A Multicenter Cohort Study of AI-Based Methods for Pulmonary Nodule Diagnosis and Follow-up

ConditionsPulmonary Nodules Lung Neoplasms Artificial Intelligence (AI)

Trial statusNot yet recruiting

Trial phaseNot listed

Trial typeObservational

Biological sexAll

Age18+

SponsorShanghai East Hospital

About this trial

This is an observational, multicentre study. The primary objective of this study was to evaluate the diagnostic performance and clinical applicability of artificial intelligence models for pulmonary nodule segmentation, benign-malignant risk stratification, and follow-up management. We will collect CT images and medical data from participants at several hospitals. Participants will not receive any drugs or medical interventions.

Eligibility criteria

This trial does not accept healthy volunteers

Qualifiers

None

Disqualifiers

Poor CT image quality with severe artifacts that preclude AI-based analysis;

Expected survival <12 months or inability to complete follow-up;

History of prior ipsilateral lung malignancy or local treatment. -

Trial population

Consecutively enrolled, representative patients (aged ≥18 years, with a maximum nodule diameter of ≥3 mm and ≤30 mm) who underwent chest CT for routine clinical care and were found to have pulmonary nodules, including solid, part-solid, and pure ground-glass nodules.

Trial design

Design model

Cohort

Time perspective

Prospective

Treatments tested in this trial

Not listed

Trial groups

16,880 Participants

are grouped into 2 trial groups

Group A: Benign Pulmonary Nodule Group

Group B: Malignant Pulmonary Nodule Group

Trial outcomes

Primary outcomes

Diagnostic performance of the AI model for pulmonary nodule malignancy

Area under the receiver operating characteristic curve (AUC), sensitivity, and specificity of the AI model for classifying benign and malignant nodules, using pathology results or longitudinal stability as the reference standard.

Time frame

Up to 24 months after enrollment

Secondary outcomes

Risk stratification accuracy across different nodule sizes

The ability of the AI model to correctly stratify nodules into low, intermediate, and high-risk categories compared to clinical judgement.

Time frame

Up to 24 months

Locations

This trial has no locations.

Sponsors and contacts

Click on the lead sponsor to view all of their trials.

Shanghai East Hospital

Lead sponsor

Shanghai Chest Hospital of Shanghai Jiao Tong University

Collaborator

RenJi Hospital