{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T18:14:44Z","timestamp":1783361684089,"version":"3.54.6"},"reference-count":32,"publisher":"BMJ","issue":"1","license":[{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"unspecified","delay-in-days":24,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Digit Health"],"accepted":{"date-parts":[[2026,5,5]]},"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Data on cardiac index (CI) in patients undergoing coronary angiography (CAG) can enhance decision-making and improve clinical outcomes. However, this necessitates an additional invasive procedure, and therefore, it is frequently omitted. This study explores the novel application of convolutional neural networks (CNNs) to predict CI from routine CAGs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods and analysis<\/jats:title>\n                    <jats:p>Patients who underwent CAG and simultaneous right heart catheterisation at Mayo Clinic between 2002 and 2023 were included. A three-dimensional (3D)-CNN model (X3D architecture) was developed to predict binary CI categories (normal: CI\u22652.2\u2009vs abnormal: CI&lt;2.2\u2009L\/min\/m\u00b2) from CAG videos. CAGs were randomly split into training (70%), validation (15%) and test (15%) sets. All available videos from each study were entered into the model. The model\u2019s performance was evaluated using the area under the curve (AUC), sensitivity, specificity and F1 score.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>A total of 15 297 CAG studies were considered. After applying a quality-check algorithm to exclude low-quality or irrelevant CAGs, 11\u2009475 studies from 9103 patients were included. CI was abnormal in 25.2% of studies. The model achieved an AUC of 0.83 (95% CI 0.81 to 0.85), sensitivity of 0.72 (95% CI 0.68 to 0.77), specificity of 0.78 (95% CI 0.75 to 0.80) and F1 score of 0.62 (95% CI 0.58 to 0.65) on the test dataset. Limiting the input to 4, 3 or 2 prespecified CAG videos representing standard views did not significantly affect the model\u2019s performance, supporting its applicability in varied clinical workflows.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study demonstrates the feasibility of leveraging deep learning models to predict CI from CAG videos. The proposed 3D-CNN model shows promise as a tool for providing physicians with real-time data to aid decision-making during CAG procedures.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjdh-2026-000080","type":"journal-article","created":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T14:20:25Z","timestamp":1782397225000},"page":"e000080","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["Predicting cardiac index from coronary angiogram videos: a novel application of 3D convolutional neural networks"],"prefix":"10.1136","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1664-4818","authenticated-orcid":false,"given":"Shih-Sheng","family":"Chang","sequence":"first","affiliation":[{"name":"Artificial Intelligence and Robotic Innovation Center, China Medical University Hospital, Taichung, Taiwan"},{"name":"Division of Cardiovascular Medicine, Department of Internal Medicine, China Medical University Hospital, Taichung, Taiwan"},{"name":"School of Medicine, China Medical University, Taichung, Taiwan"},{"name":"Department of Cardiovascular Medicine, Mayo Clinic, Rochester, Minnesota, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1091-0388","authenticated-orcid":false,"given":"Behrouz","family":"Rostami","sequence":"additional","affiliation":[{"name":"Department of Cardiovascular Medicine, Mayo Clinic, Rochester, Minnesota, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6701-0308","authenticated-orcid":false,"given":"Gerardo","family":"Lo Russo","sequence":"additional","affiliation":[{"name":"Department of Cardiovascular Medicine, Mayo Clinic, Rochester, Minnesota, USA"},{"name":"Department of Clinical Sciences and Community Health, University of Milan, Milan, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chia-Hao","family":"Liu","sequence":"additional","affiliation":[{"name":"Division of Cardiovascular Medicine, Department of Internal Medicine, China Medical University Hospital, Taichung, Taiwan"},{"name":"Department of Cardiovascular Medicine, Mayo Clinic, Rochester, Minnesota, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6476-9527","authenticated-orcid":false,"given":"Eunjung","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Cardiovascular Medicine, Mayo