|
An Artificial Neural Network Prediction Model of Respiratory Illness Among Medical Students during Gross Anatomy |
|---|---|
| รหัสดีโอไอ | |
| Creator | 1. Arroon Ketsakorn 2. Saowanee Norkaew 3. Kanjana Changkaew 4. Chalermchai Chaikittiporn 5. Vanusaya Su-angkavatin 6. Pannathorn Thammabut 7. Ratchapong Chaiyadej |
| Title | An Artificial Neural Network Prediction Model of Respiratory Illness Among Medical Students during Gross Anatomy |
| Publisher | Thai Society of Higher Education Institutes on Environment |
| Publication Year | 2564 |
| Journal Title | EnvironmentAsia |
| Journal Vol. | 14 |
| Journal No. | 3 |
| Page no. | 91-101 |
| Keyword | Respiratory illness, Indoor air quality, Artificial neural network model, Gross anatomy dissection |
| URL Website | http://www.tshe.org/ea/index.html |
| Website title | EnvironmentAsia |
| ISSN | 1906-1714 |
| Abstract | Exposure to indoor air pollutants can cause adverse health outcomes. This study aimed to develop an Artificial Neural Network (ANN) model to predict respiratory illness among students during gross anatomy dissection classes. All participants were interviewed face-to-face using questionnaires. General information, gross anatomy laboratory room characteristics, and symptoms of respiratory illness during gross anatomy dissection were assessed. The environmental parameters related to indoor air quality, total fungi, and bacteria in a gross anatomy dissection room were measured. Pearson's correlation, spearman's rank correlation and regression analysis were used to analyse data. The findings revealed ten factors significantly associated with respiratory illness (P < 0.05). The six influencing variables including formaldehyde concentration (personal sampling), bacteria, relative humidity, fungi, time of gross anatomy dissection class, and formaldehyde concentration (area sampling) as tested using regression analysis. ANN model was then run to predict the respiratory illness from those six variables. Predictive accuracy was assessed by the Mean Absolute Deviation (MAD), Mean Absolute Percentage Error (MAPE), Mean Square Error (MSE), and Root Mean Square Error (RMSE) value. ANN model showed the least value of MAD, MAPE, MSE, and RMSE when comparing an error value of less than 10%. Therefore, the ANN model is accurate and valid for respiratory illness prediction in individuals in order to plan for solving problems according to the factors influencing the respiratory illness before starting a class. Further research is recommended to improve to model by large-sample-size research. |
