Thoracic DiseasesNCT07846553
Artificial Intelligence Versus Anesthesiology Residents in Chest X-Ray Interpretation
An observational study of Thoracic Diseases, run by Çiğdem Ünal Kantekin at 1 site in Turkey (Türkiye).
Trial summary
This observational study will compare how accurately anesthesiology residents and an artificial intelligence system (hChestXR) identify abnormalities on chest X-rays. Approximately 35 volunteer anesthesiology residents at Kayseri City Hospital will review the same set of 150 anonymized posteroanterior chest… Read more about this study
- Who is it for?
- Ages 18 years and olderHealthy volunteers can take part
- Conditions the study is for
- Thoracic Diseases
- How many people
- 35 participants
- Where
- 1 siteTurkey (Türkiye)
- Study dates
- 15 Oct 2026to 15 Nov 2026
- Phase
- Observational
- Are there results?
- Not yet: the study is under way
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 18 years and older
- All sexes
- Healthy volunteers accepted
- Adult, Older adult
Study population: Approximately 35 adult anesthesiology and reanimation residents working at Kayseri City Hospital who volunteer and provide written informed consent. Enrollment refers to resident readers, not to the 150 retrospectively selected, anonymized chest radiographs used as the assessment dataset.
Who may be able to join
- An anesthesiology and reanimation resident working at Kayseri City Hospital.
- Voluntarily agrees to participate in the study.
- Provides written informed consent.
- Agrees to evaluate the posteroanterior chest radiographs presented in the study.
Who cannot join
- Failure to complete the 150-radiograph assessment.
- Withdrawal of consent before completion of the assessment.
Trial locations and contacts
1 site in 1 country. Contact the study team or a site near you to ask about taking part.
Turkey (Türkiye)1 site
Kayseri City Hospital
Kayseri, 38080
Çiğdem Ünal Kantekin, MD, +90 505 443 30 56, drcgdm@hotmail.com
About this study
Official title: Comparison of the Diagnostic Performance of an Artificial Intelligence System and Anesthesiology Residents in Interpreting Posteroanterior Chest Radiographs
This observational study will compare how accurately anesthesiology residents and an artificial intelligence system (hChestXR) identify abnormalities on chest X-rays. Approximately 35 volunteer anesthesiology residents at Kayseri City Hospital will review the same set of 150 anonymized posteroanterior chest radiographs selected from the hospital imaging archive. The set will include normal images and images showing findings such as infiltration, atelectasis, and pleural effusion. Two radiologists will independently assess the images and resolve disagreements by consensus to establish the reference standard. Residents will not see the radiologists' assessments or the artificial intelligence results while interpreting the images. The study will measure diagnostic accuracy and other measures of diagnostic performance. No additional imaging, treatment, or change in patient care is planned.
Read the detailed description
This single-center, cross-sectional, observational diagnostic accuracy study will be coordinated by the Department of Anesthesiology and Reanimation at Kayseri City Hospital. Volunteer resident assessments will be collected prospectively using retrospectively selected chest radiographs. The observational model is classified as Other because this is a comparative multi-reader, multi-case assessment of a fixed image set, without longitudinal follow-up.
A dataset of 150 posteroanterior chest radiographs will be selected from the hospital PACS to represent normal findings, common thoracic abnormalities, and a limited number of atypical or diagnostically challenging cases. The distribution of findings will be balanced to avoid marked overrepresentation or underrepresentation of particular abnormalities. All patient-identifying information will be removed before assessment.
Two radiologists will independently evaluate each radiograph. Disagreements will be resolved through joint review and consensus. Their final assessments will serve as the reference standard. The same radiographs will be analyzed by the hChestXR artificial intelligence system and independently interpreted by approximately 35 anesthesiology residents who provide informed consent. Residents will record suspected findings using a predefined multiple-choice assessment form and will be blinded to the radiologist and artificial intelligence assessments. Resident training year will also be recorded.
Diagnostic accuracy, sensitivity, specificity, positive predictive value, and negative predictive value will be calculated overall and by finding. Comparisons between resident and hChestXR performance will account for the paired image assessments and the multi-reader, multi-case structure of the data. McNemar testing will be used for appropriate paired comparisons, and analyses will account for variability across readers and radiographs. Agreement with the radiologist reference standard will be evaluated using Cohen's kappa. A multi-reader, multi-case approach will consider individual resident performance and variability across readers interpreting the same image set. Analyses will use SPSS version 31.0, with p < 0.05 considered statistically significant.
