{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T23:14:10Z","timestamp":1790723650975,"version":"4.1.0"},"reference-count":0,"publisher":"IOP Publishing","license":[{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Physiol. Meas."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Objective. Automated electrocardiogram (ECG) interpretation is increasingly delivered as cloud deep-learning services, trading data sovereignty, auditability and robustness for accuracy. This study tests whether an offline, explainable framework can remove that trade-off.&amp;#xD;&amp;#xD;Approach. Three independent interpreters feed a decision-fusion layer: a deterministic engine of 26 executable clinical criteria, each finding linked to a highlighted signal segment and a literature source; a compact one-dimensional residual network trained on PTB-XL and run on-device via the Open Neural Network Exchange runtime; and an optional agentic vision\u2013language model reading a rendered ECG image behind a security screen with human-in-the-loop escalation. Format-agnostic ingestion, lead-aware capability tiering and a three-tier signal-quality gate precede interpretation. Evaluation covers diagnostic accuracy, on-device latency, noise resilience, modality ablation and zero-shot external validation.&amp;#xD;&amp;#xD;Main results. On the PTB-XL test fold (n = 2198) the network reaches a macro-averaged area under the receiver operating characteristic curve (AUROC) of 0.932 (95% confidence interval (CI) 0.918\u20130.943), matching published GPU baselines, while the complete pipeline runs in 108 \u00b1 25 ms on a CPU with no network access. Performance degrades gracefully to a signal-to-noise ratio of 5 dB (AUROC 0.951) as the quality gate rejects uninterpretable signals, and rules and network agree only weakly (Cohen's kappa 0.26), indicating complementary errors. Applied without retraining to an independent cohort (Chapman\u2013Shaoxing, n = 1599) the model retains a macro-AUROC of 0.898. In a small pilot (25 records; 30 rule\/network disagreements) the general-purpose agentic model was the weakest adjudicator (accuracy 0.267, 95% CI 0.142\u20130.444; exact McNemar test versus rules, p = 0.09).&amp;#xD;&amp;#xD;Significance. Edge inference, intrinsic explainability and governed multi-modal fusion give competitive accuracy with auditable findings. The agentic layer is positioned for governance rather than diagnosis, motivating ECG-specialized models. The open-source system is a research prototype, not a medical device.<\/jats:p>","DOI":"10.1088\/1361-6579\/aeaded","type":"journal-article","created":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T22:53:01Z","timestamp":1790722381000},"source":"Crossref","is-referenced-by-count":0,"title":["A tri-modal, offline, and explainable framework for 12-lead electrocardiogram interpretation: fusing deterministic rules, a local residual network, and an agentic vision-language model"],"prefix":"10.1088","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6369-7915","authenticated-orcid":false,"given":"Mohammad Mahbubur Rahman","family":"Khan Mamun","sequence":"first","affiliation":[{"name":"Independent researcher"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,9,29]]},"container-title":["Physiological Measurement"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aeaded","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aeaded\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aeaded\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aeaded\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T22:53:02Z","timestamp":1790722382000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aeaded"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,29]]},"references-count":0,"URL":"https:\/\/doi.org\/10.1088\/1361-6579\/aeaded","relation":{},"ISSN":["0967-3334","1361-6579"],"issn-type":[{"value":"0967-3334","type":"print"},{"value":"1361-6579","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,29]]}}}