Brijesh V. Patel ^1,2 Sharon Mumby ³ Nicholas Johnson ⁴ Rhodri Handslip ¹ Sunil Patel ¹ Teresa Lee ¹ Martin S. Andersen ⁵ Emanuela Falaschetti ⁴ Ian M. Adcock ³ Danny McAuley ⁶ Masao Takata ¹ Thomas Staudinger ⁷ Dan S. Karbing ⁵ Matthieu Jabaudon ⁸ Peter Schellongowski ⁷ Stephen E. Rees ^5,9*

• ¹ Section of Anaesthetics, Pain Medicine and Intensive Care, Department of Surgery and Cancer, Faculty of Medicine, Imperial College London, London, England, United Kingdom
• ² Royal Brompton Hospital, London, United Kingdom
• ³ Airways Disease Section, National Heart and Lung Institute, Faculty of Medicine, Imperial College London, London, England, United Kingdom
• ⁴ Imperial Clinical Trials Unit, Imperial College London, London, United Kingdom
• ⁵ Department of Health Science and Technology, Aalborg University, Aalborg, Denmark
• ⁶ Wellcome-Wolfson Centre for Experimental Medicine, Faculty of Medicine, Health and Life Sciences, Queen's University Belfast, Belfast, Northern Ireland, United Kingdom
• ⁷ Department of Emergency Medicine, Medical University of Vienna, Vienna, Vienna, Austria
• ⁸ Service de Anesthésie Réanimation, Centre Hospitalier Universitaire de Clermont-Ferrand, Clermont Ferrand, France
• ⁹ Aalborg University, Aalborg, Denmark

Background. Acute respiratory distress syndrome (ARDS) is highly heterogenous, both in clinical presentation and in the physiological response of patients to changes in mechanical ventilator settings such as PEEP. This study investigates the clinical efficacy of a physiological model-based ventilatory decision support system (DSS) to personalize ventilator therapy in ARDS patients. Methods. An international, multi-centre, randomized, open-label study enrolling patients with ARDS during the COVID-19 pandemic (registered in clinicaltrials.gov (NCT04115709)), with patients randomized to having the advice of the system active (intervention) or not (control). The primary outcome was to detect a reduction in average driving pressure between groups. Secondary outcomes included several clinically relevant measures of respiratory physiology, ventilator free days; time from control mode to support mode; number of changes in ventilator settings per day; percentage of time in control and support mode ventilation; ventilation related and device related adverse events; and number of times the advice is followed. Results. 95 patients were randomized to this study. The DSS showed no effect in the average driving pressure between arms. Patients in the intervention arm had statistically improved oxygenation index when in support mode ventilation (-1.41, 95% CI: -2.76, -0.08; p=0.0370). Ventilatory ratio was also significantly improved in the intervention arm for patients in control mode ventilation (-0.63, 95% CI: -1.08, -0.17, p= 0.0068). The application of the DSS resulted in a significantly increased number of ventilator changes for pressure settings and respiratory frequency. Conclusions. The application of a physiological model-based decision support system for advice on mechanical ventilation in patients with COVID-19 and non-COVID-19 ARDS showed no significant difference in driving pressure as a primary outcome measure, but that that application of about 60% of advice improved the patient’s physiological state.