An a priori sample size calculation was performed to determine the number of resident readers. Assuming an absolute difference of 15 percentage points in diagnostic accuracy between anesthesiology residents and hChestXR, a standard deviation of 25 percentage points in reader-level accuracy, a two-sided significance level of 0.05, and 90% power, the required minimum sample size was 32 residents (standardized effect size, Cohen's d = 0.60). To allow for incomplete assessments or participant withdrawal, at least 35 anesthesiology residents are planned for enrollment. The 150 radiographs constitute the image dataset and are distinct from the enrolled resident participants.
The study involves no patient intervention. Resident assessment data will be coded and de-identified for analysis, and identifying information will remain confidential. The planned study period is October 15, 2026, through November 15, 2026. Ethics approval was granted by the Kayseri City Hospital Non-Interventional Clinical Research Ethics Committee on August 26, 2026 (decision number 1081).
- Conditions
- Thoracic Diseases
- Keywords
- Artificial Intelligence, Chest Radiography, Anesthesiology Residents, Diagnostic Accuracy, hChestXR
- Medical subject headings
- Thoracic Diseases
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
| Study group | Role | What they receive |
|---|---|---|
| Anesthesiology Residents | Approximately 35 volunteer anesthesiology and reanimation residents at Kayseri City Hospital will independently interpret 150 anonymized posteroanterior chest radiographs using a predefined multiple-choice form. Residents will be blinded to radiologist assessments and hChestXR outputs. Their diagnostic performance will be compared with hChestXR analysis of the same images, using the consensus of two radiologists as the reference standard. The artificial intelligence system is an image-level comparator, not a separate participant cohort. No treatment is assigned and no patient care is changed. |
What is being measured
The primary outcome is the main question the study is designed to answer.
Diagnostic Accuracy for Detection of Thoracic Abnormalities
Percentage of correctly classified image-finding pairs, calculated as (true positives + true negatives) / all evaluated image-finding classifications × 100, using the consensus of two radiologists as the reference standard. Accuracy will be calculated for each resident and for hChestXR overall and separately for each predefined thoracic finding.
Measured: During completion of the 150-radiograph assessment, within the 1-month study period
Secondary outcomes (5)
Sensitivity for Detection of Thoracic Abnormalities
Percentage of reference-positive classifications correctly identified: true positives / (true positives + false negatives) × 100. Sensitivity will be calculated for residents and hChestXR overall and by finding, using the consensus of two radiologists as the reference standard.
Measured: During completion of the 150-radiograph assessment, within the 1-month study period
Specificity for Detection of Thoracic Abnormalities
Percentage of reference-negative classifications correctly identified: true negatives / (true negatives + false positives) × 100. Specificity will be calculated for residents and hChestXR overall and by finding, using the consensus of two radiologists as the reference standard.
Measured: During completion of the 150-radiograph assessment, within the 1-month study period
Positive Predictive Value
Percentage of positive classifications confirmed by the radiologist reference standard: true positives / (true positives + false positives) × 100. Calculated for residents and hChestXR overall and by finding within the constructed study dataset.
Measured: During completion of the 150-radiograph assessment, within the 1-month study period
Negative Predictive Value
Percentage of negative classifications confirmed by the radiologist reference standard: true negatives / (true negatives + false negatives) × 100. Calculated for residents and hChestXR overall and by finding within the constructed study dataset.
Measured: During completion of the 150-radiograph assessment, within the 1-month study period
Agreement With the Radiologist Reference Standard
Agreement of resident interpretations and hChestXR classifications with the consensus radiologist reference standard will be assessed using Cohen's kappa. Cohen's kappa will be calculated separately for each resident and for hChestXR, with resident results summarized across readers. Kappa ranges from -1 to 1; 1 indicates perfect agreement, 0 agreement expected by chance, and negative values less agreement than expected by chance. Individual reader results will be evaluated within the multi-reader, multi-case framework.
Measured: During completion of the 150-radiograph assessment, within the 1-month study period
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted29 Sep 2026
- Study start15 Oct 2026 (estimated)
- Primary completion15 Nov 2026 (estimated)
- Study completion15 Nov 2026 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Publications (4)Papers the sponsor has linked to this study.
