Socio-Economic Factors and Clinical Context Can Predict Adherence to Incidental Pulmonary Nodule Follow-up via Machine Learning Models.

Autor:	Wang Z; Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania., Mortani Barbosa EJ Jr; Director of CT Modality at the Thoracic Imaging Section, Division of Cardiothoracic Imaging, Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania. Electronic address: Eduardo.Barbosa@pennmedicine.upenn.edu.
Jazyk:	angličtina
Zdroj:	Journal of the American College of Radiology : JACR [J Am Coll Radiol] 2024 Oct; Vol. 21 (10), pp. 1620-1631. Date of Electronic Publication: 2024 Mar 08.
DOI:	10.1016/j.jacr.2024.02.031
Abstrakt:	Objective: To quantify the relative importance of demographic, contextual, socio-economic, and nodule-related factors that influence patient adherence to incidental pulmonary nodule (IPN) follow-up visits and evaluate the predictive performance of machine learning models utilizing these features. Methods: We curated a 1,610-subject patient data set from electronic medical records consisting of 13 clinical and socio-economic predictors and IPN follow-up adherence status (timely, delayed, or never) as the outcome. Univariate analysis and multivariate logistic regression were performed to quantify the predictors' contributions to follow-up adherence. Three additional machine learning models (random forests, neural network, and support vector machine) were fitted and cross-validated to examine prediction performance across different model architectures and evaluate intermodel concordance. Results: On univariate basis, all 13 predictors except comorbidity were found to have a significant association with follow-up. In multiple logistic regression, inpatient or emergency clinical context (odds ratio favoring never following up: 7.28 and 8.56 versus outpatient, respectively) and high nodule risk (odds ratio: 0.25 versus low risk) are the most significant predictors of follow-up, and sex, race, and marital status become additionally significant if clinical context is removed from the model. Clinical context itself is associated with sex, race, insurance, employment, marriage, income, nodule risk, and smoking status, suggesting its role in mediating socio-economic inequities. On cross-validation, all four machine learning models demonstrated comparable and good predictive performances, with mean area under the curve ranging from 0.759 to 0.802, with sensitivity 0.641 to 0.660 and specificity 0.768 to 0.840. Conclusion: Socio-economic factors and clinical context are predictive of IPN follow-up adherence, with clinical context being the most significant contributor and likely representing uncaptured socio-economic determinants. (Copyright © 2024 American College of Radiology. Published by Elsevier Inc. All rights reserved.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu