Related Experiment Video
Updated: Aug 18, 2026
A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
Published on: May 19, 2023
A deep learning model for opportunistic screening of chronic kidney disease using chest radiographs: a multicentre
Theodorus Dapamede1, Kéana Aitcheson2,3, Pola Lydia Lagari4
1Department of Radiology and Imaging Sciences, Emory University, Atlanta, USA.
Insights
A new AI tool, CXR-CKD5, uses chest X-rays to predict chronic kidney disease (CKD) risk without lab tests. This offers a scalable screening method for early detection of CKD.
Area of Science:
- Artificial Intelligence in Medical Imaging
- Cardiovascular and Renal Medicine
- Public Health Screening
Background:
- Chronic kidney disease (CKD) affects over 843 million globally and is often underdiagnosed.
- Current risk assessment tools require laboratory data, limiting their use in routine clinical settings.
- Chest radiographs (CXRs) are frequently performed, presenting an opportunity for opportunistic screening.
Purpose of the Study:
- To develop and validate CXR-CKD5, an AI-driven score predicting 5-year incident CKD risk using only CXR data.
- To compare the performance of CXR-CKD5 against existing clinical risk models.
Main Methods:
- A retrospective study included 97,553 adults without baseline CKD from two US centers.
- A convolutional neural network extracted 10 cardiopulmonary and metabolic features from CXRs.
- An XGBoost model was trained to predict 5-year incident CKD, with performance evaluated using C-indices.
Main Results:
- CXR-CKD5 demonstrated good discrimination, with C-indices of 0.774 in development and 0.713 in external validation.
- A combined imaging-clinical model showed the highest discrimination (C-index 0.734) in external validation.
- Model performance was notably stronger in non-diabetic patients compared to diabetic patients.
Conclusions:
- Routine chest radiographs analyzed by AI can identify individuals at elevated risk for CKD, enabling opportunistic screening.
- Further recalibration and prospective studies are necessary to assess clinical outcomes and workflow integration before widespread deployment.
Background:
Chronic kidney disease (CKD) affects 843 million people worldwide yet remains underdiagnosed. Current risk stratification, including the CKD Prognosis Consortium (CKD-PC) score, relies on laboratory data rarely evaluated outside nephrology settings. Chest radiographs (CXR) are among the most frequently performed imaging procedures globally, offering an opportunistic screening pathway. CXR-CKD5, a CXR-derived AI score for predicting 5-year incident CKD without laboratory data, was developed and externally validated.
Methods:
In this retrospective two-centre study conducted at two sites in the USA, 97,553 adults (≥18 years) without baseline CKD who underwent routine CXR were included: Emory University (development cohort, 2008-2021, n = 75,683) and University of Illinois Chicago (external validation cohort, 2010-2020, n = 21,870). Patients with a CKD diagnosis within 90 days of the index CXR were excluded. A convolutional neural network extracted 10 cardiopulmonary and metabolic risk features from routine CXRs, which were used to train an XGBoost accelerated failure time model. The primary outcome was 5-year incident CKD. Discrimination (C-index) and calibration were evaluated against a clinical base model and the CKD-PC score.
Findings:
CXR-CKD5 achieved apparent C-indices of 0.774 (95% CI: 0.768-0.780) in development (optimism-corrected: 0.737) and 0.713 (95% CI: 0.697-0.729) at external validation. A combined imaging-clinical model achieved the highest external validation discrimination (C-index 0.734, 95% CI: 0.719-0.751). Performance was strongest in non-diabetic patients (development C-index 0.783, 95% CI: 0.775-0.790; external validation 0.714, 95% CI: 0.689-0.739) and attenuated in diabetic patients across both cohorts (development C-index 0.658, 95% CI: 0.645-0.671; external validation 0.607, 95% CI: 0.580-0.634). Absolute risk was overestimated at external validation, indicating that calibration would be required before deployment at new institutions. A threshold of ≥15% predicted risk identified the top 20% at risk.
Interpretation:
CXR-CKD5 demonstrates that routine chest radiographs can identify patients at elevated CKD risk without laboratory data, offering a scalable opportunistic screening pathway. Recalibration and prospective evaluation assessing clinical outcomes and workflow integration are needed before deployment.
Funding:
NHLBI and the University of Illinois Chicago AI.Health4All Initiative.