{"id":"97e5b6f4cbfd","type":"article","url":"https://hartvaat.nl/2026/05/26/accurhythm-ai-vermindert-valse-alarmen-bij-ilr-met-62-bespaart-honderden-klinisc/","title":"AccuRhythm AI vermindert valse alarmen bij ILR met 62% — bespaart honderden klinische uren","title_en":"","category":"algemeen","category_label":"Algemeen","professions":["cardioloog"],"tags":[],"journal":"Heart","doi":"http://heart.bmj.com/cgi/content/short/112/12/667?rss=1","source_url":"https://doi.org/http://heart.bmj.com/cgi/content/short/112/12/667?rss=1","authors":["Cocchiara","L.","Brescia","B.","Marchese","P.","Nardi","S.","Arabia","G.","Salucci","A.","Gennaro","F.","Mazzotta","G.","Addeo","L.","Calvi","E.","Mitacchione","G.","Strisciuglio","T.","Vergara","P.","Esposito","G.","Rapacciuolo","A."],"significance":6,"published":"2026-07-02","source_date":"2026-05-26","image":"https://hartvaat.nl/global/img/737cbe5a1f5d.webp","kennis":["https://hartvaat.nl/kennis/coronairlijden/esc-richtlijn-chronisch-coronairlijden-2024/","https://hartvaat.nl/kennis/antistolling/doacs-overzicht/"],"congress":"","summary_en":"Multicenter retrospective study in 800 patients with an implantable loop recorder (Reveal LINQ or LINQ II) evaluating the cloud-based AI filtering algorithm AccuRhythm AI for false-positive alerts and clinical workload. AI filtering reduced false pause alerts by 62% and false AF alerts by 33%, saving 210 clinician hours over 6 months. At the patient level (n=465 Reveal LINQ users), the proportion of patients with ≥1 false-positive transmission fell from 55.5% to 15.1% (p<0.001), saving 1,128 hours. All residual false alerts occurred in patients with R-wave amplitudes <0.4 mV. AccuRhythm AI thus reduces workload without compromising diagnostic accuracy, with R-wave amplitude as the critical factor — underscoring the importance of optimal device implantation and signal quality.","created":"2026-07-03T10:33:09Z","updated":"2026-07-03T13:32:03Z","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":"Multicenter retrospectieve studie bij 800 patiënten met een implanteerbare loop recorder (Reveal LINQ of LINQ II) waarin het cloud-gebaseerde AI-filteralgoritme AccuRhythm AI werd geëvalueerd op false-positive alarmen en klinische werklast. AI-filtering verlaagde false-pause-alarmen met 62% en false-AF-alarmen met 33%, met 210 klinische uren bespaard over 6 maanden. Op patiëntniveau (n=465 Reveal LINQ-gebruikers) daalde het percentage patiënten met ≥1 false-positive transmissie van 55,5% naar 15,1% (p<0,001), goed voor 1.128 bespaarde uren. Alle resterende valse alarmen traden op bij patiënten met R-top-amplitudes <0,4 mV. AccuRhythm AI vermindert dus arbeidsbelasting zonder de diagnostische accuratesse aan te tasten, met R-top-amplitude als kritische sleutelfactor — onderstreept het belang van optimale device-implantatie en signaalkwaliteit.","abstract_original":"<sec><st>Background</st>\n<p>False-positive (FP) alerts from implantable loop recorders increase clinical workload and may delay appropriate intervention. AccuRhythm AI, a cloud-based filtering algorithm, is designed to reduce these alerts in Reveal LINQ and LINQ II devices. This study assessed the algorithm&rsquo;s effect on FP and clinician burden reduction, with a focus on the influence of R-wave sensing amplitude.</p>\n</sec>\n<sec><st>Methods</st>\n<p>This multicentre, retrospective study included 800 patients with either Reveal LINQ or LINQ II. We analysed automated artificial intelligence (AI) reports and compared FP rates and transmission burden before and after software-based AI activation in the subset of Reveal LINQ patients to assess patient-level changes. The relationship between R-wave amplitude and FP incidence was also evaluated.</p>\n</sec>\n<sec><st>Results</st>\n<p>AI-based filtering, by AccuRhythm AI automatic analysis, reduced false pause alerts by 62% and false atrial fibrillation alerts by 33%, saving 210 clinician hours over 6 months. Patient level analysis, among 465 Reveal LINQ patients, showed FP+ patients (patients with &ge;1 false-positive transmission) reduction from 55.5% to 15.1% post-AI (p&lt;0.001), translating to 1128 hours saved. All residual false alerts occurred in patients with R-wave amplitudes &lt;0.4 mV.</p>\n</sec>\n<sec><st>Conclusion</st>\n<p>Use of AccuRhythm AI was associated with a significant reduction in FPs and clinician workload while preserving diagnostic accuracy. R-wave amplitude remained a key factor influencing alert specificity, emphasising the continued importance of optimal device implantation and signal quality.</p>\n</sec>"}