Guanjin Wang

Vaccine hesitancy and uptake have been important issues in controlling the current COVID-19 pandemic in many regions around the globe, but the increase in vaccination rates has been slow or even halted in some countries. Therefore, people who have hesitated in getting the vaccine need to be addressed. One driver influencing vaccination uptake is closing the knowledge gap among the public by equipping them with a deeper understanding of how a vaccine works inside our cells to activate the immune system and develop immunity. Viral immunology is highly conceptual and requires an appreciation of molecular biology in the cell. To give individuals an intuitive awareness of the operation of a mRNA-type virus vaccine for COVID-19, we designed and developed a Virtual Reality (VR) based serious game called ‘Cell Traveler’. Through this innovative VR serious game, the player can control and interact with a sequence of critical real-life events inside a cell triggered by the injected mRNA COVID-19 vaccine. In this paper, we describe the prototype of the ‘Cell Traveler’. We utilize the concepts of serious game to create an experience to encourage students and the public to develop deeper mRNA vaccine knowledge through a memorable and fun experience.

By simulating humanlike stylistic classification behaviors, a novel design methodology called S2CM for stylistic data classification is developed in this study. The core of S2CM is to build a social network consisting of subnetworks corresponding to each data class in the training dataset, and then compute both the influence of each node and the authority of each subnetwork such that style information existing in the training dataset can be well expressed according to the philosophy of social networks. With the built social network, the prediction of S2CM for an unseen sample can be cheaply implemented. Experimental results on artificial and benchmarking datasets show that S2CM outperforms the comparison methods on stylistic data.

To apply intelligent model in serious practical applications like medical diagnosis, the reliability and interpretability of the model are very important to users. Among the existing intelligent models, type-2 fuzzy systems are distinctive in interpretability and modeling uncertainty. However, like most existing models, the reliability determination of fuzzy system for recognition task training is an unsolved problem. In this study, a method of constructing minimax probability interval type-2 TSK fuzzy logic system classifier (MP-IT2TSK-FLSC) based on reliability learning is proposed. The classifier can provide the lower limit of the correct classification of the model and is an important index to quantify the reliability of the model. Experimental results on medical datasets have demonstrated the advantages of this method, exhibiting remarkable interpretability and reliability of the proposed fuzzy classifier.

Prostate cancer is a common malignancy among men, necessitating accurate and timely diagnosis at an early stage. With the advent of Artificial Intelligence (AI) technologies in the health field, support vector machines (SVMs) as one of the most well-known machine learning methods have been widely applied for prostate cancer detection. They have good generalization performances but no interpretability on the learned patterns, which bring difficulties for health professionals to understand the inner working of the predictive model. In this paper, we aim to build a computer aided diagnostic tool for prostate cancer using the SVMs where rule extraction is enabled. Experimental results on a real-world prostate cancer dataset collected in a Hong Kong hospital show that the proposed model not only had the ability for rule generation but also achieved better prediction results compared with decision tree, exhibiting a potential to assist physicians with clinical decision support in future.

An early diagnosis of prostate cancer (PC) is key for the successful treatment. Although invasive prostate biopsies can provide a definitive diagnosis, the number of biopsies should be reduced to avoid side effects and risks especially for the men with the low risk of cancer. Therefore, an accurate model is in need to predict PC with the aim of reducing unnecessary biopsies. In this study, we developed predictive models using four machine learning methods including Support Vector Machine (SVM), Least Squares Support Vector Machine (LS-SVM), Artificial Neural Network (ANN) and Random Forest (RF) to detect PC cases using available prebiopsy information. The models were constructed and evaluated on a cohort of 1625 Chinese men with prostate biopsies from Hong Kong hospital. All the models have the excellent performances in detecting significant PC cases, with ANN achieving the highest accuracy of 0.9527 and the AUC value of 0.9755. RF outperformed the other three methods in classifying benign, significant and insignificant PC cases, with an accuracy of 0.9741 and a F1 score of 0.8290.

Many medical applications face a situation that the on-hand data cannot fully fit an existing predictive model or on-line tool, since these models or tools only use the most common predictors and the other valuable features collected in the current scenario are not considered altogether. On the other hand, the training data in the current scenario is not sufficient to learn a predictive model effectively yet. In order to overcome these problems and construct an efficient classifier, for these real situations in medical fields, in this work we present an approach based on the least squares support vector machine (LS-SVM), which utilizes a transfer learning framework to make maximum use of the data and guarantee its enhanced generalization capability. The proposed approach is capable of effectively learning a target domain with limited samples by relying on the probabilistic outputs from the other previously learned model using a heterogeneous method in the source domain. Moreover, it autonomously and quickly decides how much output knowledge to transfer from source domain to the target one using a fast leave-one-out cross validation strategy. This approach is applied on a real-world clinical dataset to predict 5-year mortality of bladder cancer patients after radical cystectomy, and the experimental results indicate that the proposed method can achieve better performances compared to traditional machine learning methods, consistently showing the potential of the proposed method under the circumstances with insufficient data.