Table 1.

Predictive studies on hospital and ED readmissions.

Study	Readmission facility	Disease(s)a	Sample size (patients)	Period	Best performing method	Metric	Value
[68]	Hospital	COPD	106	30 days	Random Forest	AUC	0.720
[69]	Hospital	Multiple	92,530	30 days	LASSO & SVM	AUC	0.680
[70]	Hospital	PN COPD CHF AMI THA/TKA	40,442 31,457 25,941 29,060 23,128	30 days	Deep Neural Network (DNN)	AUC	0.734 0.711 0.676 0.649 0.638
[71]	Hospital	HF AMI PN	4210 2379 2825	30 days	SVM	AUC	0.660 0.650 0.630
[72]	Hospital	CHF	1641	30 days	PSO-SVM	Accuracy Sensitivity Specificity	0.784 0.973 0.086
[73]	Hospital	Multiple	64,912	3 days 7 days 15 days 30 days	Ensemble	AUC	0.666 0.681 0.700 0.720
[74]	Hospital	CHF	4840	30 days	CHAID Decision Tree	AUC	0.707
[75]	Hospital	Diabetes	Not Given	30 days	Recurrent NN	AUC	0.800
[76]	Hospital	Multiple	32,718	30 days	DNN	AUC	0.780
[77]	Hospital	Multiple	304,888	30 days	Ensemble	AUC	0.771
[78]	Hospital	Lupus	9457	30 days	DNN	AUC	0.700
[2]	Hospital	Multiple	700	30 days	DNN	AUC	0.730
[12]	Hospital	CHF COPD	32,350 31,070	30 days	Random Forest	AUC	0.742 0.754
[79]	Hospital	COPD	111,992	30 days	Gradient Boosting Tree	AUC	0.653
[80]	Hospital	Multiple	38,597	30 days	DNN	AUC	0.714
[81]	ED	Multiple	279,611	30 days	Decision Tree	Accuracy Sensitivity AUC	0.772 0.402 0.732
[82]	ED	Multiple	330,631	3 days	Gradient Boosting	Sensitivity Precision AUC	0.16 0.75 0.76
[83]	ED	Multiple	120,000	3 days	DNN	Accuracy Sensitivity AUC	0.680 0.679 0.755
[48]	ED	Multiple	290,000	3 days	Ensemble	Accuracy AUC	0.957 0.610

*AUC stands for Area Under the (Receiver Operating Characteristic) Curve.

^aCOPD: Chronic Obstructive Pulmonary Disease; PN: Pneumonia; CHF: Congestive Heart Failure; AMI: Acute Myocardial Infarction; THA/TKA: Total Hip/Knee Arthroplasty.