- Other trials for Thoracic DiseasesStudies of the same condition, open and under way.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Observational
- Observational model
- Other
- Time perspective
- Cross-sectional
- Enrolment
- 35 participants (estimated)
Sponsor and investigators
- Lead sponsor
- Çiğdem Ünal Kantekin
- Sponsor type
- Other government
- Responsible party
- Sponsor-investigator, Çiğdem Ünal Kantekin, Kayseri City Hospital
- Investigators
- Çiğdem Ünal Kantekin, MD, Principal investigator, Kayseri City Hospital
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07846553
- Sponsor's protocol ID
- KCH-PAAG-AI-2026-1081
- Status last verified
- Sep 2026
- First submitted
- 23 Sep 2026
- Last updated
- 29 Sep 2026
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- No: Individual participant data will not be shared with third parties, in accordance with the confidentiality provisions of the study protocol. Data will be used for scientific analyses, and findings will be disseminated in aggregate through presentations and publications.
Publications
Colquitt J, Jordan M, Court R, Loveman E, Parr J, Ghosh I, Auguste P, Patel M, Stinton C. Artificial intelligence software for analysing chest X-ray images to identify suspected lung cancer: an evidence synthesis early value assessment. Health Technol Assess. 2024 Aug;28(50):1-75. doi: 10.3310/LKRT4721.
PubMed 39254229Nam JG, Park S, Hwang EJ, Lee JH, Jin KN, Lim KY, Vu TH, Sohn JH, Hwang S, Goo JM, Park CM. Development and Validation of Deep Learning-based Automatic Detection Algorithm for Malignant Pulmonary Nodules on Chest Radiographs. Radiology. 2019 Jan;290(1):218-228. doi: 10.1148/radiol.2018180237. Epub 2018 Sep 25.
PubMed 30251934Rajpurkar P, Irvin J, Ball RL, Zhu K, Yang B, Mehta H, Duan T, Ding D, Bagul A, Langlotz CP, Patel BN, Yeom KW, Shpanskaya K, Blankenberg FG, Seekins J, Amrhein TJ, Mong DA, Halabi SS, Zucker EJ, Ng AY, Lungren MP. Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists. PLoS Med. 2018 Nov 20;15(11):e1002686. doi: 10.1371/journal.pmed.1002686. eCollection 2018 Nov.
PubMed 30457988Eisen LA, Berger JS, Hegde A, Schneider RF. Competency in chest radiography. A comparison of medical students, residents, and fellows. J Gen Intern Med. 2006 May;21(5):460-5. doi: 10.1111/j.1525-1497.2006.00427.x.
PubMed 16704388
Study at a glance
From the registry record, last updated by the sponsor on 29 Sep 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- Comparison of the Diagnostic Performance of an Artificial Intelligence System and Anesthesiology Residents in Interpreting Posteroanterior Chest Radiographs
- ClinicalTrials.gov ID
- NCT07846553
- Acronym / sponsor ID
- KCH-PAAG-AI-2026-1081
- Conditions
- Thoracic Diseases
- Keywords
- Artificial Intelligence, Chest Radiography, Anesthesiology Residents, Diagnostic Accuracy, hChestXR
- Study type
- Observational
- Recruitment status
- Not yet recruiting
- Enrolment
- 35 participants (estimated)
- Lead sponsor
- Çiğdem Ünal KantekinOther government
- Study start
- 15 Oct 2026 (estimated)
- Primary completion
- 15 Nov 2026 (estimated)
- Study completion
- 15 Nov 2026 (estimated)
- First posted
- 29 Sep 2026 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
This observational study will compare how accurately anesthesiology residents and an artificial intelligence system (hChestXR) identify abnormalities on chest X-rays. Approximately 35 volunteer anesthesiology residents at Kayseri City Hospital will review the same set of 150 anonymized posteroanterior chest radiographs selected from the hospital imaging archive. The set will include normal images and images showing findings such as infiltration, atelectasis, and pleural effusion. Two radiologists will independently assess the images and resolve disagreements by consensus to establish the reference standard. Residents will not see the radiologists' assessments or the artificial intelligence results while interpreting the images. The study will measure diagnostic accuracy and other measures of diagnostic performance. No additional imaging, treatment, or change in patient care is planned.
Detailed description
This single-center, cross-sectional, observational diagnostic accuracy study will be coordinated by the Department of Anesthesiology and Reanimation at Kayseri City Hospital. Volunteer resident assessments will be collected prospectively using retrospectively selected chest radiographs. The observational model is classified as Other because this is a comparative multi-reader, multi-case assessment of a fixed image set, without longitudinal follow-up.
