Enhanced ECG Arrhythmia Detection Accuracy by Optimizing Divergence-Based Data Fusion Article Swipe

PDF

Baozhuo Su , Qingli Dou , Liu Kang , Zhengxian Qu , Jianjun Deng , Ting Tan , Yanan Gu ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.21203/rs.3.rs-6265131/v1

AI computation in healthcare faces significant challenges when clinical datasets are limited and heterogeneous. Integrating datasets from multiple sources and different equipments is critical for effective AI computation but is complicated by their diversity, complexity, and lack of representativeness, so we often need to join multiple datasets for analysis. The currently used method is fusion after normalization. But when using this method, it can introduce redundant information, decreasing the signal-to-noise ratio and reducing classification accuracy. To tackle this issue, we propose a feature-based fusion algorithm utilizing Kernel Density Estimation (KDE) and Kullback-Leibler (KL) divergence. Our approach involves initially preprocessing and continuous estimation on the extracted features, followed by employing the gradient descent method to identify the optimal linear parameters that minimize the KL divergence between the feature distributions. Using our in-house datasets consisting of ECG signals collected from 2000 healthy and 2000 diseased individuals by different equipments and verifying our method by using the publicly available PTB-XL dataset which contains 21,837 ECG recordings from 18,885 patients. We employ a Light Gradient Boosting Machine (LGBM) model to do the binary classification. The results demonstrate that the proposed fusion method significantly enhances feature-based classification accuracy for abnormal ECG cases in the merged datasets, compared to the normalization method. This data fusion strategy provides a new approach to process heterogeneous datasets for the optimal AI computation results.

Related Topics

Jazz Fusion

Artificial Intelligence

Concepts

Divergence (linguistics) Fusion Artificial intelligence Sensor fusion Computer science Data mining Pattern recognition (psychology) Philosophy Linguistics

Metadata

Type: preprint
Language: en
Landing Page: https://doi.org/10.21203/rs.3.rs-6265131/v1
PDF: https://www.researchsquare.com/article/rs-6265131/latest.pdf
OA Status: gold
Related Works: 10
OpenAlex ID: https://openalex.org/W4408989055

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4408989055

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.21203/rs.3.rs-6265131/v1

Digital Object Identifier
Title: Enhanced ECG Arrhythmia Detection Accuracy by Optimizing Divergence-Based Data Fusion

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-03-31

Full publication date if available
Authors: Baozhuo Su, Qingli Dou, Liu Kang, Zhengxian Qu, Jianjun Deng, Ting Tan, Yanan Gu

List of authors in order
Landing page: https://doi.org/10.21203/rs.3.rs-6265131/v1

Publisher landing page
PDF URL: https://www.researchsquare.com/article/rs-6265131/latest.pdf

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: gold

Open access status per OpenAlex
OA URL: https://www.researchsquare.com/article/rs-6265131/latest.pdf

Direct OA link when available
Concepts: Divergence (linguistics), Fusion, Artificial intelligence, Sensor fusion, Computer science, Data mining, Pattern recognition (psychology), Philosophy, Linguistics

