# Clinical Evidence and Sources

Citations and external references used by Laudos.AI across marketing surfaces, methodology footnotes and product claims.

## Radiologist workload and productivity
- Bruls RJM, Kwee RM. Workload for radiologists during on-call hours: dramatic increase in the past 15 years. *Insights into Imaging.* 2020;11(1):121. DOI: 10.1186/s13244-020-00925-z. https://doi.org/10.1186/s13244-020-00925-z
- Forsberg D, Rosipko B, Sunshine JL. Radiologists' Variation of Time to Read Across Different Procedure Types. *J Digital Imaging.* 2017;30(1):86-94. DOI: 10.1007/s10278-016-9911-z. https://doi.org/10.1007/s10278-016-9911-z
- McDonald RJ, Schwartz KM, Eckel LJ, et al. The effects of changes in utilization and technological advancements of cross-sectional imaging on radiologist workload. *Acad Radiol.* 2015;22(9):1191-1198.

## Radiology AI evidence and posture
- van Leeuwen KG, Schalekamp S, Rutten MJCM, et al. Artificial intelligence in radiology: 100 commercially available products and their scientific evidence. *European Radiology.* 2021;31(6):3797-3804.
- Recht MP, Dewey M, Dreyer K, et al. Integrating artificial intelligence into the clinical practice of radiology: challenges and recommendations. *European Radiology.* 2020;30(6):3576-3584.

## Brazilian regulatory references
- Lei Geral de Proteção de Dados (LGPD), Lei 13.709/2018 — https://www.planalto.gov.br/ccivil_03/_ato2015-2018/2018/lei/l13709.htm
- Resolução CFM 2.454/2026 (Inteligência Artificial em Medicina) — https://portal.cfm.org.br
- ANVISA RDC 657/2022 (Software como Dispositivo Médico — SaMD) — https://www.gov.br/anvisa/pt-br
- Resolução CFM 1.821/2007 (Prontuário Eletrônico, retenção 20 anos) — https://portal.cfm.org.br
- Marco Civil da Internet, Lei 12.965/2014 — https://www.planalto.gov.br/ccivil_03/_ato2011-2014/2014/lei/l12965.htm

## Radiology classifications referenced
- BI-RADS, 5th Edition — American College of Radiology, 2013. https://www.acr.org/Clinical-Resources/Reporting-and-Data-Systems/Bi-Rads
- TI-RADS (ACR) — Tessler FN et al. *J Am Coll Radiol.* 2017;14(5):587-595.
- LI-RADS v2018 — https://www.acr.org/Clinical-Resources/Reporting-and-Data-Systems/LI-RADS
- Lung-RADS v2022 — https://www.acr.org/Clinical-Resources/Reporting-and-Data-Systems/Lung-Rads
- PI-RADS v2.1 — https://www.acr.org/Clinical-Resources/Reporting-and-Data-Systems/PI-RADS
- O-RADS — Andreotti RF et al. *Radiology.* 2020;294(1):168-185 (US); MRI version 2020.
- RECIST 1.1 — Eisenhauer EA et al. *Eur J Cancer.* 2009;45(2):228-247.
- Bosniak classification update — Silverman SG et al. *Radiology.* 2019;292(2):475-488.
- Fleischner Society pulmonary nodules — MacMahon H et al. *Radiology.* 2017;284(1):228-243.
- ASPECTS — Barber PA et al. *Lancet.* 2000;355(9216):1670-1674.

## Internal production telemetry
- Source: copilot.laudos.ai production export.
- Methodology: TAT = time between editor open and signature, computed per finalized report (status = signed). Cohort: paying radiologists on the Pro plan over a 30-day rolling window, excluding internal QA. Verification: oi@laudos.ai.
- See: /pricing.md and /governance.md for full reproducibility notes.