Background <p>Intraoperative frozen section is insufficient to diagnose lung cancer invasion; thus, additional procedures are required to evaluate the pathological tumor invasiveness. We aimed to identify risk factors and establish the validity of a model that serves as a supplementary tool to evaluate the risk of lung cancer invasion beyond its primary site.</p> Methods <p>Overall, 1426 patients diagnosed with stage I lung adenocarcinoma who had performed spirometry within 3&#xa0;months preoperatively were enrolled. Least absolute shrinkage and selection operator logistic regression was used to select optimal indicators to construct the predictive nomogram model to identify invasiveness. The area under the receiver operating characteristic curve (AUC) and decision curve analysis were used to evaluate the predictive performance of the model.</p> Results <p>Lung function impairment was detected in 565 patients (39.62%). Patients with age ≥ 60&#xa0;years (odds ratio [OR] = 1.02), tumor size &gt; 2&#xa0;cm (OR = 1.31), impaired lung function (OR = 3.10), basophils ≤ 0.01 (OR = 0.51), and direct bilirubin levels &gt; 4.4 (OR = 1.15) had an increased risk of tumor invasion. The AUCs for predicting lung cancer invasion were 0.820 (95% confidence interval [CI] 0.781–0.858), 0.758 (95% CI 0.659–0.858), 0.838 (95% CI 0.797–0.879), and 0.807 (95% CI 0.704–0.891), in the training, internal validation, external validation, and prospective validation sets, respectively, indicating good performance. In the multivariable analysis, patients with restrictive ventilation impairment (OR 2.86 [95% CI 1.43–5.69]) and diffusion capacity impairment (OR 4.23 [95% CI 1.00–17.84]) had high tumor invasion risks.</p> Conclusions <p>The nomogram incorporating spirometric and clinical indices serves as a quantitative tool for clinicians to more accurately assess tumor invasiveness preoperatively, thereby making more informed decisions regarding clinical treatment strategies.</p> <p><i>Clinical Trial registration</i>: NCT05830812.</p>