Top concepts (fields/topics) attached by OpenAlex
Cited by: 0

Total citation count in OpenAlex
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4408989055
doi	https://doi.org/10.21203/rs.3.rs-6265131/v1
ids.doi	https://doi.org/10.21203/rs.3.rs-6265131/v1
ids.openalex	https://openalex.org/W4408989055
fwci	0.0
type	preprint
title	Enhanced ECG Arrhythmia Detection Accuracy by Optimizing Divergence-Based Data Fusion
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T11021
topics[0].field.id	https://openalex.org/fields/27
topics[0].field.display_name	Medicine
topics[0].score	0.8611999750137329
topics[0].domain.id	https://openalex.org/domains/4
topics[0].domain.display_name	Health Sciences
topics[0].subfield.id	https://openalex.org/subfields/2705
topics[0].subfield.display_name	Cardiology and Cardiovascular Medicine
topics[0].display_name	ECG Monitoring and Analysis
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C207390915
concepts[0].level	2
concepts[0].score	0.5262566804885864
concepts[0].wikidata	https://www.wikidata.org/wiki/Q1230525
concepts[0].display_name	Divergence (linguistics)
concepts[1].id	https://openalex.org/C158525013
concepts[1].level	2
concepts[1].score	0.45315974950790405
concepts[1].wikidata	https://www.wikidata.org/wiki/Q2593739
concepts[1].display_name	Fusion
concepts[2].id	https://openalex.org/C154945302
concepts[2].level	1
concepts[2].score	0.443888783454895
concepts[2].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[2].display_name	Artificial intelligence
concepts[3].id	https://openalex.org/C33954974
concepts[3].level	2
concepts[3].score	0.43384677171707153
concepts[3].wikidata	https://www.wikidata.org/wiki/Q486494
concepts[3].display_name	Sensor fusion
concepts[4].id	https://openalex.org/C41008148
concepts[4].level	0
concepts[4].score	0.43003562092781067
concepts[4].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[4].display_name	Computer science
concepts[5].id	https://openalex.org/C124101348
concepts[5].level	1
concepts[5].score	0.3496878147125244
concepts[5].wikidata	https://www.wikidata.org/wiki/Q172491
concepts[5].display_name	Data mining
concepts[6].id	https://openalex.org/C153180895
concepts[6].level	2
concepts[6].score	0.32466182112693787
concepts[6].wikidata	https://www.wikidata.org/wiki/Q7148389
concepts[6].display_name	Pattern recognition (psychology)
concepts[7].id	https://openalex.org/C138885662
concepts[7].level	0
concepts[7].score	0.0
concepts[7].wikidata	https://www.wikidata.org/wiki/Q5891
concepts[7].display_name	Philosophy
concepts[8].id	https://openalex.org/C41895202
concepts[8].level	1
concepts[8].score	0.0
concepts[8].wikidata	https://www.wikidata.org/wiki/Q8162
concepts[8].display_name	Linguistics
keywords[0].id	https://openalex.org/keywords/divergence
keywords[0].score	0.5262566804885864
keywords[0].display_name	Divergence (linguistics)
keywords[1].id	https://openalex.org/keywords/fusion
keywords[1].score	0.45315974950790405
keywords[1].display_name	Fusion
keywords[2].id	https://openalex.org/keywords/artificial-intelligence
keywords[2].score	0.443888783454895
keywords[2].display_name	Artificial intelligence
keywords[3].id	https://openalex.org/keywords/sensor-fusion
keywords[3].score	0.43384677171707153
keywords[3].display_name	Sensor fusion
keywords[4].id	https://openalex.org/keywords/computer-science
keywords[4].score	0.43003562092781067
keywords[4].display_name	Computer science
keywords[5].id	https://openalex.org/keywords/data-mining
keywords[5].score	0.3496878147125244
keywords[5].display_name	Data mining
keywords[6].id	https://openalex.org/keywords/pattern-recognition
keywords[6].score	0.32466182112693787
keywords[6].display_name	Pattern recognition (psychology)
language	en
locations[0].id	doi:10.21203/rs.3.rs-6265131/v1
locations[0].is_oa	True
locations[0].source
locations[0].license	cc-by
locations[0].pdf_url	https://www.researchsquare.com/article/rs-6265131/latest.pdf
locations[0].version	acceptedVersion
locations[0].raw_type	posted-content
locations[0].license_id	https://openalex.org/licenses/cc-by
locations[0].is_accepted	True
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	https://doi.org/10.21203/rs.3.rs-6265131/v1
indexed_in	crossref
