AI-based measurement of cardiothoracic ratio in chest X-rays and prediction of echocardiographic congestive heart failure
Background: This study presents an artificial intelligence (AI) model for automated cardiothoracic ratio (CTR) measurement from chest X-rays (CXRs) and evaluates its association with severe left ventricular hypertrophy (SLVH) and dilated left ventricle (DLV) diagnosed by echocardiography. The study...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | International Journal of Cardiology: Heart & Vasculature |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352906725000818 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849727840323371008 |
|---|---|
| author | Joshua Ra Heejun Shin Christopher Park Yong-Xiang Wang Dongmyung Shin |
| author_facet | Joshua Ra Heejun Shin Christopher Park Yong-Xiang Wang Dongmyung Shin |
| author_sort | Joshua Ra |
| collection | DOAJ |
| description | Background: This study presents an artificial intelligence (AI) model for automated cardiothoracic ratio (CTR) measurement from chest X-rays (CXRs) and evaluates its association with severe left ventricular hypertrophy (SLVH) and dilated left ventricle (DLV) diagnosed by echocardiography. The study also assesses CTR’s prognostic value for predicting future SLVH/DLV development. Methods: In this retrospective cohort study, an AI algorithm measured CTR on 71,129 CXRs from 24,673 patients from 2013 to 2018 in the CheXchoNet database. SLVH/DLV was defined using echocardiographic criteria. Diagnostic accuracy was assessed using AUROC and AUPRC alongside sensitivity and specificity at various CTR thresholds. Logistic regression was performed for CXR-echocardiogram pairs. Time-to-event analysis was performed on 9,890 patients without baseline SLVH/DLV. Results: Among 24,673 patients (mean age: 62.1 years; female sex: 56.9 %), mean CTR was higher in SLVH/DLV patients (0.56 ± 0.07) than those without (0.52 ± 0.07; p < 0.001). AUROC was 0.70 (95 % CI: 0.69–0.70). At a CTR threshold of 0.53, sensitivity was 70 % and specificity 60 %. Increased CTR was associated with SLVH/DLV risk on paired echocardiogram, with an odds ratio of 1.26 at a CTR of 0.65 compared to CTR at 0.50 (95 % CI: 1.24–1.27, p < 0.001). Time-to-event analysis on patients without baseline SLVH/DLV showed patients with baseline CTR > 0.65 had a 4.13-fold increased risk of developing SLVH/DLV in the future compared to patients with CTR ≤ 0.50 (adjusted HR: 4.13; 95 % CI: 2.48–6.89; p < 0.01). Conclusion: AI-based CTR measurement helps predict SLVH/DLV and could be used for risk stratification for cardiovascular care. |
| format | Article |
| id | doaj-art-acb3751a7dff464b827124469dcbca69 |
| institution | DOAJ |
| issn | 2352-9067 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Cardiology: Heart & Vasculature |
| spelling | doaj-art-acb3751a7dff464b827124469dcbca692025-08-20T03:09:44ZengElsevierInternational Journal of Cardiology: Heart & Vasculature2352-90672025-06-015810167810.1016/j.ijcha.2025.101678AI-based measurement of cardiothoracic ratio in chest X-rays and prediction of echocardiographic congestive heart failureJoshua Ra0Heejun Shin1Christopher Park2Yong-Xiang Wang3Dongmyung Shin4Division of Cardiology, Mount Sinai Morningside-BronxCare, NY, USAArtificial Intelligence Engineering Division, RadiSen Co. Ltd., Seoul, South KoreaNew York University, NY, USAMarketech International Corp., Taipei, TaiwanArtificial Intelligence Engineering Division, RadiSen Co. Ltd., Seoul, South Korea; Corresponding author.Background: This study presents an artificial intelligence (AI) model for automated cardiothoracic ratio (CTR) measurement from chest X-rays (CXRs) and evaluates its association with severe left ventricular hypertrophy (SLVH) and dilated left ventricle (DLV) diagnosed by echocardiography. The study also assesses CTR’s prognostic value for predicting future SLVH/DLV development. Methods: In this retrospective cohort study, an AI algorithm measured CTR on 71,129 CXRs from 24,673 patients from 2013 to 2018 in the CheXchoNet database. SLVH/DLV was defined using echocardiographic criteria. Diagnostic accuracy was assessed using AUROC and AUPRC alongside sensitivity and specificity at various CTR thresholds. Logistic regression was performed for CXR-echocardiogram pairs. Time-to-event analysis was performed on 9,890 patients without baseline SLVH/DLV. Results: Among 24,673 patients (mean age: 62.1 years; female sex: 56.9 %), mean CTR was higher in SLVH/DLV patients (0.56 ± 0.07) than those without (0.52 ± 0.07; p < 0.001). AUROC was 0.70 (95 % CI: 0.69–0.70). At a CTR threshold of 0.53, sensitivity was 70 % and specificity 60 %. Increased CTR was associated with SLVH/DLV risk on paired echocardiogram, with an odds ratio of 1.26 at a CTR of 0.65 compared to CTR at 0.50 (95 % CI: 1.24–1.27, p < 0.001). Time-to-event analysis on patients without baseline SLVH/DLV showed patients with baseline CTR > 0.65 had a 4.13-fold increased risk of developing SLVH/DLV in the future compared to patients with CTR ≤ 0.50 (adjusted HR: 4.13; 95 % CI: 2.48–6.89; p < 0.01). Conclusion: AI-based CTR measurement helps predict SLVH/DLV and could be used for risk stratification for cardiovascular care.http://www.sciencedirect.com/science/article/pii/S2352906725000818Cardiothoracic ratioLeft ventricular hypertrophyChest radiographyArtificial intelligenceCardiovascular risk stratification |
| spellingShingle | Joshua Ra Heejun Shin Christopher Park Yong-Xiang Wang Dongmyung Shin AI-based measurement of cardiothoracic ratio in chest X-rays and prediction of echocardiographic congestive heart failure International Journal of Cardiology: Heart & Vasculature Cardiothoracic ratio Left ventricular hypertrophy Chest radiography Artificial intelligence Cardiovascular risk stratification |
| title | AI-based measurement of cardiothoracic ratio in chest X-rays and prediction of echocardiographic congestive heart failure |
| title_full | AI-based measurement of cardiothoracic ratio in chest X-rays and prediction of echocardiographic congestive heart failure |
| title_fullStr | AI-based measurement of cardiothoracic ratio in chest X-rays and prediction of echocardiographic congestive heart failure |
| title_full_unstemmed | AI-based measurement of cardiothoracic ratio in chest X-rays and prediction of echocardiographic congestive heart failure |
| title_short | AI-based measurement of cardiothoracic ratio in chest X-rays and prediction of echocardiographic congestive heart failure |
| title_sort | ai based measurement of cardiothoracic ratio in chest x rays and prediction of echocardiographic congestive heart failure |
| topic | Cardiothoracic ratio Left ventricular hypertrophy Chest radiography Artificial intelligence Cardiovascular risk stratification |
| url | http://www.sciencedirect.com/science/article/pii/S2352906725000818 |
| work_keys_str_mv | AT joshuara aibasedmeasurementofcardiothoracicratioinchestxraysandpredictionofechocardiographiccongestiveheartfailure AT heejunshin aibasedmeasurementofcardiothoracicratioinchestxraysandpredictionofechocardiographiccongestiveheartfailure AT christopherpark aibasedmeasurementofcardiothoracicratioinchestxraysandpredictionofechocardiographiccongestiveheartfailure AT yongxiangwang aibasedmeasurementofcardiothoracicratioinchestxraysandpredictionofechocardiographiccongestiveheartfailure AT dongmyungshin aibasedmeasurementofcardiothoracicratioinchestxraysandpredictionofechocardiographiccongestiveheartfailure |