Precision education

UPDATED . 4 MIN READ

The current process of medical education across a physician's career is challenged by inefficiencies and inequities. Like other aspects of modern life, enhanced access to—and visualization of—data can facilitate individualization. Precision education allows educators and learners to leverage data and technology to improve the personalization of education and the efficiency of learning. Precision education demands flexibility within training programs, such that the appropriate experiences and coaching are offered to support the development of each individual.

In 2023, the American Medical Association placed a new level of strategic focus on four high-priority areas in medical education:

Precision education will drive success in each of the other priority areas. As disparate sites explore capabilities to enable precision education, the AMA will serve to coordinate efforts and promote inter-operable approaches. To fulfill our vision of precision education, enhanced data capabilities must be aligned with cultural and systems changes that promote growth orientation; this has been a focus of prior work of the ChangeMedEd Initiative. Greater precision offers an opportunity to elevate equity, diversity and belonging by better understanding and addressing the experiences and needs of individuals.

Presented during the September 2023 conference, this plenary reviews barriers to lifelong learning in medical education and how precision education can be an effective tool to improve the system.

In this invited commentary, the authors acknowledge that the current system for selecting and developing the physician workforce is severely limited by the data available at all levels. Screening processes have relied on measures of convenience that are not well aligned with the desired attributes of physicians or of educational institutions. Innovations in data science and generative artificial intelligence platforms offer an opportunity for all stakeholders to act upon more meaningful information.

Continuing professional development can be a source of frustration for practicing physicians with limited time. Often, structured training is not directly relevant to the physician’s practice and physicians rely heavily on just-in-time resources that may not support deeper learning.

A multi-disciplinary team at the AMA has developed Reconnect, an AI tool aiming to personalize physician lifelong learning and improve efficiency. Reconnect integrates with EHR systems (in a manner that does not transmit protected health information) to curate and deliver personalized education content relevant to a physician’s patient panel.

The algorithm identifies multivariate nuances within patient records and trends within a physician’s practice pattern to elevate appropriate learning resources in anticipation of upcoming clinic sessions. High-yield ongoing learning is the focus; this tool does not involve recommendations regarding the care of individual patients. The concept and prototype were developed over three years and is being piloted with health systems to test feasibility. Future study and refinement will pursue long term goals of enhancing physician well-being and improving care of patients.

This project builds on the concept of resident-sensitive quality measures (RSQMs). These are clinical care measures that are both important for patient care and highly attributable to an individual resident (rather than the team, system or patient). This project introduces the concept of TRainee Attributable & Automated Care Evaluations in Real-Time (TRACERs), which are characterized as: meaningful for patient care and trainees; sufficiently attributable to the trainee of interest; automatable, meaning there is minimal human input needed once fully implemented; scalable across electronic health records (EHRs) and training environments; and amendable in real-time to formative educational feedback loops.

TRACERs builds upon RSQM research by automating the previously labor-intensive process of EHR data extraction and exploring how to make such measures scalable across institutions. This undertaking is a collaboration between researchers from the University of Cincinnati College of Medicine, NYU Grossman School of Medicine and Stanford University School of Medicine.

FEATURED STORIES