authorships[0].author.id	https://openalex.org/A5071072435
authorships[0].author.orcid	https://orcid.org/0009-0008-6077-6173
authorships[0].author.display_name	Baozhuo Su
authorships[0].affiliations[0].raw_affiliation_string	Aerie Intelligent Technology
authorships[0].author_position	first
authorships[0].raw_author_name	Baozhuo Su
authorships[0].is_corresponding	False
authorships[0].raw_affiliation_strings	Aerie Intelligent Technology
authorships[1].author.id	https://openalex.org/A5026711341
authorships[1].author.orcid
authorships[1].author.display_name	Qingli Dou
authorships[1].countries	CN
authorships[1].affiliations[0].institution_ids	https://openalex.org/I4210134759
authorships[1].affiliations[0].raw_affiliation_string	Shenzhen Bao'an District People's Hospital
authorships[1].institutions[0].id	https://openalex.org/I4210134759
authorships[1].institutions[0].ror	https://ror.org/04dkfar71
authorships[1].institutions[0].type	healthcare
authorships[1].institutions[0].lineage	https://openalex.org/I4210134759
authorships[1].institutions[0].country_code	CN
authorships[1].institutions[0].display_name	Shenzhen Bao'an District People's Hospital
authorships[1].author_position	middle
authorships[1].raw_author_name	Qingli Dou
authorships[1].is_corresponding	False
authorships[1].raw_affiliation_strings	Shenzhen Bao'an District People's Hospital
authorships[2].author.id	https://openalex.org/A5024107573
authorships[2].author.orcid	https://orcid.org/0009-0005-1307-330X
authorships[2].author.display_name	Liu Kang
authorships[2].affiliations[0].raw_affiliation_string	Aerie Intelligent Technology
authorships[2].author_position	middle
authorships[2].raw_author_name	Kang Liu
authorships[2].is_corresponding	False
authorships[2].raw_affiliation_strings	Aerie Intelligent Technology
authorships[3].author.id	https://openalex.org/A5112522168
authorships[3].author.orcid	https://orcid.org/0009-0009-0592-8741
authorships[3].author.display_name	Zhengxian Qu
authorships[3].affiliations[0].raw_affiliation_string	Aerie Intelligent Technology
authorships[3].author_position	middle
authorships[3].raw_author_name	Zhengxian Qu
authorships[3].is_corresponding	False
authorships[3].raw_affiliation_strings	Aerie Intelligent Technology
authorships[4].author.id	https://openalex.org/A5085720122
authorships[4].author.orcid	https://orcid.org/0000-0002-3057-6997
authorships[4].author.display_name	Jianjun Deng
authorships[4].affiliations[0].raw_affiliation_string	Aerie Intelligent Technology
authorships[4].author_position	middle
authorships[4].raw_author_name	Jerry Deng
authorships[4].is_corresponding	False
authorships[4].raw_affiliation_strings	Aerie Intelligent Technology
authorships[5].author.id	https://openalex.org/A5007519353
authorships[5].author.orcid	https://orcid.org/0000-0002-7533-4553
authorships[5].author.display_name	Ting Tan
authorships[5].affiliations[0].raw_affiliation_string	Aerie Intelligent Technology
authorships[5].author_position	middle
authorships[5].raw_author_name	Ting Tan
authorships[5].is_corresponding	False
authorships[5].raw_affiliation_strings	Aerie Intelligent Technology
authorships[6].author.id	https://openalex.org/A5112124425
authorships[6].author.orcid	https://orcid.org/0009-0000-7908-585X
authorships[6].author.display_name	Yanan Gu
authorships[6].countries	CN
authorships[6].affiliations[0].institution_ids	https://openalex.org/I4210134759
authorships[6].affiliations[0].raw_affiliation_string	Shenzhen Bao'an District People's Hospital
authorships[6].institutions[0].id	https://openalex.org/I4210134759
authorships[6].institutions[0].ror	https://ror.org/04dkfar71
authorships[6].institutions[0].type	healthcare
authorships[6].institutions[0].lineage	https://openalex.org/I4210134759
authorships[6].institutions[0].country_code	CN
authorships[6].institutions[0].display_name	Shenzhen Bao'an District People's Hospital
authorships[6].author_position	last
authorships[6].raw_author_name	Yanan Gu
authorships[6].is_corresponding	False
authorships[6].raw_affiliation_strings	Shenzhen Bao'an District People's Hospital
has_content.pdf	True
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://www.researchsquare.com/article/rs-6265131/latest.pdf
