Pneumonia; Pulmonary InfectionNCT07895290
A Multicenter Randomized Trial of CT-Based AI Decision Support for Early Pneumonia Care
A study testing CT-Based AI Decision Support for Pneumonia in people with Pneumonia; Pulmonary Infection, run by Union Hospital, Tongji Medical College, Huazhong University of Science and Technology at 1 site in China.
Trial summary
Adults hospitalized with pneumonia who need new or increased oxygen support or have defined immunocompromise will be assigned to usual care with or without access to a CT-based AI report. The report summarizes likely pathogen classes, lung involvement, and short-term deterioration risk. Read more about this study
- Who is it for?
- Ages 18 years and older
- Conditions the study is for
- Pneumonia; Pulmonary Infection
- What is being tested?
- CT-Based AI Decision Support for Pneumonia
- Type of treatment
- Medical device
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 4,800 participants
- Where
- 1 siteChina
- Study dates
- 1 Jan 2026to Mar 2028
- Phase
- Interventional
- 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
- No healthy volunteers
- Adult, Older adult
Who may be able to join
- Hospitalized with suspected or confirmed pneumonia and new or progressive infection-compatible chest CT abnormalities.
- At increased clinical risk: new or increased oxygen requirement above the stable pre-illness baseline attributable to the current pneumonia, OR protocol-defined immunocompromise.
- A clinically indicated CT meeting the frozen input-quality criteria is available. Randomize within 24 hours after that CT and within 48 hours of documented recognition of the current pneumonia episode.
- No primary qualifying organ support earlier in the current episode, at baseline, or already clinically indicated before allocation.
- Written informed consent from the participant or an authorized representative before randomization.
Who cannot join
- No interpretable CT suitable for the locked model; a noninfectious diagnosis fully explains the findings without suspected concomitant pneumonia.
- Qualifying invasive respiratory or circulatory support in the current episode, including support already clinically indicated even if not yet delivered.
- Previous randomization in this trial; a concurrent interventional study that conflicts with the AI care strategy.
- Known pregnancy, outside the initial intended-use population; breastfeeding alone is not an exclusion.
- Exclusive comfort-focused care or a pre-existing ceiling of care that rules out both invasive ventilation and vasopressor support.
- Consent cannot be obtained under the approved arrangements.
Trial locations and contacts
1 site in 1 country. Contact the study team or a site near you to ask about taking part.
China1 site, 1 recruiting
- Recruiting
Union Hospital, Tongji Medical College, Huazhong University of Science and Technology
Wuhan, Hubei, 430000
Xiaoyu Han, +8618202771604, xiaoyuhan1123@163.com
About this study
Official title: Diagnosis of Infectious Pneumonia and Detection of Unusual Infections Using Medical Imaging and Artificial Intelligence
Adults hospitalized with pneumonia who need new or increased oxygen support or have defined immunocompromise will be assigned to usual care with or without access to a CT-based AI report. The report summarizes likely pathogen classes, lung involvement, and short-term deterioration risk. Clinicians review the report alongside images and clinical evidence and retain responsibility for testing and treatment. The trial asks whether AI-assisted care reduces death or new invasive respiratory or circulatory support within 28 days. Patients are followed after discharge through day 90.
Read the detailed description
This pragmatic, multicenter superiority trial uses individual 1:1 randomization and blinded outcome adjudication. Patients must be enrolled early in the pneumonia episode and before any qualifying primary organ-support event. Both groups receive the same scheduled clinical reviews and access to routine investigations. Only the AI group receives patient-specific AI results. The trial estimates the effect of offering the defined AI-assisted care strategy, including cases of report failure or clinician disagreement.
The intervention is evaluated through a prespecified sequence of evidence: report delivery and review; changes in pathogen testing, antimicrobial treatment, and monitoring; and patient outcomes. Technical diagnostic performance is secondary. All randomized patients enter the primary intention-to-treat analysis, including those subsequently found to have a noninfectious diagnosis. Recruitment spans multiple seasons and includes general respiratory, infectious-disease, and hematology services without requiring a hematologic disorder.
- Conditions
- Pneumonia; Pulmonary Infection
- Being tested
- CT-Based AI Decision Support for Pneumonia
- Keywords
- Artificial intelligence; chest CT; clinical decision support; pathogen classification; organ support; randomized controlled trial.
- Medical subject headings
- Pneumonia
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
CT-Based AI Decision Support for PneumoniaDevice
A locked CT-based artificial intelligence (AI) clinical decision-support system will analyze chest CT scans obtained as part of routine clinical care for patients with pneumonia. The system provides probabilities for predefined pathogen classes, quantitative assessment of pulmonary lesion extent, longitudinal changes when prior CT scans are available, and estimates of short-term clinical deterioration risk.
For patients assigned to the intervention group, the AI-generated report will be made available to treating clinicians, with a target availability within one hour after randomization. Clinicians will review the AI findings alongside the original CT images and other clinical information within two hours and document any resulting changes in diagnosis, further testing, treatment, or monitoring.
The AI system supports clinical decision-making but does not replace physician judgment. Additional CT scans are not required, and subsequent clinically indicated scans may also be analyzed.
| Study group | Role | What they receive |
|---|---|---|
| AI-Assisted Pneumonia Care | Experimental | Usual care plus access to the locked AI report and documented review of its relevance to diagnosis and management. Receives: Device: CT-Based AI Decision Support for Pneumonia |
| Usual Pneumonia Care | No intervention | The same clinical review schedule and documentation, without access to trial AI outputs. |
What is being measured
The primary outcome is the main question the study is designed to answer.
Death or New Invasive Respiratory or Circulatory Support Within 28 Days
Measured: From randomization to 28 completed days, including events after discharge, readmission, or transfer.
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted26 Oct 2026
- Study start1 Jan 2026
- Primary completionJan 2028 (estimated)
- Study completionMar 2028 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Publications (5)Papers the sponsor has linked to this study.
- Other trials for Pneumonia; Pulmonary InfectionStudies 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
- Interventional
- Phase
- Phase N/A
- Primary purpose
- Treatment
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Masking
- Single blind
- Who is masked
- Outcomes assessor
- Enrolment
- 4,800 participants (estimated)
Sponsor and investigators
- Lead sponsor
- Union Hospital, Tongji Medical College, Huazhong University of Science and Technology
- Sponsor type
- University, hospital or other
- Responsible party
- Sponsor
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07895290
- Sponsor's protocol ID
- WHUH-PNA-AI-RCT-2026-01
- Other IDs
- 82672507, 2026JCYJ026
- Status last verified
- Oct 2026
- First submitted
- 19 Oct 2026
- Last updated
- 26 Oct 2026
- Results posted
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- Yes: Share a de-identified analysis dataset and data dictionary supporting the primary publication through controlled access. Raw imaging and directly identifying records are excluded from routine release.
Publications
Hopewell S, Chan AW, Collins GS, Hrobjartsson A, Moher D, Schulz KF, Tunn R, Aggarwal R, Berkwits M, Berlin JA, Bhandari N, Butcher NJ, Campbell MK, Chidebe RCW, Elbourne D, Farmer A, Fergusson DA, Golub RM, Goodman SN, Hoffmann TC, Ioannidis JPA, Kahan BC, Knowles RL, Lamb SE, Lewis S, Loder E, Offringa M, Ravaud P, Richards DP, Rockhold FW, Schriger DL, Siegfried NL, Staniszewska S, Taylor RS, Thabane L, Torgerson D, Vohra S, White IR, Boutron I. CONSORT 2025 statement: updated guideline for reporting randomised trials. BMJ. 2025 Apr 14;389:e081123. doi: 10.1136/bmj-2024-081123.
PubMed 40228833Chan AW, Boutron I, Hopewell S, Moher D, Schulz KF, Collins GS, Tunn R, Aggarwal R, Berkwits M, Berlin JA, Bhandari N, Butcher NJ, Campbell MK, Chidebe RCW, Elbourne DR, Farmer AJ, Fergusson DA, Golub RM, Goodman SN, Hoffmann TC, Ioannidis JPA, Kahan BC, Knowles RL, Lamb SE, Lewis S, Loder E, Offringa M, Ravaud P, Richards DP, Rockhold FW, Schriger DL, Siegfried NL, Staniszewska S, Taylor RS, Thabane L, Torgerson DJ, Vohra S, White IR, Hrobjartsson A. SPIRIT 2025 statement: updated guideline for protocols of randomised trials. BMJ. 2025 Apr 28;389:e081477. doi: 10.1136/bmj-2024-081477.
