Dataset Information

Machine learning model for circulating tumor DNA detection in chronic obstructive pulmonary disease patients with lung cancer.

ABSTRACT:

Background

Patients with chronic obstructive pulmonary disease (COPD) have a high risk of developing lung cancer. Due to the high rates of complications from invasive diagnostic procedures in this population, detecting circulating tumor DNA (ctDNA) as a non-invasive method might be useful. However, clinical characteristics that are predictive of ctDNA mutation detection remain incompletely understood. This study aimed to investigate factors associated with ctDNA detection in COPD patients with lung cancer.

Methods

Herein, 177 patients with COPD and lung cancer were prospectively recruited. Plasma ctDNA was genotyped using targeted deep sequencing. Comprehensive clinical variables were collected, including the emphysema index (EI), using chest computed tomography. Machine learning models were constructed to predict ctDNA detection.

Results

At least one ctDNA mutation was detected in 54 (30.5%) patients. After adjustment for potential confounders, tumor stage, C-reactive protein (CRP) level, and milder emphysema were independently associated with ctDNA detection. An increase of 1% in the EI was associated with a 7% decrease in the odds of ctDNA detection (adjusted odds ratio =0.933; 95% confidence interval: 0.857-0.999; P=0.047). Machine learning models composed of multiple clinical factors predicted individuals with ctDNA mutations at high performance (AUC =0.774).

Conclusions

ctDNA mutations were likely to be observed in COPD patients with lung cancer who had an advanced clinical stage, high CRP level, or milder emphysema. This was validated in machine learning models with high accuracy. Further prospective studies are required to validate the clinical utility of our findings.

SUBMITTER: Shin SH

PROVIDER: S-EPMC10891398 | biostudies-literature | 2024 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning model for circulating tumor DNA detection in chronic obstructive pulmonary disease patients with lung cancer.

Shin Sun Hye SH Cha Soojin S Lee Ho Yun HY Shin Seung-Ho SH Kim Yeon Jeong YJ Park Donghyun D Han Kyung Yeon KY Oh You Jin YJ Park Woong-Yang WY Ahn Myung-Ju MJ Kim Hojoong H Won Hong-Hee HH Park Hye Yun HY

Translational lung cancer research 20240129 1

<h4>Background</h4>Patients with chronic obstructive pulmonary disease (COPD) have a high risk of developing lung cancer. Due to the high rates of complications from invasive diagnostic procedures in this population, detecting circulating tumor DNA (ctDNA) as a non-invasive method might be useful. However, clinical characteristics that are predictive of ctDNA mutation detection remain incompletely understood. This study aimed to investigate factors associated with ctDNA detection in COPD patient ...[more]

PMID: 38404987

Similar Datasets

Project description:Despite being a major cause of morbidity and mortality, chronic obstructive pulmonary disease (COPD) is frequently undiagnosed. Yet the burden of disease among the undiagnosed is significant, as these individuals experience symptoms, exacerbations, and excess mortality compared to those without COPD. The U.S. Preventive Services Task Force recommends against routine screening of asymptomatic individuals with spirometry. Hence, case-finding approaches are needed. A recently developed instrument, the five-item COPD Assessment in Primary Care to Identify Undiagnosed Respiratory Disease and Exacerbation Risk questionnaire plus peak expiratory flow, demonstrates good sensitivity and specificity for distinguishing cases from control subjects and is being studied prospectively in primary care settings to determine its impact on patient outcomes. However, finding the undiagnosed is only half the battle. Mounting evidence suggests significant COPD-like respiratory burden among individuals without airflow obstruction. Many experience dyspnea, mucus production, and exacerbation events and have emphysema and airway abnormalities on computed tomographic (CT) imaging of the chest. However, it is still unclear how to best treat these individuals and which individuals go on to develop spirometric obstruction. These challenges underline the importance of defining what constitutes "early disease." A recently proposed definition characterizes early COPD as either: 1) airflow limitation, 2) compatible CT imaging abnormalities, or 3) accelerated forced expiratory volume in 1 second decline in persons younger than 50 years and with greater than a 10 pack-year smoking history. Although it is recognized that this definition does not encompass all individuals who will develop COPD, it is an attempt to identify a group of individuals with most rapid decline to better understand mechanisms of disease development and where disease-modifying interventions are most likely to be successful. Ultimately, leveraging tools such as chest CT imaging, the electronic medical record, and machine learning algorithms may aid in the identification of such individuals.

Dataset Information

Machine learning model for circulating tumor DNA detection in chronic obstructive pulmonary disease patients with lung cancer.

Background

Methods

Results

Conclusions

Publications

Machine learning model for circulating tumor DNA detection in chronic obstructive pulmonary disease patients with lung cancer.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets