Skip to main content
. Author manuscript; available in PMC: 2017 Sep 1.
Published in final edited form as: Lung Cancer. 2016 Jul 6;99:137–142. doi: 10.1016/j.lungcan.2016.07.006

Table 3.

Propensity Score Analysis: Comparison of Overall and Lung Cancer-Specific Survival of Patients Treated with and without Statins

Model Overall Survival
Hazard Ratio (95% CI*)		 Lung Cancer Survival
Hazard Ratio (95% CI*)
Primary Analysis: Entire Cohort
  Inverse Probability Weighted 0.77 (0.74–0.81) 0.78 (0.74–0.82)
  Stratified by Propensity Score Quintiles 0.75 (0.70–0.80) 0.74 (0.68–0.81)
  Matched Analysis (N=4556) 0.77 (0.72–0.83) 0.75 (0.68–0.82)
Secondary Analyses
  Patients who received systemic chemotherapy
    Inverse Probability Weighted 0.86 (0.81–0.91) 0.81 (0.75–0.87)
    Stratified by Propensity Score Quintiles 0.83 (0.75–0.92) 0.78 (0.68–0.89)
    Matched Analysis (N=2052) 0.86 (0.78–0.95) 0.79 (0.70–0.90)
Patients who received oral chemotherapy
    Inverse Probability Weighted 0.87 (0.75–1.03) 0.94 (0.77–1.15)
    Stratified by Propensity Score Quintiles 0.85 (0.66–1.11) 0.96 (0.69–1.33)
    Matched Analysis (N=304) 0.90 (0.69–1.17) 0.98 (0.70–1.36)
Patients who did not receive systemic or oral chemotherapy
    Inverse Probability Weighted 0.74 (0.70–0.79) 0.78 (0.73–0.84)
    Stratified by Propensity Score Quintiles 0.71 (0.64–0.79) 0.72 (0.64–0.82)
    Matched Analysis (N=2220) 0.70 (0.63–0.78) 0.71 (0.63–0.81)
Patients who underwent a PET scan
    Inverse Probability Weighted 0.81 (0.75–0.87) 0.79 (0.72–0.87)
    Stratified by Propensity Score Quintiles 0.78 (0.70–0.88) 0.77 (0.66–0.89)
    Matched Analysis (N=1625) 0.82 (0.73–0.91) 0.78 (0.68–0.91)
Patients who did not undergo a PET scan
    Inverse Probability Weighted 0.77 (0.74–0.81) 0.79 (0.74–0.84)
    Stratified by Propensity Score Quintiles 0.74 (0.68–0.81) 0.74 (0.67–0.83)
    Matched Analysis (N=2931) 0.75 (0.69–0.83) 0.74 (0.66–0.83)
Low potency (vs. high potency) statin 0.92 (0.88–0.96) 0.91 (0.87–0.96)
*

CI denotes confidence interval. The hazard ratio represents the risk of death of a patient treated with a statin compared with a patient who did not receive a statin. All models were also adjusted for tumor histology, tumor site, receipt of PET scan, mediastinoscopy, fine needle aspiration, and use of systemic and oral chemotherapy.