The Detection of Colorectal Cancer through Machine Learning-Based Breath Sensor Analysis
Colorectal cancer (CRC) is the third most common malignancy and the second most common cause of cancer-related deaths worldwide. While CRC screening is already part of organized programs in many countries, there remains a need for improved screening tools. In recent years, a potential approach for c...
Main Authors: | , , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-10-01
|
Series: | Diagnostics |
Subjects: | |
Online Access: | https://www.mdpi.com/2075-4418/13/21/3355 |
_version_ | 1797632039180042240 |
---|---|
author | Inese Poļaka Linda Mežmale Linda Anarkulova Elīna Kononova Ilona Vilkoite Viktors Veliks Anna Marija Ļeščinska Ilmārs Stonāns Andrejs Pčolkins Ivars Tolmanis Gidi Shani Hossam Haick Jan Mitrovics Johannes Glöckler Boris Mizaikoff Mārcis Leja |
author_facet | Inese Poļaka Linda Mežmale Linda Anarkulova Elīna Kononova Ilona Vilkoite Viktors Veliks Anna Marija Ļeščinska Ilmārs Stonāns Andrejs Pčolkins Ivars Tolmanis Gidi Shani Hossam Haick Jan Mitrovics Johannes Glöckler Boris Mizaikoff Mārcis Leja |
author_sort | Inese Poļaka |
collection | DOAJ |
description | Colorectal cancer (CRC) is the third most common malignancy and the second most common cause of cancer-related deaths worldwide. While CRC screening is already part of organized programs in many countries, there remains a need for improved screening tools. In recent years, a potential approach for cancer diagnosis has emerged via the analysis of volatile organic compounds (VOCs) using sensor technologies. The main goal of this study was to demonstrate and evaluate the diagnostic potential of a table-top breath analyzer for detecting CRC. Breath sampling was conducted and CRC vs. non-cancer groups (105 patients with CRC, 186 non-cancer subjects) were included in analysis. The obtained data were analyzed using supervised machine learning methods (i.e., Random Forest, C4.5, Artificial Neural Network, and Naïve Bayes). Superior accuracy was achieved using Random Forest and Evolutionary Search for Features (79.3%, sensitivity 53.3%, specificity 93.0%, AUC ROC 0.734), and Artificial Neural Networks and Greedy Search for Features (78.2%, sensitivity 43.3%, specificity 96.5%, AUC ROC 0.735). Our results confirm the potential of the developed breath analyzer as a promising tool for identifying and categorizing CRC within a point-of-care clinical context. The combination of MOX sensors provided promising results in distinguishing healthy vs. diseased breath samples. Its capacity for rapid, non-invasive, and targeted CRC detection suggests encouraging prospects for future clinical screening applications. |
first_indexed | 2024-03-11T11:31:16Z |
format | Article |
id | doaj.art-01ee4628f711419287eaefc1bc8bffe8 |
institution | Directory Open Access Journal |
issn | 2075-4418 |
language | English |
last_indexed | 2024-03-11T11:31:16Z |
publishDate | 2023-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Diagnostics |
spelling | doaj.art-01ee4628f711419287eaefc1bc8bffe82023-11-10T15:01:04ZengMDPI AGDiagnostics2075-44182023-10-011321335510.3390/diagnostics13213355The Detection of Colorectal Cancer through Machine Learning-Based Breath Sensor AnalysisInese Poļaka0Linda Mežmale1Linda Anarkulova2Elīna Kononova3Ilona Vilkoite4Viktors Veliks5Anna Marija Ļeščinska6Ilmārs Stonāns7Andrejs Pčolkins8Ivars Tolmanis9Gidi Shani10Hossam Haick11Jan Mitrovics12Johannes Glöckler13Boris Mizaikoff14Mārcis Leja15Institute of Clinical and Preventive Medicine, University of Latvia, LV-1586 Riga, LatviaInstitute of Clinical and Preventive Medicine, University of Latvia, LV-1586 Riga, LatviaInstitute of Clinical and Preventive Medicine, University of Latvia, LV-1586 Riga, LatviaInstitute of Clinical and Preventive Medicine, University of Latvia, LV-1586 Riga, LatviaHealth Centre 4, LV-1012 Riga, LatviaInstitute of Clinical and Preventive Medicine, University of Latvia, LV-1586 Riga, LatviaInstitute of Clinical and Preventive Medicine, University of Latvia, LV-1586 Riga, LatviaInstitute of Clinical and Preventive Medicine, University of Latvia, LV-1586 Riga, LatviaInstitute of Clinical and Preventive Medicine, University of Latvia, LV-1586 Riga, LatviaFaculty of Medicine, Riga Stradins University, LV-1007 Riga, LatviaLaboratory for Nanomaterial-Based Devices, Technion—Israel Institute of Technology, Haifa 3200003, IsraelLaboratory for Nanomaterial-Based Devices, Technion—Israel Institute of Technology, Haifa 3200003, IsraelJLM Innovation GmbH, D-72070 Tübingen, GermanyInstitute of Analytical and Bioanalytical Chemistry, Ulm University, 89081 Ulm, GermanyInstitute of Analytical and Bioanalytical Chemistry, Ulm University, 89081 Ulm, GermanyInstitute of Clinical and Preventive Medicine, University of Latvia, LV-1586 Riga, LatviaColorectal cancer (CRC) is the third most common malignancy and the second most common cause of cancer-related deaths worldwide. While CRC screening is already part of organized programs in many countries, there remains a need for improved screening tools. In recent