Early detection of coronary microvascular dysfunction using machine learning algorithm based on vectorcardiography and cardiodynamicsgram features

Xiaoye Zhao, Yinglan Gong, Jucheng Zhang, Haipeng Liu, Tianhai Huang, Jun Jiang, Yanli Niu, Ling Xia, Jiandong Mao

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)
12 Downloads (Pure)


Purpose As a main etiology of myocardial ischemia, coronary microvascular dysfunction (CMD) can occur in patients with or without obstructive coronary artery disease. Currently, there is a lack of a non-invasive approach for early detection of CMD. Aim We aim to develop a multilayer perceptron (MLP) algorithm to achieve non-invasive early detection of CMD based on vectorcardiography (VCG) and cardiodynamicsgram (CDG) features. Methods Electrocardiograms of 82 CMD patients and 107 healthy controls were collected and synthesized into VCGs. The VCGs' ST-T segments were extracted and fed into a deterministic learning algorithm to develop CDGs. Temporal heterogeneity index, spatial heterogeneity index, sample entropy, approximate entropy, and complexity index were extracted from VCGs' ST-T segments and CDGs, entitled as STT- and CDG-based features, respectively. The most effective feature subsets were determined from CDG-based, STT-based, and the combined features (i.e., all features) via the sequential backward selection algorithm as inputs for CDG-, STT-, and CDG-STT-based MLP models optimized with an improved sparrow search algorithm, respectively. Finally, the classification capacity of the corresponding models was evaluated via five-fold cross-validations and tested on a testing dataset to verify the optimal one. Results The CDG-STT-based MLP model had significantly higher evaluated metrics than CDG- and STT-based ones on the validation dataset, with the accuracy, sensitivity, specificity, F1 score, and AUC of 0.904, 0.925, 0.870, 0.870, and 0.897 on the testing dataset respectively. Conclusions The MLP model based on VCG and CDG features showed high efficiency in identifying CMD. The CDG-STT-based MLP model may afford a potential computer-aided tool for non-invasive detection of CMD.
Original languageEnglish
Article number100805
Number of pages14
Issue number6
Publication statusPublished - Dec 2023

Bibliographical note

© 2023 AGBM. Published by Elsevier Masson SAS. This is an open access article under the CC BY-NC-ND license (http://


This work has been supported by: Natural Science Foundation of Ningxia Province, [grant number 2022AAC03242]; North Minzu University Scientific Research Projects, [grant number 2021JCYJ10]; Natural Science Foundation of China (NSFC) [grant number 62171408]; Major Scientific Project of Zhejiang Laboratory [grant number 2020ND8AD01]; Key Research and Development Program of Zhejiang Province, [grant number 2020C03016]; Ningxia First-Class Discipline and Scientific Research Projects (Electronic Science and Technology) [grant number NXYLXK2017A07]; Plan for Leading Talents of the State Ethnic Affairs Commission of the People's Republic of China; Innovation Team of Lidar Atmosphere Remote Sensing of Ningxia Province; High Level Talent Selection and Training Plan of North Minzu University; Key Research and Development Plan in Ningxia Province, [grant number 2023BEG02065]; Sub-themes of Key and Major Special Projects of Scientific and Technological Innovation of Yinchuan Science and Technology Plan Project, [grant number 2021-SF-009].


  • Cardiodynamicsgram (CDG)
  • Coronary microvascular dysfunction (CMD)
  • Entropy
  • Multilayer perceptron (MLP)
  • Sparrow search algorithm (SSA)
  • Vectorcardiogram (VCG)

ASJC Scopus subject areas

  • Biophysics
  • Biomedical Engineering


Dive into the research topics of 'Early detection of coronary microvascular dysfunction using machine learning algorithm based on vectorcardiography and cardiodynamicsgram features'. Together they form a unique fingerprint.

Cite this