Predictive modelling in mental health : a data science approach

Saraee, M, Silva, HCE and Saraee, MH ORCID: https://orcid.org/0000-0002-3283-1912 2019, Predictive modelling in mental health : a data science approach , in: 2019 IEEE Conference on Sustainable Utilization and Development in Engineering and Technology (IEEE CSUDET), 7 to 9 November 2019, Penang, Malaysia.

[img]
Preview
PDF - Accepted Version
Download (293kB) | Preview
Official URL: http://csudet2019.com/

Abstract

In national and local level, understanding of factors associated with public health issues like mental health is paramount important. This framework evaluation aims to use the decision Tree technique to improve the degree of understanding of the mental health among various geographical areas by identifying behavioural factors associated with mental health. The uncovered relationships will be represented in the form of Association rules. The outcomes of this research will be beneficial to organisations that work in public health to improve mental health among the citizens. Also, this new proposed data science approach will help to improve the degree of understanding by identifying factors associated with mental health within the city or state level. Mental health professionals may use findings from this study to enhance awareness of mental health among citizens who living in identified high risk geographical areas. The study found that areas which have low excessive drinking percentage and high obesity and high smoking percentage has the highest frequent of mental distress. Also, these rules have shown high confidence threshold among females rather than males. Furthermore, the study suggests that the association between excessive drinking, obesity, physical inactivity, smoking and frequent mental distress among residents in USA is consistent enough to assume concretely a plausible and significant association. Also, this new proposed data science approach will help healthcare authorities to improve the degree of understanding of mental wellbeing within different geographical areas like cites or states.

Item Type: Conference or Workshop Item (Paper)
Schools: Schools > School of Computing, Science and Engineering > Salford Innovation Research Centre
Journal or Publication Title: 2019 IEEE Conference on Sustainable Utilization and Development in Engineering and Technology (IEEE CSUDET)
Publisher: IEEE
Depositing User: Prof. Mo Saraee
Date Deposited: 25 Nov 2019 09:36
Last Modified: 25 Nov 2019 15:32
URI: http://usir.salford.ac.uk/id/eprint/53163

Actions (login required)

Edit record (repository staff only) Edit record (repository staff only)

Downloads

Downloads per month over past year