Using AI in task-based needs analysis for nurse-patient English course design: a case study to improve methodological effectiveness

As the first step in course design, Task-based Needs Analysis (TBNA) has gained increasing attention in the field of English for Specific Purposes (ESP) (Smith et al., 2022). By identifying authentic target tasks relevant to workplace communication, TBNA can inform a customized syllabus for ESP learners, ultimately enhancing their language performance in professional settings. However, despite the rapid advancement of technology, few studies have explored the integration of artificial intelligence (AI) into TBNA practices. This study investigates the potential of AI-assisted TBNA in enhancing the accuracy and efficiency of identifying, sequencing, and designing target task lists for a nurse-patient English communication course. The TBNA practice was conducted at a vocational university in Hainan, China, and focused on undergraduate nursing students to improve their nurse-patient communication in future workplaces. Data collection used a mixed-methods approach that included an online survey, onsite observations, questionnaires, and semi-structured interviews with nurses, trainees, and students. Multiple data sources and methods were triangulated to identify the most frequent target tasks in nurse-patient communication within professional settings. Ultimately, 21 target tasks were identified and organized into six task types, which informed the development of the nurse-patient English syllabus. The results reveal that AI can enhance survey tools, streamline research methods, and assist in data analysis. Consequently, an AI-assisted TBNA practice framework was proposed to improve the effectiveness of TBNA implementation.