open_access.oa_status	gold
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Enhanced ECG Arrhythmia Detection Accuracy by Optimizing Divergence-Based Data Fusion
has_fulltext	False
is_retracted	False
updated_date	2025-11-09T23:09:16.995542
primary_topic.id	https://openalex.org/T11021
primary_topic.field.id	https://openalex.org/fields/27
primary_topic.field.display_name	Medicine
primary_topic.score	0.8611999750137329
primary_topic.domain.id	https://openalex.org/domains/4
primary_topic.domain.display_name	Health Sciences
primary_topic.subfield.id	https://openalex.org/subfields/2705
primary_topic.subfield.display_name	Cardiology and Cardiovascular Medicine
primary_topic.display_name	ECG Monitoring and Analysis
related_works	https://openalex.org/W4403822433, https://openalex.org/W3208095355, https://openalex.org/W2177370417, https://openalex.org/W2052507016, https://openalex.org/W2180461068, https://openalex.org/W2051816080, https://openalex.org/W2132659060, https://openalex.org/W2031992971, https://openalex.org/W3214791684, https://openalex.org/W2152662039
cited_by_count	0
locations_count	1
best_oa_location.id	doi:10.21203/rs.3.rs-6265131/v1
best_oa_location.is_oa	True
best_oa_location.source
best_oa_location.license	cc-by
best_oa_location.pdf_url	https://www.researchsquare.com/article/rs-6265131/latest.pdf
best_oa_location.version	acceptedVersion
best_oa_location.raw_type	posted-content
best_oa_location.license_id	https://openalex.org/licenses/cc-by
best_oa_location.is_accepted	True
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	https://doi.org/10.21203/rs.3.rs-6265131/v1
primary_location.id	doi:10.21203/rs.3.rs-6265131/v1
primary_location.is_oa	True
primary_location.source
primary_location.license	cc-by
primary_location.pdf_url	https://www.researchsquare.com/article/rs-6265131/latest.pdf
primary_location.version	acceptedVersion
primary_location.raw_type	posted-content
primary_location.license_id	https://openalex.org/licenses/cc-by
primary_location.is_accepted	True
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	https://doi.org/10.21203/rs.3.rs-6265131/v1
publication_date	2025-03-31
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	82, 169, 212
abstract_inverted_index.AI	1, 27, 222
abstract_inverted_index.KL	123
abstract_inverted_index.To	76
abstract_inverted_index.We	167
abstract_inverted_index.by	32, 108, 145, 152
abstract_inverted_index.do	177
abstract_inverted_index.in	3, 198
abstract_inverted_index.is	23, 30, 54
abstract_inverted_index.it	63
abstract_inverted_index.of	38, 134
abstract_inverted_index.on	103
abstract_inverted_index.so	40
abstract_inverted_index.to	44, 114, 176, 203, 215
abstract_inverted_index.we	41, 80
abstract_inverted_index.But	58
abstract_inverted_index.ECG	135, 162, 196
abstract_inverted_index.Our	95
abstract_inverted_index.The	50, 181
abstract_inverted_index.and	13, 20, 36, 72, 91, 100, 141, 148
abstract_inverted_index.are	11
abstract_inverted_index.but	29
abstract_inverted_index.can	64
abstract_inverted_index.for	25, 48, 194, 219
abstract_inverted_index.new	213
abstract_inverted_index.our	130, 150
abstract_inverted_index.the	69, 104, 110, 116, 122, 126, 154, 178, 185, 199, 204, 220
abstract_inverted_index.(KL)	93
abstract_inverted_index.2000	139, 142
abstract_inverted_index.This	207
abstract_inverted_index.data	208
abstract_inverted_index.from	17, 138, 164
abstract_inverted_index.join	45
abstract_inverted_index.lack	37
abstract_inverted_index.need	43
abstract_inverted_index.that	120, 184
abstract_inverted_index.this	61, 78
abstract_inverted_index.used	52
abstract_inverted_index.when	8, 59
abstract_inverted_index.(KDE)	90
abstract_inverted_index.Light	170
abstract_inverted_index.Using	129
abstract_inverted_index.after	56
abstract_inverted_index.cases	197
abstract_inverted_index.faces	5
abstract_inverted_index.model	175
abstract_inverted_index.often	42
abstract_inverted_index.ratio	71
abstract_inverted_index.their	33
abstract_inverted_index.using	60, 153
abstract_inverted_index.which	159
abstract_inverted_index.(LGBM)	174
abstract_inverted_index.18,885	165
abstract_inverted_index.21,837	161
abstract_inverted_index.Kernel	87
abstract_inverted_index.PTB-XL	157
