4.0 Article

Machine learning based model for detecting depression during Covid-19 crisis

Journal

SCIENTIFIC AFRICAN
Volume 20, Issue -, Pages -

Publisher

ELSEVIER
DOI: 10.1016/j.sciaf.2023.e01716

Keywords

Covid-19; Machine Learning; Depression; Artificial Intelligence

Ask authors/readers for more resources

Covid-19 has negatively impacted people worldwide in various ways, including health, employment, mental health, education, social isolation, economic inequality, and access to healthcare. Depression has emerged as a common illness that can lead to early death and other health conditions. Early detection and intervention are crucial in preventing the severity of depression and its associated risks. A survey using the Hamilton tool and input from psychiatrists was conducted, and machine learning techniques such as Decision Tree, KNN, and Naive Bayes were employed for analysis. The study concludes that KNN yielded better results in terms of accuracy, while decision tree performed better in detecting depression promptly. The suggestion is made to replace conventional methods of detecting depression with a machine learning-based model that involves asking people encouraging questions and obtaining regular feedback.
Covid-19 has impacted negatively on people all over the world. Some of the ways that it has affected people include such as Health, Employment, Mental Health, Education, Social isolation, Economic Inequality and Access to healthcare and essential services. Apart from physical symptoms, it has caused considerable damage to mental health of individuals. Among all, depression is identified as one of the common illnesses which leads to early death. People suffering from depression are at a higher risk of developing other health conditions, such as heart disease and stroke, and are also at a higher risk of suicide. The importance of early detection and intervention of depression cannot be overstated. Iden-tifying and treating depression early can prevent the illness from becoming more severe and can also prevent the development of other health conditions. Early detection can also prevent suicide, which is a leading cause of death among people with depression. Millions of people have affected from this disease. To proceed with the study of depres-sion detection among individuals we have conducted a survey with 21 questions based on Hamilton tool and advise of psychiatrist. With the use of Python's scientific programming principles and machine learning methods like Decision Tree, KNN, and Naive Bayes, survey results were analysed. Further a comparison of these techniques is done. Study concludes that KNN has given better results than other techniques based on the accuracy and de-cision tree has given better results in the terms of latency to detect the depression of a person. At the conclusion, a machine learning-based model is suggested to replace the con-ventional method of detecting sadness by asking people encouraging questions and getting regular feedback from them.& COPY; 2023 The Author(s). Published by Elsevier B.V. on behalf of African Institute of Mathematical Sciences / Next Einstein Initiative. This is an open access article under the CC BY-NC-ND license ( http://creativecommons.org/licenses/by-nc-nd/4.0/ )

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.0
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available