untitled4

July 9, 2024

[1]: import pandas as pd

from scipy.stats import chi2_contingency, ttest_ind
import numpy as np

# Data for the analysis

data = {
"age": [51, 39, 28, 60, 52, 48, 77, 55, 43, 25, 55, 55, 49, 48, 46, 56, 31,␣
↪50, 57, 35, 45, 23, 31, 53, 53, 44, 71, 48, 24, 43, 35, 22],

"sex": [0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0,␣

↪0, 1, 1, 0, 1, 0, 0, 0, 0, 0],

"BMI": [52.1, 44.5, 60, 38.2, 42.9, 35.8, 42.19, 49.3, 51.1, 46.2, 51.5, 46.
↪8, 38.1, 62, 46.7, 60, 50, 48, 46.2, 40, 41.5, 43.6, 51.1, 53.4, 46.6, 40,␣

↪35.7, 68, 36, 46.4, 46.5, 45.4],

"surgery": [1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 1, 0, 0, 1,␣

↪0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0],

"haemoglobin_status": [0, 1, 1, 0, 1, 1, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 0,␣

↪0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1],

"B12_status": [1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0,␣

↪0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 1, 1],

"Ionized_Ca_status": [1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1,␣

↪0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 0],

"Vit_D3_status": [1, 1, 0, 0, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1,␣

↪0, 0, 0, 1, 0, 1, 0, 1, 1, 1, 0, 1, 1]

# Convert to DataFrame
df = pd.DataFrame(data)

# Replace status values

statuses = ["haemoglobin_status", "B12_status", "Ionized_Ca_status",␣
↪"Vit_D3_status"]

for status in statuses:

df[status] = df[status].replace({1: 'deficient', 0: 'normal'})

# Helper function to create contingency tables with percentages

def create_contingency_table(variable, status):
contingency_table = pd.crosstab(variable, status)

1
 contingency_table_percentage = contingency_table.apply(lambda r: r /␣
↪len(variable) * 100, axis=1)
contingency_table_combined = contingency_table.astype(str) + " (" +␣
↪contingency_table_percentage.round(1).astype(str) + "%)"

return contingency_table_combined
# Helper function to print tables in CSV format
def print_csv_format(contingency_table, table_name):
print(f"\n{table_name}")
print(contingency_table.to_csv(index=True))
# Analyze each status
for status in statuses:
print(f"\n\nAnalysis for␣
↪{status}--------------------------------------------")

# Total and percentage of patients

total_deficient = df[df[status] == 'deficient'].shape[0]
total_normal = df[df[status] == 'normal'].shape[0]
percent_deficient = round((total_deficient / len(df)) * 100, 1)
percent_normal = round((total_normal / len(df)) * 100, 1)

# Calculate mean and SD for age

mean_age_normal = df[df[status] == 'normal']['age'].mean()
sd_age_normal = df[df[status] == 'normal']['age'].std()
mean_age_deficient = df[df[status] == 'deficient']['age'].mean()
sd_age_deficient = df[df[status] == 'deficient']['age'].std()
# Calculate mean and SD for BMI
mean_bmi_normal = df[df[status] == 'normal']['BMI'].mean()
sd_bmi_normal = df[df[status] == 'normal']['BMI'].std()
mean_bmi_deficient = df[df[status] == 'deficient']['BMI'].mean()
sd_bmi_deficient = df[df[status] == 'deficient']['BMI'].std()
# AGE
bins_age = [0, 30, 40, 50, 60, float('inf')]
df['Age Category'] = pd.cut(df['age'], bins=bins_age, labels=["<=30",␣
↪"31-40", "41-50", "51-60", "61+"])

contingency_table_age = create_contingency_table(df['Age Category'],␣

↪df[status])

chi2_stat_age, p_val_age, dof_age, ex_age = chi2_contingency(pd.

↪crosstab(df['Age Category'], df[status]))

# SEX
contingency_table_sex = create_contingency_table(df['sex'], df[status])
chi2_stat_sex, p_val_sex, dof_sex, ex_sex = chi2_contingency(pd.
↪crosstab(df['sex'], df[status]))

# BMI
bins_bmi = [0, 30, 40, 50, float('inf')]

2
 df['BMI Category'] = pd.cut(df['BMI'], bins=bins_bmi, labels=["<=30",␣
↪"31-40", "41-50", "51+"])
contingency_table_bmi = create_contingency_table(df['BMI Category'],␣
↪df[status])

chi2_stat_bmi, p_val_bmi, dof_bmi, ex_bmi = chi2_contingency(pd.

