Detection of early-stage lung cancer in sputum using automated flow cytometry and machine learning
Abstract Background Low-dose spiral computed tomography (LDCT) may not lead to a clear treatment path when small to intermediate-sized lung nodules are identified. We have combined flow cytometry and machine learning to develop a sputum-based test (CyPath Lung) that can assist physicians in decision...
Main Authors: | , , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2023-01-01
|
Series: | Respiratory Research |
Subjects: | |
Online Access: | https://doi.org/10.1186/s12931-023-02327-3 |
_version_ | 1797945771477172224 |
---|---|
author | Madeleine E. Lemieux Xavier T. Reveles Jennifer Rebeles Lydia H. Bederka Patricia R. Araujo Jamila R. Sanchez Marcia Grayson Shao-Chiang Lai Louis R. DePalo Sheila A. Habib David G. Hill Kathleen Lopez Lara Patriquin Robert Sussman Roby P. Joyce Vivienne I. Rebel |
author_facet | Madeleine E. Lemieux Xavier T. Reveles Jennifer Rebeles Lydia H. Bederka Patricia R. Araujo Jamila R. Sanchez Marcia Grayson Shao-Chiang Lai Louis R. DePalo Sheila A. Habib David G. Hill Kathleen Lopez Lara Patriquin Robert Sussman Roby P. Joyce Vivienne I. Rebel |
author_sort | Madeleine E. Lemieux |
collection | DOAJ |
description | Abstract Background Low-dose spiral computed tomography (LDCT) may not lead to a clear treatment path when small to intermediate-sized lung nodules are identified. We have combined flow cytometry and machine learning to develop a sputum-based test (CyPath Lung) that can assist physicians in decision-making in such cases. Methods Single cell suspensions prepared from induced sputum samples collected over three consecutive days were labeled with a viability dye to exclude dead cells, antibodies to distinguish cell types, and a porphyrin to label cancer-associated cells. The labeled cell suspension was run on a flow cytometer and the data collected. An analysis pipeline combining automated flow cytometry data processing with machine learning was developed to distinguish cancer from non-cancer samples from 150 patients at high risk of whom 28 had lung cancer. Flow data and patient features were evaluated to identify predictors of lung cancer. Random training and test sets were chosen to evaluate predictive variables iteratively until a robust model was identified. The final model was tested on a second, independent group of 32 samples, including six samples from patients diagnosed with lung cancer. Results Automated analysis combined with machine learning resulted in a predictive model that achieved an area under the ROC curve (AUC) of 0.89 (95% CI 0.83–0.89). The sensitivity and specificity were 82% and 88%, respectively, and the negative and positive predictive values 96% and 61%, respectively. Importantly, the test was 92% sensitive and 87% specific in cases when nodules were < 20 mm (AUC of 0.94; 95% CI 0.89–0.99). Testing of the model on an independent second set of samples showed an AUC of 0.85 (95% CI 0.71–0.98) with an 83% sensitivity, 77% specificity, 95% negative predictive value and 45% positive predictive value. The model is robust to differences in sample processing and disease state. Conclusion CyPath Lung correctly classifies samples as cancer or non-cancer with high accuracy, including from participants at different disease stages and with nodules < 20 mm in diameter. This test is intended for use after lung cancer screening to improve early-stage lung cancer diagnosis. Trial registration ClinicalTrials.gov ID: NCT03457415; March 7, 2018 |
first_indexed | 2024-04-10T21:00:24Z |
format | Article |
id | doaj.art-d3f1133571fa41c98dbfa1a17abe84ab |
institution | Directory Open Access Journal |
issn | 1465-993X |
language | English |
last_indexed | 2024-04-10T21:00:24Z |
publishDate | 2023-01-01 |
publisher | BMC |
record_format | Article |
series | Respiratory Research |
spelling | doaj.art-d3f1133571fa41c98dbfa1a17abe84ab2023-01-22T12:22:44ZengBMCRespiratory Research1465-993X2023-01-0124111610.1186/s12931-023-02327-3Detection of early-stage lung cancer in sputum using automated flow cytometry and machine learningMadeleine E. Lemieux0Xavier T. Reveles1Jennifer Rebeles2Lydia H. Bederka3Patricia R. Araujo4Jamila R. Sanchez5Marcia Grayson6Shao-Chiang Lai7Louis R. DePalo8Sheila A. Habib9David G. Hill10Kathleen Lopez11Lara Patriquin12Robert Sussman13Roby P. Joyce14Vivienne I. Rebel15BioinfobioAffinity TechnologiesbioAffinity TechnologiesbioAffinity TechnologiesbioAffinity TechnologiesbioAffinity TechnologiesbioAffinity TechnologiesbioAffinity TechnologiesDepartment of Medicine, Icahn School of Medicine at Mount SinaiSouth Texas Veterans Health Care System (STVHCS), Audie L. Murphy Memorial Veterans HospitalWaterbury Pulmonary Associates LLCRadiology Associates of AlbuquerqueRadiology Associates of AlbuquerqueAtlantic Respiratory InstitutePrecision Pathology ServicesbioAffinity TechnologiesAbstract Background Low-dose spiral computed tomography (LDCT) may not lead to a clear treatment path when small to intermediate-sized lung nodules are identified. We have combined flow cytometry and machine learning to develop a