International Journal of Medical Informatics最新文献_第8页

A systematic review on the impact of artificial intelligence on electrocardiograms in cardiology 人工智能对心脏病学心电图影响的系统回顾。

IF 3.7 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2024-12-09 DOI: 10.1016/j.ijmedinf.2024.105753

Oluwafemi Ayotunde Oke , Nadire Cavus

Background

Artificial intelligence (AI) has revolutionized numerous industries, enhancing efficiency, scalability, and insight generation. In cardiology, particularly through electrocardiogram (ECG) analysis, AI has the potential to improve diagnostic accuracy and reduce the time needed for diagnosis. This systematic review explores the integration of AI, machine learning (ML), and deep learning (DL) in ECG analysis, focusing on their impact on predictive diagnostics and treatment support in cardiology.

Methods

A systematic literature review was conducted following the PRISMA 2020 framework, using four high-impact databases to identify studies from 2014 to -2024. The inclusion criteria included English-language journal articles and research papers that focused on AI applications in cardiology, specifically ECG analysis. Records were screened, duplicates were removed, and final selections were made on the basis of their relevance to AI-ECG integration for cardiac health.

Results

The review included 46 studies that met the inclusion criteria, covering diverse AI models such as CNNs, RNNs, and hybrid models. These models were applied to ECG data to detect and predict heart conditions such as arrhythmia, myocardial infarction, and heart failure. These findings indicate that AI-driven ECG analysis improves diagnostic accuracy and provides significant support for early diagnosis and personalized treatment.

Conclusions

AI technologies, especially ML and DL, enhance ECG-based cardiology diagnostics by increasing accuracy, reducing diagnosis time, and supporting timely interventions and personalized care. Continued research in this area is essential to refine algorithms and integrate AI tools into clinical practice for improved patient outcomes in cardiology.

背景：人工智能（AI）为众多行业带来了变革，提高了效率、可扩展性和洞察力。在心脏病学领域，尤其是通过心电图（ECG）分析，人工智能有可能提高诊断准确性并缩短诊断所需时间。本系统性综述探讨了人工智能、机器学习（ML）和深度学习（DL）在心电图分析中的整合，重点关注它们对心脏病学中预测性诊断和治疗支持的影响：按照 PRISMA 2020 框架进行了系统性文献综述，使用四个高影响力数据库来识别 2014 年至 2024 年的研究。纳入标准包括英语期刊论文和研究论文，重点关注人工智能在心脏病学中的应用，特别是心电图分析。对记录进行筛选，剔除重复内容，并根据其与人工智能-心电图整合用于心脏健康的相关性进行最终筛选：综述包括 46 项符合纳入标准的研究，涵盖各种人工智能模型，如 CNN、RNN 和混合模型。这些模型被应用于心电图数据，以检测和预测心律失常、心肌梗死和心力衰竭等心脏状况。这些研究结果表明，人工智能驱动的心电图分析提高了诊断准确性，为早期诊断和个性化治疗提供了重要支持：结论：人工智能技术，尤其是 ML 和 DL，通过提高准确性、缩短诊断时间、支持及时干预和个性化治疗，提高了基于心电图的心脏病诊断水平。该领域的持续研究对于完善算法和将人工智能工具融入临床实践以改善心脏病学患者的预后至关重要。

{"title":"A systematic review on the impact of artificial intelligence on electrocardiograms in cardiology","authors":"Oluwafemi Ayotunde Oke , Nadire Cavus","doi":"10.1016/j.ijmedinf.2024.105753","DOIUrl":"10.1016/j.ijmedinf.2024.105753","url":null,"abstract":"<div><h3>Background</h3><div>Artificial intelligence (AI) has revolutionized numerous industries, enhancing efficiency, scalability, and insight generation. In cardiology, particularly through electrocardiogram (ECG) analysis, AI has the potential to improve diagnostic accuracy and reduce the time needed for diagnosis. This systematic review explores the integration of AI, machine learning (ML), and deep learning (DL) in ECG analysis, focusing on their impact on predictive diagnostics and treatment support in cardiology.</div></div><div><h3>Methods</h3><div>A systematic literature review was conducted following the PRISMA 2020 framework, using four high-impact databases to identify studies from 2014 to -2024. The inclusion criteria included English-language journal articles and research papers that focused on AI applications in cardiology, specifically ECG analysis. Records were screened, duplicates were removed, and final selections were made on the basis of their relevance to AI-ECG integration for cardiac health.</div></div><div><h3>Results</h3><div>The review included 46 studies that met the inclusion criteria, covering diverse AI models such as CNNs, RNNs, and hybrid models. These models were applied to ECG data to detect and predict heart conditions such as arrhythmia, myocardial infarction, and heart failure. These findings indicate that AI-driven ECG analysis improves diagnostic accuracy and provides significant support for early diagnosis and personalized treatment.</div></div><div><h3>Conclusions</h3><div>AI technologies, especially ML and DL, enhance ECG-based cardiology diagnostics by increasing accuracy, reducing diagnosis time, and supporting timely interventions and personalized care. Continued research in this area is essential to refine algorithms and integrate AI tools into clinical practice for improved patient outcomes in cardiology.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"195 ","pages":"Article 105753"},"PeriodicalIF":3.7,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142824901","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Evaluation of a low-cost training application to train microelectrode recording identification in deep brain stimulation surgeries 脑深部刺激手术中微电极记录识别的低成本训练应用评估。

IF 3.7 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2024-12-07 DOI: 10.1016/j.ijmedinf.2024.105759

Ignacio Oropesa , Marta Naranjo-Castresana , Marta Colmenar , Ainara Carpio , Óscar Ansótegui , María Elena Hernando

Objective

Deep brain stimulation (DBS) is a surgical technique that alleviates motor symptoms in Parkinson’s disease. Surgically implanted microelectrodes stimulate the basal ganglia to improve patients’ symptoms. One of the training challenges for neurophysiologists is to identify during surgery the target area of the brain in which the electrodes must be implanted. Identification is based both on visual and auditory inspection of the microelectrode recordings (MERs) as they are lowered through the basal ganglia. We present the preliminary evaluation of DBSTrainer, a novel desktop application to train neurophysiologists in the identification of signals corresponding to different basal structures.

