Objectives: The aim of the study is to investigate the performance of artificial intelligence (AI) convolutional neural networks (CNN) in detecting lung nodules on chest computed tomography of patients with complex lung disease, and demonstrate its noninferiority when compared against an experienced radiologist through clinically relevant assessments.
Methods: A CNN prototype was used to retrospectively evaluate 103 complex lung disease cases and 40 control cases without reported nodules. Computed tomography scans were blindly evaluated by an expert thoracic radiologist; a month after initial analyses, 20 positive cases were re-evaluated with the assistance of AI. For clinically relevant applications: (1) AI was asked to classify each patient into nodules present or absent and (2) AI results were compared against standard radiology reports. Standard statistics were performed to determine detection performance.
Results: AI was, on average, 27 seconds faster than the expert and detected 8.4% of nodules that would have been missed. AI had a sensitivity of 67.7%, similar to an accuracy reported for experienced radiologists. AI correctly classified each patient (nodules present/absent) with a sensitivity of 96.1%. When matched against radiology reports, AI performed with a sensitivity of 89.4%. Control group assessment demonstrated an overall specificity of 82.5%. When aided by AI, the expert decreased the average assessment time per case from 2:44 minutes to 35.7 seconds, while reporting an overall increase in confidence.
Conclusion: In a group of patients with complex lung disease, the sensitivity of AI is similar to an experienced radiologist and the tool helps detect previously missed nodules. AI also helps experts analyze for lung nodules faster and more confidently, a feature that is beneficial to patients and favorable to hospitals due to increased patient load and need for shorter turnaround times.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1097/RTI.0000000000000613 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Carbidopa and ZnCarbidopa Induce Reductive Stress in MDA-MB-231 Cells.
Chempluschem
December 2024
Centre for Inorganic Chemistry, Chemistry, Bv 120, e/ 60 y 64, Nº1465, 1900, La Plata, ARGENTINA.
The redox imbalance, caused by depletion or generation of reactive oxygen species (ROS), is a key mechanism by which metal complexes exert anticancer effects. Carbidopa has shown the ability to inhibit the MDA-MB-231 cell line, a highly aggressive triple-negative human breast adenocarcinoma, by inducing reductive stress. The metal complex of carbidopa with zinc (ZnCarbi) was designed to modify carbidopa's structure and exhibited increased cytotoxicity against MDA-MB-231 cells.
View Article and Find Full Text PDFHigh Interleukin (IL)-6 is Associated with Lower Lung Function and Increased Likelihood of Metabolic Dysfunction in Asthma.
Pulm Ther
December 2024
Division of Pulmonary and Critical Care Medicine, University of Michigan, Ann Arbor, MI, USA.
Introduction: Asthma is a complex condition characterized by airway inflammation. Interleukin-6 (IL-6) plays a significant role in asthma pathogenesis through its effects on T cells and its association with pro-inflammatory responses. Both lung and circulating IL-6 levels are elevated in asthma.
View Article and Find Full Text PDFLymphangioleiomyomatosis (LAM) is a cystic lung disease that primarily affects women. LAM is caused by the invasion of metastatic smooth muscle-like cells into the lung parenchyma, leading to abnormal cell proliferation, lung remodeling and progressive respiratory failure. LAM cells have TSC gene mutations, which occur sporadically or in people with Tuberous Sclerosis Complex.
View Article and Find Full Text PDFImpact of Immune Abnormalities on COVID-19 Vaccine Effectiveness in Infected Patients.
Cureus
November 2024
Pulmonary and Critical Care Medicine, Foshan Sanshui District People's Hospital, Foshan, CHN.
Objective To assess the protective effect of COVID-19 vaccines in patients with varying immune states by analyzing lactate dehydrogenase (LDH), C-reactive protein (CRP), and D-dimer (D-Di) levels in COVID-19-infected individuals under different vaccination scenarios and immune statuses. Methods This is a single-center retrospective study involving 338 SARS-CoV-2-infected patients treated at a tertiary medical center in Foshan, China, between November 2022 and January 2023. The primary outcome was the vaccine's protective effect on LDH, CRP, and D-Di levels.
View Article and Find Full Text PDFDevelopment of a dyadic mindfulness self-compassion intervention for patients with lung cancer and their family caregivers: A multi-method study.
Asia Pac J Oncol Nurs
December 2025
Xiangya School of Nursing, Central South University, Changsha, China.
Objective: Lung cancer and its prolonged treatment are profoundly unsettling for patients and their family caregivers, and developing dyadic measures to alleviate their negative affectivity is pivotal. This study aimed to develop a complex intervention to alleviate dyadic psychological stress among patients with lung cancer and their family caregivers.
Methods: A stepwise multi-method study was conducted following the Medical Research Council framework.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!