Actionable companion · Feedback & scaffolding

Learning with agency: Effect of a sports-medicine–guided football program on physical fitness in adolescents: A controlled school-based trial

AI-assisted editorial implementation guide, separate from the original research. Proposed actions are not claims or recommendations attributed to the source authors. No independent peer review of this guide is asserted.

Read original paper Search paper agent CC BY 4.0

Evidence and context

Title and abstract screening; stage labels describe reported settings, not verified numerical ages. Design labels require full-text appraisal. Reported stage(s): Secondary school. Verify the participant population and task before transferring the findings.

Original authors’ abstract, reproduced under the linked source license:

Integrating artificial intelligence (AI) with sports medicine principles into school-based physical education may enhance physical fitness and reduce injury risk among adolescents. This study aimed to evaluate whether a 10-week sports-medicine-guided football curriculum augmented with explainable machine-learning feedback produces greater improvements in physical fitness and injury-prevention outcomes than a standard physical-education curriculum. A total of 195 healthy junior high school students (mean age 14.1 ± 0.7 years) participated in a controlled school-based intervention and were allocated to either an AI-supported sports-medicine curriculum (intervention) or a standard curriculum (control). Physical fitness outcomes, including lung capacity, estimated maximal oxygen uptake (VO2max), sprint performance, standing long jump, and middle-distance running performance (800 m girls/1000 m boys), were assessed before and after the 10-week program. Outcomes were analyzed using 2-way mixed analysis of variance to test Group × Time interactions. Injury risk prediction was supported by an explainable machine-learning ensemble model (CatBoost + Gradient Boosting) interpreted using SHAPley Additive explanations. Significant Group × Time interactions were observed for lung capacity (P .05). A school-based football curriculum integrating sports-medicine principles with explainable AI-driven feedback leads to significantly greater improvements in key physical-fitness outcomes than a standard physical-education curriculum. This approach directly supports individualized training adaptation and injury-risk awareness, offering a scalable model for enhancing adolescent health and safety in school physical education.

What kind of evidence is this?

Supporting AI learning science · Design requires full-text appraisal

Stage: Secondary school. Screening labels describe reported context and study-design language. They are not a risk-of-bias rating or proof of effectiveness for an age band.

Participant ages · source passage

A total of 195 healthy junior high school students (mean age 14.1 ± 0.7 years) participated in a controlled school-based intervention and were allocated to either an AI-supported sports-medicine curriculum (intervention) or a standard curriculum (control).

Study methods · source passage

This controlled, school-based educational intervention was conducted among 195 healthy, second-year junior-high-school students (mean age 14.1 ± 0.7 years; 96 boys and 99 girls) recruited through school-wide announcements and screened for eligibility.

Limitations and uncertainty · source passage

Several limitations should be considered when interpreting the present findings. First, although participants were screened for health status and training background, habitual physical activity outside the school program and dietary intake were not objectively monitored, which may have influenced the magnitude of adaptation. Second, maturational status was self-reported rather than clinically verified; therefore, minor differences in pubertal stage may have affected physiological responses. Third, although both groups trained with the same weekly frequency, exercise intensity and actual training volume were not continuously quantified, limiting precise comparison of workload exposure between programs. Environmental factors such as sleep and hydration were standardized only through general guidance rather than objective monitoring. Blinding was also limited. Although outcome assessors were independent of curriculum delivery and data were coded, full participant blinding was not feasible due to the nature of the school-based intervention, which may have introduced performance-related bias. In addition, the absence of a true non-exercise control group limits the ability to isolate the independent effects of exercise exposure from curriculum design. Future studies incorporating an inactive comparison group may better distinguish the relative contributions of training volume and program structure. Finally, although the AI-based injury-risk model was calibrated for adolescent application, it was originally derived from adult football datasets and therefore requires further external validation in school-aged populations to confirm generalizability. Future research should incorporate objective monitoring of heart rate and training load, validated indices of biological maturation, and standardized dietary assessment. Longitudinal follow-up is also warranted to determine whether improvements in fitness and injury-risk awareness are sustained beyond the structured intervention period.

Design the system before the pilot

Use this study to inform a learning mechanism or implementation question. It is not direct evidence that autonomous agents improve learning. Keep the proposed agent behavior separate from what the source actually tested.

Give feedback on the learner’s reasoning, then fade hints. Record whether the learner can complete the next task without that scaffold.
Use common rubrics, blind scoring where feasible and a fresh unaided reasoning task. Document permissible assistance and avoid treating AI-detector scores as proof of misconduct.

A 90-day district pilot

Days 1–15 · Appraise. Have the curriculum lead and a teacher read the methods and limitations. Record the study design, sample, comparator, outcomes and evidence gaps. Define a local question that the study can help inform.
Days 16–30 · Design. Ask learners to attempt a problem unaided, compare an agent hint, explain a revision and verify the final reasoning against a trusted source. Make the permitted use explicit for each assignment. Name an accountable owner and set the baseline, success threshold and budget before implementation.
Days 31–60 · Test. Start with a small voluntary cohort, preserve an accessible non-AI route and require teacher review. Use synthetic or de-identified examples; approve data handling and tool terms through district processes.
Days 61–90 · Decide. Measure unaided transfer and delayed retention, calibration of confidence and the ability to identify an incorrect AI explanation. Record whether help-seeking becomes answer copying. Compare with baseline, document uncertainty and stop or revise if learning worsens, access is unequal or critical errors persist.

The board decision brief

Report the learning problem, evidence quality, participating population, total cost including review time, measured benefit, errors, access differences and remaining uncertainties. Make a dated recommendation to stop, revise or expand. A positive perception survey alone does not establish learning improvement.

Attribution and reuse

Ke Shi; Yuelong Ye; Tianlun Zheng; Kaiyue Tang; Jing Bin; Liuxiang Wei; Lin Wang. Effect of a sports-medicine–guided football program on physical fitness in adolescents: A controlled school-based trial. Medicine (2026-05-01). https://doi.org/10.1097/md.0000000000048649

Companion prepared 2026-10-30. Original authorship and DOI are preserved. The abstract is an attributed source extract; the implementation plan is new AI-assisted editorial material, offered under the same CC BY 4.0 license. This guide has not undergone independent peer review.