You are viewing the site in preview mode

Skip to main content

Advertisement

Table 2 Significance of each trend indicator when added separately to the existing time-dependent model

From: Does adding risk-trends to survival models improve in-hospital mortality predictions? A cohort study

Trend indicator added to the existing model -2 log likelihood (46389.92) p-value* AIC** (46445.92)
Absolute change in the risk score from the previous day 46340.45 < .0001 46398.45
Absolute change in the risk score from the start of the trend 46303.56 < .0001 46361.56
Relative change in the risk score from the previous day 46389.70 0.6386 46447.70
Relative change in the risk score from the start of the trend 46389.87 0.8361 46447.87
Number of consecutive days with a trend in the risk score 46377.89 0.0005 46435.89
  1. for the existing time-dependent model with no trend indicators
  2. *p-value from the likelihood ratio test comparing the existing time-dependent model with and without the trend indicator
  3. **Akaike's Information Criterion
  4. For all trend indicators, the value was expressed as a positive or negative number for an increase or decrease in the risk score, respectively. We defined a trend as a period of time over which the risk score consistently increased or decreased. If there was no change in the risk score or no previous risk score for comparison (i.e. on the first day of the hospitalization), the value of all trend indicators was set to 0.