Predicting Generalized Anxiety Disorder among women using random forest approach

Autor: Neesha Jothi, Lee Ker Xin, Wahidah Husain, Nur'Aini Abdul Rashid
Rok vydání: 2016
Předmět:
Zdroj: 2016 3rd International Conference on Computer and Information Sciences (ICCOINS).
DOI: 10.1109/iccoins.2016.7783185
Popis: Mental health presents one of the greatest challenges to the current generation. Generalized Anxiety Disorder (GAD) is one of the many mental health problems. People with this disorder experience exaggerated worries and tensions about everyday events. It has been reported that about 5% of the population in developed countries is affected by GAD, with women twice as likely to be affected compared to men. Anxiety disorders are a growing occurrence in Malaysia, and this phenomenon has contributed to extensive mental health related data. This raw data is a valuable resource, but it is underutilized. It could potentially be transformed into useful knowledge via data mining technology. Data mining reveals significant insights due to its nature in identifying hidden patterns and relationships that can be used for predicting generalized anxiety disorder. For effective prediction, random forest approach is one of the classification data mining techniques which embeds good predictive characteristics. Therefore, this research adopts random forest approach to predict Generalized Anxiety Disorder among women, and the accuracy of the predictive result is reported. The generated prediction model is expected to provide an effective screening process for Generalized Anxiety Disorder among women in Malaysia.
Databáze: OpenAIRE