Basic Information Extracted from the Body Mass Index Dataset through Data Visualization Using Python.
Everyone is celebrating Taylor Swift’s August song, anyway.
Holla, people! There were moments when I wrote, erased, and rewrote, and finally found the courage to release this article. In my initial outline, I found myself unsure whether to label this as my data science project or simply a piece of health information. It delves into topics like Body Mass Index (BMI), fat and muscle composition, and their impacts on later life.
Initially, I aimed for simplicity in discussing a subject I am well-versed in. Afterward, I visualized and explained the data’s implications to the audience.
Introduction to Body Mass Index
In simple terms, Body Mass Index is calculated as weight in kilograms divided by the square of height in meters. From my experience, BMI is commonly used to assess obesity and associated health risks.
Through the BMI formula, we categorize individuals into wasting, underweight, ideal, overweight, and obese.
However, some research suggests that BMI cannot precisely estimate the percentage of fat and muscle composition. Nonetheless, BMI is correlated with fat composition in the body and poses health risks in the future. Individuals with a higher BMI (BMI > 30 kg/m²) are strongly correlated with the incidence of degenerative diseases, such as diabetes mellitus, hypertension, and heart failure. To conduct further research, additional data on waist circumference and waist-hip ratio is required to identify fat percentage and predictors of non-communicable disease (NCD) risk.
Identifying the Data
In March 2023, I downloaded the dataset, performed data cleansing, conducted basic feature engineering, and finally, carried out data visualization to extract insights from the data itself.
A long time ago, we struggled to balance our diets to achieve an ideal weight due to a lack of proper nutrition. However, it’s surprising that, many years later, we have become progressively heavier each year, primarily due to changing lifestyles, the prevalence of junk food, stress-induced and emotional eating, socioeconomic factors, advertising, marketing, and more. Regrettably, this has led to a situation where we now experience dual forms of malnutrition — both wasting and extreme obesity simultaneously.
Nutrition education has become an essential approach that we need to extend to all levels of society. This will enable us to adopt balanced and mindful eating habits, addressing these concerning trends.
BMI & Gender
Initially, I assumed that women tend to be heavier than men, and this notion has even been acknowledged by the World Health Organization (WHO). This tendency is rooted in the fact that women naturally possess more body fat than men. Another contributing factor is the research indicating that estrogen in women’s bodies reduces their post-meal energy expenditure, leading to the accumulation of more fat. This fat storage is a natural process that has evolutionary benefits.
On the contrary, the prevailing assumption is that men are becoming heavier due to contemporary changes in lifestyle, particularly the adoption of sedentary habits.
Conclusion:
While there are both advantages and disadvantages to using BMI as a measure, it is important to note that BMI may not accurately estimate body fat composition, particularly in certain cases such as athletes. However, in a broader sense, BMI can still provide insights into your fat composition. As far as my understanding goes, it can serve as a basic screening tool to predict the likelihood of future non-communicable diseases.
Counseling and education have emerged as essential and effective solutions to enlighten society about potential future consequences. Often, people fail to comprehend that non-communicable diseases can lead to reduced productivity and economic losses due to illness in the later stages of life. Furthermore, non-communicable diseases have become the primary factor contributing to the decline in life expectancy within the country.
Regrettably, this research did not provide information about the economic status of the respondents, though I assumed there would be no significant differences based on economic status. However, certain news reports suggest that obesity is more prevalent among individuals with a lower economic level, possibly due to their carbohydrate-heavy daily consumption. Perhaps we can delve into this topic later?
Thank you
find my work at: https://github.com/nashabrina/Medium/blob/main/BMI_Dataset_Descriptive_Statistics.ipynb
