RESUMEN
The COVID-19 pandemic has worsened the psychological and social stress levels of university students due to physical illness, enhanced dependence on mobile devices and internet, a lack of social activities, and home confinement. Therefore, early stress detection is crucial for their successful academic performance and mental well-being. The advent of machine learning (ML)-based prediction models can have a crucial impact in predicting stress at its early stages and taking necessary steps for the well-being of individuals. This study aims to develop a reliable machine learning-based prediction model for perceived stress prediction and validate the model using real-world data collected through an online survey among 444 university students from different ethnicity. The machine learning models were built using supervised machine learning algorithms. Principal Component Analysis (PCA) and the chi-squared test were employed as feature reduction techniques. Moreover, Grid Search Cross-Validation (GSCV) and Genetic Algorithm (GA) were employed for hyperparameter optimization (HPO). According to the findings, around 11.26% of individuals were identified with high levels of social stress. In comparison, approximately 24.10% of people were found to be suffering from extremely high psychological stress, which is quite alarming for students' mental health. Furthermore, the prediction results of the ML models demonstrated the most remarkable accuracy (80.5%), precision (1.000), F1 score (0.890), and recall value (0.826). The Multilayer Perceptron model was shown to have the maximum accuracy when combined with PCA as a feature reduction approach and GSCV for HPO. The convenience sampling technique used in this study only considers self-reported data, which may have biased results and lack generalizability. Future research should consider a large sample of data and focus on tracking long-term impacts with coping strategies and interventions. The results of this study can be used to develop strategies to mitigate adverse effects of the overuse of mobile devices and promote student well-being during pandemics and other stressful situations.
RESUMEN
Background: COVID-19 has affected many people globally, including in Bangladesh. Due to a lack of preparedness and resources, Bangladesh has experienced a catastrophic health crisis, and the devastation caused by this deadly virus has not yet been halted. Hence, precise and rapid diagnostics and infection tracing are essential for managing the condition and limiting its spread. The conventional screening procedure, such as reverse transcription polymerase chain reaction (RT-PCR), is not available in most rural areas and is time-consuming. Therefore, a data-driven intelligent surveillance system can be advantageous for rapid COVID-19 screening and risk estimation. Objectives: This study describes the design, development, implementation, and characteristics of a nationwide web-based surveillance system for educating, screening, and tracking COVID-19 at the community level in Bangladesh. Methods: The system consists of a mobile phone application and a cloud server. The data is collected by community health professionals via home visits or telephone calls and analyzed using rule-based artificial intelligence (AI). Depending on the results of the screening procedure, a further decision is made regarding the patient. This digital surveillance system in Bangladesh provides a platform to support government and non-government organizations, including health workers and healthcare facilities, in identifying patients at risk of COVID-19. It refers people to the nearest government healthcare facility, collecting and testing samples, tracking and tracing positive cases, following up with patients, and documenting patient outcomes. Results: This study began in April 2020, and the results are provided in this paper till December 2022. The system has successfully completed 1,980,323 screenings. Our rule-based AI model categorized them into five separate risk groups based on the acquired patient information. According to the data, around 51% of the overall screened populations are safe, 35% are low risk, 9% are high risk, 4% are mid risk, and the remaining 1% is very high risk. The dashboard integrates all collected data from around the nation onto a single platform. Conclusion: This screening can help the symptomatic patient take immediate action, such as isolation or hospitalization, depending on the severity. This surveillance system can also be utilized for risk mapping, planning, and allocating health resources to more vulnerable areas to reduce the virus's severity.
RESUMEN
Bone marrow transplant (BMT) is an effective surgical treatment for bone marrow-related disorders. However, several associated risk factors can impair long-term survival after BMT. Machine learning (ML) technologies have been proven useful in survival prediction of BMT receivers along with the influences that limit their resilience. In this study, an efficient classification model predicting the survival of children undergoing BMT is presented using a public dataset. Several supervised ML methods were investigated in this regard with an 80-20 train-test split ratio. To ensure prediction with minimal time and resources, only the top 11 out of the 59 dataset features were considered using Chi-square feature selection method. Furthermore, hyperparameter optimization (HPO) using the grid search cross-validation (GSCV) technique was adopted to increase the accuracy of prediction. Four experiments were conducted utilizing a combination of default and optimized hyperparameters on the original and reduced datasets. Our investigation revealed that the top 11 features of HPO had the same prediction accuracy (94.73%) as the entire dataset with default parameters, however, requiring minimal time and resources. Hence, the proposed approach may aid in the development of a computer-aided diagnostic system with satisfactory accuracy and minimal computation time by utilizing medical data records.