S22 The incidence of malignancy in a prospective observational study on incidental pulmonary nodules (IDEAL study). (11th November 2022)

• Record Type: Journal Article
• Authors: Ng, KL; Moreland, JA; Hickes, W; Barton, TC; Callister, ME; Baldwin, DR; Gleeson, F
• Is Part Of: Thorax. Volume 77(2022)Supplement 1
• Page Start: A17
• Page End: A18
• Publication Date: 2022-11-11
• Subjects: Chest -- Diseases -- Periodicals; Thorax; Chest -- Diseases; Periodicals; Periodicals; 617.54
• DOI: 10.1136/thorax-2022-BTSabstracts.28
• Languages: English
• ISSNs: 0040-6376

Abstract

Abstract : Introduction and Objectives: Lung cancer remains the leading cause of cancer mortality worldwide, with a known reduced mortality when diagnosed at an early stage. Approximately 2–4% of pulmonary nodules identified on CT as part of Lung Cancer Screening (LCS) programmes are due to lung cancer. Our prospective observational study, Artificial Intelligence and Big Data for Early Lung Cancer Diagnosis Prospective Study (Phase 2) – IDEAL study, aimed to test the use of an Artificial Intelligence (AI) algorithm, the Lung Cancer Prediction Convolutional Neural Network (LCP-CNN) model incorporated into a clinical risk model to better characterise incidental pulmonary nodules. Here we are reporting on the incidence of malignant nodules discovered incidentally on CT in the UK performed outside of a LCS programme. Methods: Participants aged 18 years or older with new 5–15 mm solid or predominantly solid pulmonary nodules reported on CT were recruited from four NHS hospital trusts between August 2018 and March 2021. Patients with a known history of extra-thoracic malignancy and ground-glass opacities were excluded. The clinical management of the nodules was determined according to the BTS Pulmonary Nodule Guidelines and the Brock Risk Model calculator, with the nodules categorised into: Group 1 – Benign requiring no further follow up Group 2 – Indeterminate requiring further CT follow up Group 3 – Potentially malignant being referred to lung MDT The final diagnosis was Benign - if categorised as Group 1, or no growth at 2 years, or Malignant – if proven histologically, or following determination at a Lung Cancer MDT using the Herder risk if a PET-CT had been performed. Results : 1102 patients with 1685 nodules were included in this analysis. 40/1102 (3.63%) patients had malignant nodules with one patient having two synchronous malignant nodules. Of the malignant nodules 41/1685 (2.43%), 39 were primary lung cancers, with adenocarcinoma being the most common histological type. 11/1685 (0.65%) of the nodules were diagnosed as malignant on their presentation CT, with 30/1685 (1.78%) being diagnosed as malignant on subsequent follow-up scans. Conclusions : The rate of malignancy in incidental CT-identified pulmonary nodules in IDEAL, and investigated according to the BTS Guidelines, is approximately 2.5%, of which 93% are early-stage lung cancers.