> For the complete documentation index, see [llms.txt](https://docs.nested-knowledge.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.nested-knowledge.com/review-workflow/meta-analytical-extraction/smart-ma-extraction.md).

# Smart MA Extraction (beta)

Learn how to generate meta-analytical data automatically with Smart MA Extraction.

**Smart MA Extraction (SMAE),** in *beta,* reads your included studies' full texts and populates your meta-analytical hierarchy automatically from study tables. This extracted data populates Quantitative Synthesis without manual extraction study by study.

SMAE is best suited to quickly validating a research hypothesis or running an exploratory meta-analysis on a smaller set of studies, rather than as the default extraction method for every review. See the requirements below for its current limits.

### Before You Begin

Three conditions need to be in place:

* **Studies are included.** If your nest has multiple screening rounds, studies must be included at the final screening stage to qualify.
* **Full texts are uploaded**, and contain tabular data. SMAE reads tables in full texts — it doesn't work from abstracts, and won't extract quantitative data from text alone.
* **Fewer than 30 studies are included.** At this stage, SMAE works reliably below this threshold.

### Generate With Smart MA Extraction

{% stepper %}
{% step %}

#### Turn On MA Extraction

In [Nest Settings](/your-nests/nest-settings.md), confirm **Smart Tags** is on (it is by default) and turn on **Meta-Analytical Extraction** just below it. MA Extraction then appears as a module in the left-hand menu.

<figure><img src="https://305208404-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fxb7uNGATUgwQAjDVQRXG%2Fuploads%2FGJ9glsB38VKQ3cguK0uz%2Fsmae%20settings.png?alt=media&amp;token=5f07322c-982f-423e-9c66-b0edfd33b31d" alt=""><figcaption></figcaption></figure>
{% endstep %}

{% step %}

#### Open Configure MA Extraction

Select **Configure** **MA Extraction** <i class="fa-gear">:gear:</i> in the left-hand menu. If you've already built a tag hierarchy, it's shown here — but building one first isn't necessary to use SMAE. SMAE configures its own hierarchy independently, and doesn't affect any hierarchy or extracted data you already have.

<figure><img src="https://305208404-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fxb7uNGATUgwQAjDVQRXG%2Fuploads%2FbGWAaC6yyVrZ5QyjTHXS%2Fextract%20sparkle.png?alt=media&amp;token=ea1c3a2c-abc3-4099-bf48-daddf9f26b61" alt=""><figcaption></figcaption></figure>
{% endstep %}

{% step %}

#### Enter Your Research Question And Extract

Select **Extract** in the upper left. In the modal, confirm or refine your research question — pre-filled if you've already used **Smart Search, Smart Screener** or **Core Smart Tags**. Detail in the question about which interventions and data elements matter most improves what SMAE extracts, alongside full texts with informative tables.

In Single MA Extraction mode (the default), select **Extract** directly and the result is assigned as final, though still editable. In Dual mode, you also have the option to extract as a single reviewer.

Select **Extract** to begin. Generation runs in the background; check progress from the icon in the top right.

<figure><img src="https://305208404-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fxb7uNGATUgwQAjDVQRXG%2Fuploads%2FkkFXAucNOWPTnrslO5o6%2Fsmae%20modal.png?alt=media&amp;token=cf2ea0cc-0098-4173-80f5-13e51dd8fc6e" alt=""><figcaption></figcaption></figure>
{% endstep %}

{% step %}

#### Review Extracted Data

Once generation finishes, the configured hierarchy appears on Configure MA Extraction, and extracted data is available in the **MA Extraction** module or under the **MA Extract** tab in Study Inspector. Each value links back to the table it came from, so you can verify it against the source. Every extracted value stays editable.

<figure><img src="https://305208404-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fxb7uNGATUgwQAjDVQRXG%2Fuploads%2FGtSdRXZl19VPBSYUfgyd%2Fsmae%20extract.png?alt=media&amp;token=3be65d2b-0b87-4bb9-8bc5-f35d7188e281" alt=""><figcaption></figcaption></figure>
{% endstep %}
{% endstepper %}

### Where Smart MA Extraction Output Shows Up

Extracted data elements appear in [Quantitative Synthesis](/review-workflow/synthesis/navigate-synthesis-outputs/quantitative-synthesis.md) at every stage of the workflow, including within the NMA interface, where you can drill into individual interventions. You can also export the extracted data as a spreadsheet from Study Inspector — filter to the studies of interest, then select **Download → Meta-Analytical Extracted Data**.

### FAQs

<details>

<summary>Does Smart MA Extraction work from abstracts if a study has no full text?</summary>

No. SMAE reads tables in full texts only, so a study without an uploaded full text — or without tabular data in it — won't be extracted.

</details>

<details>

<summary>What happens if I run Smart MA Extraction with more than 30 included studies?</summary>

The tool will fail to run in Background Jobs.

</details>

<details>

<summary>Does Smart MA Extraction overwrite data I've already extracted manually?</summary>

No. SMAE configures and extracts independently of any existing hierarchy or extracted data — it doesn't affect what's already there.

</details>

<details>

<summary>Can I edit data that Smart MA Extraction generated?</summary>

Yes — every extracted value is editable after generation, the same as manually extracted data.

</details>

<details>

<summary>Does Smart MA Extraction work in Dual MA Extraction mode?</summary>

Yes — you have the option to extract as a single reviewer, feeding into the same adjudication workflow as manual dual extraction. See [Configure Meta-Analytical Extraction](/review-workflow/meta-analytical-extraction/configure-meta-analytical-extraction.md) to set this up.

</details>

### Next Steps

<table data-card-size="large" data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><i class="fa-sliders">:sliders:</i><br><strong>Configure Meta-Analytical Extraction</strong></td><td>Review or adjust the interventions and data elements SMAE generated.</td><td><a href="/review-workflow/meta-analytical-extraction/configure-meta-analytical-extraction.md">Configure Meta-Analytical Extraction</a></td></tr><tr><td><i class="fa-calculator">:calculator:</i><br><strong>Extract Meta-Analytical Data</strong></td><td>Extract or edit data manually, study by study.</td><td><a href="/review-workflow/meta-analytical-extraction/extract-meta-analytical-data.md">Extract Meta-Analytical Data</a></td></tr><tr><td><i class="fa-chart-line">:chart-line:</i><br><strong>Quantitative Synthesis</strong></td><td>View pooled estimates and Network Meta-Analysis outputs.</td><td><a href="/review-workflow/synthesis/navigate-synthesis-outputs/quantitative-synthesis.md">Quantitative Synthesis</a></td></tr></tbody></table>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.nested-knowledge.com/review-workflow/meta-analytical-extraction/smart-ma-extraction.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.