作者: Mizuho Nishio , Takeshi Kubo , Kaori Togashi
DOI: 10.1371/JOURNAL.PONE.0210720
关键词: Area under the curve 、 In patient 、 Computed tomography 、 Gastroenterology 、 Cancer screening 、 Retrospective cohort study 、 Lung 、 Internal medicine 、 Lung cancer 、 Logistic regression 、 Medicine
摘要: The purpose of this study was to assess whether homology-based emphysema quantification (HEQ) is significantly associated with lung cancer risk. This retrospective approved by our institutional review board. We included 576 patients nodules (317 men and 259 women; age, 66.8 ± 12.3 years), who were selected from a database previously generated for computer-aided diagnosis. Of these, 283 diagnosed cancer, whereas the remaining 293 showed benign nodules. HEQ performed percentage low-attenuation area (LAA%) calculated on basis computed tomography scans. Statistical models constructed estimate risk using logistic regression; sex, smoking history (Brinkman index), LAA%, considered independent variables. following three evaluated: base model (sex, history); LAA% (the + LAA%); HEQ). Model performance assessed receiver operating characteristic analysis under curve (AUC). Differences in AUCs among evaluated Delong’s test. base, 0.585, 0.593, 0.622, respectively. coefficient statistically significant (P = 0.00487), but not 0.199). test revealed difference between 0.0455). In conclusion, after adjusting