Methods

A pilot study was conducted with neurologists and neurophysiologists at the Hospital Universitario La Paz (Madrid, Spain). After completing a series of tasks with the application, they were asked to complete an evaluation questionnaire. Usability was assessed using the System Usability Scale (SUS). Functionality, contents, and perceived usefulness were assessed using an ad-hoc Likert questionnaire following the e-MIS framework for surgical learning platforms.

Results

15 volunteers participated in the study. Obtained SUS score was 86.7 ± 0.47. Most positive aspects on functionality were platform design and interactivity. Contents were found realistic and aligned with learning outcomes. Minor problems were identified with signal loading times.

Conclusions

This study provides preliminary evidence on the usefulness of DBSTrainer. It is, to our knowledge, the first Technology Enhanced Learning application to train neurophysiologists outside the operating room, and thus its introduction can have a real impact on patient safety and surgical outcomes.

目的：脑深部电刺激（DBS）是一种缓解帕金森病运动症状的手术技术。通过手术植入的微电极刺激基底神经节来改善患者的症状。神经生理学家的训练挑战之一是在手术中确定必须植入电极的大脑目标区域。识别是基于对微电极记录（MERs）的视觉和听觉检查，因为它们通过基底神经节降低。我们提出了dbfilter的初步评估，dbfilter是一种新的桌面应用程序，用于训练神经生理学家识别与不同基础结构相对应的信号。方法：一项由拉巴斯大学医院（西班牙马德里）的神经学家和神经生理学家进行的初步研究。在完成了应用程序的一系列任务后，他们被要求完成一份评估问卷。可用性评估使用系统可用性量表（SUS）。在外科学习平台的e-MIS框架下，使用特设Likert问卷对功能、内容和感知有用性进行评估。结果：15名志愿者参与了研究。所得SUS评分为86.7±0.47。功能最积极的方面是平台设计和交互性。内容切合实际，与学习成果相一致。在信号加载时间上发现了一些小问题。结论：本研究为dbfilter的有效性提供了初步证据。据我们所知，这是第一个在手术室外培训神经生理学家的技术增强学习应用程序，因此它的引入可以对患者安全和手术结果产生真正的影响。

{"title":"Evaluation of a low-cost training application to train microelectrode recording identification in deep brain stimulation surgeries","authors":"Ignacio Oropesa , Marta Naranjo-Castresana , Marta Colmenar , Ainara Carpio , Óscar Ansótegui , María Elena Hernando","doi":"10.1016/j.ijmedinf.2024.105759","DOIUrl":"10.1016/j.ijmedinf.2024.105759","url":null,"abstract":"<div><h3>Objective</h3><div>Deep brain stimulation (DBS) is a surgical technique that alleviates motor symptoms in Parkinson’s disease. Surgically implanted microelectrodes stimulate the basal ganglia to improve patients’ symptoms. One of the training challenges for neurophysiologists is to identify during surgery the target area of the brain in which the electrodes must be implanted. Identification is based both on visual and auditory inspection of the microelectrode recordings (MERs) as they are lowered through the basal ganglia. We present the preliminary evaluation of DBSTrainer, a novel desktop application to train neurophysiologists in the identification of signals corresponding to different basal structures.</div></div><div><h3>Methods</h3><div>A pilot study was conducted with neurologists and neurophysiologists at the Hospital Universitario La Paz (Madrid, Spain). After completing a series of tasks with the application, they were asked to complete an evaluation questionnaire. Usability was assessed using the System Usability Scale (SUS). Functionality, contents, and perceived usefulness were assessed using an ad-hoc Likert questionnaire following the e-MIS framework for surgical learning platforms.</div></div><div><h3>Results</h3><div>15 volunteers participated in the study. Obtained SUS score was 86.7 ± 0.47. Most positive aspects on functionality were platform design and interactivity. Contents were found realistic and aligned with learning outcomes. Minor problems were identified with signal loading times.</div></div><div><h3>Conclusions</h3><div>This study provides preliminary evidence on the usefulness of DBSTrainer. It is, to our knowledge, the first Technology Enhanced Learning application to train neurophysiologists outside the operating room, and thus its introduction can have a real impact on patient safety and surgical outcomes.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"195 ","pages":"Article 105759"},"PeriodicalIF":3.7,"publicationDate":"2024-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142822924","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Estimated carbon emissions and support cost savings to telemedicine for patients with tracheal diseases 估计碳排放和支持成本节约远程医疗为气管疾病患者。

IF 3.7 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2024-12-07 DOI: 10.1016/j.ijmedinf.2024.105757

Pedro Prosperi Desenzi Ciaralo , Paulo Francisco Guerreiro Cardoso , Helio Minamoto , Benoit Jacques Bibas , Carlos Roberto Ribeiro de Carvalho , Paulo Manuel Pego-Fernandes

Objective

The patient’s journey to the medical center for an outpatient visit can often mean hours of travel in their vehicle, leading to increased expenses and greater carbon dioxide (CO2) emissions into the environment. The study demonstrates the estimated carbon emission and cost savings associated with a telemedicine program dedicated to patients with tracheal disease in the Brazilian public health system.

Methods

Cross-sectional study of telemedicine visits for patients with tracheal disease referred to a public academic hospital between August 1, 2020, and December 30, 2023. The consultations occurred in a telemedicine department using the hospital’s proprietary platform. The analysis included the round-trip distance savings using home postal codes; CO2 emissions savings by transportation using the Greenhouse Gas Protocol (GHG Protocol) adapted to the Brazilian reality (“Programa Brasileiro GHG Protocol”); and the cost savings in transportation and support using the Brazil Ministry of Health program.

Results

1767 telemedicine visits with 680 patients were conducted, 363 (53.4 %) male and 317 (46.6 %) female, a median [IQR] age of 33 [12.0–51.0] years. Patients were from 170 Brazilian cities from 22 states. There were 2.219.544,3 round-trip kilometers saved (median per patient [IQR] 542,88km [190,36-2.672,6]), corresponding to an estimated 353.097,55kg of CO2 emissions savings (median per patient [IQR] 102,56kg [36,56-496,96]). The cost savings was 305.187,96 dollars (median per patient [IQR] $48,22 [24,97-162,51] dollars).

Conclusion

Telemedicine consultations, in addition to significantly reducing carbon emissions and costs, promote greater accessibility and sustainability in medical care. These findings may influence public policies to expand telemedicine programs, especially in remote regions, and strengthen environmental initiatives in healthcare.

目标：患者前往医疗中心门诊就医往往需要花费数小时的车程，这不仅增加了开支，还增加了二氧化碳（CO2）的排放量。本研究展示了巴西公共卫生系统中专门针对气管疾病患者的远程医疗项目的碳排放量估算和成本节约情况：对 2020 年 8 月 1 日至 2023 年 12 月 30 日期间转诊至一家公立学术医院的气管疾病患者进行远程医疗访问的横断面研究。会诊在远程医疗部门进行，使用的是医院的专有平台。分析包括使用家庭邮政编码节省的往返距离；使用适应巴西现实情况的《温室气体议定书》（"Programa Brasileiro GHG Protocol"）节省的交通二氧化碳排放量；以及使用巴西卫生部计划节省的交通和支持成本：共对 680 名患者进行了 1767 次远程医疗访问，其中男性 363 人（53.4%），女性 317 人（46.6%），年龄中位数[IQR]为 33 [12.0-51.0] 岁。患者来自巴西 22 个州的 170 个城市。节省的往返公里数为 2.219.544.3 公里（每位患者的中位数[IQR] 为 542.88 公里[190.36-2.672.6]），估计可减少 353.097.55 千克的二氧化碳排放量（每位患者的中位数[IQR] 为 102.56 千克[36.56-496.96]）。节省的费用为 305.187.96 美元（每位患者的中位数[IQR]为 48.22 [24.97-162.51] 美元）：结论：远程医疗会诊除了能显著减少碳排放和成本外，还能提高医疗服务的可及性和可持续性。这些发现可能会影响公共政策，以扩大远程医疗项目，尤其是在偏远地区，并加强医疗保健中的环保措施。

{"title":"Estimated carbon emissions and support cost savings to telemedicine for patients with tracheal diseases","authors":"Pedro Prosperi Desenzi Ciaralo , Paulo Francisco Guerreiro Cardoso , Helio Minamoto , Benoit Jacques Bibas , Carlos Roberto Ribeiro de Carvalho , Paulo Manuel Pego-Fernandes","doi":"10.1016/j.ijmedinf.2024.105757","DOIUrl":"10.1016/j.ijmedinf.2024.105757","url":null,"abstract":"<div><h3>Objective</h3><div>The patient’s journey to the medical center for an outpatient visit can often mean hours of travel in their vehicle, leading to increased expenses and greater carbon dioxide (CO2) emissions into the environment. The study demonstrates the estimated carbon emission and cost savings associated with a telemedicine program dedicated to patients with tracheal disease in the Brazilian public health system.</div></div><div><h3>Methods</h3><div>Cross-sectional study of telemedicine visits for patients with tracheal disease referred to a public academic hospital between August 1, 2020, and December 30, 2023. The consultations occurred in a telemedicine department using the hospital’s proprietary platform. The analysis included the round-trip distance savings using home postal codes; CO2 emissions savings by transportation using the Greenhouse Gas Protocol (GHG Protocol) adapted to the Brazilian reality (“Programa Brasileiro GHG Protocol”); and the cost savings in transportation and support using the Brazil Ministry of Health program.</div></div><div><h3>Results</h3><div>1767 telemedicine visits with 680 patients were conducted, 363 (53.4 %) male and 317 (46.6 %) female, a median [IQR] age of 33 [12.0–51.0] years. Patients were from 170 Brazilian cities from 22 states. There were 2.219.544,3 round-trip kilometers saved (median per patient [IQR] 542,88km [190,36-2.672,6]), corresponding to an estimated 353.097,55kg of CO2 emissions savings (median per patient [IQR] 102,56kg [36,56-496,96]). The cost savings was 305.187,96 dollars (median per patient [IQR] $48,22 [24,97-162,51] dollars).</div></div><div><h3>Conclusion</h3><div>Telemedicine consultations, in addition to significantly reducing carbon emissions and costs, promote greater accessibility and sustainability in medical care. These findings may influence public policies to expand telemedicine programs, especially in remote regions, and strengthen environmental initiatives in healthcare.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"195 ","pages":"Article 105757"},"PeriodicalIF":3.7,"publicationDate":"2024-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142822922","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A novel approach to antimicrobial resistance: Machine learning predictions for carbapenem-resistant Klebsiella in intensive care units 抗菌药耐药性的新方法：重症监护病房耐碳青霉烯类克雷伯氏菌的机器学习预测。

IF 3.7 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2024-12-07 DOI: 10.1016/j.ijmedinf.2024.105751

V. Alparslan , Ö. Güler , B. İnner , A. Düzgün , N. Baykara , A. Kuş

This study was conducted at Kocaeli University Hospital in Turkey and aimed to predict carbapenem-resistant Klebsiella pneumoniae infection in intensive care units using the Extreme Gradient Boosting (XGBoost) algorithm, a form of artificial intelligence. This was a retrospective case-control study involving 289 patients, including 159 carbapenem-resistant and 130 carbapenem-susceptible individuals as controls. The model’s predictive analysis combined a diverse range of demographic, clinical, and laboratory data, resulting in an average accuracy of 83.0%, precision of 83%, sensitivity of 88%, F1 score of 85%, and Matthews Correlation Coefficient of 0.66. Prolonged hospitalization and intensive care unit stay were significant predictors of carbapenem-resistant Klebsiella pneumoniae infection. The role of artificial intelligence role in healthcare, particularly in ICUs for managing antibiotic-resistant infections, is a major development in medicine. This study emphasizes the potential of artificial intelligence to predict antimicrobial resistance and improve clinical decisions in resource-limited settings. The study was approved by ClinicalTrials.gov (trial registration number NCT05985057 on 02.08.2023).

这项研究是在土耳其Kocaeli大学医院进行的，旨在使用极端梯度增强（XGBoost）算法（一种人工智能形式）预测重症监护病房中碳青霉烯耐药性肺炎克雷伯菌感染。这是一项涉及289例患者的回顾性病例对照研究，其中包括159例碳青霉烯耐药个体和130例碳青霉烯敏感个体作为对照。该模型的预测分析结合了多种人口统计学、临床和实验室数据，平均准确率为83.0%，精密度为83%，灵敏度为88%，F1评分为85%，马修斯相关系数为0.66。延长住院时间和重症监护病房住院时间是耐碳青霉烯肺炎克雷伯菌感染的重要预测因素。人工智能在医疗保健中的作用，特别是在管理抗生素耐药感染的icu中的作用，是医学的一项重大发展。这项研究强调了人工智能在预测抗菌素耐药性和改善资源有限环境下的临床决策方面的潜力。该研究已获ClinicalTrials.gov批准（试验注册号NCT05985057，于2023年8月2日批准）。

{"title":"A novel approach to antimicrobial resistance: Machine learning predictions for carbapenem-resistant Klebsiella in intensive care units","authors":"V. Alparslan , Ö. Güler , B. İnner , A. Düzgün , N. Baykara , A. Kuş","doi":"10.1016/j.ijmedinf.2024.105751","DOIUrl":"10.1016/j.ijmedinf.2024.105751","url":null,"abstract":"<div><div>This study was conducted at Kocaeli University Hospital in Turkey and aimed to predict carbapenem-resistant <em>Klebsiella pneumoniae</em> infection in intensive care units using the Extreme Gradient Boosting (XGBoost) algorithm, a form of artificial intelligence. This was a retrospective case-control study involving 289 patients, including 159 carbapenem-resistant and 130 carbapenem-susceptible individuals as controls. The model’s predictive analysis combined a diverse range of demographic, clinical, and laboratory data, resulting in an average accuracy of 83.0%, precision of 83%, sensitivity of 88%, F1 score of 85%, and Matthews Correlation Coefficient of 0.66. Prolonged hospitalization and intensive care unit stay were significant predictors of carbapenem-resistant <em>Klebsiella pneumoniae</em> infection. The role of artificial intelligence role in healthcare, particularly in ICUs for managing antibiotic-resistant infections, is a major development in medicine. This study emphasizes the potential of artificial intelligence to predict antimicrobial resistance and improve clinical decisions in resource-limited settings. The study was approved by <span><span>ClinicalTrials.gov</span><svg><path></path></svg></span> (trial registration number NCT05985057 on 02.08.2023).</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"195 ","pages":"Article 105751"},"PeriodicalIF":3.7,"publicationDate":"2024-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142824897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The digital prescription: A systematic review and meta-analysis of smartphone apps for blood pressure control 数字处方：对智能手机血压控制应用程序的系统回顾和荟萃分析。

IF 3.7 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2024-12-06 DOI: 10.1016/j.ijmedinf.2024.105755

Emily Motta-Yanac , Victoria Riley , Naomi J. Ellis , Aman Mankoo , Christopher J. Gidlow

Objective

Assess the effectiveness of digital health interventions (DHIs) in reducing blood pressure (BP) among individuals with high blood pressure and identify the impact of age, sex, and phone-based delivery methods on BP.

Methods

A systematic review and meta-analysis was undertaken according to the PRISMA and JBI. A comprehensive search was conducted across multiple databases. Randomised controlled trials (RCTs), mixed methods, descriptive, and experimental studies enrolling adult patients (≥ 18 years) with high BP and containing DHIs with blood pressure management aspect were included. We used a random-effects meta-analysis weighted mean difference (MD) between the comparison groups to pool data from the included studies. The outcome included the pooled MD reflecting systolic (SBP) or diastolic (DBP) change from baseline to 6-month period. Risk of bias was assessed using standardised tools.

Results

Thirty-six studies with 33,826 participants were included in the systematic review. The pooled estimate (26 RCTs) showed a significant reduction in SBP (MD = −1.45 mmHg, 95 % CI: −2.18 to −0.71) but not in DBP (MD = −0.50 mmHg, 95 % CI: −1.03 to 0.03), with evidence of some heterogeneity. Subgroup analysis indicated that smartphone app interventions were more effective in lowering SBP than short message services (SMS) or mobile phone calls. Additionally, the interventions significantly reduced the SBP compared with the control, regardless of participant sex.

Conclusion

Our findings indicate that DHIs, particularly smartphone apps, can lower SBP after 6 months in individuals with hypertension or high-risk factors, although changes might not be clinically significant. Further research is needed to understand the long-term impact and optimal implementation of DHIs for BP management across diverse populations.

目的：评估数字健康干预（DHIs）在降低高血压患者血压（BP）方面的有效性，并确定年龄、性别和基于电话的传递方式对血压的影响。方法：根据PRISMA和JBI进行系统回顾和荟萃分析。在多个数据库中进行了全面的搜索。纳入了随机对照试验（RCTs）、混合方法、描述性和实验性研究，纳入了血压高且含有血压管理方面DHIs的成人患者（≥18岁）。我们使用随机效应荟萃分析比较组间加权平均差异（MD）来汇总纳入研究的数据。结果包括从基线到6个月期间反映收缩压（SBP）或舒张压（DBP）变化的汇总MD。使用标准化工具评估偏倚风险。结果：36项研究33,826名受试者被纳入系统评价。汇总估计（26个随机对照试验）显示收缩压（MD = -1.45 mmHg, 95% CI: -2.18至-0.71）显著降低，但舒张压（MD = -0.50 mmHg, 95% CI: -1.03至0.03）无显著降低，有证据表明存在一定的异质性。亚组分析表明，智能手机应用干预在降低收缩压方面比短信服务（SMS）或手机通话更有效。此外，与对照组相比，干预显著降低了收缩压，无论参与者性别如何。结论：我们的研究结果表明，DHIs，特别是智能手机应用程序，可以在有高血压或高危因素的个体6个月后降低收缩压，尽管这种变化可能没有临床意义。需要进一步的研究来了解DHIs对不同种群BP管理的长期影响和最佳实施。

{"title":"The digital prescription: A systematic review and meta-analysis of smartphone apps for blood pressure control","authors":"Emily Motta-Yanac , Victoria Riley , Naomi J. Ellis , Aman Mankoo , Christopher J. Gidlow","doi":"10.1016/j.ijmedinf.2024.105755","DOIUrl":"10.1016/j.ijmedinf.2024.105755","url":null,"abstract":"<div><h3>Objective</h3><div>Assess the effectiveness of digital health interventions (DHIs) in reducing blood pressure (BP) among individuals with high blood pressure and identify the impact of age, sex, and phone-based delivery methods on BP.</div></div><div><h3>Methods</h3><div>A systematic review and <em>meta</em>-analysis was undertaken according to the PRISMA and JBI. A comprehensive search was conducted across multiple databases. Randomised controlled trials (RCTs), mixed methods, descriptive, and experimental studies enrolling adult patients (≥18 years) with high BP and containing DHIs with blood pressure management aspect were included. We used a random-effects <em>meta</em>-analysis weighted mean difference (MD) between the comparison groups to pool data from the included studies. The outcome included the pooled MD reflecting systolic (SBP) or diastolic (DBP) change from baseline to 6-month period. Risk of bias was assessed using standardised tools.</div></div><div><h3>Results</h3><div>Thirty-six studies with 33,826 participants were included in the systematic review. The pooled estimate (26 RCTs) showed a significant reduction in SBP (MD = −1.45 mmHg, 95 % CI: −2.18 to −0.71) but not in DBP (MD = −0.50 mmHg, 95 % CI: −1.03 to 0.03), with evidence of some heterogeneity. Subgroup analysis indicated that smartphone app interventions were more effective in lowering SBP than short message services (SMS) or mobile phone calls. Additionally, the interventions significantly reduced the SBP compared with the control, regardless of participant sex.</div></div><div><h3>Conclusion</h3><div>Our findings indicate that DHIs, particularly smartphone apps, can lower SBP after 6 months in individuals with hypertension or high-risk factors, although changes might not be clinically significant. Further research is needed to understand the long-term impact and optimal implementation of DHIs for BP management across diverse populations.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"195 ","pages":"Article 105755"},"PeriodicalIF":3.7,"publicationDate":"2024-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142808681","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-horizon event detection for in-hospital clinical deterioration using dual-channel graph attention network 基于双通道图关注网络的院内临床恶化多视界事件检测。

IF 3.7 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2024-12-06 DOI: 10.1016/j.ijmedinf.2024.105745

Thanh-Cong Do , Hyung-Jeong Yang , Soo-Hyung Kim , Bo-Gun Kho , Jin-Kyung Park

Objective

In hospitals globally, the occurrence of clinical deterioration within the hospital setting poses a significant healthcare burden. Rapid clinical intervention becomes a crucial task in such cases. In this research, we propose an end-to-end deep learning architecture that interpolates high-dimensional sequential data for the early detection of clinical deterioration events.

Materials and methods

We consider the problem of detecting deterioration events with two stages: predicting the “detection” status, a pre-event state; and predicting the event from detection time. Our approach involves the development of dual-channel graph attention networks with multi-task learning strategy by jointly learning task relatedness with a shared model for multiple prediction in multivariate time-series.

Results

The experiments are conducted on two clinical time-series datasets collected from intensive care units (ICUs). Our model has shown the potential performance compared to other state-of-the-art methods, in terms of the area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC).

Discussion

The proposed dual-channel graph attention networks can explicitly learn the correlations in both features and time domains of multivariate time-series. Our proposed objective function also can handle the problems of learning task relations and reducing task imbalance effects in multi-task learning.

Conclusion

Applying our proposed framework architecture could facilitate the implementation of early detecting in-hospital deterioration events.

目的：在全球范围内的医院，临床恶化的发生在医院设置造成了显著的医疗负担。在这种情况下，快速的临床干预成为一项至关重要的任务。在这项研究中，我们提出了一个端到端深度学习架构，该架构插入高维序列数据，用于早期检测临床恶化事件。材料和方法：我们从两个阶段来考虑变质事件的检测问题：预测“检测”状态，即事件前状态；并从探测时间预测事件。我们的方法涉及到开发具有多任务学习策略的双通道图注意网络，通过与多元时间序列中多个预测的共享模型共同学习任务相关性。结果：在重症监护病房（icu）收集的两个临床时间序列数据集上进行了实验。与其他最先进的方法相比，我们的模型在接收者工作特征曲线（AUROC）和精确召回曲线（AUPRC）下的面积方面显示了潜在的性能。讨论：提出的双通道图注意网络可以明确地学习多变量时间序列特征域和时间域的相关性。我们提出的目标函数还可以处理多任务学习中学习任务关系和减少任务不平衡效应的问题。结论：应用我们提出的框架架构可以促进院内恶化事件的早期发现。

{"title":"Multi-horizon event detection for in-hospital clinical deterioration using dual-channel graph attention network","authors":"Thanh-Cong Do , Hyung-Jeong Yang , Soo-Hyung Kim , Bo-Gun Kho , Jin-Kyung Park","doi":"10.1016/j.ijmedinf.2024.105745","DOIUrl":"10.1016/j.ijmedinf.2024.105745","url":null,"abstract":"<div><h3>Objective</h3><div>In hospitals globally, the occurrence of clinical deterioration within the hospital setting poses a significant healthcare burden. Rapid clinical intervention becomes a crucial task in such cases. In this research, we propose an end-to-end deep learning architecture that interpolates high-dimensional sequential data for the early detection of clinical deterioration events.</div></div><div><h3>Materials and methods</h3><div>We consider the problem of detecting deterioration events with two stages: predicting the “detection” status, a pre-event state; and predicting the event from detection time. Our approach involves the development of dual-channel graph attention networks with multi-task learning strategy by jointly learning task relatedness with a shared model for multiple prediction in multivariate time-series.</div></div><div><h3>Results</h3><div>The experiments are conducted on two clinical time-series datasets collected from intensive care units (ICUs). Our model has shown the potential performance compared to other state-of-the-art methods, in terms of the area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC).</div></div><div><h3>Discussion</h3><div>The proposed dual-channel graph attention networks can explicitly learn the correlations in both features and time domains of multivariate time-series. Our proposed objective function also can handle the problems of learning task relations and reducing task imbalance effects in multi-task learning.</div></div><div><h3>Conclusion</h3><div>Applying our proposed framework architecture could facilitate the implementation of early detecting in-hospital deterioration events.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"195 ","pages":"Article 105745"},"PeriodicalIF":3.7,"publicationDate":"2024-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142808659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Corrigendum to “Application of the openEHR reference model for PGHD: A case study on the DH-Convener initiative” [Int. J. Med. Inf. 193 (2025) 105686] “开放式电子病历参考模型在PGHD中的应用：卫生保健召集人倡议的案例研究”的更正[Int.]医学杂志，193(2025)105686]。

IF 3.7 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2024-12-06 DOI: 10.1016/j.ijmedinf.2024.105750

Somayeh Abedian , Sten Hanke , Rada Hussein

引用次数: 0

*Correspondence on “Large language models can support generation of standardized discharge summaries − A retrospective study utilizing ChatGPT-4 and electronic health records” *关于“大型语言模型可支持生成标准化出院摘要——利用ChatGPT-4和电子健康记录的回顾性研究”的通信。

IF 3.7 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2024-12-06 DOI: 10.1016/j.ijmedinf.2024.105756

Amnuay Kleebayoon , Viroj Wiwanitkit

引用次数: 0

CPRS: a clinical protocol recommendation system based on LLMs CPRS：基于llm的临床方案推荐系统。

IF 3.7 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2024-12-04 DOI: 10.1016/j.ijmedinf.2024.105746

Jingkai Ruan , Qianmin Su , Zihang Chen , Jihan Huang , Ying Li

Background: As fundamental documents in clinical trials, clinical trial protocols are intended to ensure that trials are conducted according to the objectives set by researchers. The advent of large models with superior semantic performance compared to traditional models provides fresh perspectives for research recommendations in clinical trial protocols.

Method: A clinical trial protocol recommendation system based on Large Language Models (LLMs) is proposed in this paper, combining GPT-4 and knowledge graph to assist in clinical trial protocol recommendations. Using knowledge graphs as an auxiliary tool, a finite set of clinical trial projects with similar features is identified. Subsequently, through the semantic capabilities of GPT-4, targeted recommendations are made to patients.

Results: Experiments were conducted to compare GPT-4 and multiple models from the SBERT family that handle semantic similarity. The results indicate that GPT-4 is capable of better sorting clinical trial protocols based on similarity criteria and offering targeted recommendations to patients. Consequently, this capability meets the matching requirements between projects and patients and enhances the automation of clinical trial protocol recommendations. Additionally, in the future, personal factors of patients will be fully considered during the recommendation process to provide more accurate and personalized protocol recommendations.

Conclusion: By integrating knowledge graphs and LLMs, a better understanding and processing of clinical trial protocol information can be achieved, enabling the recommendation of appropriate protocols for patients and enhancing both matching efficiency and accuracy. Furthermore, the application of this system contributes to the automation of clinical trial protocol recommendations, playing a crucial role in medical research institutions such as clinical trial research institutes and public health management departments. Additionally, it significantly aids in advancing the development of clinical trials and the medical field at large.

背景：临床试验方案作为临床试验的基础性文件，旨在确保试验按照研究者设定的目标进行。与传统模型相比，具有优越语义性能的大型模型的出现为临床试验方案的研究建议提供了新的视角。方法：本文提出了一种基于大语言模型（Large Language Models, LLMs）的临床试验方案推荐系统，将GPT-4与知识图谱相结合，辅助临床试验方案推荐。使用知识图谱作为辅助工具，确定了具有相似特征的有限临床试验项目集。随后，通过GPT-4的语义能力，对患者进行有针对性的推荐。结果：通过实验比较了GPT-4和来自SBERT家族的多个处理语义相似度的模型。结果表明，GPT-4能够基于相似性标准更好地筛选临床试验方案，并为患者提供有针对性的推荐。因此，该功能满足了项目和患者之间的匹配需求，并增强了临床试验方案推荐的自动化。此外，在未来的推荐过程中，将充分考虑患者的个人因素，提供更加准确和个性化的方案推荐。结论：将知识图谱与法学模型相结合，可以更好地理解和处理临床试验方案信息，为患者推荐合适的方案，提高匹配效率和准确性。此外，该系统的应用有助于实现临床试验方案推荐的自动化，在临床试验研究所、公共卫生管理部门等医学研究机构中发挥着至关重要的作用。此外，它大大有助于推进临床试验和整个医学领域的发展。

{"title":"CPRS: a clinical protocol recommendation system based on LLMs","authors":"Jingkai Ruan , Qianmin Su , Zihang Chen , Jihan Huang , Ying Li","doi":"10.1016/j.ijmedinf.2024.105746","DOIUrl":"10.1016/j.ijmedinf.2024.105746","url":null,"abstract":"<div><div>Background: As fundamental documents in clinical trials, clinical trial protocols are intended to ensure that trials are conducted according to the objectives set by researchers. The advent of large models with superior semantic performance compared to traditional models provides fresh perspectives for research recommendations in clinical trial protocols.</div><div>Method: A clinical trial protocol recommendation system based on Large Language Models (LLMs) is proposed in this paper, combining GPT-4 and knowledge graph to assist in clinical trial protocol recommendations. Using knowledge graphs as an auxiliary tool, a finite set of clinical trial projects with similar features is identified. Subsequently, through the semantic capabilities of GPT-4, targeted recommendations are made to patients.</div><div>Results: Experiments were conducted to compare GPT-4 and multiple models from the SBERT family that handle semantic similarity. The results indicate that GPT-4 is capable of better sorting clinical trial protocols based on similarity criteria and offering targeted recommendations to patients. Consequently, this capability meets the matching requirements between projects and patients and enhances the automation of clinical trial protocol recommendations. Additionally, in the future, personal factors of patients will be fully considered during the recommendation process to provide more accurate and personalized protocol recommendations.</div><div>Conclusion: By integrating knowledge graphs and LLMs, a better understanding and processing of clinical trial protocol information can be achieved, enabling the recommendation of appropriate protocols for patients and enhancing both matching efficiency and accuracy. Furthermore, the application of this system contributes to the automation of clinical trial protocol recommendations, playing a crucial role in medical research institutions such as clinical trial research institutes and public health management departments. Additionally, it significantly aids in advancing the development of clinical trials and the medical field at large.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"195 ","pages":"Article 105746"},"PeriodicalIF":3.7,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142792791","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Error rates of data processing methods in clinical research: A systematic review and meta-analysis of manuscripts identified through PubMed 临床研究中数据处理方法的错误率：通过PubMed识别的手稿的系统回顾和荟萃分析。

IF 3.7 2区医学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

International Journal of Medical Informatics

Pub Date : 2024-12-04 DOI: 10.1016/j.ijmedinf.2024.105749

Maryam Y. Garza , Tremaine Williams , Songthip Ounpraseuth , Zhuopei Hu , Jeannette Lee , Jessica Snowden , Anita C. Walden , Alan E. Simon , Lori A. Devlin , Leslie W. Young , Meredith N. Zozus

Background

In clinical research, prevention of data errors is paramount to ensuring reproducibility of trial results and the safety and efficacy of the resulting interventions. Over the last 40 years, empirical assessments of data accuracy in clinical research have been reported, however, there has been little systematic synthesis of these results. Although notable exceptions exist, little evidence exists regarding the relative accuracy of different data processing methods.

