Machine learning to develop and validate a model for predicting the risk of lymph node metastasis in colorectal cancer patients.

Learning engagement, broadly defined as a psychological state reflecting students’ active involvement in the learning process, encompasses behavioral, cognitive, and emotional dimensions (). Rather than merely focusing on observable academic actions, this construct encompasses active psychological processes, proactive attitudes, and deep cognitive reflection. Theoretically, learning engagement not only drives academic achievement and deep learning but also promotes students’ psychological well-being and holistic development (). Consistently, argued that effective learning requires such active engagement and continuous reflection, rather than a reliance on rote memorization. The rapid advancement of generative artificial intelligence, exemplified by platforms such as ChatGPT and DeepSeek, has profoundly reshaped higher education by offering unprecedented opportunities to personalize learning, enrich feedback, and support students’ cognitive and emotional development (). As these technologies become increasingly embedded in academic environments, a critical need emerges to understand the processes through which students’ acceptance of generative AI may be associated with meaningful learning outcomes, particularly learning engagement (). Grounded in the Technology Acceptance Model (TAM), prior research has demonstrated that perceived usefulness and ease of use predict learners’ behavioral intentions toward educational technologies (; ). However, growing evidence suggests that the relationship between technology acceptance and learning outcomes is rarely direct; rather, it is mediated by learners’ internal psychological processes (). Despite the rapid diffusion of GenAI in education, the specific motivational and emotional mechanisms linking generative AI acceptance to learning engagement remain insufficiently understood. Learning motivation serves as a pivotal psychological mechanism that drives academic behaviors and goal-directed pursuits. Grounded in self-determination theory, educational technologies perceived as autonomy-supportive and competence-enhancing can foster intrinsic motivation by fulfilling learners’ basic psychological needs (). Consistently, accumulating empirical evidence indicates that digital tool acceptance positively predicts learning motivation, which in turn facilitates learning engagement (). Within digital and online learning environments, robust motivation has been shown to directly determine both cognitive engagement and metacognitive regulation strategies (). Furthermore, recent empirical insights confirm that technology acceptance indirectly enhances learning engagement by boosting students’ intrinsic motivation (). Consequently, learning motivation acts as a critical psychological bridge connecting initial technology acceptance to sustained behavioral and cognitive investment.