Variables predictive of mortality for T0 model
| Beta-coefficient from lasso* | |
| FEV1 (% predicted) | −0.044 |
| Insurance | |
| Private insurance only | Reference group |
| Medicare only | 0 |
| Combination of any insurance including Medicaid | 0.16 |
| Ventilation machine (non-invasive) | |
| No | Reference group |
| Yes | 0.103 |
| Unknown | 0 |
| Oxygen therapy | |
| No | Reference group |
| Yes, continuously | 0.46 |
| Yes, nocturnal and/or with exertion | 0 |
| Yes, during exacerbation | 0 |
| Yes, prn | 0 |
| Unknown | 0 |
| Burkho complex (Burkholderia species) | |
| No | Reference group |
| Yes | 0.315 |
| Liver disease, cirrhosis | |
| No | Reference group |
| Yes | 0.116 |
| Renal failure requiring dialysis | |
| No | Reference group |
| Yes | 0.584 |
| Smoking | |
| No | Reference group |
| Occasionally | 0.141 |
| Regularly, <1 ppd | 0.429 |
| Regularly, 1 ppd or more | 0 |
| Unknown | 0 |
| Mutation class | |
| 1–3 | Reference group |
| 4–5 | 0 |
| Other | 0 |
| Unknown missing | 0.302 |
| # of pulmonary exacerbations in the year preceding advanced stage CF diagnosis | 0.093 |
| Baseline lung transplant evaluation status | |
| Not pertinent | Reference group |
| Accepted, on waiting list | −0.102 |
| Evaluated, final decision pending | 0 |
| Evaluated, rejected | 0 |
| Unknown | 0 |
Parameter estimates do not represent the true magnitude of effect. In other words, unlike in Cox regression models that use classical techniques of variable selection, exponentiation of the lasso beta-coefficient is not an estimate of the true HR. However, when taken in context of the model it can determine relative importance in prediction and positive or negative association with the predicted outcome.
*A negative value indicates predictive of lower mortality.
CF, cystic fibrosis; FEV1, forced expiratory volume in 1 s.