{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T22:41:24Z","timestamp":1773268884578,"version":"3.50.1"},"reference-count":29,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T00:00:00Z","timestamp":1773187200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Mol. Biosci."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Pulmonary embolism (PE) is a critical cardiovascular emergency requiring prompt, accurate diagnosis. CT pulmonary angiography (CTPA) is the diagnostic gold standard, yet rising case volumes and radiologist shortages challenge clinical workflows. Artificial intelligence (AI) offers potential to enhance diagnostic precision and efficiency. This multicenter study validates the performance of a commercially available AI system compared with radiologist interpretation alone and in combination.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this retrospective analysis, 600 consecutive patients suspected of PE underwent CTPA between January 2024 and May 2025 at three hospitals in Xinjiang. All scans employed 256-slice CT with standardized protocols (100 kV, 0.625 mm slice thickness, iohexol contrast). Images were processed using uAIDiscover PE software, generating Pulmonary Thrombus Burden Score (PTBS). Manual Pulmonary Artery Obstruction Index (PAOI) was independently scored via the Qanadli system by consensus of three senior radiologists, serving as the reference standard. Diagnostic accuracy and correlation between AI and manual scores were assessed (SPSS 24.0; P &amp;lt; 0.05).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among 600 patients analyzed, 271 (45.2%) had pulmonary embolism. PE patients had significantly higher BMI and greater prevalence of hypertension and coronary artery disease (P &amp;lt; 0.05). ROC analysis demonstrated superior diagnostic performance for the combined manual + AI approach across all centers (AUC: 0.928\u20130.934) compared to AI alone (AUC: 0.807\u20130.810) or manual reading alone (AUC: 0.888\u20130.914). AI processing was remarkably fast at 0.19 \u00b1 0.02 min versus 5.26 \u00b1 0.94 min for radiologists alone, while combined approach required 2.61 \u00b1 0.69 min. Strong correlation was observed between AI-derived PTBS and manually calculated PAOI (r = 0.863, P &amp;lt; 0.001). The combined approach significantly reduced diagnostic errors to 7 cases compared to 43 for AI alone and 29 for manual reading alone.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Integration of AI with manual interpretation improves pulmonary embolism detection accuracy and reduces reading time, supporting its implementation to optimize clinical workflow and patient outcomes.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmolb.2026.1774152","type":"journal-article","created":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T06:53:31Z","timestamp":1773212011000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["External validation of a commercial AI system for pulmonary embolism detection on chest CTPA: a multicenter study"],"prefix":"10.3389","volume":"13","author":[{"given":"Mireayi","family":"Tudi","sequence":"first","affiliation":[{"name":"Department of Infection, The First People\u2019s Hospital of Kashi (Kashgar) Prefecture","place":["Kashi, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Saimaitikari","family":"Abudoubari","sequence":"additional","affiliation":[{"name":"Department of Radiology, The First People\u2019s Hospital of Kashi (Kashgar) Prefecture","place":["Kashi, China"]},{"name":"The Xinjiang Key Laboratory of Artificial Intelligence Assisted Imaging Diagnosis","place":["Kashi, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xierenayi","family":"Waresi","sequence":"additional","affiliation":[{"name":"Department of Radiology, The First People\u2019s Hospital of Kashi (Kashgar) Prefecture","place":["Kashi, China"]},{"name":"The Xinjiang Key Laboratory of Artificial Intelligence Assisted Imaging Diagnosis","place":["Kashi, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aikebaierjiang","family":"Ainiwaer","sequence":"additional","affiliation":[{"name":"Department of Geriatrics, Shache County People\u2019s Hospital","place":["Kashi, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nuermaimaijiang","family":"Abudouwufu","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics, Kashi University","place":["Kashi, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Palidanmu","family":"Wumaier","sequence":"additional","affiliation":[{"name":"Department of Radiology, The First People\u2019s Hospital of Kashi (Kashgar) Prefecture","place":["Kashi, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adilijiang","family":"Abula","sequence":"additional","affiliation":[{"name":"Department of Radiology, The First People\u2019s Hospital of Kashi (Kashgar) Prefecture","place":["Kashi, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuwei","family":"Xia","sequence":"additional","affiliation":[{"name":"Shanghai United Imaging Intelligence Medical Technology Co., Ltd.","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ailiyaerjiang","family":"Aisika","sequence":"additional","affiliation":[{"name":"Department of Radiology, The Fourth Affiliated Hospital of Xinjiang Medical University (Xinjiang Hospital of Traditional Chinese Medicine)","place":["Urumqi, Xinjiang, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ya","family":"Qiu","sequence":"additional","affiliation":[{"name":"Department