Deep Neural Networks for Automatic Atrial Fibrillation Detection Using Long-Term Ambulatory Electrocardiography: Retrospective Diagnostic Accuracy Study

Jagdeep Sedha, Jukka A Lipponen, Antti Aho, Helena Jäntti, Onni E Santala, Tomi P Laitinen, Tiina M Laitinen, Jari Halonen, Mika P Tarvainen, Eemu-Samuli Seljola, Noora S Naukkarinen, Olli Rantula, Tuomas T Rissanen, Juha E K Hartikainen, Tero J Martikainen, Andrew Coristine · 2026

Read Deep Neural Networks for Automatic Atrial Fibrillation Detection Using Long-Term Ambulatory Electrocardiography: Retrospective Diagnostic Accuracy Study by Jagdeep Sedha, Jukka A Lipponen, Antti Aho, Helena Jäntti, Onni E Santala, Tomi P Laitinen, Tiina M Laitinen, Jari Halonen, Mika P Tarvainen, Eemu-Samuli Seljola, Noora S Naukkarinen, Olli Rantula, Tuomas T Rissanen, Juha E K Hartikainen, Tero J Martikainen, Andrew Coristine (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13318395.txt.

Description

Jagdeep Sedha leads a 2026 diagnostic accuracy study of a deep neural network. The model spots atrial fibrillation and flutter in long-term heart rhythm recordings. Both conditions raise stroke risk yet often pass unnoticed. Training drew on public sets, earlier study data, and hospital recordings.

Testing used 1,039 recordings from 1,010 patients at Kuopio University Hospital. Experts had checked every recording. At the level of time segments, the model reached 96.4 percent sensitivity. Specificity stayed above 99.99 percent across the test set. Whole recordings were caught with full sensitivity, and false alarms stayed rare. Most false alarms involved other rhythm problems. Performance held across ages, illnesses, and poor-quality traces, suggesting less manual review work.

Catalog record

CREATORJagdeep Sedha, Jukka A Lipponen, Antti Aho, Helena Jäntti, Onni E Santala, Tomi P Laitinen, Tiina M Laitinen, Jari Halonen, Mika P Tarvainen, Eemu-Samuli Seljola, Noora S Naukkarinen, Olli Rantula, Tuomas T Rissanen, Juha E K Hartikainen, Tero J Martikainen, Andrew Coristine
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE40423
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13318395

Browse the full library · About the Tower of Babel