A dataset of 150 posteroanterior chest radiographs will be selected from the hospital PACS to represent normal findings, common thoracic abnormalities, and a limited number of atypical or diagnostically challenging cases. The distribution of findings will be balanced to avoid marked overrepresentation or underrepresentation of particular abnormalities. All patient-identifying information will be removed before assessment.
Two radiologists will independently evaluate each radiograph. Disagreements will be resolved through joint review and consensus. Their final assessments will serve as the reference standard. The same radiographs will be analyzed by the hChestXR artificial intelligence system and independently interpreted by approximately 35 anesthesiology residents who provide informed consent. Residents will record suspected findings using a predefined multiple-choice assessment form and will be blinded to the radiologist and artificial intelligence assessments. Resident training year will also be recorded.
Diagnostic accuracy, sensitivity, specificity, positive predictive value, and negative predictive value will be calculated overall and by finding. Comparisons between resident and hChestXR performance will account for the paired image assessments and the multi-reader, multi-case structure of the data. McNemar testing will be used for appropriate paired comparisons, and analyses will account for variability across readers and radiographs. Agreement with the radiologist reference standard will be evaluated using Cohen's kappa. A multi-reader, multi-case approach will consider individual resident performance and variability across readers interpreting the same image set. Analyses will use SPSS version 31.0, with p < 0.05 considered statistically significant.
An a priori sample size calculation was performed to determine the number of resident readers. Assuming an absolute difference of 15 percentage points in diagnostic accuracy between anesthesiology residents and hChestXR, a standard deviation of 25 percentage points in reader-level accuracy, a two-sided significance level of 0.05, and 90% power, the required minimum sample size was 32 residents (standardized effect size, Cohen's d = 0.60). To allow for incomplete assessments or participant withdrawal, at least 35 anesthesiology residents are planned for enrollment. The 150 radiographs constitute the image dataset and are distinct from the enrolled resident participants.
The study involves no patient intervention. Resident assessment data will be coded and de-identified for analysis, and identifying information will remain confidential. The planned study period is October 15, 2026, through November 15, 2026. Ethics approval was granted by the Kayseri City Hospital Non-Interventional Clinical Research Ethics Committee on August 26, 2026 (decision number 1081).
Study design
- Observational model
- Other
- Time perspective
- Cross-sectional
- Number of arms
- 1
| Arm | Type | Receives |
|---|---|---|
| Anesthesiology Residents | – | –Approximately 35 volunteer anesthesiology and reanimation residents at Kayseri City Hospital will independently interpret 150 anonymized posteroanterior chest radiographs using a predefined multiple-choice form. Residents will be blinded to radiologist assessments and hChestXR outputs. Their diagnostic performance will be compared with hChestXR analysis of the same images, using the consensus of two radiologists as the reference standard. The artificial intelligence system is an image-level comparator, not a separate participant cohort. No treatment is assigned and no patient care is changed. |
Who may qualify
- Ages
- 18 years and older
- Sex
- All
- Healthy volunteers
- Accepted
- Age groups
- Adult, Older adult
- Study population
- Approximately 35 adult anesthesiology and reanimation residents working at Kayseri City Hospital who volunteer and provide written informed consent. Enrollment refers to resident readers, not to the 150 retrospectively selected, anonymized chest radiographs used as the assessment dataset.
Key inclusion criteria (4 listed)
- An anesthesiology and reanimation resident working at Kayseri City Hospital.
- Voluntarily agrees to participate in the study.
- Provides written informed consent.
- Agrees to evaluate the posteroanterior chest radiographs presented in the study.
Key exclusion criteria (2 listed)
- Failure to complete the 150-radiograph assessment.
- Withdrawal of consent before completion of the assessment.
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Primary outcome
Diagnostic Accuracy for Detection of Thoracic Abnormalities
Time frame: During completion of the 150-radiograph assessment, within the 1-month study period
Percentage of correctly classified image-finding pairs, calculated as (true positives + true negatives) / all evaluated image-finding classifications × 100, using the consensus of two radiologists as the reference standard. Accuracy will be calculated for each resident and for hChestXR overall and separately for each predefined thoracic finding.
5 secondary outcomes
Sensitivity for Detection of Thoracic Abnormalities
Time frame: During completion of the 150-radiograph assessment, within the 1-month study period
Specificity for Detection of Thoracic Abnormalities
Time frame: During completion of the 150-radiograph assessment, within the 1-month study period
Positive Predictive Value
Time frame: During completion of the 150-radiograph assessment, within the 1-month study period
Negative Predictive Value
Time frame: During completion of the 150-radiograph assessment, within the 1-month study period
Agreement With the Radiologist Reference Standard
Time frame: During completion of the 150-radiograph assessment, within the 1-month study period
Results and safety
This study is still under way. Results are not available in the source record yet.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 29 Sep 2026.