Clinic, Rochester, Minnesota, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3847-0959","authenticated-orcid":false,"given":"Mohamad","family":"Alkhouli","sequence":"additional","affiliation":[{"name":"Department of Cardiovascular Medicine, Mayo Clinic, Rochester, Minnesota, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,6,25]]},"reference":[{"key":"2026070610205010000_2.1.e000080.1","doi-asserted-by":"publisher","DOI":"10.1186\/cc6975"},{"key":"2026070610205010000_2.1.e000080.2","doi-asserted-by":"crossref","DOI":"10.1161\/JAHA.120.019843","article-title":"Right Heart Catheterization in Cardiogenic Shock Is Associated With Improved Outcomes: Insights From the Nationwide Readmissions Database","volume":"10","author":"Ranka","year":"2021","journal-title":"J Am Heart Assoc"},{"key":"2026070610205010000_2.1.e000080.3","doi-asserted-by":"crossref","DOI":"10.1161\/JAHA.122.026589","article-title":"Right Heart Catheterization-To Do or Not To Do? Introducing a New Diagnostic Algorithm for Pulmonary Hypertension","volume":"11","author":"Ryan","year":"2022","journal-title":"J Am Heart Assoc"},{"key":"2026070610205010000_2.1.e000080.4","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1007\/s11886-022-01655-y","article-title":"Current State and Future Perspectives of Artificial Intelligence for Automated Coronary Angiography Imaging Analysis in Patients with Ischemic Heart Disease","volume":"24","author":"Molenaar","year":"2022","journal-title":"Curr Cardiol Rep"},{"key":"2026070610205010000_2.1.e000080.5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2023.107660"},{"key":"2026070610205010000_2.1.e000080.6","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-16066-6"},{"key":"2026070610205010000_2.1.e000080.7","doi-asserted-by":"crossref","first-page":"586","DOI":"10.1001\/jamacardio.2023.0968","article-title":"Automated Assessment of Cardiac Systolic Function From Coronary Angiograms With Video-Based Artificial Intelligence Algorithms","volume":"8","author":"Avram","year":"2023","journal-title":"JAMA Cardiol"},{"key":"2026070610205010000_2.1.e000080.8","doi-asserted-by":"crossref","DOI":"10.1016\/j.jacadv.2023.100632","article-title":"Deep Learning to Estimate Left Ventricular Ejection Fraction From Routine Coronary Angiographic Images","volume":"2","author":"Rostami","year":"2023","journal-title":"JACC Adv"},{"key":"2026070610205010000_2.1.e000080.9","doi-asserted-by":"crossref","DOI":"10.1016\/j.mcpdig.2025.100195","article-title":"Optimizing Input Selection for Cardiac Model Training and Inference: An Efficient 3D Convolutional Neural Networks-Based Approach to Automate Coronary Angiogram Video Selection","volume":"3","author":"Chang","year":"2025","journal-title":"Mayo Clin Proc Digit Health"},{"key":"2026070610205010000_2.1.e000080.10","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C . X3D: expanding architectures for efficient video recognition. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); Seattle, WA, USA, 2020:200\u201310. doi:10.1109\/CVPR42600.2020.00028 Available: https:\/\/ieeexplore.ieee.org\/xpl\/mostRecentIssue.jsp?punumber=9142308","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"2026070610205010000_2.1.e000080.11","doi-asserted-by":"crossref","first-page":"1090","DOI":"10.1001\/jamacardio.2017.2945","article-title":"Thermodilution vs Estimated Fick Cardiac Output Measurement in Clinical Practice: An Analysis of Mortality From the Veterans Affairs Clinical Assessment, Reporting, and Tracking (VA CART) Program and Vanderbilt University","volume":"2","author":"Opotowsky","year":"2017","journal-title":"JAMA Cardiol"},{"key":"2026070610205010000_2.1.e000080.12","unstructured":"Patel N , Durland J , Makaryus AN . Physiology, cardiac index. In: StatPearls. Treasure Island (FL): StatPearls Publishing, 2024."},{"key":"2026070610205010000_2.1.e000080.13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2010.04.018"},{"key":"2026070610205010000_2.1.e000080.14","doi-asserted-by":"crossref","DOI":"10.1186\/s12916-019-1466-7","article-title":"Calibration: the Achilles heel of predictive analytics","volume":"17","author":"Van Calster","year":"2019","journal-title":"BMC Med"},{"key":"2026070610205010000_2.1.e000080.15","doi-asserted-by":"publisher","DOI":"10.1177\/0272989X06295361"},{"key":"2026070610205010000_2.1.e000080.16","unstructured":"Jones E , Oliphant T , Peterson P . SciPy: open source scientific tools for python. 2001."