PubMed 40294953Cruz Rivera S, Liu X, Chan AW, Denniston AK, Calvert MJ; SPIRIT-AI and CONSORT-AI Working Group; SPIRIT-AI and CONSORT-AI Steering Group; SPIRIT-AI and CONSORT-AI Consensus Group. Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI extension. Nat Med. 2020 Sep;26(9):1351-1363. doi: 10.1038/s41591-020-1037-7. Epub 2020 Sep 9.
PubMed 32908284Liu X, Cruz Rivera S, Moher D, Calvert MJ, Denniston AK; SPIRIT-AI and CONSORT-AI Working Group. Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension. Nat Med. 2020 Sep;26(9):1364-1374. doi: 10.1038/s41591-020-1034-x. Epub 2020 Sep 9.
PubMed 32908283Gohil SK, Septimus E, Kleinman K, Varma N, Avery TR, Heim L, Rahm R, Cooper WS, Cooper M, McLean LE, Nickolay NG, Weinstein RA, Burgess LH, Coady MH, Rosen E, Sljivo S, Sands KE, Moody J, Vigeant J, Rashid S, Gilbert RF, Smith KN, Carver B, Poland RE, Hickok J, Sturdevant SG, Calderwood MS, Weiland A, Kubiak DW, Reddy S, Neuhauser MM, Srinivasan A, Jernigan JA, Hayden MK, Gowda A, Eibensteiner K, Wolf R, Perlin JB, Platt R, Huang SS. Stewardship Prompts to Improve Antibiotic Selection for Pneumonia: The INSPIRE Randomized Clinical Trial. JAMA. 2024 Jun 18;331(23):2007-2017. doi: 10.1001/jama.2024.6248.
PubMed 38639729
Study at a glance
From the registry record, last updated by the sponsor on 26 Oct 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- Diagnosis of Infectious Pneumonia and Detection of Unusual Infections Using Medical Imaging and Artificial Intelligence
- ClinicalTrials.gov ID
- NCT07895290
- Acronym / sponsor ID
- WHUH-PNA-AI-RCT-2026-01
- Conditions
- Pneumonia; Pulmonary Infection
- Keywords
- Artificial intelligence; chest CT; clinical decision support; pathogen classification; organ support; randomized controlled trial.
- Study type
- Interventional
- Recruitment status
- Recruiting
- Enrolment
- 4,800 participants (estimated)
- Lead sponsor
- Union Hospital, Tongji Medical College, Huazhong University of Science and TechnologyUniversity, hospital or other
- Study start
- 1 Jan 2026 (actual)
- Primary completion
- Jan 2028 (estimated)
- Study completion
- Mar 2028 (estimated)
- First posted
- 26 Oct 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.
Adults hospitalized with pneumonia who need new or increased oxygen support or have defined immunocompromise will be assigned to usual care with or without access to a CT-based AI report. The report summarizes likely pathogen classes, lung involvement, and short-term deterioration risk. Clinicians review the report alongside images and clinical evidence and retain responsibility for testing and treatment. The trial asks whether AI-assisted care reduces death or new invasive respiratory or circulatory support within 28 days. Patients are followed after discharge through day 90.
Detailed description
This pragmatic, multicenter superiority trial uses individual 1:1 randomization and blinded outcome adjudication. Patients must be enrolled early in the pneumonia episode and before any qualifying primary organ-support event. Both groups receive the same scheduled clinical reviews and access to routine investigations. Only the AI group receives patient-specific AI results. The trial estimates the effect of offering the defined AI-assisted care strategy, including cases of report failure or clinician disagreement.
The intervention is evaluated through a prespecified sequence of evidence: report delivery and review; changes in pathogen testing, antimicrobial treatment, and monitoring; and patient outcomes. Technical diagnostic performance is secondary. All randomized patients enter the primary intention-to-treat analysis, including those subsequently found to have a noninfectious diagnosis. Recruitment spans multiple seasons and includes general respiratory, infectious-disease, and hematology services without requiring a hematologic disorder.
