Estimating Incidence of Solitary Pulmonary Nodules: Novel Methods Using Claims Data to Answer Unknown Epidemiological Questions

Iñiguez, Carlos Bravo; Kwon, Nicollette K.; Jacobson, Francine L.; Learn, Peter A.; Jaklitsch, Michael T.; Haider, Adil H.; Mody, Gita N.

doi:10.1016/j.chest.2018.08.597

Cited by 3 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Pulmonary nodules are a common incidental finding on computed tomography (CT) [ 1 ]. Current guidelines emphasise the importance of assessing the likelihood that a nodule is malignant, with further management being dependent on the predicted risk of malignancy [ 2 , 3 ].…”

Section: Introductionmentioning

confidence: 99%

Developing an understanding of artificial intelligence lung nodule risk prediction using insights from the Brock model

Chetan

Dowson²,

Price³

et al. 2022

Eur Radiol

View full text Add to dashboard Cite

Objectives To determine if predictions of the Lung Cancer Prediction convolutional neural network (LCP-CNN) artificial intelligence (AI) model are analogous to the Brock model. Methods In total, 10,485 lung nodules in 4660 participants from the National Lung Screening Trial (NLST) were analysed. Both manual and automated nodule measurements were inputted into the Brock model, and this was compared to LCP-CNN. The performance of an experimental AI model was tested after ablating imaging features in a manner analogous to removing predictors from the Brock model. First, the nodule was ablated leaving lung parenchyma only. Second, a sphere of the same size as the nodule was implanted in the parenchyma. Third, internal texture of both nodule and parenchyma was ablated. Results Automated axial diameter (AUC 0.883) and automated equivalent spherical diameter (AUC 0.896) significantly improved the accuracy of Brock when compared to manual measurement (AUC 0.873), although not to the level of the LCP-CNN (AUC 0.936). Ablating nodule and parenchyma texture (AUC 0.915) led to a small drop in AI predictive accuracy, as did implanting a sphere of the same size as the nodule (AUC 0.889). Ablating the nodule leaving parenchyma only led to a large drop in AI performance (AUC 0.717). Conclusions Feature ablation is a feasible technique for understanding AI model predictions. Nodule size and morphology play the largest role in AI prediction, with nodule internal texture and background parenchyma playing a limited role. This is broadly analogous to the relative importance of morphological factors over clinical factors within the Brock model. Key Points • Brock lung cancer risk prediction accuracy was significantly improved using automated axial or equivalent spherical measurements of lung nodule diameter, when compared to manual measurements. • Predictive accuracy was further improved by using the Lung Cancer Prediction convolutional neural network, an artificial intelligence-based model which obviates the requirement for nodule measurement. • Nodule size and morphology are important factors in artificial intelligence lung cancer risk prediction, with nodule texture and background parenchyma contributing a small, but measurable, role.

show abstract

Section: Introductionmentioning

confidence: 99%

Developing an understanding of artificial intelligence lung nodule risk prediction using insights from the Brock model

Chetan

Dowson²,

Price³

et al. 2022

Eur Radiol

View full text Add to dashboard Cite

show abstract

“…Nodules were detected in 8.5 % of polytrauma examinations, of which over 80 % required follow-up according to the Fleischner criteria [27]. Even in a young cohort aged between 18 and 24, an incidence of clinically relevant nodules of 0.6 per 1,000 person years could still be determined [28].…”

Section: Main Partmentioning

confidence: 99%

“…So wurden in 8,5 % der Polytrauma-Untersuchungen Rundherde erkannt, von denen über 80 % nach den Fleischner-Kriterien eine Verlaufskontrolle benötigten [27]. Auch in einer jungen Kohorte zwischen 18-24 Jahre konnte immerhin noch eine Inzidenz von klinisch relevanten Rundherden von 0,6 pro 1000 Personenjahre ermittelt werden [28].…”

Section: Hauptteilunclassified

Incidental pulmonary nodules – current guidelines and management

Glandorf,

Vogel-Claussen

2023

Rofo

View full text Add to dashboard Cite

Background Due to the greater use of high-resolution cross-sectional imaging, the number of incidental pulmonary nodules detected each year is increasing. Although the vast majority of incidental pulmonary nodules are benign, many early lung carcinomas could be diagnosed with consistent follow-up. However, for a variety of reasons, the existing recommendations are often not implemented correctly. Therefore, potential for improvement with respect to competence, communication, structure, and process is described. Methods This article presents the recommendations for incidental pulmonary nodules from the current S3 guideline for lung cancer (July 2023). The internationally established recommendations (BTS guidelines and Fleischner criteria) are compared and further studies on optimized management were included after a systematic literature search in PubMed. Results and Conclusion In particular, AI-based software solutions are promising, as they can be used in a support capacity on several levels at once and can lead to simpler and more automated management. However, to be applicable in routine clinical practice, software must fit well into the radiology workflow and be integrated. In addition, “Lung Nodule Management” programs or clinics that follow a high-quality procedure for patients with incidental lung nodules or nodules detected by screening have been established in the USA. Similar structures might also be implemented in Germany in a future screening program in which patients with incidental pulmonary nodules could be included. Key Points: Citation Format

show abstract

Radiologische Abklärung pulmonaler Rundherde

Glandorf

Dettmer

2022

Z Pneumologie

View full text Add to dashboard Cite

Estimating Incidence of Solitary Pulmonary Nodules: Novel Methods Using Claims Data to Answer Unknown Epidemiological Questions

Cited by 3 publications

References 0 publications

Developing an understanding of artificial intelligence lung nodule risk prediction using insights from the Brock model

Developing an understanding of artificial intelligence lung nodule risk prediction using insights from the Brock model

Incidental pulmonary nodules – current guidelines and management

Radiologische Abklärung pulmonaler Rundherde

Contact Info

Product

Resources

About