A novel method for Assessing Cardiac Function in Patients with Coronary Heart Disease based on Wrist Pulse Analysis (Preprint)

Author:

Wu Wen-jie,CHEN Rui,GUO Rui,YAN Jian-jun,ZHANG Chun-keORCID,WANG Yi-qin,YAN Hai-xia,ZHANG Ye-qing

Abstract

BACKGROUND

Chronic heart failure is a serious complication of the terminal stage of coronary heart disease (CHD); both disorders are leading causes of death. B-type natriuretic peptide (BNP) is a plasma biomarker of the presence and severity of chronic heart failure. Therefore, the timely assessment of the BNP levels and detection of pathological cardiovascular changes are critical for chronic heart failure prevention in patients with CHD. Novel instruments for wrist pulse detection include wearable devices that can be used to obtain pathophysiological information on the cardiovascular system.

OBJECTIVE

we investigated whether wrist pulse detection could be used to assess the BNP levels of patients with CHD and accordingly evaluated the potential of wrist pulse signals for use in the real-time cardiac monitoring of patients with CHD.

METHODS

On the basis of BNP levels, 419 patients with CHD were assigned to Group 1 (BNP < 95 pg/mL, n = 249), 2 (95 < BNP < 221 pg/mL, n = 85), and 3 (BNP > 221 pg/mL, n = 85). Wrist pulse signals were measured noninvasively. Both the time-domain method and multiscale entropy (MSE) method were used to extract pulse features. Decision tree (DT) and random forest (RF) algorithms were employed to construct models for classifying BNP level groups, and the models’ accuracy, precision, recall, and F1-score were compared.

RESULTS

The pulse (time-domain and MSE) features of the three groups differed significantly, suggesting different pathological states of the cardiovascular system in patients with CHD. Moreover, the RF models outperformed the DT models in accuracy and average precision, recall, and F1-score. Furthermore, the optimal RF model was that based on a dataset comprising both time-domain and MSE features, achieving accuracy, average precision, average recall, and an average F1-score of 90.900%, 91.048%, 90.900%, and 90.897%, respectively.

CONCLUSIONS

The wrist pulse detection technology employed in the present study is useful for assessing the cardiac function of patients with CHD.

Publisher

JMIR Publications Inc.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3