# Sybil (MIT/MGH lung cancer risk from CT)

Source: https://onco.cc/technologies/sybil/  
OnCo record `sybil` (Technology). Data CC BY-NC 4.0, attribute "Data from OnCo (onco.cc)"; commercial use needs a licence.

## TL;DR

Predicts a person's six-year lung cancer risk from one low-dose CT, even when no nodule is visible.

## Summary

Sybil is a 3D convolutional neural network from MIT and MGH that takes a single low-dose CT of the chest and outputs a person's risk of lung cancer over the next six years, trained on time-to-cancer rather than on visible nodules. The JCO 2023 paper trained it on National Lung Screening Trial (NLST) CTs and validated it at MGH and in Taiwan, and the code is open source. It is aimed at screening programmes, where it is being tested to personalise screening intervals, lengthening them for low-risk people and shortening them for high-risk ones. The model was trained on screening populations, so its performance in people outside screening criteria, such as never-smokers, is less certain, and prospective trials of interval adjustment are still needed. For a newcomer: Sybil reads one screening CT and says how likely lung cancer is in the coming years, even before anything is visible.

## Fields

- Kind: Technology
- Status: emerging
- Last checked: 2026-09-08
- Tags: risk-model; radiology
- Principle: 3D CNN over the whole CT volume trained on time-to-cancer.
- Since: 2023
- Strengths: Open, externally validated
- Limitations: Trained on screening populations

## Sources

- JCO 2023: https://doi.org/10.1200/JCO.22.01345

## Connected records

- cancers: [Non-small-cell lung cancer](https://onco.cc/cancers/nsclc/)
- fronts: [AI & Computation](https://onco.cc/fronts/ai-computation/), [Early Detection & Screening](https://onco.cc/fronts/early-detection/)
- technologies: [AI in radiology](https://onco.cc/technologies/radiology-ai-screening/), [CT (computed tomography)](https://onco.cc/technologies/ct/)
- institutions: [Massachusetts General Hospital Cancer Center](https://onco.cc/institutions/mgh/)
- key papers: [Sybil: A Validated Deep Learning Model to Predict Future Lung Cancer Risk From a Single Low-Dose Chest Computed Tomography](https://onco.cc/key-papers/paper-mikhael-j-clin-oncol/)
- collections: [NCI CDAS: NLST and PLCO screening trial data](https://onco.cc/collections/cdas-nlst-plco/)
- roadmaps: [AI in oncology roadmap: pattern readers → foundation models → agents in the workflow](https://onco.cc/roadmaps/ai-oncology-roadmap/), [AI in the oncology clinic: from narrow cleared tools to multimodal decision support](https://onco.cc/roadmaps/ai-oncology-clinic/)
- drugs: [Optellum Virtual Nodule Clinic](https://onco.cc/drugs/optellum-virtual-nodule-clinic/)

---
JSON: https://onco.cc/api/v1/entities/sybil.json