emergency surgery or medical patients, BioSign alerts were generated, on average, every 8 hours; 95% of these were classified as 'True' by clinical experts. Retrospective analysis has also shown that the data fusion algorithm in BioSign is capable of detecting critical events in advance of single-channel alerts.

Twentieth IEEE International Symposium on Computer-Based Medical Systems (CBMS'07), 2007

Intensive Care Units are widely considered as the most technologically advanced environments within a hospital. In such environments, physicians are confronted with multiple medical devices that monitor the inpatients. The capability to collect, store, process, and share inpatient monitoring data along with the remarks of the treating physicians can bring tremendous benefits to all aspects of Intensive Care Medicine (practice, research, education). The IC-Window makes it feasible for physicians to extract, view, store, and replay Clinically Interesting Episodes through simple, intuitive user interfaces.

This paper introduces the INTCare system, an intelligent decision support system for intensive medi- cine. The system aims at the automation of the Knowledge Discovery Process by using autonomous agents that are responsible for the various constituent steps. The system enables automation of data acquisition and model updating avoiding human intervention. We present the first impres- sions after the deployment of INTCare in a real environ- ment (Intensive Care Unit of the Hospital de Santo António, Oporto, Portugal) where it is supporting the physicians' decisions by means of prognostic Data Mining models. In particular, these techniques are used to predict organ failure and mortality assessment. The main intention is to change the current reactive behaviour to a pro-active one, enhancing the Quality of Service.