Pathophysiology (Physical Therapy) & Psychology and Community Health (Nursing)

Team members

Luis Flores Abarca, Mauricio Carrasco Ruz, and Paula Sepúlveda Gallegos from Universidad de O’Higgins, Chile.

Programs/courses

Pathophysiology (Physical Therapy) and Psychology & Community Health (Nursing).

How have you used Clinical Mind AI in your teaching or research?

Pathophysiology (Physical Therapy) We implemented two simulation activities with Clinical Mind AI in the Pathophysiology course for second-year Kinesiology students (44 students in total). In the first activity, students were asked to identify and classify the pain reported by a simulated patient, based on their clinical history and complementary tests, to determine whether it was nociceptive, neuropathic, or nociplastic. In the same activity, we evaluated the history, documentation in the medical record, and an application question related to the case and the reviewed material, using multiple rubrics. In the second activity, we worked with a clinical case of a patient with an asthma exacerbation. Students were asked to analyze the simulated patient's clinical history, identify relevant signs and symptoms, and explain the underlying pathophysiology to answer the guiding question: "How does alveolar hypoventilation lead to oxygen desaturation?"

Psychology & Community Health (Nursing) The implementation takes place in the course Psychology and Community Health for nursing, in which each student interacts with five virtual patients. The objective is to assess patients from a community-health perspective, collecting information on both medical history and social background, with particular emphasis on the social determinants of health. Students interact with patients via written chat, probing their assigned case and then completing an interview rubric and medical notes. The rubric is first scored by the AI, after which the instructor reviews the output to verify accuracy and adds annotations as needed. This activity is implemented mid-semester. Students work in groups and subsequently share and discuss their findings. The aim is to extract relevant information about community stakeholders in order to identify the key problems affecting the group. The project is currently underway, and we expect full participation from the course (two sections of ~75 students each; n ≈ 150).

What impact or benefits have you observed for your students or teaching practice?

Pathophysiology (Physical Therapy) When we framed for students the significance and rarity of having access to Clinical Mind AI and the ability to run AI-driven clinical simulations it generated a high level of engagement. In that context, we observed procedural improvements: greater organization and thoroughness in history-taking, more precise use of terminology, and more structured documentation in the patient chart, all of which strengthened their understanding of the underlying pathophysiology in each case. From my teaching role, the platform has allowed me to design learning experiences in which students take a truly active role in their formation. It also gives me the flexibility to simulate multiple scenarios in biopsychosocial contexts, adjusting both the tone of the responses and the simulated patient’s persona. In addition, students find it motivating, which promotes peer discussion grounded in critical analysis of the simulated patient’s answers to the various questions they pose.

Psychology & Community Health (Nursing) Student feedback indicates that the platform is highly engaging. While students commonly use AI to supplement their studies, they have not typically done so in such a methodical and structured manner. We have observed improved performance relative to prior cohorts, particularly in the completeness and quality of data collection.

Anything else you’d like to share about your experience?

This has been a major pedagogical innovation for us. We have leveraged the platform’s potential effectively within the course context, and it provides an excellent stepping stone toward adoption in the Adult and Older Adult course, where primary care is addressed comprehensively. It also complements the course’s simulation activities. Our main challenge has been varying levels of digital literacy among faculty and occasional resistance to change—both characteristics of the broader paradigm shift toward using AI as a complementary tool rather than an obstacle to teaching and learning process. Looking ahead, we plan to extend the platform to additional specialty courses, as well as to courses such as Clinical Semiology and Care Management.

Clinical Mind AI represents a key pedagogical innovation, as it allows educators to create realistic clinical scenarios and provide structured feedback to students. Its impact on health education is reflected in the enhanced development of clinical reasoning and the preparation of future professionals to face the challenges of an increasingly complex practice. The collaboration with Stanford expands this contribution, benefiting both faculty and students with a tool of international scope and global projection.