# EviStreams: Human-in-the-Loop AI Data Extraction for Systematic Reviews in Medicine

arXiv: https://arxiv.org/abs/2609.27418 · HTML: https://mlsanity.com/paper/2609.27418/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 35 references that are in the map.
- First posted on arXiv 23 Sep 2026.

## Builds on (most cited first, 11 of 11)

- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://mlsanity.com/paper/2210.02406/) (2022)
- [Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs](https://mlsanity.com/paper/2406.11695/) (2024)
- [POTATO: The Portable Text Annotation Tool](https://mlsanity.com/paper/2212.08620/) (2022)
- [Trialstreamer: Mapping and Browsing Medical Evidence in Real-Time](https://mlsanity.com/paper/2005.10865/) (2020)
- [What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction](https://mlsanity.com/paper/2507.15152/) (2025)
- [ROBoto2: An Interactive System and Dataset for LLM-assisted Clinical Trial Risk of Bias Assessment](https://mlsanity.com/paper/2511.03048/) (2025)
- [ScheMatiQ: From Research Question to Structured Data through Interactive Schema Discovery](https://mlsanity.com/paper/2604.09237/) (2026)
- [DocSpiral: A Platform for Integrated Assistive Document Annotation through Human-in-the-Spiral](https://mlsanity.com/paper/2505.03214/) (2025)
- [ClinicalTrialsHub: Bridging Registries and Literature for Comprehensive Clinical Trial Access](https://mlsanity.com/paper/2512.08193/) (2025)
- [AutoForest: Automatically Generating Forest Plots from Biomedical Studies with End-to-End Evidence Extraction and Synthesis](https://mlsanity.com/paper/2606.02403/) (2026)

## Abstract (arXiv)

Systematic reviews underpin clinical guidelines, yet their data-extraction step is a major expert-labor bottleneck bound by a protocolized workflow: two reviewers extract each study independently, an adjudicator resolves disagreements, and the team keeps an auditable record of how every value was produced. Large language models can assist with extraction, but that assistance must fit established review protocols and preserve reproducibility. We present EviStreams, a live, open-source, no-code web platform that puts review teams in control of AI-assisted extraction at three key stages: program design (a structured decomposition approved before any code runs), field specification (typed field definitions calibrated from a pilot), and extracted predictions (reviewer-blinded dual review with adjudication). Working through a form builder, a domain expert defines typed fields rather than prompts, runs extraction over uploaded PDFs, inspects every value alongside the supporting passage it came from, and resolves a reviewer-blinded dual review into an auditable consensus export. An evaluation across four clinical corpora and three frontier model families, released with the system, shows that extraction quality is shaped far more by the field specification than by the choice of model. EviStreams is live at https://evistreams.com/demo and released under Apache-2.0.