A pilot study on parallel factor analysis as a diagnostic tool for oral cancer diagnosis: A statistical modeling approach
Bibliographic record
Abstract
Abstract Excitation‐emission matrix (EEM) has been extensively used as the comprehensive diagnostic tool to extract the biochemical fingerprint of the intrinsic fluorophores in a single scan window. However, there is a gap between the rigorous applications of the statistical tool with respect to discrimination of different stages of the disease which has been the subject for many years. Parallel factor analysis (PARAFAC) is one among the powerful statistical modeling approaches among others. In the present study, a total of 70 EEM matrices of normal, premalignant, and malignant oral tissues were given as a input, and seven intrinsic fluorophores were extracted as “components.” The extracted components were well correlated with respect to the appropriate excitation and emission spectral characteristics of the multiple intrinsic fluorophores such as tryptophan, flavin adenine dinucleotide (FAD), nicotinamide adenine dinucleotide (NADH), collagen‐1, porphyrin, tyrosine, and collagen. Subsequently, the student's t test and linear discriminant analysis (LDA) have been carried out with respect to the fluorescence intensity scores between normal vs. premalignant, normal vs. cancer, and premalignant vs. malignant groups. In normal vs. premalignant, all the seven fluorophores exhibit good statistical accuracy except porphyrin; normal vs. cancer exhibits higher statistical significance for tryptophan, NADH, and FAD than rest of the fluorophores, and premalignant vs. malignant shows proper classification in discriminating FAD, collagen‐1, and collagen. In summary, based on positive predictive value, the normal vs. premalignant exhibits 100% classification than the other two groups. Hence, the PARAFAC analysis could be the alternative and useful diagnostic tool in oral cancer 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 | 0.018 | 0.015 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".