of Radiology, The First People\u2019s Hospital of Kashi (Kashgar) Prefecture","place":["Kashi, China"]},{"name":"The Xinjiang Key Laboratory of Artificial Intelligence Assisted Imaging Diagnosis","place":["Kashi, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maimaitiaili","family":"Tuerxun","sequence":"additional","affiliation":[{"name":"Department of Infection, The First People\u2019s Hospital of Kashi (Kashgar) Prefecture","place":["Kashi, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abudouresuli","family":"Tuersun","sequence":"additional","affiliation":[{"name":"Department of Radiology, The First People\u2019s Hospital of Kashi (Kashgar) Prefecture","place":["Kashi, China"]},{"name":"The Xinjiang Key Laboratory of Artificial Intelligence Assisted Imaging Diagnosis","place":["Kashi, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,11]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"e15734056367860","DOI":"10.2174\/0115734056367860250630072749","article-title":"Artificial intelligence for detecting pulmonary embolisms via CT: a workflow-oriented implementation","volume":"21","author":"Abed","year":"2025","journal-title":"Curr. Med. Imaging"},{"key":"B2","doi-asserted-by":"publisher","first-page":"e85845","DOI":"10.7759\/cureus.85845","article-title":"Clinical utility and outcomes of repeat computed tomography pulmonary angiography in suspected pulmonary embolism: a retrospective cohort study","volume":"17","author":"Albeladi","year":"2025","journal-title":"Cureus"},{"key":"B3","first-page":"129","article-title":"Pulmonary embolism, part I: epidemiology, risk factors and risk stratification, pathophysiology, clinical presentation, diagnosis and nonthrombotic pulmonary embolism","volume":"18","author":"B\u0115lohl\u00e1vek","year":"2013","journal-title":"Exp. Clin. Cardiol."},{"key":"B4","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1097\/RCT.0b013e3181b2e383","article-title":"Computer-aided detection of acute pulmonary embolism with 64-slice multi-detector row computed tomography: impact of the scanning conditions and overall image quality in the detection of peripheral clots","volume":"34","author":"Dewailly","year":"2010","journal-title":"J. Comput. Assist. Tomogr."},{"key":"B5","doi-asserted-by":"publisher","first-page":"7169","DOI":"10.21037\/qims-2024-2750","article-title":"Evaluation of pulmonary perfusion and ventilation in suspected chronic thromboembolic pulmonary hypertension via phase-resolved functional lung magnetic resonance imaging: correlations with hemodynamics and cardiopulmonary function","volume":"15","author":"Duan","year":"2025","journal-title":"Quant. Imaging Med. Surg."},{"key":"B6","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1053\/j.tvir.2017.07.002","article-title":"Epidemiology, pathophysiology, stratification, and natural history of pulmonary embolism","volume":"20","author":"Giordano","year":"2017","journal-title":"Tech. Vasc. Interv. Radiol."},{"key":"B7","doi-asserted-by":"publisher","first-page":"271","DOI":"10.2214\/ajr.14.13938","article-title":"Overdiagnosis of pulmonary embolism by pulmonary CT angiography","volume":"205","author":"Hutchinson","year":"2015","journal-title":"AJR Am. J. Roentgenol."},{"key":"B8","doi-asserted-by":"publisher","first-page":"2683555251363305","DOI":"10.1177\/02683555251363305","article-title":"Computed tomography pulmonary angiography for detection of pulmonary embolisms in Chinese patients","author":"Jin","year":"2025","journal-title":"Phlebology"},{"key":"B9","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1097\/rti.0000000000000361","article-title":"Radiologist performance in the detection of pulmonary embolism: features that favor correct interpretation and risk factors for errors","volume":"33","author":"Kligerman","year":"2018","journal-title":"J. Thorac. Imaging"},{"key":"B10","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1007\/s00330-023-10048-w","article-title":"An artificial intelligence algorithm for pulmonary embolism detection on polychromatic computed tomography: performance on virtual monochromatic images","volume":"34","author":"Langius-Wiffen","year":"2024","journal-title":"Eur. Radiol."},{"key":"B11","doi-asserted-by":"publisher","first-page":"110402","DOI":"10.1016\/j.compbiomed.2025.110402","article-title":"Meta-analysis of AI-based pulmonary embolism detection: how reliable are deep learning models?","volume":"193","author":"Lanza","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"B12","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1177\/0885066610392658","article-title":"Diagnosis and management of life-threatening pulmonary embolism","volume":"26","author":"Marshall","year":"2011","journal-title":"J. Intensive Care Med."