Developing a Conversational Virtual Standardized Patient to Enable Students to Practice History-Taking Skills.

INTRODUCTION: Although traditional virtual patient simulations are designed to teach and assess clinical reasoning skills, few employ conversational dialogue with the patients. The virtual standardized patients (VSPs) described herein represent standardized patients that students interview using natural language. Students take histories and develop differential diagnoses of the VSPs as much as they would with standardized or actual patients. The student-VSP interactions are recorded, creating a comprehensive record of questions and the order in which they were asked, which can be analyzed to assess information-gathering skills. Students document the encounter in an electronic medical record created for the VSPs. METHODS: The VSP was developed by integrating a dialogue management system (ChatScript) with emotionally responsive 3D characters created in a high-fidelity game engine (Unity). The system was tested with medical students at the Ohio State University College of Medicine. Students are able to take a history of a VSP, develop a differential diagnosis, and document the encounter in the electronic medical record. RESULTS: Accuracy of the VSP responses ranged from 79% to 86%, depending on the complexity of the case, type of history obtained, and skill of the student. Students were able to accurately develop an appropriate differential diagnosis on the basis of the information provided by the patient during the encounter. CONCLUSIONS: The VSP enables students to practice their history-taking skills before encounters with standardized or actual patients. Future developments will focus on creating an assessment module that will automatically analyze VSP sessions and provide immediate student feedback.

Enhancing cancer screening in primary care: rationale, design, analysis plan, and recruitment results.

Colorectal cancer (CRC) is the third leading type of cancer and the third leading cause of cancer death in the United States. National policy-making organizations recognize and support a variety of CRC screening strategies among average-risk adults aged 50 and older based on strong evidence showing that screening decreases mortality from CRC and can also reduce the incidence of the disease. The goal of this study was to test a multi-level stepped intervention to increase CRC screening rates. We used a group-randomized trial design where the units of assignment were clinics and the units of observation were eligible patients receiving care at those clinics, with stratified random assignment of clinics to study conditions. The primary analysis was planned as a mixed-model logistic regression to account for the expected positive intraclass correlation associated with clinics. Our recruitment experience reflected the difficulties of conducting research in the real world where changes in economic conditions, staff turnover/layoff, inadequate medical records, and poor acceptance of research can significantly impact study plans. It demonstrated the problems that can emerge when procedures used in the study depart from those used in the pilot work to generate parameter estimates for power analysis. It also demonstrated the importance of allowing for attrition at the group and patient levels so that if recruitment falls short, it is possible to maintain adequate power with only a slight increase in the detectable difference. This experience should assist others planning group-randomized trials, whether in cancer screening or in other areas.