Unlocking the Potential of Precision Education: Maximizing Learning Outcomes with Assessment and Analytics
Published on Dec 1, 2023. Updated on Dec 18, 2023.
In today's Osmosis blog, Dr. Sean Tackett discusses the evolution of precision education and how educators can leverage assessment and analytics to boost learning outcomes.
There's no question that everyone is different, from our genes to our environments. These shape how our neurons connect with one another, and by the time we're adults, these neural connections create networks and brain structures that are unlike any other, manifesting as diversity in knowledge, attitudes, and skills.
Given how obvious it is that each of us is unique, it's surprising how often everyone is treated the same in education. The intentions may be good; we want to standardize the quality of educational experiences and make sure that the goals of an educational session are achieved. Yet the challenge for educators is to accommodate (or even capitalize on) individual differences while helping everyone progress along the same learning objectives.
What is precision education?
Precision education is one of the latest formulations for meeting the challenge of individual learner needs. The term derives from precision medicine, which was based on the idea that combining the vast accumulation of medical knowledge with increasing computational power and more sophisticated data science would permit medical therapies to become tailored to individuals to maximize their benefits and limit their side effects.
Precision medical education was formally defined in a 2023 article by Marc Triola and Jesse Burk-Rafel, clinician educators and researchers at NYU Grossman School of Medicine . They drew from the "P4" framework proposed for precision medicine to describe a P4 for precision medical education:
- Proactive: Data should be provided to learners, guidance given for how they can use it, and appropriate support from faculty coaches.
- Personalized: Data and interventions should be customized to individual needs and goals.
- Participatory: Learners should be full partners in the design and implementation of precision education.
- Predictive: Data should be used to anticipate meaningful learning, patient care, and system-level outcomes.
This framework aligns with other longstanding concepts in education. For example, the adult learning principles proposed by Malcolm Knowles decades earlier emphasized that learners want to be self-directed and pursue goals that they find relevant (corresponding closely to the proactivity, personalization, and participatory elements of P4). There have also been many studies that have tried to determine what measures would predict future outcomes, ranging from who should be admitted to health profession programs to what would predict clinical practice behaviors.
The Evolution of Precision EducationPrecision education itself has already been occurring in analog form for years. For instance, it's common for clinical preceptors to target the learning needs demonstrated during patient presentations and for procedural practice or simulation scenarios to create opportunities for customized instruction.
However, what is new is how precision education can be accomplished through automation. For example, all manner of digital data can be collected through web and mobile platforms to produce a variety of analytics. Clicks in educational apps have been used to understand learning processes [3,4], and mobile trackers have generated granular data to see how learners spend their time . Data can be automatically visualized in the form of dashboards that can be used by individual learners to check their performance and set goals and by programs to monitor their overall effects. When integrated with electronic health records, dashboards can be used to track actual clinical experiences .
Generative artificial intelligence (GenAI) technologies may make precision education more accessible. GenAI chatbots connected to the internet give learners access to learning partners with essentially infinite knowledge. GenAI can role play, offering opportunities for communication skills practice and training. Educators can use GenAI to help them develop learning resources. The GenAI landscape is rapidly evolving, and its use in educational settings must be done with caution, as GenAI requires supervision and often makes errors. However, GenAI is likely to become a mainstay of the precision education movement, and guidance on how to use GenAI in HPE is emerging [7,8].
The ultimate purpose of precision education is to accelerate learning so that individuals can take only the time they need in one stage of training before advancing to the next. It takes a lot of time and money to train health professionals, and there are health worker shortages worldwide. Making learning more efficient would not only help learners progress more quickly but allow them to help patients sooner.
Initiating Precision Education in Your Program
The first step to getting started with precision education is recognizing that it works best with large amounts of digital data. To take full advantage of precision education, it helps to implement new technologies that collect high-quality data, automatically analyze it, and partner with a multidisciplinary team. However, even if you don't have the latest digital technologies or a squad of data scientists at your disposal, you can still get a cutting-edge education. Observations of learners and discussions with them still comprise data that can lead to individualized instruction and feedback.
As a final word, remember that while there can be incredible amounts of digital data collected and applied to learning, they still offer a relatively small view into a learner's knowledge, attitudes, skills, and experiences. Human connection cannot be automated, and there is no substitute for establishing relationships with students that make them feel safe to try new things and make mistakes. As educators, we should strive to create environments that give learners a sense of belonging and feel they are part of a larger, inclusive learning community.
About the AuthorSean Tackett (MD, MPH) is a General Internist at Johns Hopkins, Bayview Medical Center, and Research Director for Osmosis. His career aspiration is to contribute to improvements in the quality of health professional education internationally. Dr. Tackett completed his residency and a fellowship in Internal Medicine at Johns Hopkins. He was awarded his MD from the University of Pittsburgh, School of Medicine and graduated from Notre Dame University, magna cum laude with a BS in Biochemistry. As a member of the faculty at Johns Hopkins, he has published scholarship related to international medical school accreditation and medical student learning environments. Clinically, he practices hospital medicine and attends on inpatient medical teaching services. Alongside Osmosis, Dr. Tackett works with students and faculty to develop research projects that advance the science of education in the health professions. Topics include how new technologies can make learning more efficient and how videos impact health professional learning around the world. Traveling and eating are his favorite pastimes, especially when his wife and two boys can join—and when visits to family in Pittsburgh and Ahmedabad can be arranged.
Resources & References
- Hood L, Friend SH. Predictive, personalized, preventive, participatory (P4) cancer medicine. Nat Rev Clin Oncol. 2011 Mar;8(3):184-7.
- Triola MM, Burk-Rafel J. Precision Medical Education. Acad Med. 2023 Jul 1;98(7):775-781.
- Cirigliano MM, Guthrie CD, Pusic MV. Click-level Learning Analytics in an Online Medical Education Learning Platform. Teach Learn Med. 2020 Aug-Sep;32(4):410-421.
- Menon A, Gaglani S, Haynes MR, Tackett S. Using "big data" to guide implementation of a web and mobile adaptive learning platform for medical students. Med Teach. 2017 Sep;39(9):975-980.
- Rosen MA, Bertram AK, Tung M, Desai SV, Garibaldi BT. Use of a Real-Time Locating System to Assess Internal Medicine Resident Location and Movement in the Hospital. JAMA Netw Open. 2022 Jun 1;5(6):e2215885.
- Yarahuan JKW, Lo HY, Bass L, Wright J, Hess LM. Design, Usability, and Acceptability of a Needs-Based, Automated Dashboard to Provide Individualized Patient-Care Data to Pediatric Residents. Appl Clin Inform. 2022 Mar;13(2):380-390.
- 5 Essential AI (ChatGPT) Prompts Every Medical Student and Doctor Should be Using to 10x their Productivity
- Boscardin CK, Gin B, Golde PB, Hauer KE. ChatGPT and Generative Artificial Intelligence for Medical Education: Potential Impact and Opportunity. Acad Med. 2023 Aug 31