Table 2.

Predicting performance for the best model for each study in a holdout internal or external validation data set (N=12).

Type of cancer and study		Outcome	Training sample	Validation sample	Mortality rate (%)	Algorithm	AUROCa	Accuracy	Sensitivity	Specificity	PPVb	NPVc	Calibration	Benchmark, model (Δ AUROC)
All cancer
	Manz et al [37]	180-day death	N/Ad	24,582	4.2	GBTe	0.89	—f	0.27	0.99	0.45	0.97	Well-fit	—
	Parikh et al [39]	180-day death	18,567	7958	4.0	RFg	0.87	0.96	—	0.99	0.51	—	Well-fit at the low-risk group	LRh (0.01)
	Bertsimas et al [50]	180-day death	14,427	9556	5.6	GBT	0.87	0.87	.60	—	0.53	—	—	LR (0.11)
	Elfiky et al [43]	180-day death	17,832	9114	18.4	GBT	0.83	—	—	—	—	—	Well-fit	—
Gastrointestinal cancer
	Arostegui et al [46]	1-year death	981	964	5.1	DTi	0.84	—	—	—	—	—	Well-fit	—
	Biglarian et al [47]	1-year death	300	136	37.5	ANNj	0.92	—	0.80	0.85	—	—	—	CPHk (0.04)l
Patients with bladder cancer
	Klén et al [48]	90-day death	733	366	4.4	Regularized LR	0.72	—	—	—	—	—	—	ACCIm univariate model (0.05)
Patients with liver cancer
	Chiu et al [49]	1-year death	347	87	17	ANN	0.88	—	0.89	0.50	—	—	—	LR (0.08)
	Zhang et al [40]	1-year death	230	60	23.9	ANN	0.91	—	0.91	0.90	0.83	0.86	—	—
Patients with spinal metastasis
	Karhade et al [41]	30-day death	1432	358	8.5	BPMn	0.78	—	—	—	—	—	Well-fit	—
	Karhade et al [42]	1-year death	586	145	54.3	SGBo	0.89	—	—	—	—	—	Well-fit	—
	Karhade et al [36]	1-year death	N/A	176	56.2	SGB	0.77	—	—	—	—	—	Fairly well-fit	—

^aAUROC: area under the receiver operating characteristic curve.

^bPPV: positive predictive value.

^cNPV: negative predictive value.

^dN/A: not applicable.

^eGBT: gradient-boosted tree.

^fNo data available

^gRF: random forest.

^hLR: logistic regression.

ⁱDT: decision tree.

^jANN: artificial neural network.

^kCPH: Cox proportional hazard.

^lSignificant at the α level defined by the study.

^mACCI: adjusted Charlson comorbidity index.

ⁿBPM: Bayes point machine

^oSGB: stochastic gradient boosting.