. 2025 Apr 10;263(7):1885–1897. doi: 10.1007/s00417-025-06812-x

Table 3.

ALTAIR: Algorithm results for Experiments 1, 2, and 3

EXPERIMENT 1^a
	AUC	Accuracy	Sensitivity	Specificity	Patients in Group A^b (< 3 extension decisions taken at Visits 4, 5, 6, and 7)	Patients in Group B^b (3 or 4 extension decisions taken at Visits 4, 5, 6, and 7)
	0.78	78%	85% (31/37)	71% (36/46)	37	46
EXPERIMENT 2^a
	AUC	Accuracy	Sensitivity	Specificity	Patients with high IVT-AFL need^c	Patients with low IVT-AFL need^c
Year 1	0.79	79%	79% (27/35)	78% (42/54)	35	54
Year 2	0.78	78%	87% (34/39)	69% (26/38)	39	38
EXPERIMENT 3^a
	AUC	Accuracy	Sensitivity	Specificity	Patients with short intervals (< 12 weeks) at end of Year 2	Patients with long intervals (≥ 12 weeks) at end of Year 2
	0.77	76%	81% (34/43)	71% (24/34)	43	34

^aThe numerator and the denominator of the fractions for sensitivity and specificity are mean values of the fivefold cross-validation; as such, the result of division may not correspond exactly to the percentage value specified

^bGroup A: predicted ‘short’ interval at Visit 7; Group B: predicted ‘long’ interval at Visit 7

^cHigh IVT-AFL need was defined as ≥ 8 and ≥ 5 IVT-AFL injections per year for Year 1 and 2, respectively; low IVT-AFL need was defined as < 8 and < 5 IVT-AFL injections per year for Year 1 and 2, respectively

AUC, area under the curve; IVT-AFL, intravitreal aflibercept