Machine Learning Platform Helps Predict Oral Cancer Risk

Machine learning is a successful tool for predicting oral cancer risk and may be applied to identify ‘at-risk populations’.

A machine learning-based platform helps predict oral cancer risk. The platform also identifies Oral Potentially Malignant Disorders (OPMDs).

Visual Oral Examination (VOE) was performed among 1,467 participants of a community-based screening program by three calibrated dentists prospectively.

Oral Cancer | Mouth Cancer - Types, Causes, Symptoms, Diagnosis, Treatment & Prevention
Oral cancer is a cancer that develops in any part of the mouth. It is more common in men over 40.

‘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.’

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.

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.

A Deep-Learning Method for Oral Cancer Diagnosis

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-neighbors was implemented for class imbalance correction.

Oral Cancer in India Mainly Caused by Tobacco, Say Experts
In India, the most common cancer is oral cancer caused by a smokeless form of tobacco. In India, out of total tobacco use, cigarettes contribute 5%.

Internal validation was conducted with the unused 20% data with the comparison of outputs using McNemar’s test used for optimal model selection Performance metrics included recall, specificity, and F1-score.

Source-Eurekalert

How to Treat Oral Cancer at the Early Stage?
New study findings have significant implications for developing new and potentially more effective therapies to treat oral cancer at an early stage.

Machine Learning Models to Help Identify Long COVID Patients
Machine learning (ML) models help clinicians distinguish characteristics of people with long-COVID and factors that may help identify such patients.