Related Experiment Video
Updated: Sep 25, 2026
Monitoring Lung Function with Electrical Impedance Tomography in the Intensive Care Unit
Published on: September 6, 2024
Intelligent Lung Support in the Intensive Care Unit (IntelliLung): study protocol for an international observational,
Raphael Theilen1, Robert Huhle1, Martin Scharffenberg1
1Department of Anesthesiology and Intensive Care Medicine, Pulmonary Engineering Group, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany.
Introduction:
Mechanical ventilation (MV) is lifesaving in the intensive care unit (ICU) but can cause complications if not individualised according to the patient's needs. Artificial intelligence (AI)-driven decision support systems (AI-DSS) may theoretically optimise MV settings. This international observational, prospective, multicentre study aims to validate the IntelliLung AI-DSS in real clinical environments.
Methods And Analysis:
In this study, patients aged ≥18 years requiring invasive MV for >24 hours are included. The primary objective is to evaluate the agreement between IntelliLung AI-DSS MV recommendations and the ventilator settings implemented by healthcare providers. The IntelliLung AI-DSS continuously analyses patient-specific data, including respiratory mechanics and gas exchange, to recommend optimal MV parameters. The primary endpoints are the relative time of matching ventilator settings for each (1) positive end-expiratory pressure, (2) fraction of inspired oxygen, (3) respiratory rate and (4) tidal volume during volume-controlled ventilation or inspiratory pressure (Pinsp) during pressure-controlled ventilation. Secondary endpoints include assessments of ventilator-free days and clinical decision-making practices. Patient-centred outcomes, such as quality of life and psychological stress, are also evaluated. Data collection spans ICU stay and follow-up at 30 and 180 days after enrolment. This trial is the first to validate the IntelliLung AI-DSS in a prospective, real-world clinical setting by comparing recommendations given by the IntelliLung AI-DSS to local standards of care. The results of the trial will serve as a foundation for future interventional studies to assess the IntelliLung AI-DSS impact on patient outcomes and ICU workflows. The study addresses a critical gap in the application of AI to intensive care, advancing personalised and evidence-based MV management.
Ethics And Dissemination:
The TUD Medical Faculty Ethical Committee for clinical research approved the study on 4 November 2024 (File number Mono-EK-27907202). Additionally, the institutional review board at Sabadell, Madrid and Warsaw approved the study. IntelliLung is designed in accordance with the principles of the Declaration of Helsinki. The final main results will be published in a highly ranked, peer-reviewed scientific journal taking into account the recommendations of the International Committee of Medical Journal Editors.
Trial Registration Number:
NCT06595602.
