Construction and validation of a predictive model of invasive adenocarcinoma in pure ground-glass nodules less than 2 cm in diameter

Abstract

Objectives: In this study, we aimed to develop a multiparameter prediction model to improve the diagnostic accuracy of invasive adenocarcinoma in pulmonary pure glass nodules.

Method: We included patients with pulmonary pure glass nodules who underwent lung resection and had a clear pathology between January 2020 and January 2022 at the Qilu Hospital of Shandong University. We collected data on the clinical characteristics of the patients as well as their preoperative biomarker results and computed tomography features. Thereafter, we performed univariate and multivariate logistic regression analyses to identify independent risk factors, which were then used to develop a prediction model and nomogram. We then evaluated the recognition ability of the model via receiver operating characteristic (ROC) curve analysis and assessed its calibration ability using the Hosmer-Lemeshow test and calibration curves. Further, to assess the clinical utility of the nomogram, we performed decision curve analysis.

Result: We included 563 patients, comprising 174 and 389 cases of invasive and non-invasive adenocarcinoma, respectively, and identified seven independent risk factors, namely, maximum tumor diameter, age, serum amyloid level, pleural effusion sign, bronchial sign, tumor location, and lobulation. The area under the ROC curve was 0.839 (95% CI: 0.798-0.879) for the training cohort and 0.782 (95% CI: 0.706-0.858) for the validation cohort, indicating a relatively high predictive accuracy for the nomogram. Calibration curves for the prediction model also showed good calibration for both cohorts, and decision curve analysis showed that the clinical prediction model has clinical utility.

Conclusion: The novel nomogram thus constructed for identifying invasive adenocarcinoma in patients with isolated pulmonary pure glass nodules exhibited excellent discriminatory power, calibration capacity, and clinical utility.

Keywords: Invasive adenocarcinoma; Logical model; Nomogram; Prediction; Pulmonary pure glass nodule.

Fig. 1

Flow diagram of patient selection through the study. AAH, atypical adenomatous hyperplasia; AIS, adenocarcinoma in situ; MIA, microinvasive adenocarcinoma; IAC, invasive adenocarcinoma

Fig. 2

Multi-factor logistic regression analysis of forest plots. PNI, prognostic nutritional index; SA, serum amyloid; Cyfra21-1, cytokeratin 19-fragments; CEA, carcinoembryonic antigen; ASA, American Society of Anesthesiologists

Fig. 3

Nomogram for predicting the probability of IAC for pGGN ≤ 2 cm. SA, serum amyloid

Fig. 4

ROC curves of nomograms predicting IAC for pGGN ≤ 2 cm in the training and validation groups. ROC, receiver operating characteristic; AUC, area under the ROC curve; IAC, invasive adenocarcinoma; pGGN, pure ground glass nodule

Fig. 5

(A, B): Calibration curves of the prediction nomogram in the training cohort (A) and validation cohort (B). IAC, invasive adenocarcinoma; pGGN, pure ground glass nodule

Fig. 6

(A, B): Decision curve analysis of predicted nomogram in the training cohort (A) and validation cohort (B)

Fig. 7

(A, B): Clinical impact curves of predicted nomogram in the training cohort (A) and validation cohort (B)