sputum-based test (CyPath Lung) that can assist physicians in decision-making in such cases. Methods Single cell suspensions prepared from induced sputum samples collected over three consecutive days were labeled with a viability dye to exclude dead cells, antibodies to distinguish cell types, and a porphyrin to label cancer-associated cells. The labeled cell suspension was run on a flow cytometer and the data collected. An analysis pipeline combining automated flow cytometry data processing with machine learning was developed to distinguish cancer from non-cancer samples from 150 patients at high risk of whom 28 had lung cancer. Flow data and patient features were evaluated to identify predictors of lung cancer. Random training and test sets were chosen to evaluate predictive variables iteratively until a robust model was identified. The final model was tested on a second, independent group of 32 samples, including six samples from patients diagnosed with lung cancer. Results Automated analysis combined with machine learning resulted in a predictive model that achieved an area under the ROC curve (AUC) of 0.89 (95% CI 0.83–0.89). The sensitivity and specificity were 82% and 88%, respectively, and the negative and positive predictive values 96% and 61%, respectively. Importantly, the test was 92% sensitive and 87% specific in cases when nodules were < 20 mm (AUC of 0.94; 95% CI 0.89–0.99). Testing of the model on an independent second set of samples showed an AUC of 0.85 (95% CI 0.71–0.98) with an 83% sensitivity, 77% specificity, 95% negative predictive value and 45% positive predictive value. The model is robust to differences in sample processing and disease state. Conclusion CyPath Lung correctly classifies samples as cancer or non-cancer with high accuracy, including from participants at different disease stages and with nodules < 20 mm in diameter. This test is intended for use after lung cancer screening to improve early-stage lung cancer diagnosis. Trial registration ClinicalTrials.gov ID: NCT03457415; March 7, 2018https://doi.org/10.1186/s12931-023-02327-3SputumAutomated flow cytometryMachine learningPorphyrinEarly-stage lung cancer |
spellingShingle | Madeleine E. Lemieux Xavier T. Reveles Jennifer Rebeles Lydia H. Bederka Patricia R. Araujo Jamila R. Sanchez Marcia Grayson Shao-Chiang Lai Louis R. DePalo Sheila A. Habib David G. Hill Kathleen Lopez Lara Patriquin Robert Sussman Roby P. Joyce Vivienne I. Rebel Detection of early-stage lung cancer in sputum using automated flow cytometry and machine learning Respiratory Research Sputum Automated flow cytometry Machine learning Porphyrin Early-stage lung cancer |
title | Detection of early-stage lung cancer in sputum using automated flow cytometry and machine learning |
title_full | Detection of early-stage lung cancer in sputum using automated flow cytometry and machine learning |
title_fullStr | Detection of early-stage lung cancer in sputum using automated flow cytometry and machine learning |
title_full_unstemmed | Detection of early-stage lung cancer in sputum using automated flow cytometry and machine learning |
title_short | Detection of early-stage lung cancer in sputum using automated flow cytometry and machine learning |
title_sort | detection of early stage lung cancer in sputum using automated flow cytometry and machine learning |
topic | Sputum Automated flow cytometry Machine learning Porphyrin Early-stage lung cancer |
url | https://doi.org/10.1186/s12931-023-02327-3 |
work_keys_str_mv | AT madeleineelemieux detectionofearlystagelungcancerinsputumusingautomatedflowcytometryandmachinelearning AT xaviertreveles detectionofearlystagelungcancerinsputumusingautomatedflowcytometryandmachinelearning AT jenniferrebeles detectionofearlystagelungcancerinsputumusingautomatedflowcytometryandmachinelearning AT lydiahbederka detectionofearlystagelungcancerinsputumusingautomatedflowcytometryandmachinelearning AT patriciararaujo detectionofearlystagelungcancerinsputumusingautomatedflowcytometryandmachinelearning AT jamilarsanchez detectionofearlystagelungcancerinsputumusingautomatedflowcytometryandmachinelearning AT marciagrayson detectionofearlystagelungcancerinsputumusingautomatedflowcytometryandmachinelearning AT shaochianglai detectionofearlystagelungcancerinsputumusingautomatedflowcytometryandmachinelearning AT louisrdepalo detectionofearlystagelungcancerinsputumusingautomatedflowcytometryandmachinelearning AT sheilaahabib detectionofearlystagelungcancerinsputumusingautomatedflowcytometryandmachinelearning AT davidghill detectionofearlystagelungcancerinsputumusingautomatedflowcytometryandmachinelearning AT kathleenlopez detectionofearlystagelungcancerinsputumusingautomatedflowcytometryandmachinelearning AT larapatriquin detectionofearlystagelungcancerinsputumusingautomatedflowcytometryandmachinelearning AT robertsussman detectionofearlystagelungcancerinsputumusingautomatedflowcytometryandmachinelearning AT robypjoyce detectionofearlystagelungcancerinsputumusingautomatedflowcytometryandmachinelearning AT vivienneirebel detectionofearlystagelungcancerinsputumusingautomatedflowcytometryandmachinelearning |