Study design
- Primary purpose
- Treatment
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Masking
- Single blind (outcomes assessor)
- Number of arms
- 2
| Arm | Type | Receives |
|---|---|---|
| AI-Assisted Pneumonia Care | Experimental | Device: CT-Based AI Decision Support for PneumoniaUsual care plus access to the locked AI report and documented review of its relevance to diagnosis and management. |
| Usual Pneumonia Care | No intervention | –The same clinical review schedule and documentation, without access to trial AI outputs. |
Who may qualify
- Ages
- 18 years and older
- Sex
- All
- Healthy volunteers
- Not accepted
- Age groups
- Adult, Older adult
Key inclusion criteria (5 listed)
- Hospitalized with suspected or confirmed pneumonia and new or progressive infection-compatible chest CT abnormalities.
- At increased clinical risk: new or increased oxygen requirement above the stable pre-illness baseline attributable to the current pneumonia, OR protocol-defined immunocompromise.
- A clinically indicated CT meeting the frozen input-quality criteria is available. Randomize within 24 hours after that CT and within 48 hours of documented recognition of the current pneumonia episode.
- No primary qualifying organ support earlier in the current episode, at baseline, or already clinically indicated before allocation.
- Written informed consent from the participant or an authorized representative before randomization.
Key exclusion criteria (6 listed)
- No interpretable CT suitable for the locked model; a noninfectious diagnosis fully explains the findings without suspected concomitant pneumonia.
- Qualifying invasive respiratory or circulatory support in the current episode, including support already clinically indicated even if not yet delivered.
- Previous randomization in this trial; a concurrent interventional study that conflicts with the AI care strategy.
- Known pregnancy, outside the initial intended-use population; breastfeeding alone is not an exclusion.
- Exclusive comfort-focused care or a pre-existing ceiling of care that rules out both invasive ventilation and vasopressor support.
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| CT-Based AI Decision Support for PneumoniaA locked CT-based artificial intelligence (AI) clinical decision-support system will analyze chest CT scans obtained as part of routine clinical care for patients with pneumonia. The system provides probabilities for predefined pathogen classes, quantitative assessment of pulmonary lesion extent, longitudinal changes when prior CT scans are available, and estimates of short-term clinical deterioration risk. For patients assigned to the intervention group, the AI-generated report will be made available to treating clinicians, with a target availability within one hour after randomization. Clinicians will review the AI findings alongside the original CT images and other clinical information within two hours and document any resulting changes in diagnosis, further testing, treatment, or monitoring. The AI system supports clinical decision-making but does not replace physician judgment. Additional CT scans are not required, and subsequent clinically indicated scans may also be analyzed. | Device | AI-Assisted Pneumonia Care |
Primary outcome
Death or New Invasive Respiratory or Circulatory Support Within 28 Days
Time frame: From randomization to 28 completed days, including events after discharge, readmission, or transfer.
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 26 Oct 2026.
- Results publication: PubMed 40228833Hopewell S, Chan AW, Collins GS, Hrobjartsson A, Moher D, Schulz KF, Tunn R, Aggarwal R, Berkwits M, Berlin JA, Bhandari N, Butcher NJ, Campbell MK, Chidebe RCW, Elbourne D, Farmer A, Fergusson DA, Golub RM, Goodman SN, Hoffmann TC, Ioannidis JPA, Kahan BC, Knowles RL, Lamb SE, Lewis S, Loder E, Offringa M, Ravaud P, Richards DP, Rockhold FW, Schriger DL, Siegfried NL, Staniszewska S, Taylor RS, Thabane L, Torgerson D, Vohra S, White IR, Boutron I. CONSORT 2025 statement: updated guideline for reporting randomised trials. BMJ. 2025 Apr 14;389:e081123. doi: 10.1136/bmj-2024-081123.
