Table 1.

General characteristics of the selected studies.

Characteristic			Value (n=97), n
Types of decision support
	Detection, monitoring, and diagnosis	13
	Early identification of clinical events	32
	Outcome prediction and prognostic assessment	46
	Treatment decisions	6
Population
	Adult	82
	Pediatric patients	8
	Neonates	7
Medical setting
	Single-center	65
	Multicenter	32
Type of machine learning
	Supervised learning	88
	Unsupervised learning	3
	Reinforcement learning	6
Type of variables
	Demographic variables	74
	Laboratory values	59
	Vital signs	55
	Scores	48
	Ventilation parameters	43
	Comorbidities	27
	Medications	18
	Outcome	14
	Fluid balance	13
	Nonmedicine therapy	10
	Symptoms	7
	Medical history	4
Type of evaluation method, na
	Area under the receiver operating characteristic curve	57
	Sensitivity	37
	Specificity	31
	Accuracy	24
	Positive predictive value	11

^aMore than 1 variable type could be used in each study.