AI-Driven Accurate Diagnosis of Pathogens in Severe Pneumonia (AI-PneumoDx)

Study on Accurate Diagnosis of Pathogens in Severe Pneumonia Based on Artificial Intelligence-Driven Technology

Severe pneumonia (SP) is a critical illness characterized by complex etiology, rapid progression, and high mortality. Its precision diagnosis and treatment face two core challenges. First, traditional etiological diagnostic methods (such as culture, serology, PCR) suffer from low detection rates, long turnaround times, and limited pathogen spectrum coverage, making it difficult to meet the clinical need for early, rapid, and precise diagnosis. Even with the application of next-generation sequencing, challenges remain in result interpretation and distinguishing colonization, contamination, and true infection. Second, host immune responses are highly heterogeneous, and there is currently a lack of a subtyping system that can systematically reveal its dynamic evolution and guide precise immunomodulatory therapy. Research on viral severe pneumonia (VSP) indicates that patients exhibit a complex immune imbalance characterized by coexisting hyperactivation of innate immune cells and exhaustion/suppression of adaptive immune cells. Furthermore, this immune heterogeneity may transcend the traditional binary framework, with at least three potential immune subtypes showing significant differences in mortality rates. Therefore, the investigators propose that: By constructing a severe pneumonia cohort and developing an artificial intelligence model that integrates multimodal clinical data (clinical, imaging, microbiological), host multidimensional etiological data (e.g., metagenomic sequencing), and immunomics data (T/B cell immune repertoire, transcriptomics, etc.), it can, on one hand, achieve more accurate and faster etiological diagnosis of severe pneumonia compared to traditional methods; on the other hand, it can identify immune endotypes with distinct immune features, different clinical outcomes, and varied responses to immunomodulatory therapies (e.g., targeting hyperinflammatory or immunosuppressed subtypes). Ultimately, this integrated model system is expected to provide a scientific tool for the individualized treatment and clinical decision-making in severe pneumonia, guiding precise immune intervention to improve patient prognosis.

Study Overview

• Status: Active, not recruiting
• Conditions: Severe Pneumonia

• Study Type: Observational
• Enrollment (Estimated): 1000

Contacts and Locations

Study Locations

• China
  • Guangdong
    • Guangzhou, Guangdong, China, 510000
      • Guangzhou First People's Hospital
    • Guangzhou, Guangdong, China, 510000
      • The Second Affiliated Hospital of Guangzhou Medical University
    • Guangzhou, Guangdong, China, 510000
      • The Third Affiliated Hospital of Guangzhou Medical University
    • Guangzhou, Guangdong, China, 510000
      • The Affiliated Panyu Central Hospital of Guangzhou Medical University
    • Guangzhou, Guangdong, China, 510000
      • The Fourth Affiliated Hospital of Guangzhou Medical University
    • Guangzhou, Guangdong, China, 510000
      • the Guangzhou Red Cross Hospital

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Adult patients admitted to the ICU with a diagnosis of severe pneumonia who meet the specified inclusion and exclusion criteria.

Description

Inclusion Criteria:

• Age ≥ 18 years;
• Admitted to the ICU, meeting the diagnostic criteria for severe pneumonia;
• ICU stay > 72 hours;
• The patient or legal representative provides informed consent.

Exclusion Criteria:

• Age < 18 years;
• Expected survival time < 1 day;
• Already hospitalized in a general ward for ≥4 weeks or already treated in the ICU for ≥2 weeks;
• Pregnant or lactating women;
• Presence of contraindications to bronchoalveolar lavage;
• Participation in another clinical study or deemed unsuitable by the investigator.

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort
Severe pneumonia cohort; Plans to enroll approximately 1000 adult patients meeting the diagnostic criteria for severe pneumonia.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Accuracy of the AI model for the etiological diagnosis of severe pneumonia	The primary outcome is the accuracy of the constructed artificial intelligence model in diagnosing the etiology of severe pneumonia. Accuracy is defined as the proportion of correct predictions made by the model out of the total number of samples. It is calculated using the formula: Accuracy = (Number of Correct Predictions) / (Total Number of Samples). The AI model will integrate multimodal data including clinical, imaging, and microbiological features. The diagnostic performance of the model will be compared against a gold standard.	From baseline (Day 0) to Day 7 after enrollment.
Identification and characterization of immune subtypes in severe pneumonia	The primary outcome is the identification of distinct immune subtypes in patients with severe pneumonia using an artificial intelligence model that integrates multimodal data, including clinical parameters, imaging, and immunomics. The study aims to reveal the dynamic evolution of host immune responses. The model will identify at least 3 potential immune subtypes (such as immune hyperactivation, immunosuppression, and mixed types) with significant differences in clinical outcomes like mortality .	From baseline (Day 0) to Day 28 after enrollment.

