Bayesian Networks and Managing Psychological Mental Disorders

Primary supervisor

Abraham Oshni Alvandi

A lot of decision support systems have been developed to predict or suggest a diagnosis about the health conditions of patients with the aim to assist clinicians in their decisional process. One of the techniques that is proved to present an efficient tool for medical healthcare decision making is Bayesian networks (BNs). BNs are recognized as efficient graphical models that can be used to explain the relationships between variables. BNs have significant capabilities for investigating biomedical data either to obtain relationships between biomedical risk factors or either for medical predictions. Within healthcare domain, there has been some cross disciplinary research that have attempted to employ BNs technique in predicting the presence of mood and psychosocial disorders. There are several studies, for instance, that have examined the causal relationships between symptoms and depression.

Student cohort

Double Semester

Aim/outline

The present honours/minor thesis project is proposed to:

  1. understand the current status of BNs developed and implemented for mental health studies and,
  2. create a probabilistic model using Bayesian network-based analysis of psychological patient data.

Data could be from existing clinical data sets or can be gathered from a specialized trial including surveys, apps or wearables.

In collaboration with mental health researchers, the potential student(s) should focus on developing and implementing a model for one particular mental disorder, as a case study.

It is hoped that the thesis will create a comprehensive understanding of BNs in psychological studies, and the potential student will be able to create an early BN-based notification system for individuals and provide helpful insights in selecting the optimal setting and intensity of mental care.

URLs/references

Some useful sources: 

Chancellor, S., & De Choudhury, M. (2020). Methods in predictive techniques for mental health status on social media: a critical review. NPJ digital medicine, 3(1), 1-11. 

Becker, D., van Breda, W., Funk, B., Hoogendoorn, M., Ruwaard, J., & Riper, H. (2018). Predictive modeling in e-mental health: A common language framework. Internet interventions, 12, 57-67.

Required knowledge

Knowledge of probability and Bayesian Networks 

Data Analysis

Familiarity or demonstrated interest in psychological research and related skills including quantitative and qualitative survey development.

 

#Digitalhealth #Decision #Bayesian #Mental_State #Psychology