{"id":"87f2c6de8c77","type":"article","url":"https://hartvaat.nl/2026/11/01/ai-algoritme-detecteert-complicaties-na-hartinterventies-met-hoge-gevoeligheid/","title":"AI-algoritme detecteert complicaties na hartinterventies met hoge gevoeligheid","title_en":"Development of an artificial intelligence algorithm for automated detection of cardiovascular intervention-related complications.","category":"algemeen","category_label":"Algemeen","professions":["cardioloog"],"tags":[],"journal":"Netherlands heart journal : monthly journal of the Netherlands Society of Cardiology and the Netherlands Heart Foundation","doi":"10.1007/s12471-026-02082-2","source_url":"https://doi.org/10.1007/s12471-026-02082-2","authors":["Arnoud Okken","Rob Wanders","Andre Klappe","Kasper F Beukema","Tom Oirbans","Peter G Noordzij","Anouk van Lent","Saskia H Haanemaaier","Jippe C Balt"],"significance":4,"published":"2026-10-30","source_date":"2026-11-01","image":"","kennis":["https://hartvaat.nl/kennis/cardiometabool/cardiometabool-spreekuur/"],"congress":"","summary_en":"Researchers developed an AI tool to automatically extract cardiovascular complications (bleeding, tamponade, stroke, phrenic paralysis) from electronic health records following PVI, PTCA, and TAVI procedures. In a single-center retrospective cohort of 6,564 patients, the model achieved a sensitivity of 94.4–100% and specificity of 99.4–100%. Automating complication detection could significantly reduce administrative workload and improve data quality for clinical quality improvement cycles.","created":"2026-10-24T01:13:06Z","updated":"2026-10-24T01:13:06Z","licence":"Citeer vrij, met bronvermelding en een link naar hartvaat.nl (de url van het record). Samenvattingen zijn redactioneel werk van HartVaat; de oorspronkelijke publicaties blijven van hun uitgevers (doi). Geen medisch advies.","body_markdown":"Een onderzoeksteam ontwikkelde een AI-gereedschap dat complicaties zoals bloedingen, tamponade en CVA automatisch uit elektronische patiëntendossiers haalt bij patiënten die een PVI, PTCA of TAVI ondergaan. In een retrospectieve cohortstudie van 6.564 patiënten bereikte het model een gevoeligheid van 94,4–100% en een specificiteit van 99,4–100%. Automatische detectie kan de administratieve last voor zorgverleners verlagen en de registratiekwaliteit van interventiecomplicaties verbeteren, wat ten goede komt aan patiëntveiligheid en kwaliteitscyclus.","abstract_original":"BACKGROUND: Intervention-related complications negatively affect healthcare quality and costs. Complication registration and reporting play an important role in the improvement of healthcare outcomes but are time-consuming and hampered by under-reporting. METHODS: We developed an artificial intelligence (AI)-aided tool that extracts specific complications, including bleeding, tamponade, CVA and phrenic paralysis, from electronic healthcare records of patients undergoing pulmonary vein isolation (PVI), percutaneous transluminal coronary angioplasty (PTCA) and transcatheter aortic valve implantation (TAVI). Both structured and unstructured data were used, along with additional signals identified through machine learning. The model was optimized to achieve high sensitivity. RESULTS: Electronic records of 6,564 patients undergoing PVI, PTCA, and TAVI, performed at our hospital from 2017-2022, were used. The final model detected the various complications with a sensitivity between 94.4 and 100%, while specificity ranged from 99.4-100%. This resulted in positive predictive values ranging from 47.5-81%, with F‑scores varying between 0.64-0.87. CONCLUSION: We developed an AI-driven tool capable of automatically detecting complications following cardiac interventions from patient healthcare records, achieving a very high sensitivity. Our tool enables registration of complications while significantly reducing administrative burden on the healthcare providers and data managers. It provides valuable and high-quality input for improvement cycles, thereby enhancing patient safety and healthcare quality."}