“…We extracted information on the following study characteristics: (1) design (categorized as retrospective-, prospective observational-and clinical [categorized as the following study designs: non-randomized clinical trials and randomized clinical trials/randomized controlled trials (RCT)] designs); (2) aim (categorized as alarm reduction, assessing clinical notes, classifying sub-populations, detecting spurious recorded values, determining physiological thresholds, improving prognostic models/risk scoring system, improving upon previous methods, predicting complications, predicting health improvement, predicting length of stay, predicting medication administration, predicting mortality and predicting readmissions) (in case studies had more than one aim, all aims were recorded); (3) size of the dataset (the total number of patients used for data analysis); (4) level of validation (categorized as internal validation [models are validated on patients who are included in studies' own dataset], external validation [models are validated on data of patients from other geographical locations or times], prospective observational validation, clinical validation and no reported validation); (5) AI level of readiness, which was assessed over time by applying the general concept of technology readiness levels introduced by National Aeronautics and Space Administration (NASA), which previously has been translated to the ICU environment [the consecutive levels increase from development to the clinical implementation of AI: problem identification (level 1), proposal of solution (level 2), model prototyping and development (level 3 and 4), model validation (level 5), real-time testing (level 6), workflow integration (level 7), clinical testing (level 8), and integration in clinical practice (level 9)] [21,22]; (6) clinical study design and effects on patient outcome measures were extracted [categorized as reduced length of ICU stay, reduced overall mortality, reduced time on mechanical ventilation, reduced rate of complications and other (with details)]. Clinical study designs were considered to be either pre-postimplementation trials, non-randomized clinical trials or randomized clinical trials.…”