Publication Date: 2021/04/19
Abstract: COVID-19 Lockdown causes different health problems in the society of Ethiopia. Among these problems mental health problem such as anxiety, depression, panic and fear are common. This research aimed to redesign a neural network model of an anxiety and depression based on Hospital Anxiety and Depression Score (HADS) measurement techniques. We collected 713 data from different individuals including students, working and non-working male and female age group from 16 to 55 using online survey. In order to online survey, we prepared 7 questions using HADS standard for anxiety and depression. Each of these questions has four answer scores from 0 to 3. We generate neural network model on the basis of participant response and HADS measurement technique in order to classify the level of Anxiety and Depression. The level of anxiety and depression can be normal, mild, moderate and severe. The model was tasted and its specificity was 0.997940975 for anxiety and 0.996577687 for depression. We achieved the sensitivity value for anxiety is 0.926666667 and for depression is 0.945205479. We compared the model accuracy manually using HADS technique. We found the Average Percentage Value (APV) 0.017379846 and 0.018365 for anxiety and depression respectively. This study can further designed to recommend some advices on what an individual may do or what kind of measurements they must do in each level of Anxiety and depression.
Keywords: Anxiety, Depression, COVID-19, Artificial Neural Network, Hospital Anxiety and Depression Scale.
DOI: No DOI Available
PDF: https://ijirst.demo4.arinfotech.co/assets/upload/files/IJISRT21MAR692.pdf
REFERENCES