AI systems in clinical practice

Acute care systems
Automated clinical guidelines in Mechanical Ventilation

Knowledge-based system for the management of mechanical ventilation in Intensive Care Units (ICUs)

developed by clinical domains keywords
Draeger Medical, Intensive Care, Hôpital Henri Mondor, Créteil, France and the French National Institute for Health and Medical Research (INSERM). Management of mechanical ventilation in Intensive Care Units Knowledge-based system, clinical guidelines
location commissioned status
Hôpital Henri Mondor, Créteil, France; Hospital Sant Pau, Barcelona, Spain; University Hospital, Geneva, Switzerland; Cliniques Universitaires St-Luc, Bruxelles, Belgique; Università Cattolica, Rome, Italy; AKH Wien, Wien, Austria; University Hospital, Dresden, Germany; University Hospital, Kiel, Germany; Hôpital Bichat, Bichat, France; Bristol Royal Infirmary, Bristol, UK. A version of Automedon has been in use at the Hôpital Henri Mondor, Créteil, France since 2001.

Automedon has been embedded in Dräger Medical's EvitaXL ventilator system (commissioned mid-2003). The embedded guideline engine is a Dräger Medical product called SmartCare. The PC implementation of Automedon is is fully EU-approved but designed for research use by Dräger customers (university hospitals etc).

In clinical use
Automedon is a knowledge based workbench and methodology for computerizing, automating and executing clinical guidelines applied to critical care ventilators. Automedon is a successor to and enhancement of the NéoGanesh system, and complies with industrial requirements and regulatory quality standards such as ISO-EN 46001 and ISO 9000.

With Automedon, every clinical guideline that is appropriate for a given ventilator can be automated. The core paradigm is that if a medical device, i.e. ventilator allows for read access to its measurements, settings and contextual information (alarms, manoeuvres ...) as well as for write access to all its settings, then every clinical guideline for that medical device is potentially applicable.

The underlying methodology comprises knowledge engineering techniques, e.g. for eliciting, modelling and computerizing clinical guidelines, expert system techniques e.g. rule based forward chaining with temporal reasoning and software engineering techniques, e.g. for automated source code generation and integration with the ventilator.

A clinical guideline for pressure support ventilation has (January 2003) been implemented with Automedon for Dräger’s Evita 4 ventilator system. This EU-approved system has been successfully utilized in clinical practice in a study based in two separate centres. Its clinical benefit is currently being evaluated by a multi-centre european study involving six university hospitals. Dräger is also marketing the PC implementation of Automedon.

The pressure support system was introduced in 2003, embedded to Draeger’s new EvitaXL ventilator.

Automedon has been superseded by SmartCare™ technology and SmartCare™/PS (Pressure Support): a knowledge-based system for the management of mechanical ventilation in Intensive Care Units.

Mersmann S, Dojat M. A Flexible System Architecture for Implementation of Protocol-Based Controllers in Mechanical Ventilation. Proceedings of Workshop on "Computers in Anaesthesia and Intensive Care: Knowledge-Based Information Management" July 1th, Cascais (PT), (2001)

[]   []

" "

Dojat M, Pachet F, Guessoum Z, Touchard D, Harf A, Brochard L, NéoGanesh: a Working System for the Automated Control of Assisted Ventilation in ICUs, Art Intell Med, 11,97-117, (1997)

[]   []

" "

Dojat M, Harf A, Touchard D, Lemaire F and Brochard L. Clinical Evaluation of a Computer-Controlled Pressure Support Mode, Am. J. Respir. Crit. Care Med. 2000;161:1161-66.

[PubMed]   [American Journal of Respiratory and Critical Care Medicine]

" We have designed a computerized system providing closed-loop control of the level of pressure support ventilation (PSV). The system sets itself at the lowest level of PSV that maintains respiratory rate (RR), tidal volume (VT), and end-tidal CO(2) pressure (PET(CO(2))) within predetermined ranges defining acceptable ventilation (i.e., 12 < RR < 28 cycles/min, VT> 300 ml [> 250 if weight < 55 kg], and PET(CO(2)) < 55 mm Hg [< 65 mm Hg if chronic CO(2) retention]). Ten patients received computer-controlled (automatic) PSV and physician-controlled (standard) PSV, in random order, during 24 h for each mode. An estimation of occlusion pressure (P(0.1)) was recorded continuously. The average time spent with acceptable ventilation as previously defined was 66 +/- 24% of the total ventilation time with standard PSV versus 93 +/- 8% with automatic PSV (p < 0.05), whereas the level of PSV was similar during the two periods (17 +/- 4 cm H(2)O versus 19 +/- 6 cm H(2)O). The time spent with an estimated P(0.1) above 4 cm H(2)O was 34 +/- 35% of the standard PSV time versus only 11 +/- 17% of the automatic PSV time (p < 0.01). Automatic PSV increased the time spent within desired ventilation parameter ranges and apparently reduced periods of excessive workload. "

Bouadma L, Lellouche F, Cabello B, Porta V, Deye N, Levy S, Mancebo J, Brochard L, Use of an Automated Control System to adapt the level of Pressure Support and manage Weaning, Proceedings of European Society of Intensive Care Medicine, Barcelona (ES), (2001)

[]   []

" "
contact links

E: Michel Dojat (INSERM)
E: Stefan Mersmann (Dräger Medical)

 bullet  Automedon: further information  bullet  NéoGanesh [OC]  bullet  SmartCare/PS [OC]
Michel DOJAT (INSERM); Stefan Mersmann (Dräger Medical).

Entry on archive: March 20 2003
Last main update: March 25 2003; amendments July 18 2003
Search this site


Privacy policy User agreement Copyright Feedback

Last modified:
© Copyright OpenClinical 2002-2011