# Data extraction for systematic reviews: fields, full text, and verification

> Chapter 5 of 8 of The Systematic Review E-book by AIPRA. After screening, reviewers extract structured data from the full text of included studies. The planning step is defining extraction fields — the specific items captured from each study, such as population characteristics, interventions, outcomes, effect sizes, and risk-of-bias items. Well-chosen fields determine what the results section can support, because they form the backbone of evidence tables, figures, and narrative synthesis. For accuracy, many teams extract in duplicate with two independent reviewers and a process to reconcile discrepancies.

- Source: https://aipra.co/systematic-review-ebook/extraction
- Topics: data extraction systematic review; extraction fields; data extraction form template; dual data extraction; evidence tables
- Last updated: 2026-09-05
- Licence: free to read; cite as shown at the end of this file.

## Key points

- Define extraction fields before extracting; the field list should be driven by what your synthesis and reporting actually require.
- Extraction fields determine what your results section can support — they are the backbone of evidence tables and figures.
- Dual independent extraction with discrepancy resolution is the quality standard, mirroring dual screening.
- AI-assisted extraction should attach an exact quotation or pointer to the source passage so reviewers can verify quickly and keep an audit trail.
- Machine-filled values are drafts. Verify against the source, especially outcomes, numeric results, and nuanced design features.

## Chapter outline

1. Defining extraction fields
2. Running extraction from full text
3. AI-assisted extraction and verification

## Questions this chapter answers

### What data should you extract in a systematic review?

Extract whatever your synthesis and reporting require: study identifiers, design, population characteristics, intervention or exposure details, comparators, outcome definitions, numeric results with measures of precision, follow-up duration, and risk-of-bias items. If a field will not feed analysis or reporting, it usually should not be extracted.

### Should two reviewers extract data independently?

Dual independent extraction with a reconciliation step is the accepted quality standard, because single extraction is error-prone for numeric outcomes. Some teams extract in duplicate for all fields, others for high-risk fields only, and the approach should be prespecified.

### Can AI extract data from full-text articles?

AI can propose values for many fields directly from full text, which reduces manual transcription. The important safeguard is traceability: each machine-filled value should be linked to the exact passage it came from, and a human should confirm it against the source before it enters analysis.

## How to cite this chapter

AIPRA. Data extraction for systematic reviews: fields, full text, and verification. In: The Systematic Review E-book. Updated 2026-09-05. Available from: https://aipra.co/systematic-review-ebook/extraction