Artificial intelligence for closed-loop ventilation therapy with hemodynamic control using the open lung concept

Abstract

Purpose – The purpose of this paper is to develop an automatic control system for mechanical ventilation therapy based on the open lung concept (OLC) using artificial intelligence. In addition, mean arterial blood pressure (MAP) is stabilized by means of a decoupling controller with automated noradrenaline (NA) dosage to ensure adequate systemic perfusion during ventilation therapy for patients with acute respiratory distress syndrome (ARDS). Design/methodology/approach – The aim is to develop an automatic control system for mechanical ventilation therapy based on the OLC using artificial intelligence. In addition, MAP is stabilized by means of a decoupling controller with automated NA dosage to ensure adequate systemic perfusion during ventilation therapy for patients with ARDS. Findings – This innovative closed-loop mechanical ventilation system leads to a significant improvement in oxygenation, regulates end-tidal carbon dioxide for appropriate gas exchange and stabilizes MAP to guarantee proper systemic perfusion during the ventilation therapy. Research limitations/implications – Currently, this automatic ventilation system based on the OLC can only be applied in animal trials; for clinical use, such a system generally requires a mechanical ventilator and sensors with medical approval for humans. Practical implications – For implementation of a closed-loop ventilation system, reliable signals from the sensors are a prerequisite for successful application. Originality/value – The experiment with porcine dynamics demonstrates the feasibility and usefulness of this automatic closed-loop ventilation therapy, with hemodynamic control for severe ARDS. Moreover, this pilot study validated a new algorithm for implementation of the OLC, whereby all control objectives are fulfilled during the ventilation therapy with adequate hemodynamic control of patients with ARDS.