qXR nodule flags lead to five early-stage lung cancer diagnoses

AI system

System: qXR
Model: Not assessed
Release: Not assessed
Application developer: Qure.ai
Role: Not assessed
Configuration: Not assessed
Inputs and outputs: Not assessed
Autonomy: Not assessed
Workflow: qXR running on routine chest X-rays ordered for non-respiratory indications. A pathway from AI flag to CT or PET-CT and biopsy.
Human oversight: Not assessed
Relation to AI: qXR's nodule flag on X-rays ordered for unrelated reasons prompted low-dose CT, with or without PET-CT, and biopsy in each case. The report does not say whether radiologists had independently reported the nodules. The AI's contribution thus rests on the authors' judgment that the cases would otherwise have been missed or delayed. One of ten authors is a Qure.ai employee and the study was funded by AstraZeneca.
AI contribution: qXR's nodule flag on X-rays ordered for unrelated reasons prompted low-dose CT, with or without PET-CT, and biopsy in each case. The report does not say whether radiologists had independently reported the nodules. The AI's contribution thus rests on the authors' judgment that the cases would otherwise have been missed or delayed. One of ten authors is a Qure.ai employee and the study was funded by AstraZeneca.

Benefits

Outcome identifiers: Not assessed
Benefit: CT/biopsy confirmed early-stage lung cancer in five adults; four had surgery
Category: Improved Physical Health
Status: Not assessed
Beneficiary groups: People.
Beneficiaries: Not assessed
Reach: Not assessed
Distribution and access: Not assessed
Duration: Not assessed
Expected?: Yes
Costs and harms: Not assessed

Measurement

Studies: Not assessed
Study design: Not assessed
Measurement: Not assessed
Setting and sample: Not assessed
Measures: CT/biopsy confirmed early-stage lung cancer in five adults; four had surgery
Comparison: Assumed alternative: routine chest X-ray reading without the AI
Results: Assumed comparison. Reference: would likely have been missed or delayed. Result: early-stage lung cancer in all five cases.
Additional value from AI: Not assessed
Limitations: Not assessed
Denominators: Not assessed
Materials for replication: Not assessed

Money

Kind of value: Not assessed
Amount: Not assessed
Currency and prices: Not assessed
Period and unit: Not assessed
Realization: Not assessed
Recipients and payers: Not assessed
Gross or net: Not assessed
Included costs: Not assessed
Comparison: Not assessed
Method: Not assessed
Return and payback: Not assessed

People and places

Participants: Developer: Qure.ai. Operator: Participating centers of the CREATE study, not named in the paper; the clinical authors are affiliated with Hacettepe University (Ankara) and with Aarthi Scans and Sri Ramachandra Medical College and Hospital (Chennai).
Jurisdictions: Developer: India.
Ownership and control: Not assessed
Dependencies: Not assessed
Cross-border connections: Not assessed
Geopolitical implications: Not assessed

Follow-up

Conditions for replication: Clinicians act on AI flags on films ordered for unrelated reasons. Tissue confirmation before treatment.
Replication attempts: Not assessed
Later findings: The series was published in March 2026 and gives no follow-up.
Availability: Not assessed
Institutional decision: Not assessed
Grounds: Not assessed
Action and result: Not assessed
Success criterion: Not assessed

Evidence

Source numbers: AIBD-0080-source-0001–0003
Citations: Numbered references below.
Language: Not assessed
Source relationships: Operator
Original evidence: Not assessed
Access and versions: Not assessed
Supported findings: Not assessed
Evidence links: Not assessed
Evidence strength: Not assessed
Missing evidence: Not assessed

Grades

Assessed benefits: People.
Depth: People: 3.
Reasons: People: Five adults without respiratory symptoms had early-stage lung cancer diagnosed, four with curative surgery. The authors report positive outcomes but no survival data.
Observed or intended: Not assessed
Rubric: Not assessed
Assessor and date: Not assessed
Alternative assessments: Not assessed
Fill: The deployer's account

Entry details

Kind

Not assessed

Related entries

Same developer, Qure.ai is listed among the chest X-ray classifier developers studied, and same task: those classifiers showed gender, racial and socioeconomic bias that underdiagnoses patients, the group qXR's nodule flags benefited.

Field

Healthcare - thoracic radiology / lung cancer. AI on routine chest X-rays in a multicentre study.

Purpose

qXR is built to detect abnormalities including pulmonary nodules on chest X-rays. Flagging incidental nodules is its intended function.

Dates

Date basis unassessed: 2023 (precision unassessed). Updated: 21 October 2026.

Stage

Not assessed

Version

SHA-256: b5fdd5f9bc54…

References

Other identifiers: AI Incident Database: 81.
Category mappings: Not assessed
Brief: Not assessed
Revisions: 7 revisions. Latest: 21 October 2026.

Sources

Case report Deployer

Koksal D, Govindarajan A, Baykan A, Durhan G, Sarinc S, Akpinar MG, Demirkazik F, Mathivanan KM, Vignesh P, Shivabasappa S (2026). A Case Series From a Multicentric Study: Can Artificial Intelligence (AI)-Enabled Chest X-Ray Assist in the Incidental Detection of Early-Stage Lung Cancers? Cureus 18(3):e104881.