{"id":434035,"date":"2026-08-24T17:23:53","date_gmt":"2026-08-24T09:23:53","guid":{"rendered":"https:\/\/library.usj.edu.mo\/?post_type=tnc_col_19837_item&#038;p=434035"},"modified":"2026-08-24T18:33:14","modified_gmt":"2026-08-24T10:33:14","slug":"machine-learning-based-cardiac-activity-non-linear-analysis-for-discriminating-covid-19-patients-with-different-degrees-of-severity","status":"publish","type":"tnc_col_19837_item","link":"https:\/\/library.usj.edu.mo\/zh\/scholarly-work-usj\/machine-learning-based-cardiac-activity-non-linear-analysis-for-discriminating-covid-19-patients-with-different-degrees-of-severity\/","title":{"rendered":"MACHINE LEARNING-BASED CARDIAC ACTIVITY NON-LINEAR ANALYSIS FOR DISCRIMINATING COVID-19 PATIENTS WITH DIFFERENT DEGREES OF SEVERITY"},"content":{"rendered":"<p>OBJECTIVE: THIS STUDY HIGHLIGHTS THE POTENTIAL OF AN ELECTROCARDIOGRAM (ECG) AS A POWERFUL TOOL FOR EARLY DIAGNOSIS OF COVID-19 IN CRITICALLY ILL PATIENTS WITH LIMITED ACCESS TO CT\u2013SCAN ROOMS. METHODS: IN THIS INVESTIGATION, 3 CATEGORIES OF PATIENT STATUS WERE CONSIDERED: LOW, MODERATE, AND SEVERE. FOR EACH PATIENT, 2 DIFFERENT BODY POSITIONS HAVE BEEN USED TO COLLECT 2 ECG SIGNALS. THEN, FROM EACH COLLECTED SIGNAL, 10 NON-LINEAR FEATURES (ENERGY, APPROXIMATE ENTROPY, LOGARITHMIC ENTROPY, SHANNON ENTROPY, HURST EXPONENT, LYAPUNOV EXPONENT, HIGUCHI FRACTAL DIMENSION, KATZ FRACTAL DIMENSION, CORRELATION DIMENSION AND DETRENDED FLUCTUATION ANALYSIS) WERE EXTRACTED EVERY 1S ECG TIME-SERIES LENGTH TO SERVE AS ENTRIES FOR 19 MACHINE LEARNING CLASSIFIERS WITHIN A LEAVE-ONE-OUT CROSS-VALIDATION PROCEDURE. FOUR DIFFERENT CLASSIFICATION SCENARIOS WERE TESTED: LOW VS. MODERATE, LOW VS. SEVERE, MODERATE VS. SEVERE AND ONE MULTI-CLASS COMPARISON (ALL VS. ALL). RESULTS: THE CLASSIFICATION REPORT RESULTS WERE: (1) LOW VS. MODERATE &#8211; 100% OF ACCURACY AND 100% OF F1\u2013SCORE||(2) LOW VS. SEVERE &#8211; ACCURACY OF 91.67% AND AN F1\u2013SCORE OF 94.92%||(3) MODERATE VS. SEVERE &#8211; ACCURACY OF 94.12% AND AN F1\u2013SCORE OF 96.43%||AND (4) ALL VS ALL &#8211; 78.57% OF ACCURACY AND 84.75% OF F1\u2013SCORE. CONCLUSION: THE RESULTS INDICATE THAT THE APPLIED METHODOLOGY COULD BE CONSIDERED A GOOD TOOL FOR DISTINGUISHING COVID-19\u2019S DIFFERENT SEVERITY STAGES USING ECG SIGNALS. SIGNIFICANCE: THE FINDINGS HIGHLIGHT THE POTENTIAL OF ECG AS A FAST AND EFFECTIVE TOOL FOR COVID-19 EXAMINATION. IN COMPARISON TO PREVIOUS STUDIES USING THE SAME DATABASE, THIS STUDY SHOWS A 7.57% IMPROVEMENT IN DIAGNOSTIC ACCURACY FOR THE ALL VS ALL COMPARISON.