Using machine learning and an electronic tongue for discriminating saliva samples from oral cavity cancer patients and healthy individuals
Bibliographic record
Abstract
The diagnosis of cancer and other diseases using data from non-specific sensors - such as the electronic tongues (e-tongues) - is challenging owing to the lack of selectivity, in addition to the variability of biological samples. In this study, we demonstrate that impedance data obtained with an e-tongue in saliva samples can be used to diagnose cancer in the mouth. Data taken with a single-response microfluidic e-tongue applied to the saliva of 27 individuals were treated with multidimensional projection techniques and non-supervised and supervised machine learning algorithms. The distinction between healthy individuals and patients with cancer on the floor of mouth or oral cavity could only be made with supervised learning. Accuracy above 80% was obtained for the binary classification (YES or NO for cancer) using a Support Vector Machine (SVM) with radial basis function kernel and Random Forest. In the classification considering the type of cancer, the accuracy dropped to ca. 70%. The accuracy tended to increase when clinical information such as alcohol consumption was used in conjunction with the e-tongue data. With the random forest algorithm, the rules to explain the diagnosis could be identified using the concept of Multidimensional Calibration Space. Since the training of the machine learning algorithms is believed to be more efficient when the data of a larger number of patients are employed, the approach presented here is promising for computer-assisted diagnosis.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".