TABLE 2.
Output and state prediction errors associated with population-average model as well as individualized models with and without the use of regularization [mean (SD), N = 23].
| Population average | Individualized/no regularization (λ = 0) | Individualized/regularization | |
| Case 1: individualizing the physiological model with BV, CO, and MAP (individualized/regularization, λ = 0.10(0.06)) | |||
| BV (L) | 0.26 (0.19) | 0.10 (0.03) | 0.10 (0.04) |
| CO (L/m) | 1.31 (0.80) | 0.34 (0.18) | 0.34 (0.17) |
| MAP (mmHg) | 17.1 (8.88) | 7.23 (2.01) | 7.40 (2.05) |
| e1 | 0.25 (0.14) | 0.08 (0.02)† | 0.08 (0.02)† |
| Case 2: individualizing the physiological model with CO and MAP (individualized/regularization, λ = 0.16(0.13)) | |||
| BV (L) | 0.26 (0.19) | 0.29 (0.21) | 0.25 (0.18) |
| CO (L/m) | 1.31 (0.80) | 0.30 (0.18) | 0.32 (0.15) |
| MAP [mmHg] | 17.1 (8.88) | 6.94 (2.20) | 7.92 (2.42) |
| e1 | 0.30 (0.19) | 0.09 (0.03)† | 0.10 (0.03)† |
| e2 | 0.15 (0.15) | 0.16 (0.17) | 0.14 (0.14) |
| Case 3: individualizing the physiological model with MAP (individualized/regularization, λ = 0.22(0.17)) | |||
| BV (L) | 0.26 (0.19) | 0.43 (0.35) | 0.27 (0.18) |
| CO (L/m) | 1.31 (0.80) | 13.0 (18.0) | 1.19 (0.94) |
| MAP (mmHg) | 17.1 (8.88) | 4.85 (1.43) | 7.48 (3.03) |
| e1 | 0.24 (0.13) | 0.07 (0.02)† | 0.10 (0.04)† |
| e2 | 0.26 (0.15)* | 2.08 (2.83) | 0.24 (0.20)* |
*p < 0.016 compared to the individualized model without the use of regularization. †p < 0.016 compared to the population-average model.