Precise diagnosis and prognosis assessment of malignant lung nodules: a narrative review

Pulmonary nodules (PNs) are small (≤3 cm) radiographic opacities within lung parenchyma. The use of low-dose computed tomography (LDCT) has led to a significant increase in the identification of solitary nodules. Malignant lung nodules comprise only 5% of all nodules, with management differing greatly from benign cases. Despite diagnostic advancements, there is heterogeneity in prognosis, which can result in undertreatment of high-risk patients and inappropriate treatment for low-risk patients. Therefore, accurately distinguishing benign from malignant nodules and effectively stratifying the risk of malignant nodules is a pressing clinical challenge requiring urgent resolution. The main objectives of this review were to explore the research progress in the clinical management of malignant PNs, including early detection, individualized treatment, and prognosis prediction, in order to shed light on precision medicine for patients with PNs.

The review examined various approaches for the identification and prognosis prediction of early lung cancer characterized by lung nodules, including the use of classical clinicopathological features, liquid biopsy, and artificial intelligence.

The detection rate of early lung cancer characterized by lung nodules is increasing annually, and accurate identification and prognosis prediction are critical for appropriate therapeutic strategies and precise postoperative management. Classical clinicopathological features, such as demographic and radiological features, play an important role in the diagnosis and prognosis assessment of early lung cancer, but liquid biopsy and artificial intelligence are also promising due to their obvious convenience and accuracy.

The review highlights the importance of precision medicine in the clinical management of malignant lung nodules. The use of classical clinicopathological features, liquid biopsy, and artificial intelligence can contribute to the early detection, individualized treatment, and accurate prognosis prediction for patients with lung nodules, ultimately improving their clinical outcomes.