Non-invasive multiple cancer screening using trained detection canines and artificial intelligence: a prospective double-blind study

Abstract The specificity and sensitivity of a simple non-invasive multi-cancer screening method in detecting breast, lung, prostate, and colorectal cancer in breath samples were evaluated in a double-blind study. Breath samples of 1386 participants (59.7% males, median age 56.0 years) who underwent...

Full description

Saved in:
Bibliographic Details
Main Authors: Elizabeth Half, Adelina Ovcharenko, Ronit Shmuel, Sharon Furman-Assaf, Milana Avdalimov, Assaf Rabinowicz, Nadir Arber
Format: Article
Language:English
Published: Nature Portfolio 2024-11-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-79383-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846165406206656512
author Elizabeth Half
Adelina Ovcharenko
Ronit Shmuel
Sharon Furman-Assaf
Milana Avdalimov
Assaf Rabinowicz
Nadir Arber
author_facet Elizabeth Half
Adelina Ovcharenko
Ronit Shmuel
Sharon Furman-Assaf
Milana Avdalimov
Assaf Rabinowicz
Nadir Arber
author_sort Elizabeth Half
collection DOAJ
description Abstract The specificity and sensitivity of a simple non-invasive multi-cancer screening method in detecting breast, lung, prostate, and colorectal cancer in breath samples were evaluated in a double-blind study. Breath samples of 1386 participants (59.7% males, median age 56.0 years) who underwent screening for cancer using gold-standard screening methods, or a biopsy for a suspected malignancy were collected. The samples were analyzed using a bio-hybrid platform comprising trained detection canines and artificial intelligence tools. According to cancer screening/biopsy results, 1048 (75.6%) were negative for cancer and 338 (24.4%) were positive. Among the 338 positive samples, 261 (77.2%) were positive for one of the four cancer types that the bio-hybrid platform was trained to detect, with an overall sensitivity and specificity of 93.9% (95% confidence interval [CI] 90.3-96.2%) and 94.3% (95% CI 92.7%-95.5%), respectively. The sensitivity of each cancer type was similar; breast: 95.0% (95% CI 87.8-98.0%), lung: 95.0% (95% CI 87.8-98.0%), colorectal: 90.0% (95% CI 74.4-96.5%), prostate: 93.0% (95% CI 84.6-97.0%). The sensitivity of 14 other malignant tumors that the bio-hybrid platform was not trained to detect, but identified, was 81.8% (95% CI 71.8%-88.8%). Early cancer (0–2) detection sensitivity was 94.8% (95% CI 91.0%-97.1%). This bio-hybrid multi-cancer screening platform demonstrated high sensitivity and specificity and enables early-stage cancer detection.
format Article
id doaj-art-78580c2f440e4071a9ed6cfd15051732
institution Kabale University
issn 2045-2322
language English
publishDate 2024-11-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-78580c2f440e4071a9ed6cfd150517322024-11-17T12:18:50ZengNature PortfolioScientific Reports2045-23222024-11-0114111010.1038/s41598-024-79383-2Non-invasive multiple cancer screening using trained detection canines and artificial intelligence: a prospective double-blind studyElizabeth Half0Adelina Ovcharenko1Ronit Shmuel2Sharon Furman-Assaf3Milana Avdalimov4Assaf Rabinowicz5Nadir Arber6Gastroenterology Unit, Rambam Health Care CampusMIDGAM, The Israel Biobank for ResearchMedical consultant (independent)Medical writer and consultant (independent)SpotitEarly LtdSpotitEarly LtdIntegrated Cancer Prevention Center, Tel Aviv Souraski Medical CenterAbstract The specificity and sensitivity of a simple non-invasive multi-cancer screening method in detecting breast, lung, prostate, and colorectal cancer in breath samples were evaluated in a double-blind study. Breath samples of 1386 participants (59.7% males, median age 56.0 years) who underwent screening for cancer using gold-standard screening methods, or a biopsy for a suspected malignancy were collected. The samples were analyzed using a bio-hybrid platform comprising trained detection canines and artificial intelligence tools. According to cancer screening/biopsy results, 1048 (75.6%) were negative for cancer and 338 (24.4%) were positive. Among the 338 positive samples, 261 (77.2%) were positive for one of the four cancer types that the bio-hybrid platform was trained to detect, with an overall sensitivity and specificity of 93.9% (95% confidence interval [CI] 90.3-96.2%) and 94.3% (95% CI 92.7%-95.5%), respectively. The sensitivity of each cancer type was similar; breast: 95.0% (95% CI 87.8-98.0%), lung: 95.0% (95% CI 87.8-98.0%), colorectal: 90.0% (95% CI 74.4-96.5%), prostate: 93.0% (95% CI 84.6-97.0%). The sensitivity of 14 other malignant tumors that the bio-hybrid platform was not trained to detect, but identified, was 81.8% (95% CI 71.8%-88.8%). Early cancer (0–2) detection sensitivity was 94.8% (95% CI 91.0%-97.1%). This bio-hybrid multi-cancer screening platform demonstrated high sensitivity and specificity and enables early-stage cancer detection.https://doi.org/10.1038/s41598-024-79383-2Artificial intelligenceDetection caninesCancer screeningLungBreastColorectal
spellingShingle Elizabeth Half
Adelina Ovcharenko
Ronit Shmuel
Sharon Furman-Assaf
Milana Avdalimov
Assaf Rabinowicz
Nadir Arber
Non-invasive multiple cancer screening using trained detection canines and artificial intelligence: a prospective double-blind study
Scientific Reports
Artificial intelligence
Detection canines
Cancer screening
Lung
Breast
Colorectal
title Non-invasive multiple cancer screening using trained detection canines and artificial intelligence: a prospective double-blind study
title_full Non-invasive multiple cancer screening using trained detection canines and artificial intelligence: a prospective double-blind study
title_fullStr Non-invasive multiple cancer screening using trained detection canines and artificial intelligence: a prospective double-blind study
title_full_unstemmed Non-invasive multiple cancer screening using trained detection canines and artificial intelligence: a prospective double-blind study
title_short Non-invasive multiple cancer screening using trained detection canines and artificial intelligence: a prospective double-blind study
title_sort non invasive multiple cancer screening using trained detection canines and artificial intelligence a prospective double blind study
topic Artificial intelligence
Detection canines
Cancer screening
Lung
Breast
Colorectal
url https://doi.org/10.1038/s41598-024-79383-2
work_keys_str_mv AT elizabethhalf noninvasivemultiplecancerscreeningusingtraineddetectioncaninesandartificialintelligenceaprospectivedoubleblindstudy
AT adelinaovcharenko noninvasivemultiplecancerscreeningusingtraineddetectioncaninesandartificialintelligenceaprospectivedoubleblindstudy
AT ronitshmuel noninvasivemultiplecancerscreeningusingtraineddetectioncaninesandartificialintelligenceaprospectivedoubleblindstudy
AT sharonfurmanassaf noninvasivemultiplecancerscreeningusingtraineddetectioncaninesandartificialintelligenceaprospectivedoubleblindstudy
AT milanaavdalimov noninvasivemultiplecancerscreeningusingtraineddetectioncaninesandartificialintelligenceaprospectivedoubleblindstudy
AT assafrabinowicz noninvasivemultiplecancerscreeningusingtraineddetectioncaninesandartificialintelligenceaprospectivedoubleblindstudy
AT nadirarber noninvasivemultiplecancerscreeningusingtraineddetectioncaninesandartificialintelligenceaprospectivedoubleblindstudy