- Results publication: PubMed 40294953Chan AW, Boutron I, Hopewell S, Moher D, Schulz KF, Collins GS, Tunn R, Aggarwal R, Berkwits M, Berlin JA, Bhandari N, Butcher NJ, Campbell MK, Chidebe RCW, Elbourne DR, Farmer AJ, Fergusson DA, Golub RM, Goodman SN, Hoffmann TC, Ioannidis JPA, Kahan BC, Knowles RL, Lamb SE, Lewis S, Loder E, Offringa M, Ravaud P, Richards DP, Rockhold FW, Schriger DL, Siegfried NL, Staniszewska S, Taylor RS, Thabane L, Torgerson DJ, Vohra S, White IR, Hrobjartsson A. SPIRIT 2025 statement: updated guideline for protocols of randomised trials. BMJ. 2025 Apr 28;389:e081477. doi: 10.1136/bmj-2024-081477.
- Results publication: PubMed 32908284Cruz Rivera S, Liu X, Chan AW, Denniston AK, Calvert MJ; SPIRIT-AI and CONSORT-AI Working Group; SPIRIT-AI and CONSORT-AI Steering Group; SPIRIT-AI and CONSORT-AI Consensus Group. Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI extension. Nat Med. 2020 Sep;26(9):1351-1363. doi: 10.1038/s41591-020-1037-7. Epub 2020 Sep 9.
- Results publication: PubMed 32908283Liu X, Cruz Rivera S, Moher D, Calvert MJ, Denniston AK; SPIRIT-AI and CONSORT-AI Working Group. Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension. Nat Med. 2020 Sep;26(9):1364-1374. doi: 10.1038/s41591-020-1034-x. Epub 2020 Sep 9.
- Results publication: PubMed 38639729Gohil SK, Septimus E, Kleinman K, Varma N, Avery TR, Heim L, Rahm R, Cooper WS, Cooper M, McLean LE, Nickolay NG, Weinstein RA, Burgess LH, Coady MH, Rosen E, Sljivo S, Sands KE, Moody J, Vigeant J, Rashid S, Gilbert RF, Smith KN, Carver B, Poland RE, Hickok J, Sturdevant SG, Calderwood MS, Weiland A, Kubiak DW, Reddy S, Neuhauser MM, Srinivasan A, Jernigan JA, Hayden MK, Gowda A, Eibensteiner K, Wolf R, Perlin JB, Platt R, Huang SS. Stewardship Prompts to Improve Antibiotic Selection for Pneumonia: The INSPIRE Randomized Clinical Trial. JAMA. 2024 Jun 18;331(23):2007-2017. doi: 10.1001/jama.2024.6248.
- Individual participant dataSharing planned: Yes. Share a de-identified analysis dataset and data dictionary supporting the primary publication through controlled access. Raw imaging and directly identifying records are excluded from routine release.
Related trials for Pneumonia; Pulmonary Infection
RecruitingPhase 3
A Study of Secutrelvir in Participants With Coronavirus Disease 2019 (COVID-19) Who Are at High Risk for Progression to Severe Disease
SARS-CoV-2
RecruitingObservational study
Viral Infections in Healthy and Immunocompromised Hosts
Anogenital Herpes, COVID-19
Not yet recruiting
Multimodal Stewardship Programme to Improve Antibiotic Prescribing for Children With Lower Respiratory Tract Infections
Bronchitis, Acute, Community-acquired Pneumonia
Recruiting
The Effects of Wintergreen Essential Oil Inhalation on Alleviating Dyspnea Among Patients With Pneumonia
Pneumonia, Dyspnea
Active, not recruiting
Lupus Education Alliance Program
Systemic Lupus Erythematosus, COVID-19
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.
1 site in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
A study testing CT-Based AI Decision Support for Pneumonia in people with Pneumonia; Pulmonary Infection, run by Union Hospital, Tongji Medical College, Huazhong University of Science and Technology at 1 site in China.
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 5 inclusion and 6 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: looking for participants now, as of the sponsor's last update on 26 Oct 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 China. 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 Xiaoyu Han (+8618202771604, xiaoyuhan1123@163.com), or a site near the patient. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Death or New Invasive Respiratory or Circulatory Support Within 28 Days (time frame: From randomization to 28 completed days, including events after discharge, readmission, or transfer.). 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 NCT07895290, which also lists 5 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 26 Oct 2026.