The present study aims to examine the pedagogical effectiveness of a Chinese mathematical dialogue-based intelligent tutoring system used for teaching mathematics. The mathematical unit ‘multiplication and division of time expressions’ was taught to 134 fifth-grade students in three types of instruction conditions: the intelligent tutoring system (ITS), conventional teacher instruction and material reading. The results show that student performance was comparable between the proposed mathematical ITS and conventional instruction conditions but was significantly poorer when no teaching method was used. The questionnaire survey showed that the ITS method not only improved maths learning, but also increased motivation among the fifth graders. The effectiveness of ITS remedial instruction in mathematics is discussed.

Open-box models in medical domain have high acceptance and demand by many medical examiners. Even though the accuracy predicted by most of convolutional neural network (CNN) models is high, it is still not convincing as the detail discussion regarding the outcome is semi-transparent in the functioning process. As pneumonia is one of the top contagious infection that makes most of the population affected due to low immunity. Therefore, the goal of this paper is to implement an interpretable classification of pneumonia infection using eXplainable AI (XAI-ICP). Thus, XAI-ICP is the highly efficient system designed to solve this challenge by adapting to the recent population health conditions. The aim is to design an interpretable deep classification and transfer learning based evaluation for pneumonia infection classification. The model is primarily pre-trained using the open Chest X-Ray (CXR) dataset from National Institutes of Health (NIH). Whereas, the training input and testing given to this system is Taichung Veterans General Hospital (TCVGH) for independent learning, Taiwan + VinDr open dataset for transfer learning of pneumonia affected patients with labelled CXR images possessing three features of infiltrate, cardiomegaly and effusion. The data labelling is performed by the medical examiners with the XAI human-in-the-loop approach. The XAI-ICP demonstrates the XAI based re-configurable DCNN with human-in-the-loop as a novel approach. The interpretable deep classification provides detail transparency analysis and transfer learning for competitive accuracy. The purpose of this work, to design a re-configurable model that can continuously improve itself by using feedback system and provide feasibility for the model deployment across multiple countries to provide an efficient system for the pneumonia infection classification. The designed model then provides detail decisions taken at each step as transparency and features used within the algorithm for the pneumonia classification during the hospitalization. Thus, the scope can be given as explainable AI usage for the diagnosis classification using data preprocessing and interpretable deep convolutional neural network by the CXR evaluation. The accuracy achieved by using independent learning classification is 92.14% and is further improved based on successive transfer learning based evaluation is 93.29%. The XAI-ICP model adapts to the different population by using transfer learning, while providing competitive results to the affected conditions.

This study aimed to develop an early prediction model for identifying patients with bloodstream infections. The data resource was taken from 2015 to 2019 at Taichung Veterans General Hospital, and a total of 1647 bloodstream infection episodes and 3552 non-bloodstream infection episodes in the intensive care unit (ICU) were included in the model development and evaluation. During the data analysis, 30 clinical variables were selected, including patients’ basic characteristics, vital signs, laboratory data, and clinical information. Five machine learning algorithms were applied to examine the prediction model performance. The findings indicated that the area under the receiver operating characteristic curve (AUROC) of the prediction performance of the XGBoost model was 0.825 for the validation dataset and 0.821 for the testing dataset. The random forest model also presented higher values for the AUROC on the validation dataset and testing dataset, which were 0.855 and 0.851, respectively. The tree-based ensemble learning model enabled high detection ability for patients with bloodstream infections in the ICU. Additionally, the analysis of importance of features revealed that alkaline phosphatase (ALKP) and the period of the central venous catheter are the most important predictors for bloodstream infections. We further explored the relationship between features and the risk of bloodstream infection by using the Shapley Additive exPlanations (SHAP) visualized method. The results showed that a higher prothrombin time is more prominent in a bloodstream infection. Additionally, the impact of a lower platelet count and albumin was more prominent in a bloodstream infection. Our results provide additional clinical information for cut-off laboratory values to assist clinical decision-making in bloodstream infection diagnostics.

The current study explores students’ collaboration and problem solving (CPS) abilities using a human-to-agent (H-A) computer-based collaborative problem solving assessment. Five CPS assessment units with 76 conversation-based items were constructed using the PISA 2015 CPS framework. In the experiment, 53,855 ninth and tenth graders in Taiwan were recruited, and a multidimensional item response analysis was used to develop CPS scales and represent the students’ collaboration and problem solving performance. The results show that the developed H-A approach is feasible for measuring students’ CPS skills, and the CPS scales are also shown to be reliable. In addition, the students’ CPS performance scores are further explored and discussed under the PISA CPS framework.

Purpose: To address the contentious data sharing across hospitals, this study adopted a novel approach, federated learning (FL), to establish an aggregate model for acute kidney injury (AKI) prediction in critically ill patients in Taiwan. Methods: This study used data from the Critical Care Database of Taichung Veterans General Hospital (TCVGH) from 2015 to 2020 and electrical medical records of the intensive care units (ICUs) between 2018 and 2020 of four referral centers in different areas across Taiwan. AKI prediction models were trained and validated thereupon. An FL-based prediction model across hospitals was then established. Results: The study included 16,732 ICU admissions from the TCVGH and 38,424 ICU admissions from the other four hospitals. The complete model with 60 features and the parsimonious model with 21 features demonstrated comparable accuracies using extreme gradient boosting, neural network (NN), and random forest, with an area under the receiver-operating characteristic (AUROC) curve of approximately 0.90. The Shapley Additive Explanations plot demonstrated that the selected features were the key clinical components of AKI for critically ill patients. The AUROC curve of the established parsimonious model for external validation at the four hospitals ranged from 0.760 to 0.865. NN-based FL slightly improved the model performance at the four centers. Conclusion: A reliable prediction model for AKI in ICU patients was developed with a lead time of 24 h, and it performed better when the novel FL platform across hospitals was implemented.