Virtual clinical trials for mechanically ventilated respiratory failure patients under volume-controlled ventilation - The Challenges of Volume-Control Protocols

Resource-intensive clinical trial is a crucial step in validating the safety and effectiveness of personalised, model-based mechanical ventilation (MV) treatments prior to implementation as a clinical standard of care. An alternative first step would be validated in-silico virtual patient (VP) trials. This study evaluates the efficacy of two model-based MV protocols (MBP) in regulating key pressure-based MV outcomes in volume-controlled MV using a well-established in-silico, virtual trial methodology. Two modified, closed-loop MBPs were implemented on volume-controlled VPs (N=18; 955 hours MV data) to derive protocol-suggested MV settings and resulting VP responses to these MV settings. Virtual trial outcomes were compared between the two protocols, and with the retrospective clinical data, by assessing the adherence of measured VP responses to established clinical safety thresholds. A successful intervention is defined as an intervention interval during which the protocol successfully recommended a safe combination of MV settings, defined by established clinical safety thresholds. Both protocols performed 637 interventions with a success rate of 93.72%, improving the overall adherence of measured VP responses to established clinical safety thresholds by ∼53% compared to the retrospective clinical data. This virtual trial further validates the efficacy of VPs for long-term safety and performance assessments of MBPs. They also demonstrate the potential to safely streamline the development, optimisation and validation process of new MV decision support systems, as has been done in other areas of care. The overall outcomes could ultimately accelerate opportunities for the successful translation of these systems into clinical practice.