Truace
Subscribe
70/100

Moderate evidence

Cite
More
Export CSVExport JSONEmailLinkedInX

Review of 81 studies shows gamified AI lessons improved school science learning

Study title: The effects of gamified AI-supported digital learning environments on personalized learning and student engagement in school education: a systematic review and meta-analysis

Evidence type
Systematic review or meta-analysis
Sources
1 sourcePeer-reviewed
Published
2 min read
Truvace record
TRV-2026-2808cite or check it

Study title: The effects of gamified AI-supported digital learning environments on personalized learning and student engagement in school education: a systematic review and meta-analysis

Researchers from Kazakhstan reviewed 81 peer-reviewed studies published between 2015 and 2025 on gamified, AI-enabled digital learning environments in school science. The meta-analysis of experimental and quasi-experimental studies found a pooled standardized mean difference of 1.01 (95% CI 0.69–1.33) in science learning outcomes versus non-AI instructional conditions.

Read the study abstract

Background Gamified, AI-enabled digital learning environments (GAI-DLEs), integrating adaptive or generative AI with game-based design, are increasingly used in school science education to support personalized learning. However, consolidated evidence on their effectiveness, implementation models, and regional distribution remains limited, particularly in Central Asia. Methods Following PRISMA 2020 guidelines, a systematic search of Scopus and complementary databases identified peer-reviewed empirical studies pub…

The gain

A systematic review and meta-analysis of school studies found that students using gamified, AI-enabled learning environments scored markedly higher in science than peers in non-AI instruction (SMD = 1.01; 95% CI 0.69–1.33).

In brief

The effect was larger in secondary education (SMD 1.12) than in primary education (SMD 0.80), and studies using adaptive or generative AI tended to report bigger effects. Evidence on student engagement was generally positive but varied widely between settings.

The evidence base is uneven geographically, with Central Asia, including Kazakhstan, substantially underrepresented. The authors call for longitudinal, theory-driven studies to test which combinations of AI features, game mechanics and classroom integration produce lasting results.

Main points

  1. The search covered six databases (Web of Science, Scopus, ERIC, PsycINFO, PubMed and IEEE Xplore) for studies from January 2015 to December 2025, starting from 1,284 records.
  2. After deduplication, 962 unique records were screened, 150 full texts were assessed and 81 studies were included in the final synthesis.
  3. Eligible studies had to combine gamification and AI that used learner-generated data in a single integrated approach, enrol primary or secondary students, and compare against at least one comparison group.
  4. The pooled effect on science learning was SMD = 1.01 (95% CI 0.69–1.33; p < 0.001) against non-AI instruction.
  5. Secondary students showed a larger effect (SMD = 1.12; 95% CI 0.69–1.55) than primary students (SMD = 0.80; 95% CI 0.35–1.25).
  6. Studies with adaptive or generative AI systems tended to report larger effect sizes.
  7. Engagement findings were generally positive but varied considerably by context.

What the review found when it combined the studies

These are the review’s own pooled results, copied from its abstract. Truvace did not recalculate them.

  • Science learning outcomes of primary school students using gamified AI-enabled digital learning environments

    SMD 0.80 (95% CI 0.35 to 1.25)

    The review’s own words
    Effects were stronger in secondary education (SMD = 1.12; 95% CI: 0.69–1.55) than in primary education (SMD = 0.80; 95% CI: 0.35–1.25).

  • Science learning outcomes of secondary school students using gamified AI-enabled digital learning environments

    SMD 1.12 (95% CI 0.69 to 1.55)

    The review’s own words
    Effects were stronger in secondary education (SMD = 1.12; 95% CI: 0.69–1.55) than in primary education (SMD = 0.80; 95% CI: 0.35–1.25).

  • Science learning outcomes of school students using gamified AI-enabled digital learning environments

    SMD 1.01 (95% CI 0.69 to 1.33)

    The review’s own words
    GAI-DLEs demonstrated a significant positive effect on science learning outcomes compared with non-AI instructional conditions (SMD = 1.01; 95% CI: 0.69–1.33; p < 0.001).

Code checks every number above against the review’s text before it is shown. The short labels are an AI model’s reading of that text, so the review’s own sentence sits under each one. A pooled figure is only as strong as the studies behind it. How Truvace uses pooled results

The full story

The review followed PRISMA 2020 guidelines. Two reviewers screened titles, abstracts and full texts independently, with a third reviewer settling disagreements and Cohen's kappa used to check agreement between reviewers. The final search ran in January 2026.

To count, an intervention had to deliver gamification (points, badges, quests, progress indicators) and AI personalization as one integrated approach inside a digital learning environment. Studies where the two were separate components, or that covered higher education or informal learning, were excluded.

The meta-analysis used random-effects models, with subgroup analyses by education level, type of AI technology, publication period, study quality and region. The pooled estimate was 1.01 against non-AI conditions, with secondary schools at 1.12 and primary schools at 0.80.

The authors say the global evidence is geographically imbalanced, with Central Asia substantially underrepresented despite national digitalization agendas in Kazakhstan. They recommend longitudinal designs to test how AI functions, game mechanics and classroom integration combine to produce scalable outcomes.

Sources

1 on file
  1. Frontiers in Educationdoi:10.3389/feduc.2026.1754080
    Peer-reviewed2026-04-15

Talk it over

Four questions to start onWho gets this benefit, and who was left out of the study or story?

Start with a question

Review of 81 studies shows gamified AI lessons improved school science learninghttps://truvace.com/item/the-effects-of-gamified-ai-supported-digital-learning-environments-on-personaliz

  1. Who gets this benefit, and who was left out of the study or story?

    The gain A systematic review and meta-analysis of school studies found that students using gamified, AI-enabled learning environments scored markedly higher in science than peers in non-AI instruction (SMD = 1.01; 95% CI 0.69–1.33).

    Answer in the thread

  2. How do we know? What can this kind of evidence show, and what can’t it?

    The evidence This rests on a systematic review or meta-analysis, from Frontiers in Education.

    Answer in the thread

  3. What does it leave open? What else would you want to know before acting on it?

    The record’s own caveat The authors say the global evidence base is geographically imbalanced, with Central Asia substantially underrepresented, and that engagement results varied substantially by context.

    Answer in the thread

  4. Have you seen AI used this way where you study, work or live? Did it go the same way?

    Answer in the thread

The questions are the same on every record. The details under them are taken from this record as written.

What readers say

More from Education