- ICH GCP
- Register voor klinische proeven in de VS.
- Klinische proef NCT07841600
AI-Assisted Management of Pulmonary Nodules Found on Low-Dose CT in Health Screening (AI-NoduleCare)
Clinical Utility of Artificial Intelligence-Assisted Management Decisions for Pulmonary Nodules Detected by Low-Dose Computed Tomography in Health Screening: A Multicenter, Prospective, Cluster-Randomized Controlled Trial
Pulmonary nodules are frequently found during low-dose computed tomography (LDCT) health screening. The main challenge is not only detecting nodules, but also recommending the appropriate next step, such as routine follow-up, short-interval imaging follow-up, or specialist evaluation. This multicenter cluster-randomized trial will evaluate whether an artificial intelligence (AI)-assisted reporting workflow improves the appropriateness of pulmonary nodule management decisions in health examination settings without increasing under-management or missed referrals. Participating health examination branches, rather than individual participants, will be randomly assigned in a 1:1 ratio to a conventional reporting workflow or an AI-assisted reporting workflow. All final reports will be reviewed and signed by qualified physicians. An independent expert endpoint committee, blinded to study assignment and AI output, will determine the acceptable management range for each case. Approximately 2,000 adults with pulmonary nodules detected on LDCT will be included across at branches.
Studie Overzicht
Toestand
Studietype
Inschrijving (Geschat)
Fase
- Niet toepasbaar
Deelname Criteria
Geschiktheidscriteria
Leeftijden die in aanmerking komen voor studie
Accepteert gezonde vrijwilligers
Geslachten die in aanmerking komen voor studie
Beschrijving
Inclusion Criteria:
- Age 18 years or older.
- Undergoing chest low-dose computed tomography at a participating health examination branch during the study recruitment period.
- At least one pulmonary nodule is identified on the index LDCT and requires risk stratification and a management decision regarding follow-up, repeat imaging, or specialist evaluation.
- Thin-section reconstructed images are of sufficient quality for clinical interpretation and, where applicable, AI analysis.
- Required clinical risk information is available, including age, sex, smoking history, history of malignancy, family history of lung cancer, and available prior chest imaging.
- Included under the ethics committee-approved consent, simplified notification, waiver, and/or opt-out process, with no documented refusal of research data use.
Exclusion Criteria:
- Previously diagnosed lung cancer or currently receiving lung cancer-related treatment.
- Known pulmonary metastasis from another malignancy.
- Imaging findings that clearly require immediate entry into a lung cancer specialty diagnostic or treatment pathway and are not appropriate for routine pulmonary nodule risk-stratified management.
- An urgent thoracic condition requiring immediate management, such as pneumothorax, large pleural effusion, or acute pulmonary embolism.
- Severe imaging artifact, incompatible slice thickness or reconstruction, or a lesion type, imaging parameter, or disease extent outside the prespecified locked scope of the AI system.
- Previous enrollment in this study.
- Explicit refusal of research data use, or another reason judged by the investigator to make inclusion inappropriate.
Studie plan
Hoe is de studie opgezet?
Ontwerpdetails
- Primair doel: Screening
- Toewijzing: Gerandomiseerd
- Interventioneel model: Parallelle opdracht
- Masker: Dubbele
Wapens en interventies
Deelnemersgroep / Arm |
Interventie / Behandeling |
|---|---|
|
Experimenteel: AI-Assisted Pulmonary Nodule Reporting Workflow
Physicians first record and lock an initial pulmonary nodule management decision without viewing AI results. They then review locked-version AI outputs, including nodule characteristics, estimated malignancy risk, and a management recommendation, and issue the final physician-signed report. Physicians may accept, modify, or reject the AI recommendation. The AI cannot automatically sign reports or directly instruct participants. |
A locked-version artificial intelligence decision-support workflow applied after the physician records an initial assessment. The system displays pulmonary nodule location, size, density, morphologic features, estimated malignancy risk, and a suggested management category. The physician retains final responsibility. If the system fails, times out, or produces an abnormal output, the case returns to manual reporting. No online learning or automatic model updating is allowed during the trial. |
|
Actieve vergelijker: Conventional Pulmonary Nodule Reporting Workflow
Physicians interpret LDCT examinations and issue pulmonary nodule management recommendations using the participating branch's conventional clinical reporting workflow. Study AI output is not displayed. |
Standard manual LDCT interpretation and pulmonary nodule management recommendation by qualified physicians using the participating branch's routine reporting process, without access to study AI output. |
Wat meet het onderzoek?
