Biomedical subjects

R Sillén

Publications and source records attributed to R Sillén.

4 recordsLinked to original sources

PubMed1999

Machine learning methods applied on dental fear and behavior management problems in children.

The etiologies of dental fear and dental behavior management problems in children were investigated in a database of information on 2,257 Swedish children 4-6 and 9-11 years old. The analyses were performed using computerized inductive techniques within the field of artificial intelligence. The database held information regarding dental fear levels and behavior management problems, which were defined as outcomes, i.e. dependent variables. The attributes, i.e. independent variables, included data on dental health and dental treatments, information about parental dental fear, general anxiety, socioeconomic variables, etc. The data contained both numerical and discrete variables. The analyses were performed using an inductive analysis program (XpertRule Analyser, Attar Software Ltd, Lancashire, UK) that presents the results in a hierarchic diagram called a knowledge tree. The importance of the different attributes is represented by their position in this diagram. The results show that inductive methods are well suited for analyzing multifactorial and complex relationships in large data sets, and are thus a useful complement to multivariate statistical techniques. The knowledge trees for the two outcomes, dental fear and behavior management problems, were very different from each other, suggesting that the two phenomena are not equivalent. Dental fear was found to be more related to non-dental variables, whereas dental behavior management problems seemed connected to dental variables.

Artificial Intelligence↗

PubMed1998

Inductive analysis methods applied on questionnaires.

The am of this study was to evaluate subjective aspects from questionnaires dealing with dental trauma by applying different computerized inductive techniques within the field of artificial intelligence to questionnaires consisting of descriptive variables and of questions reflecting functional, personal, and social effects of patients' oral situation following dental trauma. As the methodology used is new to many readers in odontologic sciences, a detailed description of both the processes and the terminology is given. Utilizing a neural network as a first step in an analysis of data showed if relations existed in the training set, but the network could not make the relations explicit, so other methods, inductive methods, had to be applied. Inductive methods have the potential constructing rules from a set of examples. The rules combined with domain knowledge can reveal relations between the variables. It can be concluded that the usage of methods based on artificial intelligence can greatly improve explanatory value and make knowledge in databases explicit.

Algorithms↗

PubMed1998

Differences in co-variation of inorganic elements in the bulk and surface of human deciduous enamel: an induction analysis study.

This paper demonstrates a method for determination of co-variation between some inorganic elements in the bulk and surface areas of human tooth enamel. The technique is based on a computerised induction analysis of data obtained by secondary ion mass spectrometry (SIMS). When comparing the present data with an earlier study from our laboratory, it became evident that with only a moderate increase in the amount of data for the induction analysis, the results increased very considerably in reliability and precision. The patterns of co-variation between different elements differed between the bulk- and surface enamel. Only Mg expressed a similar pattern. In the bulk enamel the elements Na and P expressed a high degree of co-variation. Similarly, Mg and C expressed a high degree of co-variation. Mg was an element often found to co-vary with bulk enamel elements. In the enamel surface, F and Cl co-varied. In addition, Cl was an element often found to co-vary with other enamel surface elements.

Carbon↗

PubMed1996

A computerized induction analysis of possible co-variations among different elements in human tooth enamel.

In recent decades software tools in the area of artificial intelligence have rapidly developed for use in personal computers. Interactive rule induction utilizing mathematical algorithms has become a powerful tool in data analysis and in making rules and patterns explicit. Data from a Secondary Ion Mass Spectrometry (SIMS) elemental analysis of human dental enamel were used to elucidate co-variations between certain elements. A co-variation analysis was performed employing a computerized induction analysis program, as well as a neural network program. Both analyses, confirming each other, revealed co-variations between certain elements in dental enamel in addition to exclusion of data of no importance for chosen outcomes. The results are presented in hierarchic diagrams, in which the importance for every specific element is given by its position and level in the diagram (decision tree). From the results it became evident that elements such as chlorine and sodium expressed a high co-variation level. Similarly fluorine and potassium co-varied, as well as magnesium and the trace element strontium. It was demonstrated that data from an elemental analysis could be processed by an induction analysis to reveal co-variations between certain elements in tooth enamel. The biological significance of these data is not fully understood, and further analyses in the field are needed.

Algorithms↗