TABLE 4].
Variables Retained by the LASSO Procedures in the Logistic Regression for Predicting Occurrence of PRF
| Predictor Variable | Coefficient | Probability Selected, %a |
|---|---|---|
| Intercept | −7.4426 | 100 |
| Anesthesia duration, /h | 0.1921 | 100 |
| Net fluid at end of the operation, /L | 0.1681 | 100 |
| Operations on the cardiovascular system | 0.9246 | 100 |
| Medicare (as the primary payer) | 0.4672 | 100 |
| ASA class ≥ III | 0.5663 | 100 |
| Fio2, median | 0.0086 | 98 |
| Operations on the nervous system | 0.5520 | 96.4 |
| Vasopressor medication in the operating room | 0.3000 | 95.6 |
| Heart rate, median | 0.0088 | 94.8 |
| Tidal volume, median | −0.0011 | 92.4 |
| Operations on the musculoskeletal system | −0.3957 | 91.2 |
| Operations on the digestive system | 0.1136 | 88.8 |
| Surgical specialty orthopedic (nonspine) | −0.2202 | 82.8 |
| Medical (Medicaid) (as the primary payer) | 0.1937 | 82.4 |
| Operations on the urinary system | 0.1706 | 81.2 |
| BMI 30–34.9 kg/m2 (obese 1) | −0.0745 | 80.4 |
| End-tidal CO2, median | −0.0135 | 75.6 |
| Race unknown (unable to respond, unavailable or unknown, declined to state) | 0.2557 | 62.8 |
ASA = American Society of Anesthesiologists; LASSO = least absolute shrinkage and selection operator; PRF = postoperative respiratory failure;
Probability selected is the percentage of bootstrap samples in which the variable was retained.