Primaire uitkomstmaten
Uitkomstmaat |
Maatregel Beschrijving |
Tijdsspanne |
|---|---|---|
|
Proportion of Participants With an Appropriate Final Management Recommendation
Tijdsspanne: At the index LDCT report (Day 0)
|
Percentage of evaluable participants whose final physician recommendation is within the acceptable management range determined by the blinded independent expert endpoint committee. Recommendations are classified as routine or annual follow-up, short-interval imaging follow-up, or specialist evaluation/referral. The expert committee will complete adjudication using index data within approximately 30 days, but the participant-level outcome is the recommendation made at Day 0. |
At the index LDCT report (Day 0)
|
Secundaire uitkomstmaten
Uitkomstmaat |
Maatregel Beschrijving |
Tijdsspanne |
|---|---|---|
|
Proportion of Participants With Under-Management
Tijdsspanne: At the index LDCT report (Day 0)
|
Percentage of evaluable participants whose final physician recommendation is less intensive than the minimum acceptable management level determined by the blinded independent expert endpoint committee. |
At the index LDCT report (Day 0)
|
|
Proportion of Expert-Defined Referral Cases Missed by the Final Report
Tijdsspanne: At the index LDCT report (Day 0)
|
Among participants whom the blinded independent expert endpoint committee determines require specialist evaluation/referral, the percentage whose final physician report does not recommend specialist evaluation/referral. The denominator includes only expert-defined referral cases. |
At the index LDCT report (Day 0)
|
|
Proportion of Participants With Inappropriate Management Escalation
Tijdsspanne: At the index LDCT report (Day 0)
|
Percentage of evaluable participants whose final physician recommendation is more intensive than the maximum acceptable management level determined by the blinded independent expert endpoint committee. |
At the index LDCT report (Day 0)
|
|
Change in Decision Appropriateness After AI Review in the AI-Assisted Arm
Tijdsspanne: At the index LDCT report (Day 0)
|
In the AI-assisted arm, the physician's locked pre-AI decision will be compared with the final post-AI decision against the same expert-accepted management range. Results will include: (1) correction rate, the number changing from inappropriate to appropriate divided by the number with an inappropriate pre-AI decision; (2) AI-induced error rate, the number changing from appropriate to inappropriate divided by the number with an appropriate pre-AI decision; and (3) net correction rate, calculated as (number corrected minus number made incorrect) divided by all evaluable participants in the AI-assisted arm. These denominators must be locked in the statistical analysis plan before database lock. |
At the index LDCT report (Day 0)
|
|
Physician Response to the AI Recommendation
Tijdsspanne: During the index LDCT reporting session (Day 0)
|
Time in minutes from the start of physician image review to final report completion, as recorded by the reporting platform or study system. |
During the index LDCT reporting session (Day 0)
|
|
Proportion of AI-Assisted Cases With System Failure
Tijdsspanne: During the index LDCT reporting session (Day 0)
|
Percentage of eligible cases in the AI-assisted arm for which the AI system does not return a usable output because of processing failure, timeout, technical incompatibility, or an output meeting the prespecified abnormal-output fallback criteria. |
During the index LDCT reporting session (Day 0)
|
|
Proportion of Participants With a Pulmonary Nodule-Related Management Action Within 90 Days
Tijdsspanne: 90 days after the index LDCT examination (allowable window, ±14 days)
|
Percentage of participants with at least one documented pulmonary nodule-related management action during follow-up, including specialist evaluation, repeat chest CT, contrast-enhanced CT, PET-CT, biopsy, or surgery. Each component will also be summarized separately. Information will be obtained from available routine records, participant-provided records, or ethics-approved telephone follow-up. |
90 days after the index LDCT examination (allowable window, ±14 days)
|
|
Proportion of Participants With a Reporting-Workflow-Related Management or Data Security Adverse Event
Tijdsspanne: From the index LDCT report through 90 days after the index examination (allowable window, ±14 days)
|
Percentage of participants with a prespecified event potentially related to the assigned reporting workflow, including missed or substantially delayed evaluation of a high-risk nodule, an unnecessary invasive procedure, hospitalization or major psychological/economic burden caused by an erroneous recommendation, or a serious data security event. Serious events will also be reported according to applicable ethics and institutional requirements. |
From the index LDCT report through 90 days after the index examination (allowable window, ±14 days)
|
Medewerkers en onderzoekers
Studie record data
Bestudeer belangrijke data
Studie start (Geschat)
Primaire voltooiing (Geschat)
Studie voltooiing (Geschat)
Studieregistratiedata
Eerst ingediend
Eerst ingediend dat voldeed aan de QC-criteria
Eerst geplaatst (Werkelijk)
Updates van studierecords
Laatste update geplaatst (Werkelijk)
Laatste update ingediend die voldeed aan QC-criteria
Laatst geverifieerd
Meer informatie
Termen gerelateerd aan deze studie
Trefwoorden
Andere studie-ID-nummers
- AI-NC-2026-01
Informatie over medicijnen en apparaten, studiedocumenten
Bestudeert een door de Amerikaanse FDA gereguleerd geneesmiddel
Bestudeert een door de Amerikaanse FDA gereguleerd apparaatproduct
Deze informatie is zonder wijzigingen rechtstreeks van de website clinicaltrials.gov gehaald. Als u verzoeken heeft om uw onderzoeksgegevens te wijzigen, te verwijderen of bij te werken, neem dan contact op met register@clinicaltrials.gov. Zodra er een wijziging wordt doorgevoerd op clinicaltrials.gov, wordt deze ook automatisch bijgewerkt op onze website .