},{"key":"2026070610205010000_2.1.e000080.17","doi-asserted-by":"crossref","first-page":"1689","DOI":"10.1080\/03610918.2015.1065327","article-title":"Validation of Nonparametric Two-Sample Bootstrap in ROC Analysis on Large Datasets","volume":"45","author":"Wu","year":"2016","journal-title":"Commun Stat Simul Comput"},{"key":"2026070610205010000_2.1.e000080.18","doi-asserted-by":"crossref","DOI":"10.3390\/jcm8091419","article-title":"Deep Learning-Based Stroke Volume Estimation Outperforms Conventional Arterial Contour Method in Patients with Hemodynamic Instability","volume":"8","author":"Moon","year":"2019","journal-title":"J Clin Med"},{"key":"2026070610205010000_2.1.e000080.19","doi-asserted-by":"crossref","DOI":"10.2196\/24762","article-title":"Development and Validation of an Arterial Pressure-Based Cardiac Output Algorithm Using a Convolutional Neural Network: Retrospective Study Based on Prospective Registry Data","volume":"9","author":"Yang","year":"2021","journal-title":"JMIR Med Inform"},{"key":"2026070610205010000_2.1.e000080.20","doi-asserted-by":"crossref","first-page":"14281","DOI":"10.1109\/JSEN.2020.3022273","article-title":"Detection of Low Cardiac Index using a Polyvinylidene Fluoride-Based Wearable Ring and Convolutional Neural Networks","volume":"21","author":"Ansari","year":"2021","journal-title":"IEEE Sens J"},{"key":"2026070610205010000_2.1.e000080.21","article-title":"Research Progress of Machine Learning and Deep Learning in Intelligent Diagnosis of the Coronary Atherosclerotic Heart Disease","volume":"2022","author":"Lu","year":"2022","journal-title":"Comput Math Methods Med"},{"key":"2026070610205010000_2.1.e000080.22","doi-asserted-by":"crossref","DOI":"10.1038\/s41746-023-00880-1","article-title":"CathAI: fully automated coronary angiography interpretation and stenosis estimation","volume":"6","author":"Avram","year":"2023","journal-title":"NPJ Digit Med"},{"key":"2026070610205010000_2.1.e000080.23","doi-asserted-by":"publisher","DOI":"10.1097\/MCA.0000000000001305"},{"key":"2026070610205010000_2.1.e000080.24","doi-asserted-by":"publisher","DOI":"10.1136\/heartjnl-2017-311750"},{"key":"2026070610205010000_2.1.e000080.25","first-page":"122","article-title":"Right heart catheterization in clinical practice: a review of basic physiology and important issues relevant to interpretation","volume":"13","author":"Del Rio-Pertuz","year":"2023","journal-title":"Am J Cardiovasc Dis"},{"key":"2026070610205010000_2.1.e000080.26","doi-asserted-by":"crossref","DOI":"10.1038\/s41746-022-00712-8","article-title":"Multimodal machine learning in precision health: A scoping review","volume":"5","author":"Kline","year":"2022","journal-title":"NPJ Digit Med"},{"key":"2026070610205010000_2.1.e000080.27","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06555-x"},{"key":"2026070610205010000_2.1.e000080.28","unstructured":"He K , Chen X , Xie S , et al . Masked autoencoders are scalable vision learners. 2021. Available: http:\/\/arxiv.org\/abs\/2111.06377"},{"key":"2026070610205010000_2.1.e000080.29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ahj.2019.10.007"},{"key":"2026070610205010000_2.1.e000080.30","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1016\/j.ahj.2021.05.006","article-title":"Batch enrollment for an artificial intelligence-guided intervention to lower neurologic events in patients with undiagnosed atrial fibrillation: rationale and design of a digital clinical trial","volume":"239","author":"Yao","year":"2021","journal-title":"Am Heart J"},{"key":"2026070610205010000_2.1.e000080.31","doi-asserted-by":"publisher","DOI":"10.1016\/s0140-6736(22)01637-3"},{"key":"2026070610205010000_2.1.e000080.32","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0226561","article-title":"Thermodilution vs estimated Fick cardiac output measurement in an elderly cohort of patients: A single-centre experience","volume":"14","author":"Kresoja","year":"2019","journal-title":"PLoS One"}],"container-title":["BMJ Digital Health &amp; AI"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjdh-2026-000080","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T17:22:46Z","timestamp":1783358566000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjdigitalhealth.bmj.com\/lookup\/doi\/10.1136\/bmjdh-2026-000080"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,6,25]]},"published-print":{"date-parts":[[2026,6]]}},"alternative-id":["10.1136\/bmjdh-2026-000080"],"URL":"https:\/\/doi.org\/10.1136\/bmjdh-2026-000080","relation":{},"ISSN":["3049-575X"],"issn-type":[{"value":"3049-575X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}