{"id":"acd36875baab","type":"article","url":"https://hartvaat.nl/2026/05/27/multimodaal-ai-model-verhoogt-accuratesse-van-echo-diagnose-cardiale-amyloidose/","title":"Multimodaal AI-model verhoogt accuratesse van echo-diagnose cardiale amyloïdose","title_en":"","category":"hartfalen","category_label":"Hartfalen","professions":["cardioloog"],"tags":["cardiale-amyloidose"],"journal":"Circulation. Cardiovascular imaging","doi":"10.1161/CIRCIMAGING.126.019610","source_url":"https://doi.org/10.1161/CIRCIMAGING.126.019610","authors":["Jeremy A Slivnick","Sze Chi Lim","Michael Randazzo","Mathew S Maurer","Stephen Helmke","Marielle Scherrer-Crosbie","Azin Vakilpour","Karolina M Zareba","Akash Goyal","Richard Cheng","Nicole Wakamatsu","Tetsuji Kitano","Masaaki Takeuchi","Viviane Tiemi Hotta","Marcelo Luiz Campos Vieira","Pablo Elissamburu","Ricardo E Ronderos","Aldo Prado","Efstratios Koutroumpakis","Anita Deswal","Amit Pursnani","Nitasha Sarswat","Karima Addetia","Juan Cotella","Frederick L Ruberg","Matthew Frost","Marianna Fontana","Carolyn Lam Su Ping","Roberto M Lang","Federico M Asch"],"significance":7,"published":"2026-05-28","source_date":"2026-05-27","image":"","kennis":["https://hartvaat.nl/kennis/farmacologie/betablokkers-cardiale-indicaties/","https://hartvaat.nl/kennis/hartfalen/diagnose-hartfalen-stappenplan/"],"congress":"","summary_en":"The Amyloidosis Imaging International Consortium evaluated an integrated AI model (AI-ECM) combining clinical data, laboratory biomarkers, and echocardiographic parameters with the existing TTE-only AI tool Us2.Ca. In 727 patients with cardiac amyloidosis and 316 controls, the combined model significantly outperformed Us2.Ca alone: AUC 0.94 (vs 0.89), 90% accuracy, 93% sensitivity, 85% specificity. AI-ECM also classified all cases where Us2.Ca was indeterminate in 9%. A step toward scalable AI-guided diagnostics for an underdiagnosed but treatable cause of heart failure.","created":"2026-07-03T10:32:57Z","updated":"2026-07-03T13:31:52Z","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":"Het Amyloidosis Imaging International Consortium evalueerde een geïntegreerd AI-model (AI-ECM) dat klinische gegevens, laboratoriumbiomarkers en echocardiografische parameters combineert met het bestaande TTE-only AI-model Us2.Ca. Bij 727 patiënten met cardiale amyloïdose en 316 controles presteerde het gecombineerde model significant beter: AUC 0,94 (versus 0,89 voor Us2.Ca alleen), 90% accuracy, 93% sensitiviteit en 85% specificiteit. AI-ECM classificeerde bovendien álle gevallen, terwijl Us2.Ca in 9% van de gevallen geen oordeel kon geven. Een stap richting opschaalbare AI-geleide diagnostiek voor een onderdiagnostiseerde maar behandelbare oorzaak van hartfalen.","abstract_original":"BACKGROUND: Cardiac amyloidosis (CA) is an underdiagnosed yet treatable cause of heart failure in which timely diagnosis is essential to initiate life-prolonging therapies. While artificial intelligence (AI)-based tools using transthoracic echocardiography (TTE), electrocardiography, or electronic health records have demonstrated promise for CA detection, most rely on single data sources. We aimed to evaluate whether integrating clinical, laboratory, and TTE biomarkers improves the performance of an existing TTE-based AI model for CA detection. METHODS: We developed and tested a combined AI echo-clinical model (AI-ECM) incorporating demographics, laboratory biomarkers, and TTE parameters into a previously validated TTE-only AI model (Us2.Ca). Model training and internal validation were performed using the Amyloidosis Imaging International Consortium, a global multiethnic registry comprised of 727 patients with CA and 316 controls, including 202 with suspected transthyretin-CA with negative diagnostic evaluation and 114 patients with biopsy-proven extracardiac light chain amyloidosis without cardiac involvement. Ground truth CA diagnosis was adjudicated per consensus criteria. AI-ECM and Us2.Ca performance was assessed using area under the curve, accuracy, sensitivity, and specificity. RESULTS: In building the AI-ECM, feature importance analysis showed that having the Us2.Ca prediction scores, relative wall thickness, gender, and estimated glomerular filtration rate contributed most to performance. The AI-ECM demonstrated superior performance (area under the curve, 0.94; accuracy, 90%; sensitivity, 93%; specificity, 85%) compared with the Us2.Ca (area under the curve, 0.89; accuracy, 80%; sensitivity, 76%; specificity, 91%; P=0.006). While the Us2.Ca model classification was indeterminate in 9% of the cases, the AI-ECM allowed classification of all cases. The AI-ECM improved sensitivity for light chain-CA detection and maintained high accuracy across subtypes and control groups. CONCLUSIONS: A multiparametric AI model integrating basic clinical, laboratory, and TTE data with the deep learning Us2.Ca improved performance for CA detection over Us2.Ca alone. This approach represents a step toward scalable, AI-guided precision diagnostics for CA in diverse populations."}