Search

Artificial intelligence (AI) technologies have been consistently influencing the progress of education for an extended period, with its impact becoming more significant especially after the launch of ChatGPT-3.5 at the end of November 2022. In the field of physics education, recent research regarding the performance of ChatGPT-3.5 in solving physics problems discovered that its problem-solving abilities were only at the level of novice students, insufficient to cause outstanding alarm in the field of physics education. However, the release of ChatGPT-4 presented substantial improvements in reasoning and conciseness. How does this translate to performance in solving physics problems, and what kind of impact might it have on education? This study undertakes a comprehensive assessment of ChatGPT-4's performance in solving physics problems from the perspective of physics conceptual understanding and reasoning, and compares its performance with that of students. It is concluded that ChatGPT-4's performance in solving physics problems has significantly improved compared to ChatGPT-3.5, and was notably superior to the majority of middle school and high school students. This finding presents both a challenge and an opportunity for physics education and the broader educational field, and triggers immediate considerations for coping with this challenge in future teaching and assessment environments.

BackgroundIntegrative medicine is a form of medicine that combines practices and treatments from alternative medicine with conventional medicine. The diagnosis in integrative medicine involves the clinical diagnosis based on modern medicine and syndrome pattern diagnosis. Electronic medical records (EMRs) are the systematized collection of patients health information stored in a digital format that can be shared across different health care settings. Although syndrome and sign information or relative information can be extracted from the EMR and content texts can be mapped to computability vectors using natural language processing techniques, application of artificial intelligence techniques to support physicians in medical practices remains a major challenge. ObjectiveThe purpose of this study was to investigate model-based reasoning (MBR) algorithms for the clinical diagnosis in integrative medicine based on EMRs and natural language processing. We also estimated the associations among the factors of sample size, number of syndrome pattern type, and diagnosis in modern medicine using the MBR algorithms. MethodsA total of 14,075 medical records of clinical cases were extracted from the EMRs as the development data set, and an external test data set consisting of 1000 medical records of clinical cases was extracted from independent EMRs. MBR methods based on word embedding, machine learning, and deep learning algorithms were developed for the automatic diagnosis of syndrome pattern in integrative medicine. MBR algorithms combining rule-based reasoning (RBR) were also developed. A standard evaluation metrics consisting of accuracy, precision, recall, and F1 score was used for the performance estimation of the methods. The association analyses were conducted on the sample size, number of syndrome pattern type, and diagnosis of lung diseases with the best algorithms. ResultsThe Word2Vec convolutional neural network (CNN) MBR algorithms showed high performance (accuracy of 0.9586 in the test data set) in the syndrome pattern diagnosis of lung diseases. The Word2Vec CNN MBR combined with RBR also showed high performance (accuracy of 0.9229 in the test data set). The diagnosis of lung diseases could enhance the performance of the Word2Vec CNN MBR algorithms. Each group sample size and syndrome pattern type affected the performance of these algorithms. ConclusionsThe MBR methods based on Word2Vec and CNN showed high performance in the syndrome pattern diagnosis of lung diseases in integrative medicine. The parameters of each group’s sample size, syndrome pattern type, and diagnosis of lung diseases were associated with the performance of the methods. Trial RegistrationClinicalTrials.gov NCT03274908; https://clinicaltrials.gov/ct2/show/NCT03274908

BackgroundTraditional Chinese medicine (TCM) has been shown to be an efficient mode to manage advanced lung cancer, and accurate syndrome differentiation is crucial to treatment. Documented evidence of TCM treatment cases and the progress of artificial intelligence technology are enabling the development of intelligent TCM syndrome differentiation models. This is expected to expand the benefits of TCM to lung cancer patients. ObjectiveThe objective of this work was to establish end-to-end TCM diagnostic models to imitate lung cancer syndrome differentiation. The proposed models used unstructured medical records as inputs to capitalize on data collected for practical TCM treatment cases by lung cancer experts. The resulting models were expected to be more efficient than approaches that leverage structured TCM datasets. MethodsWe approached lung cancer TCM syndrome differentiation as a multilabel text classification problem. First, entity representation was conducted with Bidirectional Encoder Representations from Transformers and conditional random fields models. Then, five deep learning–based text classification models were applied to the construction of a medical record multilabel classifier, during which two data augmentation strategies were adopted to address overfitting issues. Finally, a fusion model approach was used to elevate the performance of the models. ResultsThe F1 score of the recurrent convolutional neural network (RCNN) model with augmentation was 0.8650, a 2.41% improvement over the unaugmented model. The Hamming loss for RCNN with augmentation was 0.0987, which is 1.8% lower than that of the same model without augmentation. Among the models, the text-hierarchical attention network (Text-HAN) model achieved the highest F1 scores of 0.8676 and 0.8751. The mean average precision for the word encoding–based RCNN was 10% higher than that of the character encoding–based representation. A fusion model of the text-convolutional neural network, text-recurrent neural network, and Text-HAN models achieved an F1 score of 0.8884, which showed the best performance among the models. ConclusionsMedical records could be used more productively by constructing end-to-end models to facilitate TCM diagnosis. With the aid of entity-level representation, data augmentation, and model fusion, deep learning–based multilabel classification approaches can better imitate TCM syndrome differentiation in complex cases such as advanced lung cancer.

Background: Deep discussions play an important role in students' online learning. However, researchers have largely focused on engaging students in deep discussions in online asynchronous forums. Few studies have investigated how to promote deep discussion via mobile instant messaging (MIM). Objectives: In this study, we applied learning analytical tools (i.e., KBdeX and word clouds) to enhance students' shared epistemic agency and thereby support their deep discussions in MIM. Methods: Forty Chinese college students participated in this study and reflected on their MIM engagement by participating in the learning analytics (LA)-augmented meta-discourse sessions. The study used multiple data analysis methods, including content analysis, statistical analysis, epistemic network analysis and lag sequential analysis. Results: We found that LA engaged students in deep discussions and shared epistemic agency-related discourse, such as creating shared understanding, creating knowledge objects, and projective and regulative processes. In particular, word clouds engaged students in more complete shared epistemic agency discourse trajectory which started from creating awareness of unknowns, then progressed to setting projective plans and sharing information, and ultimately, creating shared understanding. Moreover, our analysis indicated that epistemic agency discourse moves of creating shared understanding led students to a high level of deep discussion. Implications: This study contributes to research by extending the 'comparison paradigm', which focuses on comparing (a)synchronous forums with MIM, to a 'design paradigm', which mobilises design features from (a)synchronous forums to MIM and using learning analytical tools to engage students in deep online discussions by promoting their epistemic agency.