Acceptability of a head-mounted assistive mouse controller for people with upper limb disability: An empirical study using the technology acceptance model.

Due to limited motor capabilities, people with upper limb disabilities have trouble utilizing a typical mouse while operating a computer. Different wearable Assistive Mouse Controllers (AMCs) have been developed to overcome their challenges. However, these people may not be able to realize the importance, ease of use, and social approval of these AMCs due to their fear of new technology, lack of confidence, and lack of ingenuity. These may negatively affect their attitude and intention toward accepting AMCs for equitable human-computer interaction. This study presents the development of a sensor-based head-mounted AMC, followed by an empirical analysis of its acceptance using the Technology Acceptance Model (TAM) from the socioeconomic perspective of Bangladesh. In a similar vein, we examined the effects of three additional psychological constructs-technology anxiety, confidence, and innovation, on its acceptance along with the original components of the TAM. A total of 150 individuals with stroke-induced upper limb disability participated in an online survey, and their responses were analyzed using confirmatory factor analysis and structural equation modeling, following the general least square method. Analysis revealed, about 96.44% of the participants had positive attitude towards the AMC, and almost 88.56% of them had positive intentions to accept it. Furthermore, about 68.61% of them expressed signs of anxiety, 96.35% were confident, and 94.16% of them had an innovative mindset in terms of device usage. The findings imply that individuals with an innovative mentality are more capable of comprehending the practical implications of a new technology than those without one. It is also feasible to reduce technological anxiety and boost a user's confidence while using an AMC by combining an innovative mentality with straightforward device interaction techniques. Additionally, peer encouragement and motivation can significantly enhance their positive attitude towards accepting the AMC for facilitating their interaction with a computer.

Survival Prediction of Children Undergoing Hematopoietic Stem Cell Transplantation Using Different Machine Learning Classifiers by Performing Chi-Square Test and Hyperparameter Optimization: A Retrospective Analysis.

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.