ABSTRACT: BACKGROUND: Dynamic hyperinflation, hereafter called AutoPEEP (auto-positive end expiratory pressure)with some slight language abuse, is a frequent deleterious phenomenon in patients undergoingmechanical ventilation. Although not readily quantifiable, AutoPEEP can be recognized onthe expiratory portion of the flow waveform. If expiratory flow does not return to zero beforethe next inspiration, AutoPEEP is present. This simple detection however requires the eye ofan expert clinician at the patient's bedside. An automatic detection of AutoPEEP should behelpful to optimize care. METHODS: In this paper, a platform for automatic detection of AutoPEEP based on the flow signalavailable on most of recent mechanical ventilators is introduced. The detection algorithms aredeveloped on the basis of robust non-parametric hypothesis testings that require no priorinformation on the signal distribution. In particular, two detectors are proposed: one is basedon SNT (Signal Norm Testing) and the other is an extension of SNT in the sequentialframework. The performance assessment was carried out on a respiratory system analog andex-vivo on various retrospectively acquired patient curves. RESULTS: The experiment results have shown that the proposed algorithm provides relevant AutoPEEPdetection on both simulated and real data. The analysis of clinical data has shown that theproposed detectors can be used to automatically detect AutoPEEP with an accuracy of 93%and a recall (sensitivity) of 90%. CONCLUSIONS: The proposed platform provides an automatic early detection of AutoPEEP. Such functionalitycan be integrated in the currently used mechanical ventilator for continuous monitoring of thepatient-ventilator interface and, therefore, alleviate the clinician task.