# Deep generative AI models analyzing circulating orphan non-coding RNAs enable detection of early-stage lung cancer

Source: https://onco.cc/key-papers/paper-karimzadeh-oncrna-lung-cancer-nat-commun-2024/  
OnCo record `paper-karimzadeh-oncrna-lung-cancer-nat-commun-2024` (Key paper). Data CC BY-NC 4.0, attribute "Data from OnCo (onco.cc)"; commercial use needs a licence.

## TL;DR

Exai Bio's study of small RNAs found in tumours but not normal tissue, read from blood serum to detect lung cancer.

## Summary

In serum from 1,050 people with non-small cell lung cancer and matched controls, the Orion model achieved an overall sensitivity of 94 per cent (95% CI 87 to 98) at 87 per cent (95% CI 81 to 93) specificity across all stages on held-out validation data.

## Fields

- Kind: Key paper
- Last checked: 2026-11-04
- Journal: Nature Communications
- Year: 2024
- DOI: 10.1038/s41467-024-53851-9
- Authors: Karimzadeh M, Momen-Roknabadi A, Cavazos TB, et al.
- Findings: Sensitivity 94% at 87% specificity.
- What it means: Tumour-specific small RNAs are readable in serum; the specificity is too low for population screening as reported.
- Caveats: Case-control design; company authors.

## Sources

- Karimzadeh et al., Nat Commun 2024: https://doi.org/10.1038/s41467-024-53851-9
- PubMed: https://pubmed.ncbi.nlm.nih.gov/39572521/

## Connected records

- cancers: [Non-small-cell lung cancer](https://onco.cc/cancers/nsclc/)
- fronts: [Early Detection & Screening](https://onco.cc/fronts/early-detection/)
- technologies: [Liquid RNA biopsy (cell-free, vesicle and platelet RNA)](https://onco.cc/technologies/liquid-rna-biopsy/)
- companies: [Exai Bio](https://onco.cc/companies/exai-bio/)
- terms: [Biomarker](https://onco.cc/terms/biomarker/)

---
JSON: https://onco.cc/api/v1/entities/paper-karimzadeh-oncrna-lung-cancer-nat-commun-2024.json