Abstract:
Depression is one of the most common mental disorders worldwide. Individual clinical interviews are typically the “gold standard” when diagnosing depressive disorders. Ho...Show MoreMetadata
Abstract:
Depression is one of the most common mental disorders worldwide. Individual clinical interviews are typically the “gold standard” when diagnosing depressive disorders. However, these approaches are based on subjective evaluation and have many limitations. In our study, the impact of metabolomics approach on the assessment of depression is evaluated. The data mining techniques classification by fuzzy decision trees were used. We selected three profiles of metabolites from the groups of acylcarnitines, phosphatidylcholines and sphingomyelins. From these groups, the most accurate metabolites were selected using fuzzy decision tree to classify depression state. Our results clearly show that there are many metabolites that are influenced by depression when comparing with control rats. The results were verified by means and p-values. The benefit of the work is in applying a fuzzy decision tree to classify metabolites, specific for depression disorders, which could be used in clinical practice in the future.
Date of Conference: 18-21 September 2019
Date Added to IEEE Xplore: 05 December 2019
ISBN Information: