Bibliometrics analysis of clinical decision support systems research in nursing

Objective:Artificial intelligence(AI)has a big impact on healthcare now and in the future.Nurses play an important role in the medical field and will benefit greatly from this technology.AI-Enabled Clinical Decision Support Systems have received a great deal of attention recently.Bibliometric analysis can offer an objective,systematic,and comprehensive analysis of a specific field with a vast background.However,no bibliometric analysis has investigated AI-enabled clinical decision support systems research in nursing.The purpose of research to determine the characteristics of articles about the global performance and development of AI-enabled clinical decision support systems research in nursing.Methods:In this study,the bibliometric approach was used to estimate the searched data on clinical decision support systems research in nursing from 2009 to 2022,and we also utilized CiteSpace and VOSviewer software to build visualizing maps to assess the contribution of different journals,authors,et al.,as well as to identify research hot spots and promising future trends in this research field.Result:From 2009 to 2022,a total of 2,159 publications were retrieved.The number of publications and citations on AI-enabled clinical decision support systems research in nursing has increased obvious ly in recent years.However,they are understudied in the field of nursing and there is a compelling need to develop more high-quality research.Conclusion:AI-Enabled Nursing Decision Support System use in clinical practice is still in its early stages.These analyses and results hope to provide useful information and references for future research directions for researchers and nursing practitioners who use AI-enabled clinical decision support systems.

Progress of clinical decision support systems in stroke nursing care

Stroke is characterized by high incidence,high recurrence,high disability,and high morbidity and mortality in China,resulting in a heavy social and clinical burden.A clinical decision support system,as an intelli-gent computer system,can assist nurses in decision-mak-ing to collect information quickly,make the most suitable personalized decisions for patients,and improve nurses’decision-making judgment and quality of care.Promoting the development and application of decision support sys-tems in stroke nursing significantly enhances the nursing staff’s work quality and patients’prognosis.Therefore,this paper reviews the research progress of domestic and international clinical decision support systems in stroke nursing care to provide other researchers with specific research directions for developing and applying decision support systems in stroke nursing care.

Clinical decision support for drug related events: Moving towards better prevention

Clinical decision support(CDS) systems with automated alerts integrated into electronic medical records demonstrate efficacy for detecting medication errors(ME) and adverse drug events(ADEs). Critically ill patients are at increased risk for ME, ADEs and serious negative outcomes related to these events. Capitalizing on CDS to detect ME and prevent adverse drug related events has the potential to improve patient outcomes. The key to an effective medication safety surveillance system incorporating CDS is advancing the signals for alerts by using trajectory analyses to predict clinical events, instead of waiting for these events to occur. Additionally, incorporating cutting-edge biomarkers into alert knowledge in an effort to identify the need to adjust medication therapy portending harm will advance the current state of CDS. CDS can be taken a step further to identify drug related physiological events, which are less commonly included in surveillance systems. Predictive models for adverse events that combine patient factors with laboratory values and biomarkers are being established and these models can be the foundation for individualized CDS alerts to prevent impending ADEs.

Nursing decision support system:application in electronic health records

The clinical decision support system makes electronic health records(EHRs)structured,intelligent,and knowledgeable.The nursing decision support system(NDSS)is based on clinical nursing guidelines and nursing process to provide intelligent suggestions and reminders.The impact on nurses’work is mainly in shortening the recording time,improving the quality of nursing diagnosis,reducing the incidence of nursing risk events,and so on.However,there is no authoritative standard for the NDSS at home and abroad.This review introduces development and challenges of EHRs and recommends the application of the NDSS in EHRs,namely the nursing assessment decision support system,the nursing diagnostic decision support system,and the nursing care planning decision support system(including nursing intervene),hoping to provide a new thought and method to structure impeccable EHRs.

面向心律失常疾病的临床决策支持系统交互性研究与实现

目的/意义针对当前临床决策支持系统使用过程中存在的问题,提出界面设计原则并将其应用于心律失常疾病临床决策支持系统建设中。方法/过程从交互设计角度,针对可解释性、时效性、可用性、相关性、尊重性和循证性6个维度,提出界面设计原则。选取心律失常疾病决策支持作为临床场景,设计临床决策支持系统交互界面原型,阐述界面功能、信息功能、交互功能设计与实现过程。结果/结论本研究提出的界面设计原则可有效缓解6类问题,经论证具有应用于心律失常疾病临床决策支持原型系统的可行性以及可泛化性,可用于指导多种疾病辅助诊疗工具的交互设计。

ICU患者身体约束决策支持系统的研发与应用

目的:研发ICU患者身体约束决策支持系统并评价其临床应用效果,为护士进行患者身体约束决策提供便利。方法:成立研发小组,构建ICU患者身体约束影响因素预测模型并进行验证,以此为基础开发ICU患者身体约束决策支持系统并投入使用。选取2022年8月至2023年3月江苏省某三级甲等医院ICU的764例患者为研究对象,将患者随机分为干预组(n=366)和对照组(n=398),对照组护士实施基于经验性评估的常规身体约束流程,干预组护士实施基于ICU患者身体约束决策支持系统的身体约束流程,比较两组患者的身体约束率、谵妄发生率、非计划性拔管发生率;同时验证ICU患者身体约束决策支持系统与约束决策轮的一致性。结果:使用ICU患者身体约束决策支持系统后,干预组患者的约束率为24.9%,谵妄发生率为2.2%,均低于对照组(P<0.05);两组非计划性拔管发生率差异无统计学意义(P>0.05)。ICU患者身体约束决策支持系统与约束决策轮Kappa一致性检验结果为0.853(P<0.001),显示结果一致性较好。结论:ICU患者身体约束决策支持系统可以应用于临床并辅助护士决策,在有效降低身体约束率及谵妄发生率的同时不会增加非计划性拔管发生率。

中西医结合临床决策支持系统的关键技术研究

临床决策支持系统日益成为医务人员的重要工具,但目前多数落地应用集中在合理用药方面,因为在诊断辅助、治疗安全和疗效分析3个重要环节依然存在诸多技术难点,缺乏系统性和工程化解决方案。本文基于中医智能系统性的发展和临床中西医结合的现实需求,探讨中西医结合临床决策支持系统(CDSS)实现闭环的关键技术,即中西医多源异构数据分析与交叉验证;中医知识图谱和算法模型的智能辅助辨证论治;疑难杂症治疗的智能推荐和用药模型构建;疗效分析的语义理解、隐私安全与数据保护机制等。通过部分工程实例,提出中西医结合CDSS关键技术解决方案,为卫生信息管理和研究人员、企业级产品开发和临床实践应用提供参考。

中文医学术语集在真实世界临床研究中的应用

目的:通过分析国内外医学术语集的应用进展,拓展中文临床术语集在中文电子病历环境下的科研应用场景及范围。方法:检索四川大学数字图书馆出版物,通过文献回顾进行分析归纳。结果:中文医学术语集对电子病历概念识别和数据挖掘具有重要作用,有助于语义互操作。基于语义网及语义知识库,可以更深入地进行多种风险预测模型、语义相似度计算和推理性决策支持系统的研究。结论:中文医学术语集是基础性的信息化标准,可支撑多种临床智慧应用构建,建议纳入医学教育。

基于人工智能的临床决策支持系统早期临床评估的透明化报告

随着人工智能(AI)在医学领域的广泛应用,越来越多基于AI的临床决策支持系统应用于临床诊断与筛查等。早期临床评估对于评价基于AI临床决策支持系统的临床性能、安全性和人为因素具有重要意义,有利于为进一步的大规模临床试验奠定基础,但相关临床研究报告的透明度和完整性尚待提高。2022年5月,基于AI的临床决策支持系统早期临床评估报告指南(DECIDE-AI)正式在线发表。本文将结合DECIDE-AI中的AI相关报告项目及相关文献,探讨基于AI的临床决策支持系统早期临床评估的透明化报告,以期帮助我国系统开发者和研究者更好地理解与应用相关指南,提高基于AI的临床决策支持系统早期临床评估报告的透明度。

脑血管病临床决策支持系统对卒中医疗服务质量关键绩效指标的影响研究

目的探索脑血管病临床决策支持系统(clinical decision support system,CDSS)对卒中医疗服务质量关键绩效指标改进是否具有积极作用。方法回顾性连续纳入首都医科大学附属北京天坛医院血管神经病学2病区应用脑血管病CDSS前(2020年1—11月)住院治疗的缺血性卒中患者作为对照组,应用脑血管病CDSS后(2021年1—11月)收治的缺血性卒中患者作为干预组,比较两组患者的基线特征和缺血性卒中医疗服务质量关键绩效指标,评估脑血管病CDSS对卒中医疗服务质量的影响。结果本研究共纳入1331例患者,其中对照组651例,干预组680例。对照组平均年龄为(71.7±11.8)岁,男性490例(75.3%);干预组平均年龄(72.3±10.2)岁,男性498例(73.2%)。缺血性卒中医疗服务质量关键绩效指标中,干预组入院48 h内不能行走患者进行深静脉血栓预防率(86.3%vs.65.0%,P<0.01)、出院时患者抗栓治疗率(98.1%vs.96.2%,P=0.03)、出院时合并心房颤动的患者抗凝治疗率(70.1%vs.44.2%,P<0.01)均高于对照组。结论脑血管病CDSS有助于改善缺血性卒中患者的医疗服务质量关键绩效指标。

胰岛素滴定临床决策支持系统的开发及其有效性和安全性验证

目的胰岛素滴定临床决策支持系统(CDSS)的开发及其有效性和安全性验证。方法选择新乡医学院第一附属医院内分泌科2021年1月至2023年7月收治的80例在生活方式干预及口服降糖药物治疗的基础上血糖难以控制达标的2型糖尿病患者为研究对象,采用随机数字表法将患者分为观察组和对照组,每组40例。2组患者均口服二甲双胍缓释片、睡前皮下注射德谷胰岛素、三餐前皮下注射门冬胰岛素控制血糖,观察组患者采用CDSS决策意见进行胰岛素滴定,对照组患者进行常规胰岛素滴定。采用回顾式动态血糖监测系统监测葡萄糖在目标范围内时间(TIR)、平均血糖波动幅度(MAGE)、平均血糖(MBG)、血糖标准差(SDBG)、血糖变异系数(CV);记录2组患者治疗前后空腹血糖、餐后2 h血糖及住院时间、血糖控制达标所需时间、低血糖发生率。结果治疗前2组患者空腹血糖、餐后2 h血糖比较差异无统计学意义(P>0.05)。2组患者治疗后的空腹血糖、餐后2 h血糖均显著低于治疗前(P<0.05)。治疗后,观察组患者的空腹血糖、餐后2 h血糖显著低于对照组(P<0.05)。治疗后,观察组患者的TIR显著高于对照组,MAGE、MBG、SDBG、CV显著低于对照组(P<0.05)。观察组和对照组患者住院时间分别为9.0(7.3,10.0)、11.0(8.3,12.0)d,对照组患者住院时间显著长于观察组(Z=-2.408,P<0.05)。观察组和对照组患者血糖控制达标所需时间分别为6.5(5.0,8.8)d、7.5(6.0,10.0)d,对照组患者血糖控制达标所需时间显著长于观察组(Z=-2.019,P<0.05)。观察组和对照组患者低血糖发生率分别为20.0%(8/40)、12.5%(5/40),2组患者低血糖发生率比较差异无统计学意义(χ^(2)=0.827,P>0.05)。结论与常规胰岛素滴定相比,应用CDSS可以在基础-餐时胰岛素方案的实施过程中提供决策支持,可以更加有效地控制血糖,提高葡萄糖TIR,减少血糖波动,缩短患者血糖控制达标所需时间,缩短住院时间,且不增加低血糖风险。

机器学习在传染病临床决策支持系统中应用的研究进展

从应用基础、应用现状、面临挑战及未来发展趋势4个方面对机器学习临床决策支持系统在传染病管理中的相关研究进行综述,旨在进一步增强对传染性疾病的智能管理,为智慧医疗的发展提供参考及借鉴。

临床决策支持系统管理高血压患者血压和心血管风险效果的系统评价

目的系统评价临床决策支持系统(CDSS)应用于高血压患者血压与心血管风险管理的效果。方法检索中国知网、万方、维普、PubMed、EMbase等数据库,检索时限由建库至2023年5月。由2名研究人员独立进行文献筛选、数据提取、证据质量评价。结果最终纳入11项研究,临床决策支持系统功能包括辅助诊疗、诊疗质量反馈、用药推荐、随访监测、信息提醒、心血管风险评估等。结果显示,CDSS对高血压患者血压及心血管风险管理具有一定的改善作用。文献质量评价结果显示,1篇等级为“强”,4篇为“中”,6篇为“弱”。结论CDSS可以辅助改善高血压患者血压及心血管风险管理效果,未来应用前景广阔。今后的研究可以考虑加强高血压领域CDSS全程化功能设计,建设更多的本土化高血压CDSS。

智慧重症监护室建设背景下生命支持设备的临床辅助决策效能分析

目的:基于医院智慧重症监护室(ICU)建设,分析智慧ICU病房生命支持设备在临床辅助决策中的效能。方法:设计智慧ICU病房交互系统、设备管理系统、风险应对系统和智能查房系统功能模块,实时采集生命支持设备在诊疗、护理、运行和技术保障中的信息数据,为危重症患者诊疗和护理措施改善提供医疗辅助决策依据。选取2018年7月1日至2022年12月31日上海市青浦区朱家角人民医院等3家医院临床在用的115台生命支持设备,分别采用传统辅助决策管理模式(简称传统管理模式,83台)和智慧辅助决策管理模式(简称智慧管理模式,89台,含传统管理模式中57台和新增加的32台)管理,对比两种管理模式生命支持设备的管理水平和管理效果。结果:智慧管理模式下的设备数据采集时间为(5.67±2.80)min,少于传统管理模式,数据采集准确率和完整度,以及设备调配使用、监测报警、设备故障和紧急应答的有效解决率分别为(99.02±1.14)%、(94.35±3.46)%、(98.78±0.90)%、(98.99±0.91)%、(88.26±5.31)%和(90.23±5.54)%,均高于传统管理模式,其差异有统计学意义(t=6.504、6.474、3.574、7.620、6.784、4.522、3.719,P<0.05);智慧管理模式下的设备治疗、护理和康复的诊断决策有效利用率分别为(93.83±3.12)%、(94.99±2.47)%和(91.44±4.62)%,呼吸功能支持设备、循环功能支持设备、血液净化支持设备和急救监测支持设备的综合评分分别为(92.97±4.35)分、(94.34±2.95)分、(93.01±2.44)分和(94.11±1.89)分,均高于传统管理模式,其差异有统计学意义(t=4.169、4.875、5.159、4.069、3.033、2.757、6.893,P<0.05)。结论:基于智慧ICU建设能够提高生命支持设备运行数据采集质量,及时解决设备运行问题,为危重症患者诊疗、护理和康复的诊断决策提供有效依据,提升设备临床服务水平。

中医临床决策支持系统技术发展论述

中医临床决策支持系统(CDSS)作为中医临床实践的重要工具,在其发展建设中,紧密围绕中医理论、中医数据、前沿技术和理念变迁展开。本文从中医CDSS的思想理论基础和技术支持两个方面着重介绍了其发展情况。理论基础方面,将中医传统知识与现代科技相结合,为中医CDSS的建设提供了坚实的理论基础。技术支持方面,中医CDSS依托前沿技术如人工智能、大数据等,不断进行技术创新和算法优化,以适应中医临床实践的需求。未来,中医CDSS的发展趋势将更加注重数据与技术的融合,以实现个性化、精准化诊疗,推动中医临床辅助决策水平的提升。

国内临床智能决策支持系统专利权人技术情况分析

目的/意义整体分析国内临床决策支持系统(clinical decision support system,CDSS)领域专利权人技术情况,为CDSS相关技术研究提供借鉴。方法/过程从公开趋势、专利分布、技术领域分布等方面对CDSS公开专利数据进行分析,划分专利权人类别,依靠词频和词间向量分析其技术关注情况,基于活跃专利权人分析技术关联和专利独占相关情况。结果/结论CDSS专利公开数量整体呈增长趋势,该领域在国内尚未形成技术垄断,政府部门和研究机构应关注可能产生的金融风险。

A Study on the Explainability of Thyroid Cancer Prediction:SHAP Values and Association-Rule Based Feature Integration Framework

In the era of advanced machine learning techniques,the development of accurate predictive models for complex medical conditions,such as thyroid cancer,has shown remarkable progress.Accurate predictivemodels for thyroid cancer enhance early detection,improve resource allocation,and reduce overtreatment.However,the widespread adoption of these models in clinical practice demands predictive performance along with interpretability and transparency.This paper proposes a novel association-rule based feature-integratedmachine learning model which shows better classification and prediction accuracy than present state-of-the-artmodels.Our study also focuses on the application of SHapley Additive exPlanations(SHAP)values as a powerful tool for explaining thyroid cancer prediction models.In the proposed method,the association-rule based feature integration framework identifies frequently occurring attribute combinations in the dataset.The original dataset is used in trainingmachine learning models,and further used in generating SHAP values fromthesemodels.In the next phase,the dataset is integrated with the dominant feature sets identified through association-rule based analysis.This new integrated dataset is used in re-training the machine learning models.The new SHAP values generated from these models help in validating the contributions of feature sets in predicting malignancy.The conventional machine learning models lack interpretability,which can hinder their integration into clinical decision-making systems.In this study,the SHAP values are introduced along with association-rule based feature integration as a comprehensive framework for understanding the contributions of feature sets inmodelling the predictions.The study discusses the importance of reliable predictive models for early diagnosis of thyroid cancer,and a validation framework of explainability.The proposed model shows an accuracy of 93.48%.Performance metrics such as precision,recall,F1-score,and the area under the receiver operating characteristic(AUROC)are also higher than the baseline models.The results of the proposed model help us identify the dominant feature sets that impact thyroid cancer classification and prediction.The features{calcification}and{shape}consistently emerged as the top-ranked features associated with thyroid malignancy,in both association-rule based interestingnessmetric values and SHAPmethods.The paper highlights the potential of the rule-based integrated models with SHAP in bridging the gap between the machine learning predictions and the interpretability of this prediction which is required for real-world medical applications.

用于肠镜报告解读的临床决策支持系统效果评价

目的分析医师群体通过循证临床决策支持系统实施框架(GUIDES)的多个维度对面向肠镜检查患者肠镜报告解读的临床决策支持系统(CDSS)的应用效果进行评价。方法问卷设计基于GUIDES框架,分为4个维度,研究选取每个维度的2或3个核心问题设计问卷,随机选取单中心消化内科以及非消化内科医师共75名,面对面发放纸质问卷,分析不同类别、层级医师对CDSS应用效果的评价。结果共发放问卷75份,有效问卷71份,有效率为94.7%。男性与女性医师对CDSS的评分比较无显著差异(P>0.05)。非消化内科医师对CDSS的评分高于消化内科医师(P<0.05)。初级和中级职称医师对CDSS的评分均高于高级职称医师(P<0.05)。青年医师对CDSS的评分高于中年医师(P<0.01)。结论采用基于GUIDES框架的问卷调查表对CDSS进行多维度应用评价,该模型在医师群体中获得了较高的评价。

诊断类智能化临床决策支持系统应用现状与思考

医学的实践性、疾病的个体性导致误诊率居高不下,而基于人工智能和医学大数据的临床决策支持系统(clinical decision support system,CDSS)能在疾病诊断时为医生提供决策支持,成为解决此类问题的一个重要手段,且现已取得一定的成效。不过,尽管CDSS在提高医疗决策的准确性和效率方面具有潜在优势,但其在实施过程中也存在一系列的问题,这些问题可能影响CDSS的可靠性、可用性和安全性。本文对诊断类CDSS的应用现状、面临的挑战和未来发展趋势进行总结分析,以期对我国CDSS向智能化和知识化方向发展提供参考。