},{"key":"B13","doi-asserted-by":"publisher","first-page":"e0848","DOI":"10.1097\/rti.0000000000000848","article-title":"Explainable machine learning for estimating the contrast material arrival time in computed tomography pulmonary angiography","volume":"40","author":"Meng","year":"2025","journal-title":"J. Thorac. Imaging"},{"key":"B14","doi-asserted-by":"publisher","first-page":"e30891","DOI":"10.1371\/journal.pone.0030891","article-title":"Clinical presentation of acute pulmonary embolism: survey of 800 cases","volume":"7","author":"Miniati","year":"2012","journal-title":"PLoS One"},{"key":"B15","doi-asserted-by":"publisher","first-page":"e230702","DOI":"10.1148\/radiol.230702","article-title":"Prospective evaluation of AI triage of pulmonary emboli on CT pulmonary angiograms","volume":"309","author":"Rothenberg","year":"2023","journal-title":"Radiology"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-025-01639-8","article-title":"Ultra-low-dose CTPA using sparse sampling CT combined with the U-Net for deep learning-based artifact reduction: an exploratory study","author":"Sauter","year":"2025","journal-title":"J. Imaging Inf. Med"},{"key":"B17","doi-asserted-by":"publisher","first-page":"7225","DOI":"10.1007\/s00330-025-11681-3","article-title":"Deep learning reconstruction combined with contrast-enhancement boost in dual-low dose CT pulmonary angiography: a two-center prospective trial","volume":"35","author":"Shen","year":"2025","journal-title":"Eur. Radiol."},{"key":"B18","doi-asserted-by":"publisher","first-page":"005695","DOI":"10.12890\/2025_005695","article-title":"Catheter-based thrombectomy for clot-in-transit and massive pulmonary embolism in A young patient with rheumatoid arthritis: inflammation as A hidden catalyst for catastrophic thromboembolism","volume":"12","author":"Shin Lee","year":"2025","journal-title":"Eur. J. Case Rep. Intern Med."},{"key":"B19","doi-asserted-by":"publisher","first-page":"15814","DOI":"10.1038\/s41598-021-95249-3","article-title":"Deep learning for pulmonary embolism detection on computed tomography pulmonary angiogram: a systematic review and meta-analysis","volume":"11","author":"Soffer","year":"2021","journal-title":"Sci. Rep."},{"key":"B20","doi-asserted-by":"publisher","first-page":"20584601251360347","DOI":"10.1177\/20584601251360347","article-title":"Evaluation of virtual monochromatic imaging using portal-venous phase dual-energy CT for detection of pulmonary embolism","volume":"14","author":"Taguchi","year":"2025","journal-title":"Acta Radiol. Open"},{"key":"B21","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1097\/corr.0000000000002742","article-title":"Are patients with morbid obesity at increased risk of pulmonary embolism or proximal deep vein thrombosis after lower limb arthroplasty? A large-database study","volume":"482","author":"Thompson","year":"2024","journal-title":"Clin. Orthop. Relat. Res."},{"key":"B22","doi-asserted-by":"publisher","first-page":"2841851251363692","DOI":"10.1177\/02841851251363692","article-title":"Novel imaging approach using dual-layer CT to assess anticoagulant therapy efficacy in acute pulmonary embolism","volume":"66","author":"Uchiyama","year":"2025","journal-title":"Acta Radiol."},{"key":"B23","doi-asserted-by":"publisher","first-page":"111324","DOI":"10.1016\/j.ejrad.2024.111324","article-title":"A deep learning-based algorithm improves radiology residents' diagnoses of acute pulmonary embolism on CT pulmonary angiograms","volume":"171","author":"Vall\u00e9e","year":"2024","journal-title":"Eur. J. Radiol."},{"key":"B24","doi-asserted-by":"publisher","first-page":"6545","DOI":"10.1007\/s00330-020-06998-0","article-title":"Automated detection of pulmonary embolism in CT pulmonary angiograms using an AI-powered algorithm","volume":"30","author":"Weikert","year":"2020","journal-title":"Eur. Radiol."},{"key":"B25","doi-asserted-by":"publisher","first-page":"110565","DOI":"10.1016\/j.clinimag.2025.110565","article-title":"Diagnostic value of low-dose CT pulmonary angiography combined with iterative reconstruction in suspected pulmonary embolism","volume":"125","author":"Wu","year":"2025","journal-title":"Clin. Imaging"},{"key":"B26","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1016\/j.mcpdig.2024.03.009","article-title":"Electrocardiogram signal analysis with a machine learning model predicts the presence of pulmonary embolism with accuracy dependent on embolism burden","volume":"2","author":"Wysokinski","year":"2024","journal-title":"Mayo Clin. Proc. Digit. Health"},{"key":"B27","doi-asserted-by":"publisher","first-page":"101625","DOI":"10.1016\/j.lanwpc.2025.101625","article-title":"Developing a deep learning-based imaging diagnostic framework, PVDNet, for differentiating pulmonary artery sarcoma and pulmonary thromboembolism: a multi-center observational study","volume":"60","author":"Xi","year":"2025","journal-title":"Lancet Reg. Health West Pac"},{"key":"B28","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1038\/s41746-025-01807-8","article-title":"Vision-language model for report generation and outcome prediction in CT pulmonary angiogram","volume":"8","author":"Zhong","year":"2025","journal-title":"NPJ Digit. Med."},{"key":"B29","doi-asserted-by":"publisher","first-page":"112077","DOI":"10.1016\/j.ejrad.2025.112077","article-title":"Accuracy of a deep neural network for automated pulmonary embolism detection on dedicated CT pulmonary angiograms","volume":"187","author":"Zsarnoczay","year":"2025","journal-title":"Eur. J. Radiol."}],"container-title":["Frontiers in Molecular Biosciences"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmolb.2026.1774152\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T06:53:32Z","timestamp":1773212012000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmolb.2026.1774152\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,11]]},"references-count":29,"alternative-id":["10.3389\/fmolb.2026.1774152"],"URL":"https:\/\/doi.org\/10.3389\/fmolb.2026.1774152","relation":{},"ISSN":["2296-889X"],"issn-type":[{"value":"2296-889X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,11]]},"article-number":"1774152"}}