Table 5.
Mortality at Day 90 in Phenotypes Identified in the Secondary Model 2 Using the Classifier Models (Probability Cutoff ≥ 0.5)*
| Model | Mortality at Day 90 in the Hypoinflammatory Phenotype |
Mortality at Day 90 in the Hyperinflammatory Phenotype |
P Value | |||||
|---|---|---|---|---|---|---|---|---|
| Total [n (%)] | Low PEEP [n (%)] | High PEEP [n (%)] | Total [n (%)] | Low PEEP [n (%)] | High PEEP [n (%)] | |||
| Clinical classifier | 73/372 (20) | 27/184 (15) | 46/188 (25) | 75/177 (42) | 42/89 (47) | 33/88 (38) |
0.0113 | |
| Sparse combined | 85/402 (21) | 35/200 (18) | 50/202 (25) | 63/147 (43) | 34/73 (47) | 29/74 (39) |
0.0748 | |
| LCA (7) | 81/404 (20) | 33/202 (16) | 48/202 (24) | 67/145 (46) | 36/71 (51) | 31/74 (42) | 0.049 | |
Definition of abbreviations: ALVEOLI = Assessment of Low Vt and Elevated End-Expiratory Pressure to Obviate Lung Injury; ARMA = High vs. Low Vt; FACTT = Fluids and Catheter Treatment Trial; LCA = latent class analysis; PEEP = positive end-expiratory pressure; SAILS = Statins for Acutely Injured Lungs from Sepsis.
Training data sets: ARMA, FACTT, and SAILS; validation data set: ALVEOLI trial (n = 549). P value represents the interaction between phenotype assignment and randomly assigned treatment-strategy for mortality at Day 90. LCA-derived classes were extracted from the original LCA study (7) and not from the derivation data set. Outcomes are shown in phenotypes derived by three different models: clinical-classifier model comprising all the predictor variables, the sparse-combined model comprising only laboratory values and vital signs variables, and the original latent class model (7). Outcomes were substratified by randomized treatment strategy in the original trials.