The application of artificial intelligence algorithms for testing the correlation between the state of oral health and adolescent behavior concerning oral health

• Main Authors: Gajić Milica, Lalić Maja, Kalevski Katarina, Lazić Emira, Pavlović Maja, Ivanović Mirjana, Milić Jasmina, Matijević Dušanka, Vojinović Jovan
• Format: Article
• Language: English
• Published: Military Health Department, Ministry of Defance, Serbia 2021-01-01
• Series: Vojnosanitetski Pregled
• Subjects: mouth; health; intelligence, artificial; adolescence; algorithms
• Online Access: http://www.doiserbia.nb.rs/img/doi/0042-8450/2021/0042-84502000003G.pdf

Background/Aim. A period of adolescence is characterized by turbulent emotional, physical and physiological changes. There are numerous risk factors that may endanger the oral health of adolescents as the influence of parents reduces, while the influence of the environment and peers increases. Therefore, the main aim of this study was to determine the behavior of adolescents concerning oral health, using a new statistical method – artificial intelligence algorithms. Methods. In the first part of the survey, data on the behavior of adolescents related to oral health were collected. Hiroshima University Dental Behavioral Inventory (HU DBI) questionnaire was used, and additionally expanded with three questions. The second part of the study included clinical examination. The research was conducted at the Faculty of Dentistry in Pančevo, Serbia. The first and second grade high school students were selected for the observation unit. The total sample consisted of 374 students (128 males and 246 females). We applied a special programming language called Python for parsing data, creating a database in digital form, processing data by standard statistical methods and through the Singular Value Decomposition (SVD) method. Results. The artificial intelligence algorithms clustered the respondents into two groups, based on their responses from the HU DBI questionnaire. Thus, the quality of the method and the need for analysis of this type in dental studies are demonstrated and proven. Conclusion. Based on the results obtained through artificial intelligence algorithms, we could conclude that respondents should rather be clustered into characteristic groups and analyzed than divided and observed according to sex, as it is the intuitive division.