The necessity and demand of machine learning in treatment and diagnostics in dentistry

Abstract

Aim: to justify the necessity of machine learning technology in treatment and diagnostics in dentistry.Material and methods: the research was taken using the method of anonymous questionnaire to estimate the demand and necessity of machine learning technology in diagnostics and treatment in dentistry on the basis of the E.V Borovsky Institute of Dentistry I.M Sechenov First Moscow State Medical University (Sechenov University). 100 participants from different dental specialities aged 20 to 54 took part in the questionnaire. Wilson score interval and Student’s T Critical Values were used for the statistical analysis of the Results.Results: during the study, it was found that the majority of dentists who participated in the questionnaire (54%) have challenges in diagnosing oral mucosal diseases. Herewith dentists with work experience more than 5 years diagnose this kind of disease more frequently than specialists with less work experience (p<0.05). Surgical dentists (46,6%) and prosthetic specialists (50%) diagnose this pathology most often. Clinicians attribute diagnostic challenges to the lack of experience (85%) and low occurrence of patients with this group of diseases. During treatment and diagnostics 84% of residents mentioned that they compare their patients’ clinical cases with clinical cases from the Internet and other resources, 78% of residents believe that machine learning will help to increase the efficiency of diagnosing oral mucosal diseases in clinical work. During the held research, it was found that 85% of participating dentists would definitely use digital programs with machine learning in their clinical work for treatment and diagnostics.Conclusions: the presence of problems in treatment and diagnostics of oral mucosal diseases was confirmed, and to solve it, the demand and the need to develop and implement digital systems based on artificial intelligence using machine learning technology were substantiated.