A large percentage of medical students undergo heavy amounts of pressure and stress casued mt a multitude of factors such as difficult coursework, working long hours, and exposure to patients with high risk health conditions. As heavily researched by the American Health Organization, many medical students are at risk for symptoms of depression. For instance, the odds for a first year medical student developing depression by their fourth year increased by 50%.
By analyzing the how being a medical student causes experiences of high levels of depression or burnout, we can gain a better understanding of how different demographic groups are being affected by the field. By isloating a few variables ( for example - age, sex, or health status), we can potentially analyze which groups are experiencing the most amount of burnout or depression.
If successful, this work may shed insight about different types of psychological profiles of medical students. It can also help medical programs create more tailored mental health support resources that are aimed at targeted groups. Additionally, understanding the unique challenges faced by different demographic groups can improve communication between medical students, faculty, and administrators.
We will use a Kaggle Dataset of Medical Students Mental Health to observe the following features for each student:
import pandas as pd
data = pd.read_csv("medical.csv")
data.head(10)
| id | age | year | sex | glang | part | job | stud_h | health | psyt | jspe | qcae_cog | qcae_aff | amsp | erec_mean | cesd | stai_t | mbi_ex | mbi_cy | mbi_ea | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 2 | 18 | 1 | 1 | 120 | 1 | 0 | 56 | 3 | 0 | 88 | 62 | 27 | 17 | 0.738095 | 34 | 61 | 17 | 13 | 20 |
| 1 | 4 | 26 | 4 | 1 | 1 | 1 | 0 | 20 | 4 | 0 | 109 | 55 | 37 | 22 | 0.690476 | 7 | 33 | 14 | 11 | 26 |
| 2 | 9 | 21 | 3 | 2 | 1 | 0 | 0 | 36 | 3 | 0 | 106 | 64 | 39 | 17 | 0.690476 | 25 | 73 | 24 | 7 | 23 |
| 3 | 10 | 21 | 2 | 2 | 1 | 0 | 1 | 51 | 5 | 0 | 101 | 52 | 33 | 18 | 0.833333 | 17 | 48 | 16 | 10 | 21 |
| 4 | 13 | 21 | 3 | 1 | 1 | 1 | 0 | 22 | 4 | 0 | 102 | 58 | 28 | 21 | 0.690476 | 14 | 46 | 22 | 14 | 23 |
| 5 | 14 | 26 | 5 | 2 | 1 | 1 | 1 | 10 | 2 | 0 | 102 | 48 | 37 | 17 | 0.690476 | 14 | 56 | 18 | 15 | 18 |
| 6 | 17 | 23 | 5 | 2 | 1 | 1 | 0 | 15 | 3 | 0 | 117 | 58 | 38 | 23 | 0.714286 | 45 | 56 | 28 | 17 | 16 |
| 7 | 21 | 23 | 4 | 1 | 1 | 1 | 1 | 8 | 4 | 0 | 118 | 65 | 40 | 32 | 0.880952 | 6 | 36 | 11 | 10 | 27 |
| 8 | 23 | 23 | 4 | 2 | 1 | 1 | 1 | 20 | 2 | 0 | 118 | 69 | 46 | 23 | 0.666667 | 43 | 43 | 26 | 21 | 22 |
| 9 | 24 | 22 | 2 | 2 | 1 | 1 | 0 | 20 | 5 | 0 | 108 | 56 | 36 | 22 | 0.690476 | 11 | 43 | 18 | 6 | 23 |
The scope of this analysis is limited as the data gathered took place in Switzerland. The results that are the conducted from this analysis may not apply to medical students everywhere as the participants in the study are only from one geographic region.
By isloating a few variables, we can study the relationship between the demographic variable and the level of depression a student typically experiences. Variables to measure likiliness of depression can be psyt, mbi_ex, and mbi_cy. A regression can be conducted to analyze the relationship of two or more variables through a line graph. This visualization will depict how each variable leads to an increase or decrease in likeliness of depression.