{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T06:48:27Z","timestamp":1791787707851,"version":"4.3.4"},"reference-count":22,"publisher":"Wiley","issue":"10","license":[{"start":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T00:00:00Z","timestamp":1791676800000},"content-version":"vor","delay-in-days":10,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Echocardiography"],"published-print":{"date-parts":[[2026,10]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To evaluate whether a frontline echocardiographer, without engineering support or dedicated research hardware, can independently develop a validated five\u2010class echocardiographic view classifier using artificial intelligence\u2013assisted coding, standard departmental workstation hardware, and routine clinical archives.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      A clinician used artificial intelligence\u2013assisted coding (Kimi 2.6, Moonshot AI) to develop a pipeline on a standard Tomtec echocardiographic analysis workstation (Intel Core i7, NVIDIA RTX 4060 8 GB VRAM, 32 GB RAM) running Ubuntu 22.04 LTS via Windows Subsystem for Linux 2. From 1387 transthoracic echocardiograms, 9796 B\u2010mode end\u2010diastolic frames were extracted. A batch annotation strategy was employed: 466 seed images were annotated to train an overfitted EfficientNet\u2010B0 screener, which pre\u2010classified 5029 high\u2010confidence standard\u2010view frames. These were batch\u2010reviewed in approximately 24 min, yielding 5028 verified frames from 1242 patients, partitioned into training (\n                      <jats:italic>n<\/jats:italic>\n                      = 3545), validation (\n                      <jats:italic>n<\/jats:italic>\n                      = 731), and internal test (\n                      <jats:italic>n<\/jats:italic>\n                      = 752) sets. A five\u2010class ResNet\u201018 classifier was trained and evaluated on the primary dataset and evaluated on an external validation dataset (74 patients, 263 frames) without retraining.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The total expert annotation burden was 32 min. The classifier achieved 98.27% accuracy (95% CI: 97.06%\u201399.08%) on the internal test set with a macro F1 of 0.9784. On external validation, overall accuracy was 71.48% (95% CI: 65.61%\u201376.86%) with a macro F1 of 0.7100. Parasternal short\u2010axis and apical two\u2010chamber views generalized robustly (100% and 94.23%, respectively), whereas apical four\u2010chamber, apical three\u2010chamber, and parasternal long\u2010axis views showed lower accuracy due to device\u2010specific image processing differences.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Clinical artificial intelligence development in echocardiography is substantially more accessible than conventionally assumed. A single clinician using existing hardware and artificial intelligence\u2013assisted coding can produce a validated view classifier with minimal annotation burden, providing a practical roadmap for in\u2010house customization.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1111\/echo.70591","type":"journal-article","created":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T06:31:53Z","timestamp":1791786713000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Clinician\u2010Led Feasibility Study for Echocardiographic View Classification Using Standard Workstation Hardware and Routine Clinical Archives"],"prefix":"10.1111","volume":"43","author":[{"given":"Jinjie","family":"Xie","sequence":"first","affiliation":[{"name":"Echocardiography Laboratory, Heart Center, Beijing Jishuitan Hospital Capital Medical University  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaxin","family":"Wang","sequence":"additional","affiliation":[{"name":"Medical Imaging Department Shanghai Jiahui International Hospital  Shanghai China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"Echocardiography Laboratory, Heart Center, Beijing Jishuitan Hospital Capital Medical University  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,10,11]]},"reference":[{"key":"e_1_2_15_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746\u2010020\u201000324\u20100"},{"key":"e_1_2_15_3_1","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.118.034338"},{"key":"e_1_2_15_4_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2025.8731"},{"key":"e_1_2_15_5_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamacardio.2021.0185"},{"key":"e_1_2_15_6_1","doi-asserted-by":"publisher","DOI":"10.31662\/jmaj.2024-0180"},{"key":"e_1_2_15_7_1","doi-asserted-by":"publisher","DOI":"10.21037\/jlpm\u201025\u20106"},{"key":"e_1_2_15_8_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591\u2010018\u20100316\u2010z"},{"key":"e_1_2_15_9_1","doi-asserted-by":"publisher","DOI":"10.70589\/JRTCSE.2025.13.5.1"},{"key":"e_1_2_15_10_1","article-title":"Deep Learning\u2010Based Automated Echocardiographic Quantification of Left Ventricular Ejection Fraction: A Point\u2010of\u2010Care Solution","volume":"14","author":"Asch F. M.","year":"2021","journal-title":"Circulation: Cardiovascular Imaging"},{"key":"e_1_2_15_11_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586\u2010025\u201009850\u2010x"},{"key":"e_1_2_15_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2024.108111"},{"key":"e_1_2_15_13_1","article-title":"Open World Active Learning for Echocardiography View Classification","volume":"12033","author":"Zamzmi G.","year":"2022","journal-title":"Proceedings of the Spie"},{"key":"e_1_2_15_14_1","article-title":"nnActive: A Framework for Evaluation of Active Learning in 3D Biomedical Segmentation","volume":"2025","author":"L\u00fcth C. T.","year":"2025","journal-title":"Trans Mach Learn Res"},{"key":"e_1_2_15_15_1","volume-title":"Thinking, Fast and Slow","author":"Kahneman D.","year":"2011"},{"key":"e_1_2_15_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/0010\u20100285(80)90005\u20105"},{"key":"e_1_2_15_17_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010024\u201071530\u2010z"},{"key":"e_1_2_15_18_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746\u2010025\u201001730\u2010y"},{"key":"e_1_2_15_19_1","doi-asserted-by":"crossref","first-page":"570","DOI":"10.1007\/978-3-031-72083-3_53","article-title":"BackMix: Mitigating Shortcut Learning in Echocardiography with Minimal Supervision","volume":"15004","author":"Bransby K. M.","year":"2024","journal-title":"Lecture Notes in Computer Science"},{"key":"e_1_2_15_20_1","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering13050522"},{"key":"e_1_2_15_21_1","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2023.1195235"},{"key":"e_1_2_15_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104373"},{"key":"e_1_2_15_23_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586\u2010020\u20102145\u20108"}],"container-title":["Echocardiography"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/echo.70591","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/echo.70591","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/echo.70591","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T06:31:54Z","timestamp":1791786714000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/echo.70591"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":22,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2026,10]]}},"alternative-id":["10.1111\/echo.70591"],"URL":"https:\/\/doi.org\/10.1111\/echo.70591","archive":["Portico"],"relation":{},"ISSN":["0742-2822","1540-8175"],"issn-type":[{"value":"0742-2822","type":"print"},{"value":"1540-8175","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"2026-06-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-28","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-10-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70591"}}