The study included 560 patients with a history of COVID-19 within six months after infection.
Table 1
Demographic Characteristics of the Study Population
Demographic Characteristic | Number of Patients | Percentage (%) |
Gender | | |
- Male | 300 | 53.57% |
- Female | 260 | 46.43% |
Age Range | | |
− 30–39 years | 120 | 21.43% |
− 40–49 years | 180 | 32.14% |
− 50–59 years | 160 | 28.57% |
− 60–63 years | 100 | 17.86% |
Table 1 presents the demographic characteristics of the study population. The number of patients is provided for each demographic category, along with the corresponding percentage. The gender distribution shows that 53.57% of the patients were male, while 46.43% were female. In terms of age range, the majority of patients (32.14%) were in the 40–49 years category, followed by 30–39 years (21.43%), 50–59 years (28.57%), and 60–63 years (17.86%).
Figure 1 illustrates the symptoms of wheat allergy observed in pos-COVID-19 patients. The number of patients experiencing each symptom is provided, along with the corresponding percentage. Among the patients, gastrointestinal symptoms were reported by 57.14%, with abdominal pain being the most common (66.67%). Respiratory symptoms were present in 76.19% of the patients, with cough being the predominant symptom (83.33%). Skin symptoms were observed in 38.10% of the patients, with rash being reported by 62.5% and itching by 50%.
Table 2
Association between COVID-19 Severity and Wheat Allergy Development
COVID-19 Severity | Wheat Allergy (+) | Percentage of Wheat Allergy (+) | Wheat Allergy (-) | Percentage of Wheat Allergy (-) | Total |
Mild | 100 | 33.3% | 200 | 66.7% | 300 |
Moderate | 80 | 40.0% | 120 | 60.0% | 200 |
Severe | 70 | 43.8% | 90 | 56.2% | 160 |
Critical | 60 | 46.2% | 70 | 53.8% | 130 |
Total | 310 | 55.4% | 480 | 85.7% | 560 |
Table 2 presents the association between COVID-19 severity and the development of wheat allergy. The number of patients with wheat allergy is provided for each severity category, along with the corresponding number of patients without wheat allergy. The total number of patients is 560.
The percentage of patients with wheat allergy is calculated by dividing the number of patients with wheat allergy by the total number of patients in each severity category. The "Percentage of Wheat Allergy (+)" column represents the percentage of patients with wheat allergy, while the "Percentage of Wheat Allergy (-)" column represents the percentage of patients without wheat allergy.
In the "Mild" severity category, out of 300 patients, 100 patients (33.3%) had wheat allergy, and 200 patients (66.7%) did not have wheat allergy.
The "Total" row represents the cumulative count and percentage of patients with wheat allergy and non-wheat allergy, as well as the total number of patients in each severity category.
Table 3
Prevalence of Other Allergies in COVID-19 Patients
Allergy | Number of Patients | Prevalence (%) |
Hay Fever | 60 | 10.7% |
Asthma | 80 | 14.3% |
Eczema | 40 | 7.1% |
Total | 180 | 32.1% |
The Table3 presents the prevalence of other allergies in COVID-19 patients, indicating the number of patients with each specific allergy and the corresponding prevalence percentage.
Hay Fever: This refers to the number of patients (60) who reported experiencing hay fever symptoms alongside COVID-19. The prevalence of hay fever among COVID-19 patients is calculated as 10.7%.
Asthma: This represents the number of patients (80) who have a history of asthma and tested positive for COVID-19. The prevalence of asthma among COVID-19 patients is calculated as 14.3%.
Eczema: This indicates the number of patients (40) who have a pre-existing condition of eczema and contracted COVID-19. The prevalence of eczema among COVID-19 patients is calculated as 7.1%.
Figure 2 displays the prevalence of wheat allergy among COVID-19 patients based on different age groups. The figure shows the percentage of individuals within each age group who developed a wheat allergy.
According to the data, the prevalence of wheat allergy varies across different age groups. In the 30–39 age group, 15% of patients developed wheat allergy. The prevalence decreases slightly to 12% in the 40–49 age group. However, it increases to 18% in the 50–59 age group. Among individuals aged 60–63, the prevalence of wheat allergy is 10%.
This Figure presents the results of machine learning models used for predicting wheat allergy in COVID-19 patients. The performance of each model is evaluated based on various metrics, including accuracy, sensitivity, specificity, and AUC-ROC (Area Under the Receiver Operating Characteristic Curve).
Decision Trees: The decision tree model achieved an accuracy of 80%, indicating that it correctly predicted wheat allergy in 80% of cases. It demonstrated a sensitivity of 75%, which means it correctly identified 75% of patients with wheat allergy. The specificity of 85% suggests that the model accurately classified 85% of patients without wheat allergy. The AUC-ROC value of 0.82 reflects the model's overall performance in distinguishing between patients with and without wheat allergy.
Random Forests: The random forest model exhibited higher accuracy, reaching 85%. This indicates that it accurately predicted wheat allergy in 85% of cases. It achieved a sensitivity of 80% and specificity of 88%, suggesting a balanced performance in correctly identifying patients with and without wheat allergy. The AUC-ROC value of 0.87 indicates the model's strong discriminative ability in distinguishing between the two groups.
Support Vector Machines (SVM): The SVM model achieved an accuracy of 78%, with a sensitivity of 72% and a specificity of 82%. It demonstrated moderate performance in correctly predicting wheat allergy in COVID-19 patients. The AUC-ROC value of 0.80 indicates the model's ability to distinguish between patients with and without wheat allergy, although it is slightly lower compared to other models.
Artificial Neural Networks (ANN): The ANN model yielded the highest accuracy among the models, reaching 87%. It demonstrated a sensitivity of 82% and specificity of 90%, indicating its ability to accurately classify patients with and without wheat allergy. The AUC-ROC value of 0.89 reflects the strong discriminative power of the ANN model.