A Bayesian Hidden Markov Model for Predicting Depression and Evaluating Medical Interventions
Charles Wambugu Mwangi *
Department of Mathematics and Actuarial Science, Kabarak University, Nakuru, Kenya.
Kennedy Nyongesa
Department of Mathematics, Masinde Muliro University of Science and Technology, Kakamega, Kenya.
Evelyne Akoth Odero
Department of Mathematics, Masinde Muliro University of Science and Technology, Kakamega, Kenya.
*Author to whom correspondence should be addressed.
Abstract
Depression has been the largest mental health problem affecting the public health. Early detection of people with depression is crucial for effective mitigation and treatment. The key to this can only be achieved when clear symptoms of depression are used to detect depression conditions in patients. Despite this problem, the treatment of depression among policemen is usually faced with early diagnosis challenges. This study is a predictive model of depression using the symptoms exhibited by the patient. The study also incorporates the medical intervention for depression to investigate its effect on transitional probabilities. Early recognizable proof of anxiety, guilt, retardation, insomnia, suicidal, and fatigue would be a significant step towards diagnosis and medical intervention to police men and women suffering from depression. In the latest development in the medical field, medical procedures have advanced in the need to create models that can predict mental depression with immediate medical intervention to care for the patients. This study used a treatment model to investigate the effect of medical intervention among depressed police officers. From the results of the study, it was observed that the medical intervention reduced the probabilities of depression status.
Keywords: Hidden Markov, medical intervention, treatment, parameter, naive error