- Background: PubMed 39254229Colquitt J, Jordan M, Court R, Loveman E, Parr J, Ghosh I, Auguste P, Patel M, Stinton C. Artificial intelligence software for analysing chest X-ray images to identify suspected lung cancer: an evidence synthesis early value assessment. Health Technol Assess. 2024 Aug;28(50):1-75. doi: 10.3310/LKRT4721.
- Background: PubMed 30251934Nam JG, Park S, Hwang EJ, Lee JH, Jin KN, Lim KY, Vu TH, Sohn JH, Hwang S, Goo JM, Park CM. Development and Validation of Deep Learning-based Automatic Detection Algorithm for Malignant Pulmonary Nodules on Chest Radiographs. Radiology. 2019 Jan;290(1):218-228. doi: 10.1148/radiol.2018180237. Epub 2018 Sep 25.
- Background: PubMed 30457988Rajpurkar P, Irvin J, Ball RL, Zhu K, Yang B, Mehta H, Duan T, Ding D, Bagul A, Langlotz CP, Patel BN, Yeom KW, Shpanskaya K, Blankenberg FG, Seekins J, Amrhein TJ, Mong DA, Halabi SS, Zucker EJ, Ng AY, Lungren MP. Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists. PLoS Med. 2018 Nov 20;15(11):e1002686. doi: 10.1371/journal.pmed.1002686. eCollection 2018 Nov.
- Background: PubMed 16704388Eisen LA, Berger JS, Hegde A, Schneider RF. Competency in chest radiography. A comparison of medical students, residents, and fellows. J Gen Intern Med. 2006 May;21(5):460-5. doi: 10.1111/j.1525-1497.2006.00427.x.
- Individual participant dataSharing planned: No. Individual participant data will not be shared with third parties, in accordance with the confidentiality provisions of the study protocol. Data will be used for scientific analyses, and findings will be disseminated in aggregate through presentations and publications.
Related trials for Thoracic Diseases
RecruitingPhase 1/2
Study of INBRX-106 and INBRX-106 in Combination With Pembrolizumab (Keytruda®) in Subjects With Locally Advanced or Metastatic Solid Tumors (Hexavalent OX40 Agonist)
Solid Tumor, Non-Small Cell Lung Cancer
RecruitingObservational study
A Prospective ,Multicenter ,Non-interventional ,Real-world Study Observing Changes in Molecular Markers Osimertinib Targeted Therapy in EGFRm NSCLC
Non Small Cell Lung Cancer
Active, not recruiting
Streamlined Geriatric and Oncological Evaluation Based On IC Technology
Breast Cancer, Comorbidities and Coexisting Conditions
RecruitingPhase 3
A Study Evaluating Sotorasib Platinum Doublet Combination Versus Pembrolizumab Platinum Doublet Combination as a Front-Line Therapy in Participants With Stage IV or Advanced Stage IIIB/C Nonsquamous Non-Small Cell Lung Cancers (CodeBreaK 202)
Non-Small Cell Lung Cancer (NSCLC)
Active, not recruitingPhase 2
Datopotamab Deruxtecan (Dato-DXd, DS-1062a) in Advanced and/or Unresectable Non-Small Cell Lung Cancer
Metastatic Lung Cancer, Advanced Non Small Cell Lung Cancer
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part.
Çiğdem Ünal Kantekin, MD principal investigator
Kayseri City Hospital
1 site in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
An observational study of Thoracic Diseases, run by Çiğdem Ünal Kantekin at 1 site in Turkey (Türkiye).
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 4 inclusion and 2 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: opening soon, as of the sponsor's last update on 29 Sep 2026. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 1 site in Turkey (Türkiye). Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
This study is still under way. Results are not available in the source record yet.
How can a doctor refer a patient or contact the research team?
Contact Çiğdem Ünal Kantekin, MD (+90 505 443 30 56, drcgdm@hotmail.com), or a site near the patient. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Diagnostic Accuracy for Detection of Thoracic Abnormalities (time frame: During completion of the 150-radiograph assessment, within the 1-month study period). It is what the study was designed to measure, not a finding.
Where can I read the original study information?
On the ClinicalTrials.gov record for NCT07846553, which also lists 4 linked publications.
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 29 Sep 2026.