Abstract:

In health sciences education students must connect prior knowledge and clinical practice through individual cases. Health science students must acquire competencies such as gathering relevant information, analyzing data, and making clinical judgments. A key competency is Clinical Diagnostic Reasoning (CDR), which encompasses decision-making, problem-solving, diagnostic reasoning, and clinical judgment. These terms describe the cognitive processes necessary to assess, identify and manage patient problems, including hypothetico-deductive thinking and pattern recognition strategies. These processes involve observation, reflection, inference, and integrative judgment.

CDR processes are consistent across the health sciences (Medicine, Nursing, Psychology and Speech Therapy). Clinical mentors are vital in CDR training, as they are responsible for observing how students collect information from patients, medical records, test results, and information from other healthcare professionals. Clinical lecturers provide feedback on student performance and analyze clinical cases to assess clinical reasoning skills (Bowen, 2006).

To enhance CDR training, artificial intelligence (AI) has been used to generate new virtual clinical cases from existing clinical cases digitized by health science experts, providing a robust platform to simulate real-world scenarios. This integration of AI will provide students with more clinical cases that will enable them to hone their diagnostic skills in diverse and complex situations.

Keywords:

Artificial intelligence, Clinical diagnostic reasoning, Higher education, Training.