Virtual AI-in-medicine program for high schoolers reports six-year pilot results

A fully virtual research program that pairs high school students with mentors at the intersection of artificial intelligence and cancer medicine has published the results of its six-year pilot evaluation in BMC Medical Education. The Emerging Diagnostic and Investigative Technologies, or EDIT AI, program was established in 2020, and the new paper describes both its structure and the outcomes recorded during its ongoing pilot period from 2020 to 2025.

The authors frame the program against a broader workforce problem. Artificial intelligence is rapidly reshaping biomedical research and clinical medicine, including cancer diagnostics, therapeutics, and healthcare delivery, and maximizing its translational impact will require a workforce able not only to apply AI tools but also to understand their underlying limitations, sources of bias, and clinical implications. Although early research experiences can strongly influence long-term participation in STEM fields, few pre-college programs integrate computer science with medicine, an emerging intersection with growing relevance.

EDIT AI is delivered entirely virtually through a structured three-track model consisting of Skills Development, Advanced Research, and Peer-Mentor components. The program is supported by a tiered mentorship network and by the EDIT AI Virtual Student Laboratory, where students analyze real-world clinical research datasets. Educational activities include seminars, team-based research, office hours, mentor meetings, and an end-of-summer research symposium.

The evaluation, described by the authors as a longitudinal internal review, drew on several data sources: participant demographics, pre- and post-program familiarity surveys, seminar attendance, thematic analyses of student interests and scholarly outputs, participant feedback, and alumni outcomes. The authors posed three primary questions for the pilot period: whether participation improves familiarity with biomedical AI concepts and their clinical applications; whether participation influences student interests toward emerging areas of computational oncology; and whether a fully virtual research environment can sustain meaningful engagement and scholarly outcomes.

During the six-year pilot period, the program matriculated 284 student participants from 24 states. According to the results reported in the paper, participants demonstrated significant improvements in self-reported familiarity with biomedical AI concepts. Because these measures are self-reported and the evaluation is an internal program review rather than a controlled comparison study, the findings describe the program’s own participants over time rather than a causal effect tested against a comparison group.

The thematic analyses also suggested a shift in the substance of student work. Project interests and completed research increasingly reflected emerging areas of computational oncology, including spatial biology, according to the authors. This alignment between student projects and active research directions in computational oncology was one of the program’s stated secondary aims, and the paper presents it as an observed pattern in participant interests and outputs during the pilot period.

Scholarly output formed a third strand of the results. Participants produced 39 peer-reviewed publications, presented at national and international conferences, and earned scholarships during the pilot period. Alumni went on to matriculate into college and graduate programs, and many returned to the program as near-peer mentors, a pattern the authors link to the program’s Peer-Mentor track and its tiered mentorship network.

The authors conclude that this six-year internal evaluation provides preliminary evidence supporting the feasibility of a fully virtual, mentored AI-in-medicine research program for high school students. They position EDIT AI as a framework for preparing early-stage learners to engage with interdisciplinary biomedical AI research while strengthening the future biomedical AI workforce. The paper, an open-access research article published in BMC Medical Education, was released on 16 September 2026 as an accepted manuscript shared ahead of the final Version of Record, a version the publisher notes remains subject to further edits. As the authors themselves characterize it, the evidence base is preliminary and internal; the value of the report lies in documenting what a fully virtual pre-college research program can deliver across six cohorts, and in offering a described model that other groups interested in the AI-and-medicine pipeline can examine, replicate, or evaluate independently.

Subject of Research: A six-year pilot evaluation of a virtual AI-in-cancer-medicine research program for high school students

Article Title: Building early career pathways in AI and medicine: a six-year pilot evaluation of the EDIT AI program

Article References: Levy, J. J., Mattern, B. B., Koziol, B. D., Addai, M. O., Lee, C., Robinson, A., Pietrowicz, S., Fiering, S., Asojo, O. A., Kuratani, D., Isokawa, K., Patterson, P., Freedland, S., Figueiredo, J. C., Foster-Johnson, V. L., Vaickus, L. J., & Hayden, M. S. (2026). Building early career pathways in AI and medicine: a six-year pilot evaluation of the EDIT AI program. BMC Medical Education. https://doi.org/10.1186/s12909-026-10358-9

Image Credits: AI Generated

DOI: 10.1186/s12909-026-10358-9

Keywords: EDIT AI, artificial intelligence, medical education, cancer research, high school students, virtual research program, computational oncology, mentorship, STEM pathways, BMC Medical Education, pilot evaluation, biomedical AI