The Applications of Imaging and Machine Learning Algorithm for Detecting Oral Cancer: A Systematic Review and Meta-Analysis
Bibliographic record
Abstract
Background: Recent advancements in imaging and machine learning, facilitated by Industry 4.0 technologies, including advanced aluminum technologies in medical device manufacturing, have shown promise for enhancing oral cancer detection.This systematic review and meta-analysis aimed to synthesize current evidence on the applications of these technologies for the detection and classification of oral cancer.Methods: We conducted a systematic literature search across PubMed, Embase, Scopus, Web of Science, Cochrane Library, IEEE Xplore, ACM Digital Library, and Google Scholar, selecting studies that applied imaging and machine learning algorithms to detect oral cancer.The QUADAS-AI tool was used to assess the risk of bias.Metaanalysis was performed to evaluate the differences in F-scores and accuracy between machine learning systems in distinguishing cancerous from non-cancerous cells.Results: The review included 9 studies that developed various models with high accuracy in detecting and classifying oral cancer, utilizing advanced optimization techniques and incorporating diverse datasets.The meta-analysis revealed a significant mean difference (MD) in F-scores of -3.29, with high heterogeneity across training/testing data ratios.Additionally, validation cohorts demonstrated higher accuracy than training cohorts by a pooled MD of -4.70, suggesting improved performance on unseen data despite high heterogeneity.Conclusion: The findings highlight the efficacy of machine learning algorithms in the detection of oral cancer and underscore the importance of robust model validation on independent datasets.The integration of advanced aluminum technologies in the development of imaging systems within the Industry 4.0 framework suggests a significant impact on the performance and accuracy of these detection methods.Future research should focus on standardizing methodologies to enhance comparability and generalizability of results.
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 | 0.020 | 0.041 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.016 | 0.033 |
| Bibliometrics | 0.006 | 0.007 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.003 | 0.002 |
| 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".