A machine learning-based platform to forecast the risk of oral cancer and other potentially malignant illnesses is the goal, according to a new study carried out by John Adeoye of the University of Hong Kong, SAR China.
Visual oral examination (VOE) was performed among 1467 participants of a community-based screening program by three calibrated dentists prospectively.
Each individual's status was defined as positive/negative for oral cancer/OPMDs and histologic confirmation of epithelial dysplasia (ED) and squamous cell carcinoma (SCC) was performed for positive status.
The follow-up status of those that screened negative was monitored via state-linked electronic health records. Information on demography, habitual, lifestyle and familial risk factors was obtained and expired carbon monoxide levels (in ppm) were assessed using a monitor.
Input features (n=40) and histologic diagnoses were used to populate 12 machine learning algorithms with 80:20 train-test splitting applied to the data randomly during development.
Recursive feature elimination with 10-fold cross-validation was used for feature selection while synthetic-minority-oversampling-technique with edited-nearest-neighbours was implemented for class imbalance correction.
Internal validation was conducted with the unused 20 per cent data with the comparison of outputs using McNemar's test used for optimal model selection Performance metrics included recall, specificity, and F1-score.
The study demonstrated that machine learning is a successful tool for predicting oral cancer risk and may be applied to identify 'at-risk populations' in opportunistic and organized screening. (ANI)