Table 3.
Classification Accuracy (% [95% CI]) of eRADAR Prediction Model by Validation Sample
| Measure, risk cut-off percentile | ACT, internal validation | KPWA, external validation | UCSF, external validation |
|---|---|---|---|
| Sensitivity | |||
| ≥ 99th | 6.5 (2.9–10.9) | 9.5 (8.7–10.3) | 7.1 (3.7–11.0) |
| ≥ 95th | 22.5 (15.9–29.7) | 35.2 (33.9–36.4) | 32.1 (25.7–38.5) |
| ≥ 90th | 36.2 (28.3–44.2) | 54.3 (52.9–55.6) | 44.4 (37.6–50.9) |
| ≥ 85th | 47.1 (39.1–55.8) | 65.9 (64.7–67.1) | 56.2 (49.4–62.6) |
| ≥ 75th | 65.9 (58.0–73.2) | 79.6 (78.6–80.6) | 73.6 (67.4–79.4) |
| Specificity | |||
| ≥ 99th | 99.4 (99.1–99.6) | 99.2 (99.2–99.3) | 98.9 (98.7–99.0) |
| ≥ 95th | 96.4 (95.6–97.1) | 95.3 (95.2–95.4) | 94.9 (94.5–95.2) |
| ≥ 90th | 91.6 (90.5–92.8) | 89.9 (89.8–90.1) | 89.8 (89.2–90.3) |
| ≥ 85th | 87.2 (85.8–88.7) | 84.6 (84.4–84.8) | 84.4 (83.8–85.0) |
| ≥ 75th | 78.0 (76.2–79.9) | 74.4 (74.2–74.7) | 74.4 (73.7–75.2) |
| PPV | |||
| ≥ 99th | 23.7 (11.4–37.5) | 10.1 (9.4–10.9) | 2.9 (1.5–4.4) |
| ≥ 95th | 15.7 (11.2–20.6) | 6.5 (6.2–6.7) | 2.8 (2.3–3.4) |
| ≥ 90th | 11.5 (9.1–14.2) | 4.8 (4.6–4.9) | 2.0 (1.7–2.3) |
| ≥ 85th | 10.0 (8.3–12.0) | 3.8 (3.7–3.9) | 1.6 (1.4–1.8) |
| ≥ 75th | 8.3 (7.3–9.5) | 2.8 (2.8–2.9) | 1.3 (1.2–1.4) |
ACT Adult Changes in Thought, CI confidence interval, KPWA Kaiser Permanente Washington, UCSF University of California, San Francisco