Methods

A systematic review of the literature identified through PubMed was performed to identify studies that evaluated the quality of data obtained through data processing methods typically used in clinical trials. Quantitative information on data accuracy was abstracted from the manuscripts and pooled. Meta-analysis of single proportions based on the Freeman-Tukey transformation method and the generalized linear mixed model approach were used to derive an overall estimate of error rates across data processing methods used in each study for comparison.

Results

A total of 93 papers (published from 1978 to 2008) meeting our inclusion criteria were categorized according to their data processing methods. The accuracy associated with data processing methods varied widely, with error rates ranging from 2 errors per 10,000 fields to 2,784 errors per 10,000 fields. MRA was associated with both high and highly variable error rates, having a pooled error rate of 6.57% (95% CI: 5.51, 7.72). In comparison, the pooled error rates for optical scanning, single-data entry, and double-data entry methods were 0.74% (0.21, 1.60), 0.29% (0.24, 0.35) and 0.14% (0.08, 0.20), respectively.

Conclusions

Data processing methods may explain a significant amount of the variability in data accuracy. MRA error rates, for example, were high enough to impact decisions made using the data and could necessitate increases in sample sizes to preserve statistical power. Thus, the choice of data processing methods can likely impact process capability and, ultimately, the validity of trial results.

背景：在临床研究中，预防数据错误对于确保试验结果的可重复性以及由此产生的干预措施的安全性和有效性至关重要。在过去的40年里，对临床研究中数据准确性的实证评估已经有了报道，然而，对这些结果的系统综合却很少。尽管存在明显的例外，但很少有证据表明不同数据处理方法的相对准确性。方法：通过PubMed对文献进行系统回顾，以确定通过临床试验中通常使用的数据处理方法评估数据质量的研究。从手稿中提取数据准确性的定量信息并汇总。使用基于Freeman-Tukey变换方法和广义线性混合模型方法的单一比例元分析，得出每个研究中使用的数据处理方法的误差率的总体估计，以进行比较。结果：根据数据处理方法，共纳入93篇符合纳入标准的论文（发表于1978 - 2008年）。与数据处理方法相关的准确性差异很大，错误率从每10,000个字段2个错误到每10,000个字段2,784个错误不等。MRA与高错误率和高可变错误率相关，总错误率为6.57% （95% CI: 5.51, 7.72）。相比之下，光学扫描、单数据录入和双数据录入的汇总错误率分别为0.74%（0.21,1.60）、0.29%（0.24,0.35）和0.14%（0.08,0.20）。结论：数据处理方法可以解释数据准确性的显著差异。例如，MRA错误率高到足以影响使用数据做出的决策，可能需要增加样本量以保持统计效力。因此，数据处理方法的选择可能会影响处理能力，并最终影响试验结果的有效性。

{"title":"Error rates of data processing methods in clinical research: A systematic review and meta-analysis of manuscripts identified through PubMed","authors":"Maryam Y. Garza , Tremaine Williams , Songthip Ounpraseuth , Zhuopei Hu , Jeannette Lee , Jessica Snowden , Anita C. Walden , Alan E. Simon , Lori A. Devlin , Leslie W. Young , Meredith N. Zozus","doi":"10.1016/j.ijmedinf.2024.105749","DOIUrl":"10.1016/j.ijmedinf.2024.105749","url":null,"abstract":"<div><h3>Background</h3><div>In clinical research, prevention of data errors is paramount to ensuring reproducibility of trial results and the safety and efficacy of the resulting interventions. Over the last 40 years, empirical assessments of data accuracy in clinical research have been reported, however, there has been little systematic synthesis of these results. Although notable exceptions exist, little evidence exists regarding the relative accuracy of different data processing methods.</div></div><div><h3>Methods</h3><div>A systematic review of the literature identified through PubMed was performed to identify studies that evaluated the quality of data obtained through data processing methods typically used in clinical trials. Quantitative information on data accuracy was abstracted from the manuscripts and pooled. Meta-analysis of single proportions based on the Freeman-Tukey transformation method and the generalized linear mixed model approach were used to derive an overall estimate of error rates across data processing methods used in each study for comparison.</div></div><div><h3>Results</h3><div>A total of 93 papers (published from 1978 to 2008) meeting our inclusion criteria were categorized according to their data processing methods. The accuracy associated with data processing methods varied widely, with error rates ranging from 2 errors per 10,000 fields to 2,784 errors per 10,000 fields. MRA was associated with both high and highly variable error rates, having a pooled error rate of 6.57% (95% CI: 5.51, 7.72). In comparison, the pooled error rates for optical scanning, single-data entry, and double-data entry methods were 0.74% (0.21, 1.60), 0.29% (0.24, 0.35) and 0.14% (0.08, 0.20), respectively.</div></div><div><h3>Conclusions</h3><div>Data processing methods may explain a significant amount of the variability in data accuracy. MRA error rates, for example, were high enough to impact decisions made using the data and could necessitate increases in sample sizes to preserve statistical power. Thus, the choice of data processing methods can likely impact process capability and, ultimately, the validity of trial results.</div></div>","PeriodicalId":54950,"journal":{"name":"International Journal of Medical Informatics","volume":"195 ","pages":"Article 105749"},"PeriodicalIF":3.7,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142796505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0