Digitalization in Dental problem diagnosis, Prediction and Analysis: A Machine Learning Perspective of Periodontitis
Lakshmi T.K1, Dheeba. J2

1Lakshmi T.K, Research Scholar, SCOPE,Vellore institute of Technology, Vellore, Tamil Nadu, India.
2Dheeba J*, Associate Professor, SCOPE, Vellore institute of Technology, Vellore, Tamil Nadu, India.
Manuscript received on January 02, 2020. | Revised Manuscript received on January 15, 2020. | Manuscript published on January 30, 2020. | PP: 67-74 | Volume-8 Issue-5, January 2020. | Retrieval Number: E5672018520/2020©BEIESP | DOI: 10.35940/ijrte.E5672.018520

Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: Artificial Intelligence, Machine learning, deep learning and image processing is becoming popular in medical sciences. The present digitalized world is remodelling each facetadditionally impacting dentistry and medical field from patient record maintenance, data analysisto new diagnostic methods, novel interference waysand totally different treatment choices. Oral health contributes to various diseases and conditions like Endocarditis, Cardio vascular diseases, diabetes, osteoporosis, pregnancy and birth and many more. Bad breathe, tooth decay, periodontitis, oral abscess, tooth erosion, dentinal sensitivity and many more can be even trickier to detect in plain dental radiography. The most prevalent disease periodontitis is a gum disease when left untreated, leads to tooth loss and more hazardous complications. Early Prediction and Proper diagnosis in time will protect our health from the mentioned diseases which can be implemented by making use of emerging technologies to assist and support dentists in predictions and decision making. Hence focusing more on oral health, In the current paper, the most contributing risk factors and parameters like Pocket Depth, Black Triangles, Alveolar Bone Loss, Furcation, Periodontal Abscess, Smoking, Gingivitis, Clinical Attachment Loss, Mobility Etc. that progresses the disease were taken in to consideration and a Python code was implemented which can be used as a Decision making aid to check whether person suffers or likely to suffer in future or not suffering from the disease.In this paper, literature reviews on the various automated computerized methods used to detect and diagnose the disease were discussed and an attempt was made to clearly identify and describe both the clinical and radiological parameters that a dentist/Periodontist use as a metric to grade/assess the periodontitis. The present strategy can be enhanced as a tool and can be used as a decision making aid by dentists’ in the prediction of periodontitis and can also be used for demonstrating fresher’s or upcoming dentists the progress of gum disease, grading the severity of the disease and the associated risk factors considering clinical, radiological findings and adverse habits thereby improving overall time period taken for manual predictions.
Keywords: Fuzzy Systems, Periodontitis, Neural Networks, Caries, Artificial Intelligence, Machine Learning, Dental Image Analysis, Disease Prediction, Gingivitis, Gum Disease, Dental Decision Making, Bone Loss, Dental Radiograph, Tooth Problem, Automated Dental Diagnosis.
Scope of the Article: Machine Learning.