Solitary Pulmonary Nodule Malignancy Predictive Models Applicable to Routine Clinical Practice: A Systematic Review 

Abstract

Background: Solitary Pulmonary Nodule (SPN) is a common finding in routine clinical practice when performing chest imaging tests. The vast majority of these nodules are benign, and only a small proportion are malignant. Facing clinical experience as a guide for decision-making in the management of SPN, the application of predictive models of malignancy in routine clinical practice would help to achieve better diagnostic management of SPN. For this, it is necessary to know and evaluate the current state of knowledge in relation to predictive models of malignancy of SPN in the general or low-risk population. The present systematic review was carried out with the purpose of critically assess studies aimed at developing predictive models of Solitary Pulmonary Nodule (SPN) malignancy from SPN incidentally detected in routine clinical practice. Methods: we performed a systematic review through the following bibliographic databases: MEDLINE, SCOPUS and Cochrane Library. We used The Transparent Reporting of a multivariable Prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement to describe the type of predictive model included in each study. We used The Prediction model Risk Of Bias ASsessment Tool (PROBAST) to evaluate the quality of the selected articles. The Fleischner guidelines for the management of incidental SPN were used as reference to describe the variables included in the models. Results: 186 references were retrieved and after applying the exclusion/inclusion criteria, 15 articles remained for the final review. All studies analysed clinical and radiological variables. The most frequent independent predictors of malignancy included in the models were, in order of frequency: age, diameter, spiculated edge of the SPN, calcification, and smoking history. Variables such as race, growth rate of the SPN, emphysema, fibrosis, apical scarring and exposure to asbestos, uranium and radon among others were not analysed by the majority of the studies. All studies were classified as high risk of bias due to inadequate study designs, selection bias, insufficient follow-up of the population, and lack of external validation, compromising their applicability for clinical practice.Conclusions: The studies included have been shown to have methodological weaknesses compromising the clinical applicability of the evaluated SPN malignancy predictive models and their potential influence on clinical decision-making for the SPN diagnostic management. Systematic review registration: PROSPERO International prospective register of systematic reviews: CRD42020161559.

Prediction of single pulmonary nodule growth by CT radiomics and clinical features — a one-year follow-up study

“…It can help doctors predict whether the nodules will grow after one year and has important clinical significance. In previous studies, logistic regression models have been used to predict the malignant degree of solitary pulmonary nodules ( 41 ), showing good predictive performance. The nonlinear ML algorithm can deal with multidimensional features and identify some underlying patterns from data that are not linear or polynomial.…”