Skip to main content
. 2023 Jan 26;6:10. doi: 10.1038/s41746-023-00752-8

Table 2.

Internal and external validation of the DLS in image models, clinical models and mixed models for 5-year axial length ≥26.5 mm prediction.

Model Input Variables Internal Validation (School 2 and 3) External Validation (School 1)
Threshold AUC (C.I.) Accuracy (C.I) Sensitivity (C.I.) Specificity (C.I.) Threshold AUC (C.I.) Accuracy (C.I) Sensitivity (C.I.) Specificity (C.I.)
Image model Fundus photo 0 0.67 (0.48–0.87) 0.94 (0.94–0.94) 0.38 (0.37–0.38) 0.95 (0.95–0.95) 0 0.57 (0.47–0.69) 0.84 (0.84–0.84) 0.25 (0.25–0.25) 0.90 (0.90–0.90)
Fundus photo + Age + Race + Gender 0.03 0.86 (0.76–0.96) 0.77 (0.77–0.77) 0.63 (0.62–0.63) 0.77 (0.77–0.77) 0.03 0.64 (0.49–0.80) 0.69 (0.69–0.70) 0.63 (0.62–0.63) 0.70 (0.70–0.70)
Clinical model Baseline ALa 0 0.83 (0.62–0.98) 0.84 (0.84–0.84) 0.75 (0.75–0.75) 0.84 (0.84–0.84) 0 0.91 (0.86–0.96) 0.67 (0.67–0.67) 1.00 (1.00–1.00) 0.64 (0.64–0.64)
Baseline ALa + Age + Race + Gender 0.01 0.93 (0.89–0.97) 0.86 (0.86–0.86) 0.75 (0.75–0.75) 0.86 (0.86–0.86) 0.01 0.95 (0.92–0.98) 0.71 (0.71–0.72) 1.00 (1.00–1.00) 0.69 (0.69–0.69)
Baseline ALa + Age + Race + Gender + 1-year AL* progression 0.04 0.95 (0.91–0.98) 0.88 (0.87–0.88) 0.88 (0.87–0.88) 0.88 (0.87–0.88) 0.04 0.94 (0.90–0.98) 0.74 (0.74–0.74) 0.94 (0.94–0.94) 0.72 (0.72–0.72)
Mixed model Fundus photo + Baseline ALa 0.17 0.98 (0.95–1.00) 0.93 (0.93–0.93) 0.88 (0.87–0.88) 0.93 (0.93–0.94) 0.17 0.88 (0.83–0.93) 0.85 (0.85–0.85) 0.75 (0.75–0.75) 0.86 (0.85–0.86)
Fundus photo + Baseline ALa + Age + Race + Gender 0.07 0.98 (0.96–1.00) 0.94 (0.94–0.94) 1.00 (1.00–1.00) 0.94 (0.94–0.94) 0.07 0.89 (0.83–0.94) 0.86 (0.86–0.86) 0.81 (0.81–0.81) 0.87 (0.87–0.87)
Fundus photo + Baseline ALa + Age + Race + Gender + 1-year ALa progression 0.16 0.98 (0.96–1.00) 0.92 (0.92–0.92) 0.88 (0.87–0.88) 0.92 (0.92–0.92) 0.16 0.90 (0.84–0.94) 0.83 (0.82–0.83) 0.69 (0.69–0.69) 0.84 (0.84–0.84)

AUC area-under-curves, C.I. confidence interval.

aAxial length (AL) was performed using contact ultrasound biometry.