Machine Learning from Biomarker Signatures and Correlation to Systemic Health Conditions

Imaging fluorescent disease biomarkers in tissues and skin is a non-invasive method to screen for health conditions. We report an automated process that combines intraoral fluorescent porphyrin biomarker imaging, clinical examinations, and machine learning for correlation of systemic health conditions with periodontal disease. 1,215 intraoral fluorescent images, from 284 consenting adults aged 18-90, were analyzed using a machine learning classifier that can segment periodontal inflammation. The classifier achieved an AUC of 0.677 with precision and recall of 0.271 and 0.429, respectively, indicating a learned association between disease signatures in collected images. Periodontal diseases were more prevalent among males (p=0.0012) and older subjects (p=0.0224) in the screened population. Physicians independently examined the collected images, assigning localized modified gingival indices (MGIs). MGIs and periodontal disease were then cross-correlated with responses to a medical history questionnaire, blood pressure and body mass index measurements, and optic nerve, tympanic membrane, neurological, and cardiac rhythm imaging examinations. Gingivitis and early periodontal disease were associated with subjects diagnosed with optic nerve abnormalities (p <0.0001) in their retinal scans. We also report significant co-occurrences of periodontal disease in subjects reporting swollen joints (p=0.0422) and a family history of eye disease (p=0.0337). These results indicate cross-correlation of poor periodontal health with systemic health outcomes and stress the importance of oral health screenings at the primary care level. Our screening process and analysis method, using images and machine learning, can be generalized for automated diagnoses and systemic health screenings for other diseases.

Why is this work important?

Standard practices like visual assessment and diagnosis of oral diseases using bleeding with a probe do not account for patient-to-patient variation or identify disease progression risk. This study uses a machine learning model to segment oral porphyrin biomarker levels from intraoral photographs and find correlations with and prognoses of systemic health conditions.

What has been done before?

Current methods to diagnose oral diseases include visual inspection by doctors and probing the gums. Positive correlations have been found between oral health and heart diseases, diabetes, tobacco use, and smoking, but all depend on visual examination by doctors.

What are our contributions?

We report a novel process for automated machine learning oral health examinations using images of fluorescent biomarkers and cross-correlations between oral and systemic health. We collect a novel dataset for the study and find correlations between oral health and systemic conditions like swollen joints, optical nerve abnormalities in retinal scans, and a family history of eye disease. Our approach can be generalized for predicting systemic health by analyzing other biomarker images.

What are the next steps?

We are actively expanding the work to a larger population to discover novel cross-correlations between other biomarkers and systemic health outcomes.

Related projects

  1. Technology-Enabled Mobile Phone Screenings Augment Routine Primary Care
  2. Machine Learning and Automated Segmentation of Oral Diseases using Biomarker Images

G. Yauney, A. Rana, L. C. Wong, P. Javia, A. Muftu and P. Shah, "Automated Process Incorporating Machine Learning Segmentation and Correlation of Oral Diseases with Systemic Health," 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Berlin, Germany, 2019, pp. 3387-3393, doi: 10.1109/EMBC.2019.8857965.

Past Member
Person People
Pratik Shah
Principal Research Scientist