years, a potential approach for cancer diagnosis has emerged via the analysis of volatile organic compounds (VOCs) using sensor technologies. The main goal of this study was to demonstrate and evaluate the diagnostic potential of a table-top breath analyzer for detecting CRC. Breath sampling was conducted and CRC vs. non-cancer groups (105 patients with CRC, 186 non-cancer subjects) were included in analysis. The obtained data were analyzed using supervised machine learning methods (i.e., Random Forest, C4.5, Artificial Neural Network, and Naïve Bayes). Superior accuracy was achieved using Random Forest and Evolutionary Search for Features (79.3%, sensitivity 53.3%, specificity 93.0%, AUC ROC 0.734), and Artificial Neural Networks and Greedy Search for Features (78.2%, sensitivity 43.3%, specificity 96.5%, AUC ROC 0.735). Our results confirm the potential of the developed breath analyzer as a promising tool for identifying and categorizing CRC within a point-of-care clinical context. The combination of MOX sensors provided promising results in distinguishing healthy vs. diseased breath samples. Its capacity for rapid, non-invasive, and targeted CRC detection suggests encouraging prospects for future clinical screening applications.https://www.mdpi.com/2075-4418/13/21/3355colorectal cancersensorsscreeningbreath analyzervolatile organic compoundsmachine learning |
spellingShingle | Inese Poļaka Linda Mežmale Linda Anarkulova Elīna Kononova Ilona Vilkoite Viktors Veliks Anna Marija Ļeščinska Ilmārs Stonāns Andrejs Pčolkins Ivars Tolmanis Gidi Shani Hossam Haick Jan Mitrovics Johannes Glöckler Boris Mizaikoff Mārcis Leja The Detection of Colorectal Cancer through Machine Learning-Based Breath Sensor Analysis Diagnostics colorectal cancer sensors screening breath analyzer volatile organic compounds machine learning |
title | The Detection of Colorectal Cancer through Machine Learning-Based Breath Sensor Analysis |
title_full | The Detection of Colorectal Cancer through Machine Learning-Based Breath Sensor Analysis |
title_fullStr | The Detection of Colorectal Cancer through Machine Learning-Based Breath Sensor Analysis |
title_full_unstemmed | The Detection of Colorectal Cancer through Machine Learning-Based Breath Sensor Analysis |
title_short | The Detection of Colorectal Cancer through Machine Learning-Based Breath Sensor Analysis |
title_sort | detection of colorectal cancer through machine learning based breath sensor analysis |
topic | colorectal cancer sensors screening breath analyzer volatile organic compounds machine learning |
url | https://www.mdpi.com/2075-4418/13/21/3355 |
work_keys_str_mv | AT inesepolaka thedetectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT lindamezmale thedetectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT lindaanarkulova thedetectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT elinakononova thedetectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT ilonavilkoite thedetectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT viktorsveliks thedetectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT annamarijalescinska thedetectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT ilmarsstonans thedetectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT andrejspcolkins thedetectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT ivarstolmanis thedetectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT gidishani thedetectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT hossamhaick thedetectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT janmitrovics thedetectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT johannesglockler thedetectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT borismizaikoff thedetectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT marcisleja thedetectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT inesepolaka detectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT lindamezmale detectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT lindaanarkulova detectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT elinakononova detectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT ilonavilkoite detectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT viktorsveliks detectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT annamarijalescinska detectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT ilmarsstonans detectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT andrejspcolkins detectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT ivarstolmanis detectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT gidishani detectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT hossamhaick detectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT janmitrovics detectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT johannesglockler detectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT borismizaikoff detectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis AT marcisleja detectionofcolorectalcancerthroughmachinelearningbasedbreathsensoranalysis |