Beyond traditional methods-artificial intelligence in detection of oral cancer using smartphone-based oral photographs: a systematic review
Bibliographic record
Abstract
Oral cancer is a significant global health concern that affects people of various age groups worldwide. According to Globo Can, reports from 2022 show that approximately 377,713 new cases and 177,757 deaths are reported each year worldwide. Smartphones and Artificial intelligence (AI) are increasing in healthcare for diagnosis and treatment planning. This systematic review aims to appraise the existing evidence on the effectiveness of various artificial intelligence algorithms in the detection of oral cancer based on smartphone-based oral photographs from previously published articles. A systematic electronic search was carried out through various databases that emphasize current studies on the detection or diagnosis of oral cancer using different artificial intelligence algorithms. A modified Newcastle Ottawa scale was used to evaluate the quality of the included research and the PROBAST (Prediction model Risk of Bias Assessment tool) was used to assess the risk of bias. Among 13 articles, 8 show good quality and 5 fair qualities, mostly at low bias risk. Machine learning (support vector machines) sensitivity and specificity range from 89% to 92% and 75% to 82%; deep learning (MobileNet v2, ResNet) ranges from 85.12% to 90.23% and 87.64% to 90%. The diagnostic effectiveness of artificial intelligence models differs among machine learning and deep learning techniques. According to these results, machine learning has demonstrated encouraging outcomes in identifying oral cancer. The findings demonstrate the effectiveness of smartphone photographic images in detecting oral cancer.
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 | 0.009 | 0.054 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.007 | 0.008 |
| Bibliometrics | 0.008 | 0.007 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".