The use of Electronic Health Records (EHR) by medical students during their clinical rotations provides a rich source of documentation of the students’ clinical experiences. However, accessing and summarizing those notes through the EHR is cumbersome and inefficient. There is a need to improve the digitization of notes and encounter details to better summarize the students’ experiences. We developed a program to generate summaries of specialty requirements met and those still needed by labeling and extracting information, performing entity detection and classification, and leveraging notes with known diagnosis codes to train models for accurate summaries. This methodology achieved 83.3% accuracy for notes with a SOAP (Subjective, Objective, Assessment, Plan) structure, enabling the creation of detailed progress reports. This automated system addresses inefficiencies and errors in manual tracking, providing Duke Health with a reliable and efficient means to convert students’ notes into structured data.
