Table 3 Logistic regression analysis of feature-engineered continuous variables associated with postoperative DVT risk.

From: Integrating 7-day D-dimer exposure into deep vein thrombosis risk prediction after gastrointestinal surgery

Characteristics

Univariate logistic regression

Multivariate logistic regression

OR(95% CI)

P value

OR(95% CI)

P value

7dDDE (µg/mL·day)

1.043 (1.025–1.065)

1.6E−05

1.043 (1.021–1.068)

2.6E−04

Preoperative triglycerides (mmol/L)

0.590 (0.396–0.827)

5.1E−03

0.574 (0.358–0.855)

1.3E−02

Postoperative CRP (mg/L)

1.012 (1.003–1.022)

1.2E−02

1.009 (0.999–1.02)

8.1E−02

Surgery duration (hours)

1.327 (1.127–1.583)

1.0E−03

1.234 (1.031–1.52)

4.0E−02

Preoperative D-Dimer (μg/mL)

1.168 (0.998–1.474)

1.5E−01

0.982 (0.892–1.212)

7.8E−01

  1. This table includes all continuous variables selected through feature engineering (Boruta and LASSO regression). Univariate and multivariate logistic regression models were applied to assess their associations with DVT after gastrointestinal surgery.
Back to article page