Social media sites, such as Twitter, provide the means for users to share their stories, feelings, and health conditions during the disease course. Anemia, the most common type of blood disorder, is recognized as a major public health problem all over the world. Yet very few studies have explored the potential of recognizing anemia from online posts. This study proposed a novel mechanism for recognizing anemia based on the associations between disease symptoms and patients' emotions posted on the Twitter platform. We used k-means and Latent Dirichlet Allocation (LDA) algorithms to group similar tweets and to identify hidden disease topics. Both disease emotions and symptoms were mapped using the Apriori algorithm. The proposed approach was evaluated using a number of classifiers. A higher prediction accuracy of 98.96 % was achieved using Sequential Minimal Optimization (SMO). The results revealed that fear and sadness emotions are dominant among anemic patients. The proposed mechanism is the first of its kind to diagnose anemia using textual information posted on social media sites. It can advance the development of intelligent health monitoring systems and clinical decision-support systems.
The paper aims to provide an insight into the significance of having a simulation model to forecast the supply of registered nurses for health workforce planning policy using System Dynamics. A model is highly in demand to predict the workforce demand for nurses in the future, which it supports for complete development of a needs-based nurse workforce projection using Malaysia as a case study. The supply model consists of three sub-models to forecast the number of registered nurses for the next 15 years: training model, population model and Full Time Equivalent (FTE) model. In fact, the training model is for predicting the number of newly registered nurses after training is completed. Furthermore, the population model is for indicating the number of registered nurses in the nation and the FTE model is useful for counting the number of registered nurses with direct patient care. Each model is described in detail with the logical connection and mathematical governing equation for accurate forecasting. The supply model is validated using error analysis approach in terms of the root mean square percent error and the Theil inequality statistics, which is mportant for evaluating the simulation results. Moreover, the output of simulation results provides a useful insight for policy makers as a what-if analysis is conducted. Some recommendations are proposed in order to deal with the nursing deficit. It must be noted that the results from the simulation model will be used for the next stage of the Needs-Based Nurse Workforce projection project. The impact of this study is that it provides the ability for greater planning and policy making with better predictions.