↪crosstab(df['BMI Category'], df[status]))

# SURGERY
contingency_table_surgery = create_contingency_table(df['surgery'],␣
↪df[status])

chi2_stat_surgery, p_val_surgery, dof_surgery, ex_surgery =␣

↪chi2_contingency(pd.crosstab(df['surgery'], df[status]))

# Display results
print(f"n (Deficient,Normal): ,n =␣
↪{total_deficient}({percent_deficient}%),n =␣

↪{total_normal}({percent_normal}%)")

print(f"Age (Deficient,Normal): ,{mean_age_deficient:.2f} ±␣

↪{sd_age_deficient:.2f},{mean_age_normal:.2f} ± {sd_age_normal:.2f}")

# Simulate the ages using the given mean and standard deviation
np.random.seed(0) # For reproducibility
ages_deficient = np.random.normal(mean_age_deficient, sd_age_deficient,␣
↪total_deficient)

ages_normal = np.random.normal(mean_age_normal, sd_age_normal, total_normal)

# Perform the t-test

t_stat, p_value = ttest_ind(ages_deficient, ages_normal, equal_var=False)

print(f"T-statistic: {t_stat.round(3)}")
print(f"P-value: ,{p_value.round(3)}")
print_csv_format(contingency_table_age, "Contingency Table for Age")
print(f"\nChi-square statistic: {chi2_stat_age.round(3)}")
print(f"P-value: ,{p_val_age.round(3)}")
print_csv_format(contingency_table_sex, "Contingency Table for Sex")
print(f"\nChi-square statistic: {chi2_stat_sex.round(3)}")
print(f"P-value: ,{p_val_sex.round(3)}")

print(f"\nBMI (Deficient,Normal): ,{mean_bmi_deficient:.2f} ±␣

↪{sd_bmi_deficient:.2f},{mean_bmi_normal:.2f} ± {sd_bmi_normal:.2f}")

# Simulate the ages using the given mean and standard deviation
np.random.seed(0) # For reproducibility
bmi_deficient = np.random.normal(mean_bmi_deficient, sd_bmi_deficient,␣
↪total_deficient)

3
 bmi_normal = np.random.normal(mean_bmi_normal, sd_bmi_normal, total_normal)

# Perform the t-test

t_stat, p_value = ttest_ind(bmi_deficient,bmi_normal, equal_var=False)

print(f"T-statistic: {t_stat.round(3)}")
print(f"P-value: ,{p_value.round(3)}")
print_csv_format(contingency_table_bmi, "Contingency Table for BMI")
print(f"\nChi-square statistic: {chi2_stat_bmi.round(3)}")
print(f"P-value: ,{p_val_bmi.round(3)}")
print_csv_format(contingency_table_surgery, "Contingency Table for Surgery")
print(f"\nChi-square statistic: {chi2_stat_surgery.round(3)}")
print(f"P-value: ,{p_val_surgery.round(3)}")

Analysis for haemoglobin_status--------------------------------------------

n (Deficient,Normal): ,n = 11(34.4%),n = 21(65.6%)
Age (Deficient,Normal): ,40.09 ± 10.79,48.14 ± 13.99
T-statistic: -1.045
P-value: ,0.305

Contingency Table for Age

Age Category,deficient,normal
<=30,3 (9.4%),2 (6.2%)
31-40,1 (3.1%),4 (12.5%)
41-50,6 (18.8%),4 (12.5%)
51-60,1 (3.1%),9 (28.1%)
61+,0 (0.0%),2 (6.2%)

Chi-square statistic: 8.506

P-value: ,0.075

Contingency Table for Sex

sex,deficient,normal
0,9 (28.1%),14 (43.8%)
1,2 (6.2%),7 (21.9%)

Chi-square statistic: 0.242

P-value: ,0.623

BMI (Deficient,Normal): ,46.95 ± 8.08,47.11 ± 7.77

T-statistic: 1.0
P-value: ,0.328

4
Contingency Table for BMI
BMI Category,deficient,normal
31-40,2 (6.2%),5 (15.6%)
41-50,6 (18.8%),10 (31.2%)
51+,3 (9.4%),6 (18.8%)

Chi-square statistic: 0.178

P-value: ,0.915

Contingency Table for Surgery

surgery,deficient,normal
0,9 (28.1%),12 (37.5%)
1,2 (6.2%),9 (28.1%)

