BAIS 462 Final Project

Question:

The question I want to answer is how celiac disease affects males and females differently. I want to understand this data because I have celiac disease and know many females with the disease but do not know any males with the disease so I want to understand the experience and symptoms both perspectives face.

Data Dictionary:

Age: What age the person in the dataset was during the study

Gender: The gender of the person in the study

Diabetes: Whether or not the person has any kind of diabetes (Yes or No)

Diabetes Type: What kind of diabetes the person has (Type 1, Type 2, or none)

Diarrhoea: What kind of diarrhea the person experienced prior to diagnosis

(Ex: watery, fatty, or inflammatory)

Abdominal: If the person experienced abdominal symptoms or not (Yes or No)

Short_Stature: What kind of stature the person has (PSS, DSS, or variant)(add)

Sticky_Stool: If the person was having sticky stool symptom (Yes or No)

Weight_loss: If the person experienced weight loss as a symptom (Yes or No)

IgA: Stands for immunoglobulin A which is used in blood tests that test for

celiac disease. Likely those with celiac disease will be deficient in this, a

normal level in a non-celiac patient is between 80 – 350 mg/dL

IgG: This stands for Tissue Transglutaminase Antibody, which is an antibody tested to detect Celiac Sprue disease which is a skin condition associated with the disease.

IgM: This is Symptomatic Secondary Selective, it is rare in people with celiac disease but sometimes found in male celiac patients prior to diagnosis.

Marsh: The stages of damage to the small intestine, 0= no damage to 3c= the most damage.

cd_type: This variable refers to the four types of celiac disease you can have. Silent= No symptoms present, Typical= Abdominal symptoms present, Atypical= No abdominal symptoms present, other symptoms such as tooth decay, Latent= testing positive for celiac on blood test but no intestinal damage. None= No celiac disease present.

Disease_Diagnose: Yes or no variable about whether or not a person is diagnosed with celiac disease.

Relationship between Gender and Weightloss

Interpretation: Weightloss is seen slightly more in female then in males but overall is generally a symptom in both genders.

Relationship of IGA in Males vs. Females

Interpretation: I wanted to tested this level to test if it is true that this symptom is usually seen in Males. Typically male celiac patients see a deficiency in their igM levels. This seems to hold true in this graph as the average igM level median is lower in males than females as well as the first and third quartiles. However, the minimum of the igM levels is lower in females, but the maximum in males is lower than the females.

Visualization of how different types of celiac disease present different symptoms in males and females

Interpretation: Overall a female’s celiac disease is often silent meaning they experience no symptoms, which can lead to health complications later on due to them never finding out or they have latent celiac disease meaning that blood tests indicate that the person has celiac disease but when their intestines are examined there is no damage to the villi in the small intestine. Men tend to have atypical celiac disease meaning they experience symptoms that would not be expected to be caused by celiac disease such as tooth decay rather than abdominal symptoms. They also experience typical celiac disease more than females meaning they do experience these abdominal symptoms more than women.

Table of weightloss and stool symptom in males vs. women

`summarise()` has grouped output by 'Gender', 'Weight_loss'. You can override
using the `.groups` argument.

# A tibble: 12 × 4
# Groups:   Gender, Weight_loss [4]
   Gender Weight_loss Short_Stature count
   <chr>  <chr>       <chr>         <int>
 1 Female no          DSS              34
 2 Female no          PSS             104
 3 Female no          Variant          93
 4 Female yes         DSS              55
 5 Female yes         PSS             337
 6 Female yes         Variant         306
 7 Male   no          DSS              33
 8 Male   no          PSS             184
 9 Male   no          Variant          18
10 Male   yes         DSS              66
11 Male   yes         PSS             277
12 Male   yes         Variant         336

Interpretation: This shows that the most common symptom combination of stature

and weightloss for females is they did loss weight and that their stature is

PSS meaning Psychosocial short stature which is when someone experiences short

stature or growth failure/delayed puberty. The most common

symptoms/characteristics for males is that thet experienced weight loss and

they have variant stature meaning that their stature varies. (explain better)

Marsh Type by Gender

Interpretation:

Men are more likely to experience no damage to their small intestines or the highest level of damage to small intestines. Females are often in Marsh type 1 in diagnosis meaning their IELs are increased but the villous atrophy has not yet grown on their small intestines indicating still a low level of damage to the small intestine.

Word Cloud

Above is a word cloud that shows words that were used more than twenty times in this book review of a well-rated book about Celiac Disease on Amazon called Celiac Disease: A Hidden Epidemic. I wanted to see to use this to see if the most common words were negative or how people felt about this book. This word cloud that many of the words relate to this book being informative about Celiac Disease and gluten free diets. Some of the words indicate that people may have shared personal stories in their reviews since word wife appears.

Celiac Reviews Positive/Negative Words

Interpretation: This graph shows the positive and negative scoring of words if they were used more than ten times in the reviews. Free in most cases has a positive meaning to it but in this instance it is likely people were saying that they are “gluten free” so it is irrelevant to this analysis. Sensitive is also irrelevant because many people also expressed that they were “gluten sensitive”. Helpful, healthy, excellent, and easy are all actually positive sentiments for this book review. It is likely that people found this book as helpful to understanding Celiac Disease and how they can remain healthy with it. Many of the negative sentiment words likely do not reflect the actual book but possibly what they are experiencing with Celiac Disease. In the analysis and graphs above we learned about the symptoms that people with this disease experience, many of them are painful or involve weight gain or weight loss which is likely why pain, symptoms, symptom, and fat are common words used in these reviews. Overall the negative sentiment aligns with the previous analysis.

Conclusion:

I have enjoyed exploring this topic and have learned that Celiac Disease can present itself very differently in males vs females. With so many different types of Celiac Disease and Marsh Types, it can be difficult to get a proper diagnosis. As more information like this is explored and studied less people will go undiagnosed, leading to earlier identification and management of Celiac Disease.