The Journal of International Medical Research · 8 authors, 5 centres
This summary was generated by AI from a single paper. It has not been reviewed by a clinician and is not clinical advice. Verify against the source before acting on it.
This retrospective cohort study developed a diagnostic nomogram using 13 variables, including two clinical factors and 11 metabolic markers from blood, to distinguish lung cancer from benign lung nodules. The nomogram showed good predictive performance in an internally validated cohort of 848 participants.
A retrospective cohort study of 848 participants with lung nodules was conducted to develop a diagnostic nomogram for lung cancer. Variables were selected from clinical characteristics and metabolic profiles using LASSO and stepwise regression. A nomogram incorporating 13 variables (age, sex, and 11 metabolites) was built and internally validated. The model achieved an area under the curve of 0.836 in the training set, with good calibration and a net benefit superior to baseline in decision curve analysis. The study is limited by its retrospective design, lack of external validation, and omission of factors like nodule size and smoking history.
