Marie-Christine Chambrin

INFORM : European survey of computers in intensive care units

SummaryThe aims of this study were (a) to survey and evaluate the impact of information technology applications in High Dependency Environments (HDEs) on organizational, psychological and cost-effectiveness factors, (b) to contribute information and design requirements to the other workpackages in the INFORM Project, and (c) to develop useful evaluation methodologies.The evaluation methodologies used were: questionnaires, case studies, objective findings (keystroke) and literature search and review. Six questionnaires were devised covering organizational impact, cost-benefit impact and perceived advantages and disavvantages of computerized systems in HDE (psychological impact).The general conclusion was that while existing systems have been generally well received, they are not yet designed in such a developed and integrated way as to yield their full potential. Greater user involvement in design and implementation and more emphasis on training emerged as strong requirements. Lack of reliability leading to parallel charting was a major problem with the existing systems. It proved difficult to assess cost effectiveness due toa lack of detailed accounting costs; however, it appeared that in the short term, computerisation in HDEs tended to increase costs. It is felt that through a better stock control and better decision making, costs may be reduced in the longer run and effectiveness increased; more etailed longitudinal studies appear to be needed on this subject.

INFORM: development of information management and decision support systems for High Dependency Environments.

The long-term aim in the INFORM Project is to develop, evaluate and implement a new generation of Information Systems for hospital High Dependency Environments (HDE — Intensive Care Units, Neonatal Units, Burns Units, Operating and Recovery Rooms, and other specialised areas). The distinguishing feature of the HDE is the very large amount of data that is collected through monitors and paper records about the state of critically ill patients; this has made the role of the staff a technical one in addition to a caring one. The INFORM System will integrate Decision Support with on-line, off-line and observed patient data and, in addition, will incorporate and integrate unit management features.In the Exploratory Phase of the Project, functional requirements have been set out. These are based on four components: conceptual model of the HDE; evaluation of existing HDE Information Systems; development of a novel software architecture using a Knowledge-Based Systems (KBS) methodology, and based on a critical review of KBS applied to the HDE; monitoring of appropriate leading-edge technological developments.The conceptual model has two components: a patient-related information model, and a department-related cost model. The patient-related model is identifying key and difficult areas of decision making. A key aspect of INFORM is integration of clinical Decision Support for these areas into the Information System through a layered software architecture. The lower layers are concerned with monitoring and alarming and the higher levels with patient assessment and therapy planning. The functionality and interconnection of these layers are being determined.

Computer-assisted evaluation of respiratory data in ventilated critically ill patients

In intensive care unit, a lot of data are currently available but remain unused by nurses and residents because of complexity of analysis. We have developed a system for interpretation of respiratory data (RESPAID) in order to improve monitoring of patients under respiratory support and also to provide a high level of information. RESPAID is a real-time system which interprets quantitative and qualitative aspects of the usual respiratory data at different levels of information. Initial knowledge base was built from data given by four specialists in intensive care. Major attention was paid to different aspects of the system: monitor interface, user interface and time representation. Data are issued from standard respirators and/or monitors used in the intensive care unit. Informations provided by RESPAID are alarm identification, ventilator settings modification and proposal for physiological evolution of the patient or suspected complication.RESPAID runs on IBM PCAT3 with 1st class shell. It is currently in clinical validation procedure.

A new approach to the abstraction of monitoring data in intensive care

Data driven interpretation of multiple physiological measurements in the domain of intensive care is a key point to provide decision support. The abstraction method presented in this paper provides two levels of symbolic interpretation. The first, at mono parametric level, provides 4 classes (increasing, decreasing, constant and transient) by combination of trends computed at two characteristic spans. The second, at multi parametric level, gives an index of global behavior of the system, that is used to segment the observation. Each segment is therefore described as a sequence of words that combines the results of symbolization. Each step of the abstraction process leads to a visual representation that can be validated by the clinician. Construction of sequences do not need any prior introduction of medical knowledge. Sequences can be introduced in a machine learning process in order to extract temporal patterns related to specific clinical or technical events.

INFORM: integrated support for decisions and activities in intensive care

SummaryMany medical decision support systems that have been developed in the past have failed to enter routine clinical practice. Often this is because the developers have failed to analyse in sufficient detail the precise user requirements, because they have produced a system which takes too narrow a view of the patient, or because the decision support facilities have not been sufficiently well integrated into the routine clinical data handling activities. In this paper we discuss how the AIM-INFORM project is setting out to deal with these issues, in the context of the provision of decision support in the intensive care unit.

RESPAID: computer aided decision support for respiratory data in ICU

A prototype developed to support interpretation of respiratory data for ventilated patients is described. Data are taken from standard respirators and/or monitors used in intensive care units (ICUs). An initial knowledge base was built from data given by four specialists in intensive care. Both quantitative and qualitative aspects were taken into account. Major attention was paid to different aspects of the system: monitor interface to produce valid data, user interface and time representation. The prototype, called RESPAID, runs in real-time on an IBM PC AT3 with first class shell. This shell uses the concept of learning from examples. RESPAID is currently undergoing clinical validation.<<ETX>>

Automatic characterization of events on SpO2 signal : comparison of two methods

Two methods based on trend extraction have been designed to provide automatic analysis of physiological data recorded on adult patients hospitalized in intensive care unit. We focused our work on the characterization of events occurring on SpO2 signal, this signal being used to detect vital problems. Our aim was to recognize events related to technical or vital problems to assist medical staff in his decision process. Our results show that both methods are able to detect and distinguish between probe deconnection, transient hypoxia and desaturation events.

A neural approach to knowledge base systems

An implementation for Knowledge Base systems using an Object Oriented data structure and a Neural type inference motor. Advantages are : Knowledge structuration, speed, compatibility with parallel computing, dynamic evolution of the knowledge base.

ICU Patient State Characterization Using Machine Learning in a Time Series Framework

We present a methodology for the study of real-world time-series data using supervised machine learning techniques. It is based on the windowed construction of dynamic explanatory models, whose evolution over time points to state changes. It has been developed to suit the needs of data monitoring in adult Intensive Care Unit, where data are highly heterogeneous. Changes in the built model are considered to reflect the underlying system state transitions, whether of intrinsic or exogenous origin. We apply this methodology after making choices based on field knowledge and ex-post corroborated assumptions. The results appear promising, although an extensive validation should be performed.

AutoRegulated Inspiratory Support ventilation

In order to avoid the inconvenients related to available methods of weaning (risk of hypo and hyperventlation, lung hyperinflation, and necessity to modify settings frequently to meet the patients needs), we propose a new mode of ventilation whose main characteristics are : controlled tidal volume, decreasing inspiratory flow pattern, zero flow cycled, automatic regulation from spontaneous breathing to volumetric controlled ventilation according to patients needs. Using a prototype, we have compared this new mode with controlled ventilation. With respect of minute ventilation, we found a significant decrease in peak airway pressure whereas there were no difference in mean airway pressure and blood gas results. This mode has then been implemented in a ventilator