Systems and methods for predicting adverse events and assessing level of sedation during medical procedures

Systems and methods are disclosed herein for quantitatively identifying a patient's sedation level and predicting adverse events, based on one or more capnograms or outputs from a pharmacokinetic, pharmacodynamic, or ventilatory model. A sensor measures a carbon dioxide concentration of air exhaled by a patient into a breath receiver. A processor processes the sensor data to generate a capnogram including one or more respiratory cycles, computes the outputs of pharmacokinetic, pharmacodynamic, or ventilatory models, and extracts one or more of the resulting features from the capnogram and pharmacokinetic, pharmacodynamic, or ventilatory model outputs. A multi-parameter metric is computed based on the one or more extracted features and estimates the current or predicted sedation level of the patient.