Otto-SR

Compiled by

Dean Giustini, UBC Biomed librarian, dean.giustini@ubc.ca

Updated

9 November 2025 | Part of Knowledge Synthesis (KS) & Artificial Intelligence (AI) Search Wiki 2025 & A to Z Listing

Introduction

Otto-SR is an AI-powered platform designed to automate and enhance the process of conducting systematic reviews (SRs). As of August 2025, the tool has not been released publicly. Otto-SR is led by a University of Toronto medical student, Christian Cao; see his medRxiv paper.

In 2025, consulting SRs is key in patient care and evidence-based decision-making. Although this had been true in fields such as public health and medicine for a while, it is increasingly so in disciplines in the social and applied sciences. For its part, Otto-SR uses large language models (LLMs), such as OpenAI's GPT-4.1 for screening and o3-mini for data extraction, to perform tasks such as literature screening and data extraction. In the company's published medrXiv paper, the authors state that the tool outperformed human-led SR workflows, achieving 96.7% sensitivity and 97.9% specificity in screening (compared to 81.7% and 98.1% for humans) and 93.1% accuracy in data extraction (compared to 79.7% for humans). The company says that the tool can complete reviews significantly faster than a year-long process typical for human researchers.

In its testing, it updated 12 Cochrane reviews in two days, identifying 78% more relevant studies than human screening. The platform emphasizes transparency through explainable AI (XAI), providing source-linked reasoning for decisions, and is research-grade reproducible, having benchmarked publications such as the Annals of Internal Medicine. Developed by a team from Harvard, MIT, the University of Toronto, and former Stripe engineers, Otto-SR is advised by experts like George M. Church and collaborates with Cochrane France. It’s currently in preview, available to early sign-ups at ottosr.com.

Bottom line: For health sciences librarians, otto-SR might support their work with health professionals but we just don't know. However, its underlying AI technologies raises concerns for those interested in scientific accuracy, transparency and rigour in performing reviews. Note information provided to you on this page is changing, so check the tool's website for the current information (or discuss with a librarian). I like to elucidate the distinction between searching for sources and searching for answers; LLMs provide the second while hiding the first.

Presentation (audio) generated by AI

Note: This presentation is generated by AI, not real presenters; still, some of it will be informative.

Who is behind Otto-SR?

Christian Cao, MD Student, University of Toronto https://www.linkedin.com/in/christian-cao-275b78190

Librarian criticism

Note: Despite speaking to developers, and offering suggestions, I cannot make an assessment of Otto-SR as of this writing (July 29th, 2025) as I do not have access to it. However, they did offer to share a beta version when available.

References

Cao C, Arora R, Cento P, Manta K, Farahani E, Cecere M, Selemon A, Sang J, Gong LX, Kloosterman R, Jiang S. Automation of Systematic Reviews with Large Language Models. medRxiv. 2025 Jun 13:2025-06. https://www.medrxiv.org/content/10.1101/2025.06.13.25329541v2
Roy A. Perplexity (product review). Journal of the Canadian Health Libraries Association / Journal De l’Association Des bibliothèques De La Santé Du Canada. 2025 Aug 1;46(2):47.
Soetikno BT, Nielsen CS, Pollreisz A, Ting DS. Toward autonomous discovery: agentic AI and the future of Ophthalmic research. Current Opinion in Ophthalmology.:10-97.
Van Quaquebeke N, Tonidandel S, Banks GC. Beyond efficiency: How artificial intelligence (AI) will reshape scientific inquiry and the publication process. The Leadership Quarterly. 2025 Jul 5:101895. https://www.sciencedirect.com/science/article/pii/S1048984325000347

Disclaimer

Note: Please use your critical reading skills while reading entries. No warranties, implied or actual, are granted for any health or medical search or AI information obtained while using these pages. Check with your librarian for more contextual, accurate information.