This is a preprint, a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
A new preprint design is coming!
We have improved readability, clarity, accessibility, and opportunities for engagement.
Article
License:
This work is licensed under a CC BY 4.0 License. Read Full License
Despite advances in cancer treatment, the five-year mortality rate for oral cancers (OC) is 40%, mainly due to the lack of early diagnostics. To advance early diagnostics for high-risk and average-risk populations, we developed and evaluated machine-learning (ML) classifiers using metatranscriptomic data from saliva samples (n=433) collected from oral premalignant disorders (OPMD), OC patients (n=71) and normal controls (n=171). Our diagnostic classifiers yielded a receiver operating characteristics (ROC) area under the curve (AUC) up to 0.9, sensitivity up to 83% (92.3% for stage 1 cancer) and specificity up to 97.9%. Our metatranscriptomic signature incorporates both taxonomic and functional microbiome features, and reveals a number of previously known and novel taxa and functional pathways associated with OC. For the first time, we demonstrate the potential clinical utility of an AI/ML model for diagnosing OC early, opening a new era of non-invasive diagnostics, enabling early intervention and improved patient outcomes.
Keywords
oral cancer, diagnostics, machine learning model
Figure 1
Figure 2
Figure 3
The full text of this article is available to read as a PDF.
Yes there is potential Competing Interest. Several of the authors are employees of Viome Inc, a commercial for-profit company. For the other authors there is no conflict of interest to be best of our knowledge.
This is a list of supplementary files associated with this preprint. Click to download.
- FigS0.png
Details of the discovery cohort.
- FigS1.png
Saliva sample processing procedure for NGS workflow
- FigS2.png
Distribution of Spearman correlations for inter and intra donor saliva sample pairs processed concurrently and independently (a) taxonomy data (b) functional data.
- FigS3.png
Distribution of the number of reads
- FigS4.png
ROC AUC of the classifier for Cohort C using (a) only taxa as the features and (b) only the KOs as the features.
Loading...
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
History
CURRENT STATUS: Posted
View the published article at npj Genomic Medicine.
Version 1
Posted 19 Aug, 2020
No community comments so far
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
Learn more about our company.
A new preprint design is coming!
We have improved readability, clarity, accessibility, and opportunities for engagement.
This is a preprint, a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
Article
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
History
CURRENT STATUS: Posted
View the published article at npj Genomic Medicine.
Version 1
Posted 19 Aug, 2020
No community comments so far
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
License:
This work is licensed under a CC BY 4.0 License. Read Full License
View the published article at npj Genomic Medicine.
Despite advances in cancer treatment, the five-year mortality rate for oral cancers (OC) is 40%, mainly due to the lack of early diagnostics. To advance early diagnostics for high-risk and average-risk populations, we developed and evaluated machine-learning (ML) classifiers using metatranscriptomic data from saliva samples (n=433) collected from oral premalignant disorders (OPMD), OC patients (n=71) and normal controls (n=171). Our diagnostic classifiers yielded a receiver operating characteristics (ROC) area under the curve (AUC) up to 0.9, sensitivity up to 83% (92.3% for stage 1 cancer) and specificity up to 97.9%. Our metatranscriptomic signature incorporates both taxonomic and functional microbiome features, and reveals a number of previously known and novel taxa and functional pathways associated with OC. For the first time, we demonstrate the potential clinical utility of an AI/ML model for diagnosing OC early, opening a new era of non-invasive diagnostics, enabling early intervention and improved patient outcomes.
Figure 1
Figure 2
Figure 3
The full text of this article is available to read as a PDF.
Yes there is potential Competing Interest. Several of the authors are employees of Viome Inc, a commercial for-profit company. For the other authors there is no conflict of interest to be best of our knowledge.
This is a list of supplementary files associated with this preprint. Click to download.
- FigS0.png
Details of the discovery cohort.
- FigS1.png
Saliva sample processing procedure for NGS workflow
- FigS2.png
Distribution of Spearman correlations for inter and intra donor saliva sample pairs processed concurrently and independently (a) taxonomy data (b) functional data.
- FigS3.png
Distribution of the number of reads
- FigS4.png
ROC AUC of the classifier for Cohort C using (a) only taxa as the features and (b) only the KOs as the features.
Loading...