<\/p>","protected":false},"author":2,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","format":"standard","class_list":["post-434035","tnc_col_19837_item","type-tnc_col_19837_item","status-publish","format-standard","hentry","tnc_tax_19993-sdg-3-good-health-and-well-being","tnc_tax_19818-english","tnc_tax_19716-faculty-of-business-and-law","tnc_tax_19659-journal-article"],"taxonomy_info":[],"featured_image_src_large":false,"author_info":[],"comment_info":0,"featured_img":false,"coauthors":[],"author_meta":{"author_link":"https:\/\/library.usj.edu.mo\/zh\/author\/emilychan\/","display_name":"emily chan"},"relative_dates":{"created":"Posted 4 \u5929 ago","modified":"Updated 4 \u5929 ago"},"absolute_dates":{"created":"Posted on 24 8 \u6708, 2026","modified":"Updated on 24 8 \u6708, 2026"},"absolute_dates_time":{"created":"Posted on 24 8 \u6708, 2026 5:23 \u4e0b\u5348","modified":"Updated on 24 8 \u6708, 2026 6:33 \u4e0b\u5348"},"featured_img_caption":"","tax_additional":{"tnc_tax_19993":{"linked":["<a href=\"https:\/\/library.usj.edu.mo\/zh\/sdgs\/sdg-3-good-health-and-well-being\/\" class=\"advgb-post-tax-term\">SDG 3 Good Health and Well-being<\/a>"],"unlinked":["<span class=\"advgb-post-tax-term\">SDG 3 Good Health and Well-being<\/span>"],"slug":"tnc_tax_19993","name":"SDGs"},"tnc_tax_19818":{"linked":["<a href=\"https:\/\/library.usj.edu.mo\/zh\/language\/english\/\" class=\"advgb-post-tax-term\">ENGLISH<\/a>"],"unlinked":["<span class=\"advgb-post-tax-term\">ENGLISH<\/span>"],"slug":"tnc_tax_19818","name":"LANGUAGE"},"tnc_tax_19716":{"linked":["<a href=\"https:\/\/library.usj.edu.mo\/zh\/faculty-research-unit\/faculty-of-business-and-law\/\" class=\"advgb-post-tax-term\">FACULTY OF BUSINESS AND LAW<\/a>"],"unlinked":["<span class=\"advgb-post-tax-term\">FACULTY OF BUSINESS AND LAW<\/span>"],"slug":"tnc_tax_19716","name":"FACULTY \/ RESEARCH UNIT"},"tnc_tax_19664":{"linked":[],"unlinked":[],"slug":"tnc_tax_19664","name":"SUBJECT"},"tnc_tax_19659":{"linked":["<a href=\"https:\/\/library.usj.edu.mo\/zh\/resource-type\/journal-article\/\" class=\"advgb-post-tax-term\">Journal Article<\/a>"],"unlinked":["<span class=\"advgb-post-tax-term\">Journal Article<\/span>"],"slug":"tnc_tax_19659","name":"Document Type"}},"series_order":"","_links":{"self":[{"href":"https:\/\/library.usj.edu.mo\/zh\/wp-json\/wp\/v2\/tnc_col_19837_item\/434035","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/library.usj.edu.mo\/zh\/wp-json\/wp\/v2\/tnc_col_19837_item"}],"about":[{"href":"https:\/\/library.usj.edu.mo\/zh\/wp-json\/wp\/v2\/types\/tnc_col_19837_item"}],"replies":[{"embeddable":true,"href":"https:\/\/library.usj.edu.mo\/zh\/wp-json\/wp\/v2\/comments?post=434035"}],"version-history":[{"count":1,"href":"https:\/\/library.usj.edu.mo\/zh\/wp-json\/wp\/v2\/tnc_col_19837_item\/434035\/revisions"}],"predecessor-version":[{"id":436392,"href":"https:\/\/library.usj.edu.mo\/zh\/wp-json\/wp\/v2\/tnc_col_19837_item\/434035\/revisions\/436392"}],"wp:attachment":[{"href":"https:\/\/library.usj.edu.mo\/zh\/wp-json\/wp\/v2\/media?parent=434035"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}