Chi-square statistic: 1.008

P-value: ,0.315

Analysis for B12_status--------------------------------------------

n (Deficient,Normal): ,n = 9(28.1%),n = 23(71.9%)
Age (Deficient,Normal): ,35.78 ± 12.95,49.13 ± 11.78
T-statistic: -1.286
P-value: ,0.22

Contingency Table for Age

Age Category,deficient,normal
<=30,3 (9.4%),2 (6.2%)
31-40,3 (9.4%),2 (6.2%)
41-50,1 (3.1%),9 (28.1%)
51-60,2 (6.2%),8 (25.0%)
61+,0 (0.0%),2 (6.2%)

Chi-square statistic: 7.76

P-value: ,0.101

Contingency Table for Sex

sex,deficient,normal
0,7 (21.9%),16 (50.0%)
1,2 (6.2%),7 (21.9%)

Chi-square statistic: 0.001

P-value: ,0.978

BMI (Deficient,Normal): ,46.61 ± 4.83,47.23 ± 8.72

5
T-statistic: 0.204
P-value: ,0.84

Contingency Table for BMI

BMI Category,deficient,normal
31-40,1 (3.1%),6 (18.8%)
41-50,6 (18.8%),10 (31.2%)
51+,2 (6.2%),7 (21.9%)

Chi-square statistic: 1.514

P-value: ,0.469

Contingency Table for Surgery

surgery,deficient,normal
0,5 (15.6%),16 (50.0%)
1,4 (12.5%),7 (21.9%)

Chi-square statistic: 0.113

P-value: ,0.737

Analysis for Ionized_Ca_status--------------------------------------------

n (Deficient,Normal): ,n = 9(28.1%),n = 23(71.9%)
Age (Deficient,Normal): ,41.78 ± 12.54,46.78 ± 13.70
T-statistic: 0.116
P-value: ,0.909

Contingency Table for Age

Age Category,deficient,normal
<=30,2 (6.2%),3 (9.4%)
31-40,1 (3.1%),4 (12.5%)
41-50,3 (9.4%),7 (21.9%)
51-60,3 (9.4%),7 (21.9%)
61+,0 (0.0%),2 (6.2%)

Chi-square statistic: 1.329

P-value: ,0.856

Contingency Table for Sex

sex,deficient,normal
0,7 (21.9%),16 (50.0%)
1,2 (6.2%),7 (21.9%)

Chi-square statistic: 0.001

6
P-value: ,0.978

BMI (Deficient,Normal): ,47.17 ± 4.98,47.01 ± 8.69

T-statistic: 0.544
P-value: ,0.591

Contingency Table for BMI

BMI Category,deficient,normal
31-40,1 (3.1%),6 (18.8%)
41-50,5 (15.6%),11 (34.4%)
51+,3 (9.4%),6 (18.8%)

Chi-square statistic: 0.861

P-value: ,0.65

Contingency Table for Surgery

surgery,deficient,normal
0,6 (18.8%),15 (46.9%)
1,3 (9.4%),8 (25.0%)

Chi-square statistic: 0.0

P-value: ,1.0

Analysis for Vit_D3_status--------------------------------------------

n (Deficient,Normal): ,n = 21(65.6%),n = 11(34.4%)
Age (Deficient,Normal): ,44.43 ± 12.52,47.18 ± 15.36
T-statistic: -0.77
P-value: ,0.452

Contingency Table for Age

Age Category,deficient,normal
<=30,3 (9.4%),2 (6.2%)
31-40,4 (12.5%),1 (3.1%)
41-50,7 (21.9%),3 (9.4%)
51-60,6 (18.8%),4 (12.5%)
61+,1 (3.1%),1 (3.1%)

Chi-square statistic: 0.97

P-value: ,0.914

Contingency Table for Sex

sex,deficient,normal
0,14 (43.8%),9 (28.1%)
1,7 (21.9%),2 (6.2%)

7
Chi-square statistic: 0.242
P-value: ,0.623

BMI (Deficient,Normal): ,47.20 ± 7.86,46.78 ± 7.90

T-statistic: 0.046
P-value: ,0.964

Contingency Table for BMI

BMI Category,deficient,normal
31-40,4 (12.5%),3 (9.4%)
41-50,11 (34.4%),5 (15.6%)
51+,6 (18.8%),3 (9.4%)

Chi-square statistic: 0.297

P-value: ,0.862

Contingency Table for Surgery

surgery,deficient,normal
0,14 (43.8%),7 (21.9%)
1,7 (21.9%),4 (12.5%)

Chi-square statistic: 0.0

P-value: ,1.0