Cardiac index adaptive physiological control system for continuous-flow left ventricular assist device

IF 7.5 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Expert Systems with Applications Pub Date : 2025-06-12 DOI:10.1016/j.eswa.2025.128536

Hongtao Liu , Aili Guan , Fayu Xing , Yunpeng Zhang , Wencheng Wang , Guoxu Liu

{"title":"Cardiac index adaptive physiological control system for continuous-flow left ventricular assist device","authors":"Hongtao Liu , Aili Guan , Fayu Xing , Yunpeng Zhang , Wencheng Wang , Guoxu Liu","doi":"10.1016/j.eswa.2025.128536","DOIUrl":null,"url":null,"abstract":"<div><div>A personalized continuous-flow left ventricular assist device (CFLVAD) therapy is designed to provide a precise treatment strategy based on the specific circumstances and needs of the individual patient. The aim is to improve treatment outcomes and the patient’s quality of life. Given this background, this study proposes a cardiac index adaptive physiological control (CIAPC) strategy to personalize the CFLVAD therapy. The CFLVAD physiological control system was constructed based on the cardiovascular coupling system model. A cardiac index regulator was designed by deriving a functional relationship between cardiac index and heart rate, height, and weight. The cardiac index adaptive controller consisted of the cardiac index regulator combined with a fuzzy controller and a ventricular suction prevention controller. The rotary pump flow and left ventricular pressure were measured indirectly by the model estimation method. The computer results show that the CIAPC system could maintain hemodynamic stability under extreme physiological conditions, effectively preventing ventricular suction and pump regurgitation. In a resting state, the system could automatically adjust and maintain personalized cardiac output (4 L/min, 5 L/min, and 7 L/min) based on patient body type differences, while ensuring that the cardiac index for all patients remains stable at around 3 L/min/m², which is within the normal physiological range. Furthermore, following an approximate 30 s period of transitional adjustment, the CIAPC system demonstrated the capacity to dynamically modulate cardiac output in response to patient needs. Specifically, it was able to increase the cardiac output of a patient with a normal body type from 5 L/min at rest to 8 L/min during exercise, or decrease it to 4 L/min during sleep. The CIAPC can control the rotary pump speed of the CFLVAD based on individual characteristics, enabling the delivery of personalized therapy to patients.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"291 ","pages":"Article 128536"},"PeriodicalIF":7.5000,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Expert Systems with Applications","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0957417425021554","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}

引用次数: 0

Abstract

A personalized continuous-flow left ventricular assist device (CFLVAD) therapy is designed to provide a precise treatment strategy based on the specific circumstances and needs of the individual patient. The aim is to improve treatment outcomes and the patient’s quality of life. Given this background, this study proposes a cardiac index adaptive physiological control (CIAPC) strategy to personalize the CFLVAD therapy. The CFLVAD physiological control system was constructed based on the cardiovascular coupling system model. A cardiac index regulator was designed by deriving a functional relationship between cardiac index and heart rate, height, and weight. The cardiac index adaptive controller consisted of the cardiac index regulator combined with a fuzzy controller and a ventricular suction prevention controller. The rotary pump flow and left ventricular pressure were measured indirectly by the model estimation method. The computer results show that the CIAPC system could maintain hemodynamic stability under extreme physiological conditions, effectively preventing ventricular suction and pump regurgitation. In a resting state, the system could automatically adjust and maintain personalized cardiac output (4 L/min, 5 L/min, and 7 L/min) based on patient body type differences, while ensuring that the cardiac index for all patients remains stable at around 3 L/min/m², which is within the normal physiological range. Furthermore, following an approximate 30 s period of transitional adjustment, the CIAPC system demonstrated the capacity to dynamically modulate cardiac output in response to patient needs. Specifically, it was able to increase the cardiac output of a patient with a normal body type from 5 L/min at rest to 8 L/min during exercise, or decrease it to 4 L/min during sleep. The CIAPC can control the rotary pump speed of the CFLVAD based on individual characteristics, enabling the delivery of personalized therapy to patients.

查看原文本刊更多论文

连续血流左室辅助装置心脏指数自适应生理控制系统

一种个性化的连续血流左心室辅助装置（CFLVAD）治疗旨在根据患者的具体情况和需求提供精确的治疗策略。目的是改善治疗效果和患者的生活质量。在此背景下，本研究提出了一种心脏指数适应性生理控制（CIAPC）策略来个性化CFLVAD治疗。基于心血管耦合系统模型，构建了CFLVAD生理控制系统。通过推导心脏指数与心率、身高和体重之间的函数关系，设计了心脏指数调节器。心脏指数自适应控制器由心脏指数调节器与模糊控制器和心室吸阻控制器相结合组成。采用模型估计法间接测量旋转泵流量和左心室压力。计算机结果表明，CIAPC系统能在极端生理条件下维持血流动力学稳定性，有效防止心室吸血和泵返流。在静息状态下，系统可根据患者的体型差异，自动调节并维持个性化心输出量（4 L/min、5 L/min、7 L/min），同时确保所有患者的心脏指数稳定在3 L/min/m²左右，处于正常生理范围内。此外，经过大约30秒的过渡期调整，CIAPC系统显示出动态调节心输出量以响应患者需求的能力。具体来说，它能够将正常体型患者的心输出量从休息时的5 L/min增加到运动时的8 L/min，或在睡眠时降低到4 L/min。CIAPC可以根据个体特征控制CFLVAD的旋转泵转速，从而为患者提供个性化治疗。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Expert Systems with Applications 工程技术-工程：电子与电气

CiteScore

13.80

自引率

10.60%

发文量

2045

审稿时长

8.7 months

期刊介绍： Expert Systems With Applications is an international journal dedicated to the exchange of information on expert and intelligent systems used globally in industry, government, and universities. The journal emphasizes original papers covering the design, development, testing, implementation, and management of these systems, offering practical guidelines. It spans various sectors such as finance, engineering, marketing, law, project management, information management, medicine, and more. The journal also welcomes papers on multi-agent systems, knowledge management, neural networks, knowledge discovery, data mining, and other related areas, excluding applications to military/defense systems.