abstract_inverted_index.binary	179
abstract_inverted_index.employ	168
abstract_inverted_index.fusion	55, 84, 187, 209
abstract_inverted_index.issue,	79
abstract_inverted_index.linear	118
abstract_inverted_index.merged	200
abstract_inverted_index.method	53, 113, 151, 188
abstract_inverted_index.tackle	77
abstract_inverted_index.Density	88
abstract_inverted_index.Machine	173
abstract_inverted_index.between	125
abstract_inverted_index.dataset	158
abstract_inverted_index.descent	112
abstract_inverted_index.feature	127
abstract_inverted_index.healthy	140
abstract_inverted_index.limited	12
abstract_inverted_index.method,	62
abstract_inverted_index.method.	206
abstract_inverted_index.optimal	117, 221
abstract_inverted_index.process	216
abstract_inverted_index.propose	81
abstract_inverted_index.results	182
abstract_inverted_index.signals	136
abstract_inverted_index.sources	19
abstract_inverted_index.Boosting	172
abstract_inverted_index.Gradient	171
abstract_inverted_index.abnormal	195
abstract_inverted_index.accuracy	193
abstract_inverted_index.approach	96, 214
abstract_inverted_index.clinical	9
abstract_inverted_index.compared	202
abstract_inverted_index.contains	160
abstract_inverted_index.critical	24
abstract_inverted_index.datasets	10, 16, 47, 132, 218
abstract_inverted_index.diseased	143
abstract_inverted_index.enhances	190
abstract_inverted_index.followed	107
abstract_inverted_index.gradient	111
abstract_inverted_index.identify	115
abstract_inverted_index.in-house	131
abstract_inverted_index.involves	97
abstract_inverted_index.minimize	121
abstract_inverted_index.multiple	18, 46
abstract_inverted_index.proposed	186
abstract_inverted_index.provides	211
abstract_inverted_index.publicly	155
abstract_inverted_index.reducing	73
abstract_inverted_index.results.	224
abstract_inverted_index.strategy	210
abstract_inverted_index.accuracy.	75
abstract_inverted_index.algorithm	85
abstract_inverted_index.analysis.	49
abstract_inverted_index.available	156
abstract_inverted_index.collected	137
abstract_inverted_index.currently	51
abstract_inverted_index.datasets,	201
abstract_inverted_index.different	21, 146
abstract_inverted_index.effective	26
abstract_inverted_index.employing	109
abstract_inverted_index.extracted	105
abstract_inverted_index.features,	106
abstract_inverted_index.initially	98
abstract_inverted_index.introduce	65
abstract_inverted_index.patients.	166
abstract_inverted_index.redundant	66
abstract_inverted_index.utilizing	86
abstract_inverted_index.verifying	149
abstract_inverted_index.Estimation	89
abstract_inverted_index.challenges	7
abstract_inverted_index.consisting	133
abstract_inverted_index.continuous	101
abstract_inverted_index.decreasing	68
abstract_inverted_index.divergence	124
abstract_inverted_index.diversity,	34
abstract_inverted_index.equipments	22, 147
abstract_inverted_index.estimation	102
abstract_inverted_index.healthcare	4
abstract_inverted_index.parameters	119
abstract_inverted_index.recordings	163
abstract_inverted_index.Integrating	15
abstract_inverted_index.complexity,	35
abstract_inverted_index.complicated	31
abstract_inverted_index.computation	2, 28, 223
abstract_inverted_index.demonstrate	183
abstract_inverted_index.divergence.	94
abstract_inverted_index.individuals	144
abstract_inverted_index.significant	6
abstract_inverted_index.information,	67
abstract_inverted_index.feature-based	83, 191
abstract_inverted_index.heterogeneous	217
abstract_inverted_index.normalization	205
abstract_inverted_index.preprocessing	99
abstract_inverted_index.significantly	189
abstract_inverted_index.classification	74, 192
abstract_inverted_index.distributions.	128
abstract_inverted_index.heterogeneous.	14
abstract_inverted_index.normalization.	57
abstract_inverted_index.classification.	180
abstract_inverted_index.signal-to-noise	70
abstract_inverted_index.Kullback-Leibler	92
abstract_inverted_index.representativeness,	39
abstract_inverted_index.<title>Abstract</title>	0
cited_by_percentile_year
countries_distinct_count	1
institutions_distinct_count	7
citation_normalized_percentile.value	0.16512624
citation_normalized_percentile.is_in_top_1_percent	False
citation_normalized_percentile.is_in_top_10_percent	False