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Clinical and etiological differences between community-acquired pneumonia (CAP) and hospital-acquired pneumonia (HAP)	Through the multicenter cohort, the study aims to systematically compare the differences in clinical outcomes, pathogen spectrum, and immune response characteristics between CAP and HAP patients. This comparison will help clarify the distinct clinical features and etiological backgrounds of these two types of pneumonia.	From baseline (Day 0) through Day 7 after enrollment
Exploration of triggering conditions for HAP and development of a predictive model	The study aims to explore the triggering conditions for hospital-acquired pneumonia (HAP), specifically identifying key predictive indicators for nosocomial and secondary infections, and to establish a predictive model for HAP. This will involve analyzing clinical, microbiological, and host immune data from the multicenter cohort to identify risk factors and early warning signs.	From baseline (Day 0) to Day 28 after enrollment.
Association between pathogen spectrum characteristics and host immune microenvironment in severe pneumonia.	The study will systematically collect serological tests, microbial culture, PCR, and metagenomic sequencing data to comprehensively characterize the pathogen spectrum of severe pneumonia. By integrating this with host immune indicators (such as lymphocyte subsets, cytokines) and clinical outcomes, the study aims to investigate how different pathogens (e.g., bacteria, viruses, fungi, and mixed infections) specifically drive host immune responses. This outcome seeks to reveal the dynamic association between "pathogen-host immunity-clinical outcome", providing a basis for targeted therapy.	From baseline (Day 0) to Day 28 after enrollment.
Association between dynamic evolution of immune subtypes and prognosis	This outcome explores the association between the dynamic evolution trajectory of immune subtypes and patient prognosis. Cox proportional hazards models will be used to analyze the independent relationship between subtypes and prognosis.	From baseline (Day 0) through Day 28 after enrollment.
Development of a 28-day mortality prediction model based on multimodal AI fusion.	The study aims to build an intelligent prognostic prediction model for severe pneumonia by integrating multimodal data, including clinical baseline information, scoring systems (APACHE II, SOFA), imaging features (CT/X-ray), laboratory indicators, and dynamic immune data. This is an exploratory research endpoint to determine if the AI model can predict 28-day all-cause mortality in patients with severe pneumonia.	28 days after enrollment.

Other Outcome Measures

Outcome Measure	Measure Description	Time Frame
Exploration of immune subtype-specific biomarkers and their diagnostic efficacy	The study aims to explore and identify specific biomarkers for different immune subtypes of severe pneumonia, particularly viral severe pneumonia (VSP), and evaluate their diagnostic efficacy. This involves using SHAP and other interpretability techniques to screen for key biomarker combinations from complex multi-omics features. The diagnostic performance of these subtype-specific biomarkers will be validated, aiming for an Area Under the Curve (AUC) greater than 0.75. This exploration is part of developing a simplified clinical diagnostic panel based on key immune markers and clinical data.	From baseline (Day 0) through Day 7 after enrollment.

Collaborators and Investigators

• Sponsor: Guangzhou Medical University
• Investigators: Principal Investigator: Zhen-hui Zhang, PhD, Second Affiliated Hospital of Guangzhou Medical University; Study Chair: Zi-feng Yang, State Key Laboratory of Respiratory Disease

Study record dates

Study Major Dates

• Study Start (Actual): September 18, 2025
• Primary Completion (Estimated): December 31, 2026
• Study Completion (Estimated): December 31, 2027

Study Registration Dates

• First Submitted: March 5, 2026
• First Submitted That Met QC Criteria: March 5, 2026
• First Posted (Actual): March 10, 2026

Study Record Updates

• Last Update Posted (Actual): March 12, 2026
• Last Update Submitted That Met QC Criteria: March 10, 2026
• Last Verified: March 1, 2026

More Information

Terms related to this study

• Keywords: Severe Pneumonia; Immunophenotyping; Etiological diagnosis
• Additional Relevant MeSH Terms: Respiratory Tract Infections; Infections; Respiratory Tract Diseases; Lung Diseases; Pneumonia
• Other Study ID Numbers: ICU-2025-001; GZNL2024B01008 (Other Grant/Funding Number: Guangzhou Laboratory and State Key Laboratory of Respiratory Disease)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED
• IPD Plan Description: A final decision regarding IPD sharing has not been made. Any future data sharing will comply with ethical guidelines, participant privacy protection, and relevant regulatory requirements.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No